system

Abstract

We provide the system. [Solution] Means for automatically collecting biodata and chemical information, A means for analyzing the aforementioned data and predicting new drug candidate substances using a machine learning algorithm, A means for evaluating the characteristics of a new drug candidate by performing in silico simulations based on the prediction, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Developing new drugs takes an enormous amount of time and cost. In particular, the problems are the search process for new drug candidate substances, the complexity of clinical trial design, and the inefficiency in the analysis of biodata and chemical substance information. Conventional methods have the problem that the analysis accuracy is not sufficient and a lot of resources are wasted. Therefore, there is a need for more efficient and accurate analysis and automated means for test design.

Means for Solving the Problems

[0005] This invention provides a means for predicting new drug candidates by automatically collecting biodata and chemical information and using machine learning algorithms to analyze this data. Furthermore, it enables the selection of new drug candidates by automatically generating and evaluating molecular structures using generative AI technology. In addition, by providing a means for analyzing past clinical trial data and optimizing and proposing trial designs for new drug candidates, this system can streamline the new drug development process and reduce costs.

[0006] "Biodata" refers to digital data collected from a biological perspective, including genetic information and biological response data.

[0007] "Chemical substance information" refers to data concerning the properties, structure, and reactivity of compounds and molecules.

[0008] A "candidate drug" refers to a compound that is assumed to have promising medicinal effects in the early stages of new drug development.

[0009] A "machine learning algorithm" refers to an algorithm or computational method that analyzes data as input and learns to perform a specific task.

[0010] "Generative AI technology" refers to artificial intelligence technology that can automatically generate new data and content.

[0011] "In silico simulation" refers to a simulation conducted by using a computer to mimic biological or chemical processes.

[0012] "Clinical trial design" refers to the process of systematically planning and designing a trial for a specific research objective.

[0013] "Historical data" refers to data that has been collected or generated in the past and is used for future analysis and prediction. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a system that supports new drug development using biodata and chemical information. This system enables an efficient new drug development process through the coordinated operation of the server, terminals, and users.

[0036] First, the server collects biodata and chemical information. This includes a function to obtain the latest data in conjunction with a database, and data collection can be performed according to the user's requests. The collected data is preprocessed on the server and formatted into a format suitable for analysis.

[0037] Next, the server uses machine learning algorithms to analyze the pre-processed data. This builds a predictive model for potential new drug candidates. Based on existing drug efficacy data, this model can predict the effectiveness of unknown compounds with high accuracy.

[0038] Subsequently, the server utilizes generative AI technology to automatically generate molecular structures. By analyzing the structures of promising compounds and further evaluating their properties, it supports the selection of new candidate substances.

[0039] As a thought experiment, the server performs in silico simulations to evaluate the dynamics and reactions of compounds in a virtual environment. The results are displayed on the user's terminal and used for further analysis. The user can visually review this data through the terminal and select the most suitable new drug candidate.

[0040] Furthermore, the server analyzes past trial data to optimize clinical trials and proposes trial designs suitable for new drug candidates. This allows users to plan efficient and effective clinical trials.

[0041] As a concrete example, let's assume a user wants to develop a treatment for a specific type of cancer. The server collects relevant genetic data and data on the reactivity of cancer cells, and proposes an optimal molecular structure. Subsequently, based on the simulation results, the user further refines the candidate substance before bringing it to market.

[0042] This series of processes is expected to enable faster and more accurate new drug development than before, thereby supporting innovation in the medical industry.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server accesses external biodatabases and chemical information systems to collect necessary data. It utilizes APIs to acquire information in real time and selects the type of data according to the user's research topic.

[0046] Step 2:

[0047] The server preprocesses the collected data. Specifically, it corrects missing values, removes noisy data, and normalizes the data. This prepares the data for analysis by machine learning algorithms.

[0048] Step 3:

[0049] The server executes machine learning algorithms and performs data analysis. In this process, it builds a predictive model for selecting new drug candidates. As algorithms, it applies random forests and deep neural networks, and verifies the accuracy of the model.

[0050] Step 4:

[0051] The server automatically generates new molecular structures using generative AI technology. It designs candidate substances and sets evaluation criteria considering their chemical and biological properties. This makes it possible to automatically select promising compounds.

[0052] Step 5:

[0053] The server performs in silico simulations to evaluate the properties of selected compounds in detail. The simulations utilize molecular dynamics and quantum chemical analysis to virtually verify how the new drug candidates function in living organisms.

[0054] Step 6:

[0055] The terminal receives simulation results and analysis data sent from the server and displays them visually to the user. This allows the user to make a final selection of drug candidates based on the analyzed information.

[0056] Step 7:

[0057] The server analyzes past clinical trial data and proposes trial designs that match the new drug candidate. It also provides functions to support the optimization of clinical trials, such as selecting trial participants and setting up trial groups.

[0058] Step 8:

[0059] Users review the proposed clinical trial design via their device and consider further details. This allows the development to proceed to the next stage based on sufficient data regarding the drug's safety and efficacy.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In recent years, the effective use of vast amounts of biodata and chemical information has become essential in new drug development. However, it is difficult to consistently automate the process of efficiently collecting, preprocessing, and analyzing this data to predict new drug candidates, and a great deal of time and resources are spent on trial and error. Furthermore, because there is a lack of sufficient systems to automatically propose molecular structures using generation technologies and to evaluate their properties in a virtual environment, there is a need to rapidly perform tasks from candidate substance identification to the optimization of clinical trial designs.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for automatically collecting biodata and chemical information; means for preprocessing the data and formatting it into an analyzable form; means for predicting new drug candidates using machine learning algorithms; means for automatically generating and evaluating molecular structures using generation technology; means for performing simulations in a virtual environment based on the predictions and evaluating the properties of the new drug candidates; means for visually displaying the data for user analysis; and means for analyzing past clinical trial data and optimizing the trial design for the new drug candidates. This automates the entire process from data collection to candidate substance selection and trial design proposal, enabling faster and more efficient new drug development.

[0065] "Biodata" refers to biological data such as genetic information, protein structure, and clinical trial results used in biological research and medicine.

[0066] "Chemical substance information" refers to data on the structure, properties, and reactivity of compounds, and plays a particularly important role in new drug development.

[0067] "Automated data collection" refers to the process of obtaining necessary information from databases or online resources without human intervention.

[0068] "Preprocessing" refers to data cleaning and formatting work to convert collected data into an analyzable format.

[0069] A "machine learning algorithm" refers to a computer program that learns patterns by analyzing past data and uses that knowledge to make predictions and classifications about future data.

[0070] A "new drug candidate substance" refers to a compound that shows promise as a therapeutic effect and is being considered as a component of a newly developed drug.

[0071] "Generative techniques" refer to a group of algorithms that generate new data or patterns based on known data, and are particularly used for molecular structure generation.

[0072] A "virtual environment" refers to a computer setting used to simulate and evaluate real-world phenomena through computer simulation.

[0073] "Visual display" refers to presenting data and simulation results to users in the form of images, graphs, 3D models, etc.

[0074] "Study design optimization" refers to the process of analyzing past data and proposing the most effective and efficient implementation plan for a clinical trial.

[0075] The system in this invention supports new drug development through the collaborative efforts of a server, terminal, and user. The server has means for effectively collecting biodata and chemical information. In this process, necessary information is automatically obtained via APIs through integration with databases. In particular, it uses data provided from gene sequencing databases and chemical library databases.

[0076] Upon user request, the server preprocesses the collected data and prepares it for analysis. During this process, data cleaning software is used to impute missing values ​​and normalize the data.

[0077] Next, the server uses machine learning algorithms to analyze the preprocessed data. This analysis utilizes open-source machine learning libraries (e.g., TENSORFLOW® and scikit-learn) to build a model for predicting new drug candidates. Using this model, the effectiveness of new molecules is predicted based on existing drug efficacy data.

[0078] Furthermore, the server automatically generates molecular structures of potential new drugs using generative AI models. This process employs techniques such as variational autoencoders (VAEs) and generative adversarial networks (GANs) to generate structures of potentially promising compounds.

[0079] The created molecular structures are evaluated through in silico simulations, and the server uses molecular dynamics software (e.g., GROMACS or AMBER) to simulate the dynamics and reactions of compounds in a virtual environment. Based on these results, the server sends the data to a terminal, which the user then analyzes visually. The terminal is equipped with software that enables 3D visualization of the data, allowing the user to select the most suitable new drug candidates.

[0080] Furthermore, the server utilizes statistical analysis software to analyze past clinical trial data and propose the optimal trial design for new drug candidates. This proposal allows users to plan more efficient clinical trials.

[0081] For example, if a user wants to develop a new cancer treatment drug, the server will collect gene databases and cancer cell response data and propose an optimal molecular structure. An example of a prompt to be input into the generating AI model would be, "Please propose a novel molecular structure for a cancer treatment drug. Genetic data and efficacy data are available." This system is expected to accelerate the new drug development process with high accuracy, thereby promoting innovation in the medical field.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server automatically collects biodata and chemical information from databases. It takes information from gene sequencing databases and chemical library APIs as input. By extracting this data, it outputs the latest biodataset required. Specifically, the server periodically calls the APIs to ensure updated data is available.

[0085] Step 2:

[0086] The server preprocesses the collected data. It uses the raw biodata obtained in step 1 as input. The server outputs the preprocessed data, imputing missing values ​​and performing a normalization process to convert it into a format suitable for analysis. Specifically, the server uses data cleaning software to correct incomplete data items.

[0087] Step 3:

[0088] The server uses pre-processed data to predict potential new drug candidates. It receives pre-processed data as input and analyzes it using machine learning algorithms. The server applies a model trained on existing drug efficacy data and outputs a list of promising new drug candidates. Specifically, the server uses TensorFlow to operate its predictive model through supervised learning.

[0089] Step 4:

[0090] The server automatically generates molecular structures using a generative AI model. The features of the new drug candidate obtained in step 3 are used as input. The AI ​​model performs molecular generation and outputs new molecular structure data. Specifically, the server unfolds a variational autoencoder and generates a new compound from the latent space.

[0091] Step 5:

[0092] The server performs simulations to evaluate the generated molecular structure in a virtual environment. The molecular structure generated in step 4 is used as input. The server performs molecular dynamics simulations and outputs evaluation results for chemical stability and reactivity. Specifically, the server uses GROMACS to simulate molecular dynamics on a computer.

[0093] Step 6:

[0094] The terminal visually displays the simulation results to the user. It uses evaluation results sent from the server as input. The terminal outputs visual analysis results by displaying 3D structures and graphs in a user-friendly format. Specifically, the terminal provides an interactive user interface using 3D rendering software.

[0095] Step 7:

[0096] The server analyzes historical clinical trial data and proposes optimized trial designs. It combines existing trial data and simulation results for analysis. The server presents efficient clinical trial plans and outputs proposed trial designs. Specifically, the server uses statistical analysis software and applies data trends and optimization algorithms.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] The objective of this invention is to streamline the new drug development process and support the identification of highly accurate and predictable new drug candidates. Furthermore, it aims to improve the quality of health management by rapidly providing individually optimized preventive measures and treatment plans through integration with personal health data. Additionally, it aims to optimize clinical trials by effectively visualizing clinical trial information and post-market safety information.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] This invention includes a server that automatically collects biodata and chemical information, analyzes the data and predicts new drug candidates using machine learning algorithms, performs in silico simulations based on the predictions to evaluate the characteristics of the new drug candidates, and links with individual health data to present optimal preventive measures and treatment plans. This increases the efficiency of new drug development and enables the provision of individually optimized health management. Furthermore, it can automatically generate and evaluate molecular structures using generative AI technology, select new drug candidates, and propose treatment methods based on them. Through this series of functions, it is possible to analyze past clinical trial data and optimize trial designs while visualizing clinical trial information and post-market safety information.

[0102] "Biodata" is a general term for information originating from living organisms, primarily data that indicates biological processes and states.

[0103] "Chemical substance information" refers to data concerning the chemical properties of a compound, such as its structure, properties, and reactivity.

[0104] A "machine learning algorithm" is a computer program that analyzes large amounts of data to find patterns, and is a method for making appropriate predictions and classifications from new data.

[0105] "In silico simulation" is a simulation performed in a virtual environment on a computer, and is a means of evaluating the properties of compounds and other substances without conducting physical experiments.

[0106] "Generative AI technology" refers to techniques that use artificial intelligence to automatically generate new data and structures, and is a method that supports creative work.

[0107] "Health data" is a general term for information about an individual's health status and medical history, and is used for medical care and health management.

[0108] A "treatment plan" refers to a set of medical procedures and care plans designed to improve a person's health.

[0109] "Clinical trial information" refers to information about clinical trials conducted to confirm the effectiveness and safety of new drugs.

[0110] "Post-market safety information" refers to information about side effects and effects of a drug that is reported after it has been released to the market.

[0111] "Past clinical trial data" refers to data collected from clinical trials conducted in the past, and this information can be used in future trial design and new drug development.

[0112] "Study design optimization" is the process of improving a study plan to ensure that information is obtained efficiently and effectively when planning and conducting a clinical trial.

[0113] The system implementing this invention is primarily realized through the coordinated operation of a server, terminals, and users. The server automatically collects biodata and chemical information and links it with a database to obtain the latest information. The collected data is analyzed using machine learning algorithms to predict potential new drug candidates. In this process, a program written in Python assists the analysis.

[0114] The server further utilizes generative AI technology to automatically generate and evaluate new molecular structures. These generated molecular structures, combined with the user's health data, enable the creation of individually optimized preventative measures and treatment plans. This improves the quality of health management.

[0115] The device visually displays collected and analyzed data to the user and suggests optimal treatment methods based on health data. Users can then formulate specific treatment plans based on this information. This enables the practice of medical care tailored to individual needs.

[0116] As a concrete example, individual residents of a smart city can use this system to monitor their health on a daily basis and identify the most suitable medication for preventing seasonal influenza. Furthermore, this system visualizes clinical trial information and post-market safety information, contributing to raising residents' awareness of drug safety.

[0117] Examples of prompts to input into a generative AI model include:

[0118] "Based on recent health data, please suggest the most suitable medication for the symptoms of [specific symptom]."

[0119] "Please generate a list of medications suitable for vaccination, taking into account the current health status."

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The server collects biodata and chemical information via the internet and databases. Inputs are various databases, and output is the collected raw data. Scripts on the server periodically update the information.

[0123] Step 2:

[0124] The server preprocesses the collected data. Preprocessing includes data standardization and cleaning. The input is raw data, and the output is data in a format suitable for analysis. In this process, a Python library is used to unify the data format.

[0125] Step 3:

[0126] The server runs machine learning algorithms on preprocessed data to predict potential new drug candidates. The input is standardized data, and the output is a list of potential drug candidates. Existing drug data is used to train the model, and then predictions are made on unknown data.

[0127] Step 4:

[0128] The server utilizes generative AI technology to generate and evaluate new molecular structures for proposed candidate substances. The input is a list of new drug candidates, and the output is the evaluated molecular structures. Simulations are then performed using a generative model to conduct characterization.

[0129] Step 5:

[0130] The server generates personalized treatment and preventative measures based on the user's health data. The input is individual health data and AI analysis results, and the output is a personalized medical plan. This process involves inputting prompts into an AI model to obtain a specific plan.

[0131] Step 6:

[0132] The device visually displays the generated results to the user, providing further insights. The input is an individualized medical plan, and the output is easy-to-understand information displayed in the user interface. Specifically, information is communicated through a health dashboard.

[0133] Step 7:

[0134] Users make appropriate decisions and implement treatment plans based on the information provided. The output is a record of medical actions, useful for subsequent data analysis and feedback. Users regularly update their health status through the in-app feedback function.

[0135] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0136] This invention is a new drug development support system incorporating an emotion engine, which allows for the smoother and more effective development process by recognizing the user's emotional state in real time and dynamically adjusting the system's behavior.

[0137] The server automatically collects existing biodata and chemical information. The collected data is analyzed using machine learning algorithms and used to predict potential new drug candidates. Next, generative AI technology is used to generate and evaluate the structures of candidate molecules, leading to advanced drug candidate selection.

[0138] Furthermore, the server uses emotional data transmitted from the user's terminal to activate an emotion engine and understand the user's current emotional state. The emotion engine has the ability to dynamically change the format of information presented by the system to assess how stressed the user is using the system and to maintain the user's interest and concentration.

[0139] For example, if the system detects that a user is feeling tired, it simplifies the interface on the device and highlights important information. Similarly, if a user is feeling confused or stressed, the system improves the user experience by providing support tools and detailed help information.

[0140] Regarding clinical trials, the server analyzes past trial data and proposes more effective trial designs. This process is also optimized by the emotion engine, enabling flexible suggestions based on user feedback. The emotion engine builds an optimization loop based on user feedback, effectively incorporating user preferences during the development process.

[0141] In this way, this system combines emotion recognition technology with the new drug development process to provide users with a less stressful, efficient, and supportive development environment.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server collects necessary biodata and chemical information from external biodatabases. This utilizes API connections to retrieve data in real time and performs filtering according to user requests.

[0145] Step 2:

[0146] The server preprocesses the collected data and formats it into a format suitable for analysis by machine learning algorithms. In this stage, missing values ​​are imputed, noisy data is removed, and normalization is performed.

[0147] Step 3:

[0148] The server analyzes data using machine learning algorithms to predict potential new drug candidates. Here, random forests and deep learning are utilized as algorithms to build models that predict the effectiveness of new drugs with high accuracy.

[0149] Step 4:

[0150] The server utilizes generative AI technology to generate new molecular structures. By evaluating the structures of promising compounds and selecting new candidates based on these evaluations, the accuracy of the search is improved.

[0151] Step 5:

[0152] The server performs in silico simulations on the generated candidate substances. This process uses molecular dynamics simulations and quantum chemical calculations to virtually analyze the behavior of the drugs in vivo.

[0153] Step 6:

[0154] The device collects emotional data from the user and sends it to a server. This data is analyzed using facial recognition and voice analysis technologies with a camera and microphone to detect emotions and provide real-time feedback to the server.

[0155] Step 7:

[0156] The server analyzes the received emotional data using an emotion engine. This evaluates the user's stress level and concentration level, and dynamically adjusts the system interface and feedback format based on the results.

[0157] Step 8:

[0158] Based on the analysis results from the emotion engine, the server provides users with appropriate information and optimizes the interface. For example, if the server determines that the user is in a high-stress state, it will provide a more intuitive interface and detailed help.

[0159] Step 9:

[0160] The server analyzes past clinical trial data and proposes a suitable trial design for the new drug candidate. Based on user feedback and emotional state, it customizes the trial plan and provides the appropriate support the user needs.

[0161] Step 10:

[0162] Users can review the analysis results and trial designs provided through their devices and revise the development direction as needed. This enables users to achieve efficient and less stressful new drug development.

[0163] (Example 2)

[0164] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0165] In the new drug development process, there is a need to efficiently and effectively analyze vast amounts of data to identify promising drug candidates more quickly. Furthermore, optimizing the interface to consider the user's emotional state is a challenge in reducing developer stress and improving work efficiency.

[0166] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0167] In this invention, the server includes means for automatically collecting information, means for analyzing the data and predicting substances using an algorithm, and means for evaluating based on the prediction. This makes it possible to streamline the new drug development process and optimally support the user's work.

[0168] "Means of automatically collecting information" refers to technologies for continuously acquiring necessary information from networks and databases through automated processes.

[0169] "Methods for analyzing data and predicting substances using algorithms" refers to methods for analyzing collected data using analytical techniques and predicting the properties and effectiveness of new chemical substances using machine learning algorithms.

[0170] "Methods for evaluation based on predictions" refer to the process of examining the results predicted by an algorithm according to various evaluation criteria, and confirming their effectiveness and safety based on those criteria.

[0171] "Means for the automatic generation and evaluation of structures using technology" refers to technologies that automatically create molecular structures of materials using generative algorithms, simulate the results, and determine their usefulness.

[0172] "A means of analyzing past data and proposing optimized test designs" refers to a system that analyzes accumulated test results to date, makes suggestions to help design new tests, and enables more efficient test implementation.

[0173] The implementation of this invention involves a series of systems for streamlining the new drug development process through the interaction of servers, terminals, and users.

[0174] The server first connects to the network and automatically collects biometric and chemical information from public databases and specialized information sources. The server utilizes cloud platforms, particularly Google Cloud and AWS, to collect data using APIs and web scraping techniques. The collected data is analyzed using machine learning libraries such as TensorFlow and PyTorch, and algorithms are used to predict the properties of potential new drugs. The algorithmic models are built on existing scientific knowledge and data-driven methods.

[0175] Furthermore, the server utilizes generative AI technology to automatically generate and evaluate the molecular structures of materials. This process employs specialized chemical simulation software to understand how the molecules created by the generative AI model behave physically and chemically.

[0176] The device functions as a tool for collecting user emotional data. It uses vital information from a smartwatch and facial recognition technology via a webcam to collect and send the user's emotional state to a server. The server analyzes this emotional data in real time using Python or R. Based on the analyzed emotional state, it adaptively adjusts how the user optimally interacts with the digital interface.

[0177] For example, if the device detects that the user is feeling fatigued, it simplifies the displayed content and uses highlighted important information to attract the user's attention. Furthermore, if confusion or stress is detected, the system proactively improves the user experience by providing detailed help information and support tools.

[0178] Examples of prompt statements include:

[0179] "To streamline the new drug development process, we would like to evaluate potential drug candidates using generative AI models. Furthermore, please teach us methods for analyzing users' emotional states and adjusting the system accordingly."

[0180] Thus, this invention provides a system that comprehensively supports new drug development by combining data collection, machine learning, and sentiment analysis.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The server automatically collects biometric and chemical information over the network. It requires data retrieval requests from public databases and specialized information sources using APIs or web scraping techniques as input. The server then outputs a structured dataset.

[0184] Step 2:

[0185] The server analyzes the collected data. The dataset obtained in Step 1 is used as input. Machine learning algorithms, particularly TensorFlow and PyTorch, are used to process the data and predict potential drug candidates. The output of this process is the predicted characteristics of the potential drug candidates. Specifically, this data is used to score and rank promising compounds.

[0186] Step 3:

[0187] The server uses a generative AI model to automatically generate structures for new drug candidate molecules. Using the prediction results from step 2 as input, the generative AI model generates new molecular candidates. The output is the structure of the generated molecule and its evaluation results. Specifically, the generative model performs structural simulations and physical property evaluations.

[0188] Step 4:

[0189] The device collects user emotional data. Inputs include vital data and facial recognition data from smartwatches and webcams. This data is acquired and aggregated in real time and sent to a server. The output is a dataset representing the user's current emotional state.

[0190] Step 5:

[0191] The server analyzes the emotional data sent from the terminal. The input is the emotional data collected in step 4, which is analyzed using Python or R. This allows the server to identify the user's emotional state and adjust the interface accordingly. The output is an adaptive strategy for the interface based on the user's state. Specifically, it dynamically updates the information presentation format according to the emotional state.

[0192] Step 6:

[0193] Users advance new drug development through an interface based on the analysis results. They receive the output results from Step 5 as input and can work efficiently with the optimized interface. Outputs include user feedback and progress information regarding new drug development. Specific actions include UX adjustments such as content highlighting and the presentation of additional support tools.

[0194] (Application Example 2)

[0195] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0196] In conventional drug development processes, effectively collecting and analyzing biodata and chemical information to select candidate substances was crucial. However, the lack of consideration for emotional states resulted in a heavy user burden and difficulty in efficient process management. Furthermore, there is the issue of insufficient care support that incorporates the emotions of the subjects.

[0197] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0198] In this invention, the server includes means for automatically collecting biodata and chemical information, means for analyzing the data and predicting new drug candidates using machine learning algorithms, and means for dynamically presenting information based on the user's emotional state by collecting and analyzing emotional information. This makes it possible to efficiently and interactively advance new drug development in accordance with the user's emotional state.

[0199] "Biodata" refers to information related to living organisms, and in particular, data that includes molecular biological or biochemical information.

[0200] "Chemical substance information" refers to scientific information related to chemical substances, such as their properties, structure, and reactivity.

[0201] A "machine learning algorithm" is a computational method used to analyze large amounts of data and find patterns and trends.

[0202] "Emotional information" refers to data that indicates an individual's emotional state, and includes things like facial expressions, tone of voice, and heart rate.

[0203] "Generative AI technology" is a technology that uses artificial intelligence to generate new data and information and creatively solve problems.

[0204] "Care support" refers to activities and processes that provide assistance with daily life for the elderly and those who require care.

[0205] The system realizing this invention features a program in which various software components work in coordination. The server primarily automatically collects biodata and chemical information and analyzes this data using machine learning algorithms. The analyzed data is then used to automatically generate molecular structures using generative AI technology and evaluate them. This makes it possible to efficiently select and evaluate new drug candidates.

[0206] Furthermore, using emotional information collected from the device, the server activates an emotion engine to understand the user's emotional state in real time. Based on this information, it dynamically presents information appropriate to the user's current situation. In addition, in care support settings, it is designed to flexibly adjust care procedures based on emotion analysis to reduce the user's burden.

[0207] A concrete example is when an elderly person shows anxiety; the device suggests calming exercises or music. In this invention, an example of a prompt utilizing a generative AI model is: "Analyze the elderly person's current emotional state and generate appropriate care advice. If the user shows anxiety, suggest calming exercises."

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The server automatically collects data related to living organisms and information related to chemical substances. Inputs are data from external databases and sensors, and the output is integrated, analyzable data. This data is then formatted into a specific form for subsequent processing by machine learning algorithms.

[0211] Step 2:

[0212] The server uses machine learning algorithms to analyze the collected data. The input is the data formatted in step 1. Through data patterns and hypothesis building, it predicts potential new drug candidates. This process yields an output in the form of a drug candidate list.

[0213] Step 3:

[0214] The device collects emotional information from the user. The input consists of real-time emotional data such as the user's facial expressions, voice, and heart rate. An emotion engine analyzes this data, outputting the user's emotional state. This analysis result is used to present effective support information to the user.

[0215] Step 4:

[0216] The server automatically generates and evaluates the molecular structures of predicted drug candidates using generative AI technology. The input is the list of drug candidates generated in step 2, and the output is a list of refined new drug candidates along with the evaluation results for each structure. This process selects high-quality drug candidates.

[0217] Step 5:

[0218] The device dynamically displays information optimized for the user's emotional state. The input is the result of the emotion analysis obtained in step 3, and the output is the customized information and interface adjustments presented to the user. Specific actions include displaying a calming interface and suggesting relaxation techniques.

[0219] Step 6:

[0220] Users make decisions based on the provided information on new drug development and care support alerts. Input is information dynamically presented from the terminal, and output is the user's response and feedback. This feedback is reflected in the next prompt.

[0221] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0222] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0223] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0224] [Second Embodiment]

[0225] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0226] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0227] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0228] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0229] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0230] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0231] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0232] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0233] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0234] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0235] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0236] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0237] This invention is a system that supports new drug development using biodata and chemical information. This system enables an efficient new drug development process through the coordinated operation of the server, terminals, and users.

[0238] First, the server collects biodata and chemical information. This includes a function to obtain the latest data in conjunction with a database, and data collection can be performed according to the user's requests. The collected data is preprocessed on the server and formatted into a format suitable for analysis.

[0239] Next, the server uses machine learning algorithms to analyze the pre-processed data. This builds a predictive model for potential new drug candidates. Based on existing drug efficacy data, this model can predict the effectiveness of unknown compounds with high accuracy.

[0240] Subsequently, the server utilizes generative AI technology to automatically generate molecular structures. By analyzing the structures of promising compounds and further evaluating their properties, it supports the selection of new candidate substances.

[0241] As a thought experiment, the server performs in silico simulations to evaluate the dynamics and reactions of compounds in a virtual environment. The results are displayed on the user's terminal and used for further analysis. The user can visually review this data through the terminal and select the most suitable new drug candidate.

[0242] Furthermore, the server analyzes past trial data to optimize clinical trials and proposes trial designs suitable for new drug candidates. This allows users to plan efficient and effective clinical trials.

[0243] As a concrete example, let's assume a user wants to develop a treatment for a specific type of cancer. The server collects relevant genetic data and data on the reactivity of cancer cells, and proposes an optimal molecular structure. Subsequently, based on the simulation results, the user further refines the candidate substance before bringing it to market.

[0244] This series of processes is expected to enable faster and more accurate new drug development than before, thereby supporting innovation in the medical industry.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The server accesses external biodatabases and chemical information systems to collect necessary data. It utilizes APIs to acquire information in real time and selects the type of data according to the user's research topic.

[0248] Step 2:

[0249] The server preprocesses the collected data. Specifically, it corrects missing values, removes noisy data, and normalizes the data. This prepares the data for analysis by machine learning algorithms.

[0250] Step 3:

[0251] The server executes machine learning algorithms and performs data analysis. In this process, it builds a predictive model for selecting new drug candidates. As algorithms, it applies random forests and deep neural networks, and verifies the accuracy of the model.

[0252] Step 4:

[0253] The server automatically generates new molecular structures using generative AI technology. It designs candidate substances and sets evaluation criteria considering their chemical and biological properties. This makes it possible to automatically select promising compounds.

[0254] Step 5:

[0255] The server performs in silico simulations to evaluate the properties of selected compounds in detail. The simulations utilize molecular dynamics and quantum chemical analysis to virtually verify how the new drug candidates function in living organisms.

[0256] Step 6:

[0257] The terminal receives simulation results and analysis data sent from the server and displays them visually to the user. This allows the user to make a final selection of drug candidates based on the analyzed information.

[0258] Step 7:

[0259] The server analyzes past clinical trial data and proposes trial designs that match the new drug candidate. It also provides functions to support the optimization of clinical trials, such as selecting trial participants and setting up trial groups.

[0260] Step 8:

[0261] Users review the proposed clinical trial design via their device and consider further details. This allows the development to proceed to the next stage based on sufficient data regarding the drug's safety and efficacy.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] In recent years, the effective use of vast amounts of biodata and chemical information has become essential in new drug development. However, it is difficult to consistently automate the process of efficiently collecting, preprocessing, and analyzing this data to predict new drug candidates, and a great deal of time and resources are spent on trial and error. Furthermore, because there is a lack of sufficient systems to automatically propose molecular structures using generation technologies and to evaluate their properties in a virtual environment, there is a need to rapidly perform tasks from candidate substance identification to the optimization of clinical trial designs.

[0265] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0266] In this invention, the server includes means for automatically collecting biodata and chemical information; means for preprocessing the data and formatting it into an analyzable form; means for predicting new drug candidates using machine learning algorithms; means for automatically generating and evaluating molecular structures using generation technology; means for performing simulations in a virtual environment based on the predictions and evaluating the properties of the new drug candidates; means for visually displaying the data for user analysis; and means for analyzing past clinical trial data and optimizing the trial design for the new drug candidates. This automates the entire process from data collection to candidate substance selection and trial design proposal, enabling faster and more efficient new drug development.

[0267] "Biodata" refers to biological data such as genetic information, protein structure, and clinical trial results used in biological research and medicine.

[0268] "Chemical substance information" refers to data on the structure, properties, and reactivity of compounds, and plays a particularly important role in new drug development.

[0269] "Automated data collection" refers to the process of obtaining necessary information from databases or online resources without human intervention.

[0270] "Preprocessing" refers to data cleaning and formatting work to convert collected data into an analyzable format.

[0271] A "machine learning algorithm" refers to a computer program that learns patterns by analyzing past data and uses that knowledge to make predictions and classifications about future data.

[0272] A "new drug candidate substance" refers to a compound that shows promise as a therapeutic effect and is being considered as a component of a newly developed drug.

[0273] "Generative techniques" refer to a group of algorithms that generate new data or patterns based on known data, and are particularly used for molecular structure generation.

[0274] A "virtual environment" refers to a computer setting used to simulate and evaluate real-world phenomena through computer simulation.

[0275] "Visual display" refers to presenting data and simulation results to users in the form of images, graphs, 3D models, etc.

[0276] "Study design optimization" refers to the process of analyzing past data and proposing the most effective and efficient implementation plan for a clinical trial.

[0277] The system in this invention supports new drug development through the collaborative efforts of a server, terminal, and user. The server has means for effectively collecting biodata and chemical information. In this process, necessary information is automatically obtained via APIs through integration with databases. In particular, it uses data provided from gene sequencing databases and chemical library databases.

[0278] Upon user request, the server preprocesses the collected data and prepares it for analysis. During this process, data cleaning software is used to impute missing values ​​and normalize the data.

[0279] Next, the server uses machine learning algorithms to analyze the preprocessed data. This analysis utilizes open-source machine learning libraries (e.g., TensorFlow and scikit-learn) to build a model for predicting new drug candidates. Using this model, the effectiveness of new molecules is predicted based on existing drug efficacy data.

[0280] Furthermore, the server automatically generates molecular structures of potential new drugs using generative AI models. This process employs techniques such as variational autoencoders (VAEs) and generative adversarial networks (GANs) to generate structures of potentially promising compounds.

[0281] The generated molecular structure is evaluated through in silico simulation, and the server uses molecular dynamics software (e.g., GROMACS or AMBER) to simulate the dynamics and reactions of compounds in a virtual environment. Based on this result, the server sends data to the terminal, and the user visually analyzes it. Software for enabling 3D display of data is installed on the terminal, and the user can view it and select an optimal new drug candidate.

[0282] Furthermore, the server analyzes past clinical trial data and utilizes statistical analysis software to propose an optimal test design for new drug candidate substances. With this proposal, the user can plan a more efficient clinical trial.

[0283] As a specific example, when a user wants to develop a new cancer treatment drug, the server collects gene database and cancer cell reaction data and takes the process of proposing an optimal molecular structure. An example of a prompt sentence input to the generative AI model would be in the form of "Please propose a novel molecular structure for a cancer treatment drug. There is available gene data and drug efficacy data." It is expected that this system will enable the new drug development process to be carried out quickly and with high precision, promoting innovation in the medical field.

[0284] The flow of the specific process in Example 1 will be described using FIG. 11.

[0285] Step 1:

[0286] The server automatically collects biodata and chemical substance information from the database. As input, it obtains information from the APIs of gene sequence databases and chemical substance libraries. By extracting this data, it outputs the required up-to-date biodata set. As a specific operation, the server periodically calls the API to secure updated data.

[0287] Step 2:

[0288] The server preprocesses the collected data. It uses the raw biodata obtained in step 1 as input. The server outputs the preprocessed data, imputing missing values ​​and performing a normalization process to convert it into a format suitable for analysis. Specifically, the server uses data cleaning software to correct incomplete data items.

[0289] Step 3:

[0290] The server uses pre-processed data to predict potential new drug candidates. It receives pre-processed data as input and analyzes it using machine learning algorithms. The server applies a model trained on existing drug efficacy data and outputs a list of promising new drug candidates. Specifically, the server uses TensorFlow to operate its predictive model through supervised learning.

[0291] Step 4:

[0292] The server automatically generates molecular structures using a generative AI model. The features of the new drug candidate obtained in step 3 are used as input. The AI ​​model performs molecular generation and outputs new molecular structure data. Specifically, the server unfolds a variational autoencoder and generates a new compound from the latent space.

[0293] Step 5:

[0294] The server performs simulations to evaluate the generated molecular structure in a virtual environment. The molecular structure generated in step 4 is used as input. The server performs molecular dynamics simulations and outputs evaluation results for chemical stability and reactivity. Specifically, the server uses GROMACS to simulate molecular dynamics on a computer.

[0295] Step 6:

[0296] The terminal visually displays the simulation results to the user. It uses evaluation results sent from the server as input. The terminal outputs visual analysis results by displaying 3D structures and graphs in a user-friendly format. Specifically, the terminal provides an interactive user interface using 3D rendering software.

[0297] Step 7:

[0298] The server analyzes historical clinical trial data and proposes optimized trial designs. It combines existing trial data and simulation results for analysis. The server presents efficient clinical trial plans and outputs proposed trial designs. Specifically, the server uses statistical analysis software and applies data trends and optimization algorithms.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] The objective of this invention is to streamline the new drug development process and support the identification of highly accurate and predictable new drug candidates. Furthermore, it aims to improve the quality of health management by rapidly providing individually optimized preventive measures and treatment plans through integration with personal health data. Additionally, it aims to optimize clinical trials by effectively visualizing clinical trial information and post-market safety information.

[0302] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0303] In this invention, the server includes means for automatically collecting biodata and chemical substance information, means for analyzing the data and predicting new drug candidate substances using machine learning algorithms, means for evaluating the characteristics of new drug candidates by performing in silico simulations based on the prediction, and means for presenting optimal preventive measures and treatment plans in cooperation with personal health data. As a result, the efficiency of new drug development is enhanced, and it becomes possible to provide individually optimized health management. Furthermore, by using generative AI technology, it is possible to automatically generate and evaluate molecular structures, select new drug candidate substances, and propose treatment methods based on them. With these series of functions, it is possible to optimize the test design by analyzing past data of clinical trials while visualizing clinical trial information and post-marketing safety information.

[0304] "Biodata" refers to information derived from a living body and is a general term for data mainly indicating biological processes and states.

[0305] "Chemical substance information" refers to data related to chemical characteristics such as the structure, properties, and reactivity of compounds.

[0306] "Machine learning algorithm" is a computer program for analyzing a large amount of data and finding patterns, and is a method for making appropriate predictions and classifications from new data.

[0307] "In silico simulation" is a simulation carried out in a virtual environment on a computer and is a means for evaluating the properties of compounds without conducting physical experiments.

[0308] "Generative AI technology" refers to technology for automatically generating new data and structures using artificial intelligence and is a method for assisting creative work.

[0309] "Health data" is a general term for information related to an individual's health status and medical history and is used for medical care and health management.

[0310] A "treatment plan" refers to a set of medical procedures and care plans designed to improve a person's health.

[0311] "Clinical trial information" refers to information about clinical trials conducted to confirm the effectiveness and safety of new drugs.

[0312] "Post-market safety information" refers to information about side effects and effects of a drug that is reported after it has been released to the market.

[0313] "Past clinical trial data" refers to data collected from clinical trials conducted in the past, and this information can be used in future trial design and new drug development.

[0314] "Study design optimization" is the process of improving a study plan to ensure that information is obtained efficiently and effectively when planning and conducting a clinical trial.

[0315] The system implementing this invention is primarily realized through the coordinated operation of a server, terminals, and users. The server automatically collects biodata and chemical information and links it with a database to obtain the latest information. The collected data is analyzed using machine learning algorithms to predict potential new drug candidates. In this process, a program written in Python assists the analysis.

[0316] The server further utilizes generative AI technology to automatically generate and evaluate new molecular structures. These generated molecular structures, combined with the user's health data, enable the creation of individually optimized preventative measures and treatment plans. This improves the quality of health management.

[0317] The device visually displays collected and analyzed data to the user and suggests optimal treatment methods based on health data. Users can then formulate specific treatment plans based on this information. This enables the practice of medical care tailored to individual needs.

[0318] As a concrete example, individual residents of a smart city can use this system to monitor their health on a daily basis and identify the most suitable medication for preventing seasonal influenza. Furthermore, this system visualizes clinical trial information and post-market safety information, contributing to raising residents' awareness of drug safety.

[0319] Examples of prompts to input into a generative AI model include:

[0320] "Based on recent health data, please suggest the most suitable medication for the symptoms of [specific symptom]."

[0321] "Please generate a list of medications suitable for vaccination, taking into account the current health status."

[0322] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0323] Step 1:

[0324] The server collects biodata and chemical information via the internet and databases. Inputs are various databases, and output is the collected raw data. Scripts on the server periodically update the information.

[0325] Step 2:

[0326] The server preprocesses the collected data. Preprocessing includes data standardization and cleaning. The input is raw data, and the output is data in a format suitable for analysis. In this process, a Python library is used to unify the data format.

[0327] Step 3:

[0328] The server runs machine learning algorithms on preprocessed data to predict potential new drug candidates. The input is standardized data, and the output is a list of potential drug candidates. Existing drug data is used to train the model, and then predictions are made on unknown data.

[0329] Step 4:

[0330] The server utilizes generative AI technology to generate and evaluate new molecular structures for proposed candidate substances. The input is a list of new drug candidates, and the output is the evaluated molecular structures. Simulations are then performed using a generative model to conduct characterization.

[0331] Step 5:

[0332] The server generates personalized treatment and preventative measures based on the user's health data. The input is individual health data and AI analysis results, and the output is a personalized medical plan. This process involves inputting prompts into an AI model to obtain a specific plan.

[0333] Step 6:

[0334] The device visually displays the generated results to the user, providing further insights. The input is an individualized medical plan, and the output is easy-to-understand information displayed in the user interface. Specifically, information is communicated through a health dashboard.

[0335] Step 7:

[0336] Users make appropriate decisions and implement treatment plans based on the information provided. The output is a record of medical actions, useful for subsequent data analysis and feedback. Users regularly update their health status through the in-app feedback function.

[0337] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0338] This invention is a new drug development support system incorporating an emotion engine, which allows for the smoother and more effective development process by recognizing the user's emotional state in real time and dynamically adjusting the system's behavior.

[0339] The server automatically collects existing biodata and chemical information. The collected data is analyzed using machine learning algorithms and used to predict potential new drug candidates. Next, generative AI technology is used to generate and evaluate the structures of candidate molecules, leading to advanced drug candidate selection.

[0340] Furthermore, the server uses emotional data transmitted from the user's terminal to activate an emotion engine and understand the user's current emotional state. The emotion engine has the ability to dynamically change the format of information presented by the system to assess how stressed the user is using the system and to maintain the user's interest and concentration.

[0341] For example, if the system detects that a user is feeling tired, it simplifies the interface on the device and highlights important information. Similarly, if a user is feeling confused or stressed, the system improves the user experience by providing support tools and detailed help information.

[0342] Regarding clinical trials, the server analyzes past trial data and proposes more effective trial designs. This process is also optimized by the emotion engine, enabling flexible suggestions based on user feedback. The emotion engine builds an optimization loop based on user feedback, effectively incorporating user preferences during the development process.

[0343] In this way, this system combines emotion recognition technology with the new drug development process to provide users with a less stressful, efficient, and supportive development environment.

[0344] The following describes the processing flow.

[0345] Step 1:

[0346] The server collects necessary biodata and chemical information from external biodatabases. This utilizes API connections to retrieve data in real time and performs filtering according to user requests.

[0347] Step 2:

[0348] The server preprocesses the collected data and formats it into a format suitable for analysis by machine learning algorithms. In this stage, missing values ​​are imputed, noisy data is removed, and normalization is performed.

[0349] Step 3:

[0350] The server analyzes data using machine learning algorithms to predict potential new drug candidates. Here, random forests and deep learning are utilized as algorithms to build models that predict the effectiveness of new drugs with high accuracy.

[0351] Step 4:

[0352] The server utilizes generative AI technology to generate new molecular structures. By evaluating the structures of promising compounds and selecting new candidates based on these evaluations, the accuracy of the search is improved.

[0353] Step 5:

[0354] The server performs in silico simulations on the generated candidate substances. This process uses molecular dynamics simulations and quantum chemical calculations to virtually analyze the behavior of the drugs in vivo.

[0355] Step 6:

[0356] The device collects emotional data from the user and sends it to a server. This data is analyzed using facial recognition and voice analysis technologies with a camera and microphone to detect emotions and provide real-time feedback to the server.

[0357] Step 7:

[0358] The server analyzes the received emotional data using an emotion engine. This evaluates the user's stress level and concentration level, and dynamically adjusts the system interface and feedback format based on the results.

[0359] Step 8:

[0360] Based on the analysis results from the emotion engine, the server provides users with appropriate information and optimizes the interface. For example, if the server determines that the user is in a high-stress state, it will provide a more intuitive interface and detailed help.

[0361] Step 9:

[0362] The server analyzes past clinical trial data and proposes a suitable trial design for the new drug candidate. Based on user feedback and emotional state, it customizes the trial plan and provides the appropriate support the user needs.

[0363] Step 10:

[0364] Users can review the analysis results and trial designs provided through their devices and revise the development direction as needed. This enables users to achieve efficient and less stressful new drug development.

[0365] (Example 2)

[0366] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0367] In the new drug development process, there is a need to efficiently and effectively analyze vast amounts of data to identify promising drug candidates more quickly. Furthermore, optimizing the interface to consider the user's emotional state is a challenge in reducing developer stress and improving work efficiency.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0369] In this invention, the server includes means for automatically collecting information, means for analyzing the data and predicting substances using an algorithm, and means for evaluating based on the prediction. This makes it possible to streamline the new drug development process and optimally support the user's work.

[0370] "Means of automatically collecting information" refers to technologies for continuously acquiring necessary information from networks and databases through automated processes.

[0371] "Methods for analyzing data and predicting substances using algorithms" refers to methods for analyzing collected data using analytical techniques and predicting the properties and effectiveness of new chemical substances using machine learning algorithms.

[0372] "Methods for evaluation based on predictions" refer to the process of examining the results predicted by an algorithm according to various evaluation criteria, and confirming their effectiveness and safety based on those criteria.

[0373] "Means for the automatic generation and evaluation of structures using technology" refers to technologies that automatically create molecular structures of materials using generative algorithms, simulate the results, and determine their usefulness.

[0374] "A means of analyzing past data and proposing optimized test designs" refers to a system that analyzes accumulated test results to date, makes suggestions to help design new tests, and enables more efficient test implementation.

[0375] The implementation of this invention involves a series of systems for streamlining the new drug development process through the interaction of servers, terminals, and users.

[0376] The server first connects to the network and automatically collects biometric and chemical information from public databases and specialized information sources. The server particularly utilizes cloud platforms such as Google Cloud and AWS, collecting data using APIs and web scraping techniques. The collected data is analyzed using machine learning libraries such as TensorFlow and PyTorch, and algorithms are used to predict the properties of potential new drugs. The algorithmic models are built upon existing scientific knowledge and data-driven methods.

[0377] Furthermore, the server utilizes generative AI technology to automatically generate and evaluate the molecular structures of materials. This process employs specialized chemical simulation software to understand how the molecules created by the generative AI model behave physically and chemically.

[0378] The device functions as a tool for collecting user emotional data. It uses vital information from a smartwatch and facial recognition technology via a webcam to collect and send the user's emotional state to a server. The server analyzes this emotional data in real time using Python or R. Based on the analyzed emotional state, it adaptively adjusts how the user optimally interacts with the digital interface.

[0379] For example, if the device detects that the user is feeling fatigued, it simplifies the displayed content and uses highlighted important information to attract the user's attention. Furthermore, if confusion or stress is detected, the system proactively improves the user experience by providing detailed help information and support tools.

[0380] Examples of prompt statements include:

[0381] "To streamline the new drug development process, we would like to evaluate potential drug candidates using generative AI models. Furthermore, please teach us methods for analyzing users' emotional states and adjusting the system accordingly."

[0382] Thus, this invention provides a system that comprehensively supports new drug development by combining data collection, machine learning, and sentiment analysis.

[0383] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0384] Step 1:

[0385] The server automatically collects biometric and chemical information over the network. It requires data retrieval requests from public databases and specialized information sources using APIs or web scraping techniques as input. The server then outputs a structured dataset.

[0386] Step 2:

[0387] The server analyzes the collected data. The dataset obtained in Step 1 is used as input. Machine learning algorithms, particularly TensorFlow and PyTorch, are used to process the data and predict potential drug candidates. The output of this process is the predicted characteristics of the potential drug candidates. Specifically, this data is used to score and rank promising compounds.

[0388] Step 3:

[0389] The server uses a generative AI model to automatically generate structures for new drug candidate molecules. Using the prediction results from step 2 as input, the generative AI model generates new molecular candidates. The output is the structure of the generated molecule and its evaluation results. Specifically, the generative model performs structural simulations and physical property evaluations.

[0390] Step 4:

[0391] The device collects user emotional data. Inputs include vital data and facial recognition data from smartwatches and webcams. This data is acquired and aggregated in real time and sent to a server. The output is a dataset representing the user's current emotional state.

[0392] Step 5:

[0393] The server analyzes the emotional data sent from the terminal. The input is the emotional data collected in step 4, which is analyzed using Python or R. This allows the server to identify the user's emotional state and adjust the interface accordingly. The output is an adaptive strategy for the interface based on the user's state. Specifically, it dynamically updates the information presentation format according to the emotional state.

[0394] Step 6:

[0395] Users advance new drug development through an interface based on the analysis results. They receive the output results from Step 5 as input and can work efficiently with the optimized interface. Outputs include user feedback and progress information regarding new drug development. Specific actions include UX adjustments such as content highlighting and the presentation of additional support tools.

[0396] (Application Example 2)

[0397] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0398] In conventional drug development processes, effectively collecting and analyzing biodata and chemical information to select candidate substances was crucial. However, the lack of consideration for emotional states resulted in a heavy user burden and difficulty in efficient process management. Furthermore, there is the issue of insufficient care support that incorporates the emotions of the subjects.

[0399] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0400] In this invention, the server includes means for automatically collecting biodata and chemical information, means for analyzing the data and predicting new drug candidates using machine learning algorithms, and means for dynamically presenting information based on the user's emotional state by collecting and analyzing emotional information. This makes it possible to efficiently and interactively advance new drug development in accordance with the user's emotional state.

[0401] "Biodata" refers to information related to living organisms, and in particular, data that includes molecular biological or biochemical information.

[0402] "Chemical substance information" refers to scientific information related to chemical substances, such as their properties, structure, and reactivity.

[0403] A "machine learning algorithm" is a computational method used to analyze large amounts of data and find patterns and trends.

[0404] "Emotional information" refers to data that indicates an individual's emotional state, and includes things like facial expressions, tone of voice, and heart rate.

[0405] "Generative AI technology" is a technology that uses artificial intelligence to generate new data and information and creatively solve problems.

[0406] "Care support" refers to activities and processes that provide assistance with daily life for the elderly and those who require care.

[0407] The system realizing this invention features a program in which various software components work in coordination. The server primarily automatically collects biodata and chemical information and analyzes this data using machine learning algorithms. The analyzed data is then used to automatically generate molecular structures using generative AI technology and evaluate them. This makes it possible to efficiently select and evaluate new drug candidates.

[0408] Furthermore, using emotional information collected from the device, the server activates an emotion engine to understand the user's emotional state in real time. Based on this information, it dynamically presents information appropriate to the user's current situation. In addition, in care support settings, it is designed to flexibly adjust care procedures based on emotion analysis to reduce the user's burden.

[0409] A concrete example is when an elderly person shows anxiety; the device suggests calming exercises or music. In this invention, an example of a prompt utilizing a generative AI model is: "Analyze the elderly person's current emotional state and generate appropriate care advice. If the user shows anxiety, suggest calming exercises."

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The server automatically collects data related to living organisms and information related to chemical substances. Inputs are data from external databases and sensors, and the output is integrated, analyzable data. This data is then formatted into a specific form for subsequent processing by machine learning algorithms.

[0413] Step 2:

[0414] The server uses machine learning algorithms to analyze the collected data. The input is the data formatted in step 1. Through data patterns and hypothesis building, it predicts potential new drug candidates. This process yields an output in the form of a drug candidate list.

[0415] Step 3:

[0416] The device collects emotional information from the user. The input consists of real-time emotional data such as the user's facial expressions, voice, and heart rate. An emotion engine analyzes this data, outputting the user's emotional state. This analysis result is used to present effective support information to the user.

[0417] Step 4:

[0418] The server automatically generates and evaluates the molecular structures of predicted drug candidates using generative AI technology. The input is the list of drug candidates generated in step 2, and the output is a list of refined new drug candidates along with the evaluation results for each structure. This process selects high-quality drug candidates.

[0419] Step 5:

[0420] The device dynamically displays information optimized for the user's emotional state. The input is the result of the emotion analysis obtained in step 3, and the output is the customized information and interface adjustments presented to the user. Specific actions include displaying a calming interface and suggesting relaxation techniques.

[0421] Step 6:

[0422] Users make decisions based on the provided information on new drug development and care support alerts. Input is information dynamically presented from the terminal, and output is the user's response and feedback. This feedback is reflected in the next prompt.

[0423] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0424] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0425] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0429] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0430] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0431] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0432] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0433] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0434] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0435] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0436] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0437] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0438] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0439] This invention is a system that supports new drug development using biodata and chemical information. This system enables an efficient new drug development process through the coordinated operation of the server, terminals, and users.

[0440] First, the server collects biodata and chemical information. This includes a function to obtain the latest data in conjunction with a database, and data collection can be performed according to the user's requests. The collected data is preprocessed on the server and formatted into a format suitable for analysis.

[0441] Next, the server uses machine learning algorithms to analyze the pre-processed data. This builds a predictive model for potential new drug candidates. Based on existing drug efficacy data, this model can predict the effectiveness of unknown compounds with high accuracy.

[0442] Subsequently, the server utilizes generative AI technology to automatically generate molecular structures. By analyzing the structures of promising compounds and further evaluating their properties, it supports the selection of new candidate substances.

[0443] As a thought experiment, the server performs in silico simulations to evaluate the dynamics and reactions of compounds in a virtual environment. The results are displayed on the user's terminal and used for further analysis. The user can visually review this data through the terminal and select the most suitable new drug candidate.

[0444] Furthermore, the server analyzes past trial data to optimize clinical trials and proposes trial designs suitable for new drug candidates. This allows users to plan efficient and effective clinical trials.

[0445] As a concrete example, let's assume a user wants to develop a treatment for a specific type of cancer. The server collects relevant genetic data and data on the reactivity of cancer cells, and proposes an optimal molecular structure. Subsequently, based on the simulation results, the user further refines the candidate substance before bringing it to market.

[0446] This series of processes is expected to enable faster and more accurate new drug development than before, thereby supporting innovation in the medical industry.

[0447] The following describes the processing flow.

[0448] Step 1:

[0449] The server accesses external biodatabases and chemical information systems to collect necessary data. It utilizes APIs to acquire information in real time and selects the type of data according to the user's research topic.

[0450] Step 2:

[0451] The server preprocesses the collected data. Specifically, it corrects missing values, removes noisy data, and normalizes the data. This prepares the data for analysis by machine learning algorithms.

[0452] Step 3:

[0453] The server executes machine learning algorithms and performs data analysis. In this process, it builds a predictive model for selecting new drug candidates. As algorithms, it applies random forests and deep neural networks, and verifies the accuracy of the model.

[0454] Step 4:

[0455] The server automatically generates new molecular structures using generative AI technology. It designs candidate substances and sets evaluation criteria considering their chemical and biological properties. This makes it possible to automatically select promising compounds.

[0456] Step 5:

[0457] The server performs in silico simulations to evaluate the properties of selected compounds in detail. The simulations utilize molecular dynamics and quantum chemical analysis to virtually verify how the new drug candidates function in living organisms.

[0458] Step 6:

[0459] The terminal receives simulation results and analysis data sent from the server and displays them visually to the user. This allows the user to make a final selection of drug candidates based on the analyzed information.

[0460] Step 7:

[0461] The server analyzes past clinical trial data and proposes trial designs that match the new drug candidate. It also provides functions to support the optimization of clinical trials, such as selecting trial participants and setting up trial groups.

[0462] Step 8:

[0463] Users review the proposed clinical trial design via their device and consider further details. This allows the development to proceed to the next stage based on sufficient data regarding the drug's safety and efficacy.

[0464] (Example 1)

[0465] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0466] In recent years, the effective use of vast amounts of biodata and chemical information has become essential in new drug development. However, it is difficult to consistently automate the process of efficiently collecting, preprocessing, and analyzing this data to predict new drug candidates, and a great deal of time and resources are spent on trial and error. Furthermore, because there is a lack of sufficient systems to automatically propose molecular structures using generation technologies and to evaluate their properties in a virtual environment, there is a need to rapidly perform tasks from candidate substance identification to the optimization of clinical trial designs.

[0467] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0468] In this invention, the server includes means for automatically collecting biodata and chemical information; means for preprocessing the data and formatting it into an analyzable form; means for predicting new drug candidates using machine learning algorithms; means for automatically generating and evaluating molecular structures using generation technology; means for performing simulations in a virtual environment based on the predictions and evaluating the properties of the new drug candidates; means for visually displaying the data for user analysis; and means for analyzing past clinical trial data and optimizing the trial design for the new drug candidates. This automates the entire process from data collection to candidate substance selection and trial design proposal, enabling faster and more efficient new drug development.

[0469] "Biodata" refers to biological data such as genetic information, protein structure, and clinical trial results used in biological research and medicine.

[0470] "Chemical substance information" refers to data on the structure, properties, and reactivity of compounds, and plays a particularly important role in new drug development.

[0471] "Automated data collection" refers to the process of obtaining necessary information from databases or online resources without human intervention.

[0472] "Preprocessing" refers to data cleaning and formatting work to convert collected data into an analyzable format.

[0473] A "machine learning algorithm" refers to a computer program that learns patterns by analyzing past data and uses that knowledge to make predictions and classifications about future data.

[0474] A "new drug candidate substance" refers to a compound that shows promise as a therapeutic effect and is being considered as a component of a newly developed drug.

[0475] "Generative techniques" refer to a group of algorithms that generate new data or patterns based on known data, and are particularly used for molecular structure generation.

[0476] A "virtual environment" refers to a computer setting used to simulate and evaluate real-world phenomena through computer simulation.

[0477] "Visual display" refers to presenting data and simulation results to users in the form of images, graphs, 3D models, etc.

[0478] "Study design optimization" refers to the process of analyzing past data and proposing the most effective and efficient implementation plan for a clinical trial.

[0479] The system in this invention supports new drug development through the collaborative efforts of a server, terminal, and user. The server has means for effectively collecting biodata and chemical information. In this process, necessary information is automatically obtained via APIs through integration with databases. In particular, it uses data provided from gene sequencing databases and chemical library databases.

[0480] Upon user request, the server preprocesses the collected data and prepares it for analysis. During this process, data cleaning software is used to impute missing values ​​and normalize the data.

[0481] Next, the server uses machine learning algorithms to analyze the preprocessed data. This analysis utilizes open-source machine learning libraries (e.g., TensorFlow and scikit-learn) to build a model for predicting new drug candidates. Using this model, the effectiveness of new molecules is predicted based on existing drug efficacy data.

[0482] Furthermore, the server automatically generates molecular structures of potential new drugs using generative AI models. This process employs techniques such as variational autoencoders (VAEs) and generative adversarial networks (GANs) to generate structures of potentially promising compounds.

[0483] The created molecular structures are evaluated through in silico simulations, and the server uses molecular dynamics software (e.g., GROMACS or AMBER) to simulate the dynamics and reactions of compounds in a virtual environment. Based on these results, the server sends the data to a terminal, which the user then analyzes visually. The terminal is equipped with software that enables 3D visualization of the data, allowing the user to select the most suitable new drug candidates.

[0484] Furthermore, the server utilizes statistical analysis software to analyze past clinical trial data and propose the optimal trial design for new drug candidates. This proposal allows users to plan more efficient clinical trials.

[0485] For example, if a user wants to develop a new cancer treatment drug, the server will collect gene databases and cancer cell response data and propose an optimal molecular structure. An example of a prompt to be input into the generating AI model would be, "Please propose a novel molecular structure for a cancer treatment drug. Genetic data and efficacy data are available." This system is expected to accelerate the new drug development process with high accuracy, thereby promoting innovation in the medical field.

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The server automatically collects biodata and chemical information from databases. It takes information from gene sequencing databases and chemical library APIs as input. By extracting this data, it outputs the latest biodataset required. Specifically, the server periodically calls the APIs to ensure updated data is available.

[0489] Step 2:

[0490] The server preprocesses the collected data. It uses the raw biodata obtained in step 1 as input. The server outputs the preprocessed data, imputing missing values ​​and performing a normalization process to convert it into a format suitable for analysis. Specifically, the server uses data cleaning software to correct incomplete data items.

[0491] Step 3:

[0492] The server uses pre-processed data to predict potential new drug candidates. It receives pre-processed data as input and analyzes it using machine learning algorithms. The server applies a model trained on existing drug efficacy data and outputs a list of promising new drug candidates. Specifically, the server uses TensorFlow to operate its predictive model through supervised learning.

[0493] Step 4:

[0494] The server automatically generates molecular structures using a generative AI model. The features of the new drug candidate obtained in step 3 are used as input. The AI ​​model performs molecular generation and outputs new molecular structure data. Specifically, the server unfolds a variational autoencoder and generates a new compound from the latent space.

[0495] Step 5:

[0496] The server performs simulations to evaluate the generated molecular structure in a virtual environment. The molecular structure generated in step 4 is used as input. The server performs molecular dynamics simulations and outputs evaluation results for chemical stability and reactivity. Specifically, the server uses GROMACS to simulate molecular dynamics on a computer.

[0497] Step 6:

[0498] The terminal visually displays the simulation results to the user. It uses evaluation results sent from the server as input. The terminal outputs visual analysis results by displaying 3D structures and graphs in a user-friendly format. Specifically, the terminal provides an interactive user interface using 3D rendering software.

[0499] Step 7:

[0500] The server analyzes historical clinical trial data and proposes optimized trial designs. It combines existing trial data and simulation results for analysis. The server presents efficient clinical trial plans and outputs proposed trial designs. Specifically, the server uses statistical analysis software and applies data trends and optimization algorithms.

[0501] (Application Example 1)

[0502] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0503] The objective of this invention is to streamline the new drug development process and support the identification of highly accurate and predictable new drug candidates. Furthermore, it aims to improve the quality of health management by rapidly providing individually optimized preventive measures and treatment plans through integration with personal health data. Additionally, it aims to optimize clinical trials by effectively visualizing clinical trial information and post-market safety information.

[0504] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0505] This invention includes a server that automatically collects biodata and chemical information, analyzes the data and predicts new drug candidates using machine learning algorithms, performs in silico simulations based on the predictions to evaluate the characteristics of the new drug candidates, and links with individual health data to present optimal preventive measures and treatment plans. This increases the efficiency of new drug development and enables the provision of individually optimized health management. Furthermore, it can automatically generate and evaluate molecular structures using generative AI technology, select new drug candidates, and propose treatment methods based on them. Through this series of functions, it is possible to analyze past clinical trial data and optimize trial designs while visualizing clinical trial information and post-market safety information.

[0506] "Biodata" is a general term for information originating from living organisms, primarily data that indicates biological processes and states.

[0507] "Chemical substance information" refers to data concerning the chemical properties of a compound, such as its structure, properties, and reactivity.

[0508] A "machine learning algorithm" is a computer program that analyzes large amounts of data to find patterns, and is a method for making appropriate predictions and classifications from new data.

[0509] "In silico simulation" is a simulation performed in a virtual environment on a computer, and is a means of evaluating the properties of compounds and other substances without conducting physical experiments.

[0510] "Generative AI technology" refers to techniques that use artificial intelligence to automatically generate new data and structures, and is a method that supports creative work.

[0511] "Health data" is a general term for information about an individual's health status and medical history, and is used for medical care and health management.

[0512] A "treatment plan" refers to a set of medical procedures and care plans designed to improve a person's health.

[0513] "Clinical trial information" refers to information about clinical trials conducted to confirm the effectiveness and safety of new drugs.

[0514] "Post-market safety information" refers to information about side effects and effects of a drug that is reported after it has been released to the market.

[0515] "Past clinical trial data" refers to data collected from clinical trials conducted in the past, and this information can be used in future trial design and new drug development.

[0516] "Study design optimization" is the process of improving a study plan to ensure that information is obtained efficiently and effectively when planning and conducting a clinical trial.

[0517] The system implementing this invention is primarily realized through the coordinated operation of a server, terminals, and users. The server automatically collects biodata and chemical information and links it with a database to obtain the latest information. The collected data is analyzed using machine learning algorithms to predict potential new drug candidates. In this process, a program written in Python assists the analysis.

[0518] The server further utilizes generative AI technology to automatically generate and evaluate new molecular structures. These generated molecular structures, combined with the user's health data, enable the creation of individually optimized preventative measures and treatment plans. This improves the quality of health management.

[0519] The device visually displays collected and analyzed data to the user and suggests optimal treatment methods based on health data. Users can then formulate specific treatment plans based on this information. This enables the practice of medical care tailored to individual needs.

[0520] As a concrete example, individual residents of a smart city can use this system to monitor their health on a daily basis and identify the most suitable medication for preventing seasonal influenza. Furthermore, this system visualizes clinical trial information and post-market safety information, contributing to raising residents' awareness of drug safety.

[0521] Examples of prompts to input into a generative AI model include:

[0522] "Based on recent health data, please suggest the most suitable medication for the symptoms of [specific symptom]."

[0523] "Please generate a list of medications suitable for vaccination, taking into account the current health status."

[0524] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0525] Step 1:

[0526] The server collects biodata and chemical information via the internet and databases. Inputs are various databases, and output is the collected raw data. Scripts on the server periodically update the information.

[0527] Step 2:

[0528] The server preprocesses the collected data. Preprocessing includes data standardization and cleaning. The input is raw data, and the output is data in a format suitable for analysis. In this process, a Python library is used to unify the data format.

[0529] Step 3:

[0530] The server runs machine learning algorithms on preprocessed data to predict potential new drug candidates. The input is standardized data, and the output is a list of potential drug candidates. Existing drug data is used to train the model, and then predictions are made on unknown data.

[0531] Step 4:

[0532] The server utilizes generative AI technology to generate and evaluate new molecular structures for proposed candidate substances. The input is a list of new drug candidates, and the output is the evaluated molecular structures. Simulations are then performed using a generative model to conduct characterization.

[0533] Step 5:

[0534] The server generates personalized treatment and preventative measures based on the user's health data. The input is individual health data and AI analysis results, and the output is a personalized medical plan. This process involves inputting prompts into an AI model to obtain a specific plan.

[0535] Step 6:

[0536] The device visually displays the generated results to the user, providing further insights. The input is an individualized medical plan, and the output is easy-to-understand information displayed in the user interface. Specifically, information is communicated through a health dashboard.

[0537] Step 7:

[0538] Users make appropriate decisions and implement treatment plans based on the information provided. The output is a record of medical actions, useful for subsequent data analysis and feedback. Users regularly update their health status through the in-app feedback function.

[0539] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0540] This invention is a new drug development support system incorporating an emotion engine, which allows for the smoother and more effective development process by recognizing the user's emotional state in real time and dynamically adjusting the system's behavior.

[0541] The server automatically collects existing biodata and chemical information. The collected data is analyzed using machine learning algorithms and used to predict potential new drug candidates. Next, generative AI technology is used to generate and evaluate the structures of candidate molecules, leading to advanced drug candidate selection.

[0542] Furthermore, the server uses emotional data transmitted from the user's terminal to activate an emotion engine and understand the user's current emotional state. The emotion engine has the ability to dynamically change the format of information presented by the system to assess how stressed the user is using the system and to maintain the user's interest and concentration.

[0543] For example, if the system detects that a user is feeling tired, it simplifies the interface on the device and highlights important information. Similarly, if a user is feeling confused or stressed, the system improves the user experience by providing support tools and detailed help information.

[0544] Regarding clinical trials, the server analyzes past trial data and proposes more effective trial designs. This process is also optimized by the emotion engine, enabling flexible suggestions based on user feedback. The emotion engine builds an optimization loop based on user feedback, effectively incorporating user preferences during the development process.

[0545] In this way, this system combines emotion recognition technology with the new drug development process to provide users with a less stressful, efficient, and supportive development environment.

[0546] The following describes the processing flow.

[0547] Step 1:

[0548] The server collects necessary biodata and chemical information from external biodatabases. This utilizes API connections to retrieve data in real time and performs filtering according to user requests.

[0549] Step 2:

[0550] The server preprocesses the collected data and formats it into a format suitable for analysis by machine learning algorithms. In this stage, missing values ​​are imputed, noisy data is removed, and normalization is performed.

[0551] Step 3:

[0552] The server analyzes data using machine learning algorithms to predict potential new drug candidates. Here, random forests and deep learning are utilized as algorithms to build models that predict the effectiveness of new drugs with high accuracy.

[0553] Step 4:

[0554] The server utilizes generative AI technology to generate new molecular structures. By evaluating the structures of promising compounds and selecting new candidates based on these evaluations, the accuracy of the search is improved.

[0555] Step 5:

[0556] The server performs in silico simulations on the generated candidate substances. This process uses molecular dynamics simulations and quantum chemical calculations to virtually analyze the behavior of the drugs in vivo.

[0557] Step 6:

[0558] The device collects emotional data from the user and sends it to a server. This data is analyzed using facial recognition and voice analysis technologies with a camera and microphone to detect emotions and provide real-time feedback to the server.

[0559] Step 7:

[0560] The server analyzes the received emotional data using an emotion engine. This evaluates the user's stress level and concentration level, and dynamically adjusts the system interface and feedback format based on the results.

[0561] Step 8:

[0562] Based on the analysis results from the emotion engine, the server provides users with appropriate information and optimizes the interface. For example, if the server determines that the user is in a high-stress state, it will provide a more intuitive interface and detailed help.

[0563] Step 9:

[0564] The server analyzes past clinical trial data and proposes a suitable trial design for the new drug candidate. Based on user feedback and emotional state, it customizes the trial plan and provides the appropriate support the user needs.

[0565] Step 10:

[0566] Users can review the analysis results and trial designs provided through their devices and revise the development direction as needed. This enables users to achieve efficient and less stressful new drug development.

[0567] (Example 2)

[0568] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0569] In the new drug development process, there is a need to efficiently and effectively analyze vast amounts of data to identify promising drug candidates more quickly. Furthermore, optimizing the interface to consider the user's emotional state is a challenge in reducing developer stress and improving work efficiency.

[0570] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0571] In this invention, the server includes means for automatically collecting information, means for analyzing the data and predicting substances using an algorithm, and means for evaluating based on the prediction. This makes it possible to streamline the new drug development process and optimally support the user's work.

[0572] "Means of automatically collecting information" refers to technologies for continuously acquiring necessary information from networks and databases through automated processes.

[0573] "Methods for analyzing data and predicting substances using algorithms" refers to methods for analyzing collected data using analytical techniques and predicting the properties and effectiveness of new chemical substances using machine learning algorithms.

[0574] "Methods for evaluation based on predictions" refer to the process of examining the results predicted by an algorithm according to various evaluation criteria, and confirming their effectiveness and safety based on those criteria.

[0575] "Means for the automatic generation and evaluation of structures using technology" refers to technologies that automatically create molecular structures of materials using generative algorithms, simulate the results, and determine their usefulness.

[0576] "A means of analyzing past data and proposing optimized test designs" refers to a system that analyzes accumulated test results to date, makes suggestions to help design new tests, and enables more efficient test implementation.

[0577] The implementation of this invention involves a series of systems for streamlining the new drug development process through the interaction of servers, terminals, and users.

[0578] The server first connects to the network and automatically collects biometric and chemical information from public databases and specialized information sources. The server particularly utilizes cloud platforms such as Google Cloud and AWS, collecting data using APIs and web scraping techniques. The collected data is analyzed using machine learning libraries such as TensorFlow and PyTorch, and algorithms are used to predict the properties of potential new drugs. The algorithmic models are built upon existing scientific knowledge and data-driven methods.

[0579] Furthermore, the server utilizes generative AI technology to automatically generate and evaluate the molecular structures of materials. This process employs specialized chemical simulation software to understand how the molecules created by the generative AI model behave physically and chemically.

[0580] The device functions as a tool for collecting user emotional data. It uses vital information from a smartwatch and facial recognition technology via a webcam to collect and send the user's emotional state to a server. The server analyzes this emotional data in real time using Python or R. Based on the analyzed emotional state, it adaptively adjusts how the user optimally interacts with the digital interface.

[0581] For example, if the device detects that the user is feeling fatigued, it simplifies the displayed content and uses highlighted important information to attract the user's attention. Furthermore, if confusion or stress is detected, the system proactively improves the user experience by providing detailed help information and support tools.

[0582] Examples of prompt statements include:

[0583] "To streamline the new drug development process, we would like to evaluate potential drug candidates using generative AI models. Furthermore, please teach us methods for analyzing users' emotional states and adjusting the system accordingly."

[0584] Thus, this invention provides a system that comprehensively supports new drug development by combining data collection, machine learning, and sentiment analysis.

[0585] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0586] Step 1:

[0587] The server automatically collects biometric and chemical information over the network. It requires data retrieval requests from public databases and specialized information sources using APIs or web scraping techniques as input. The server then outputs a structured dataset.

[0588] Step 2:

[0589] The server analyzes the collected data. The dataset obtained in Step 1 is used as input. Machine learning algorithms, particularly TensorFlow and PyTorch, are used to process the data and predict potential drug candidates. The output of this process is the predicted characteristics of the potential drug candidates. Specifically, this data is used to score and rank promising compounds.

[0590] Step 3:

[0591] The server uses a generative AI model to automatically generate structures for new drug candidate molecules. Using the prediction results from step 2 as input, the generative AI model generates new molecular candidates. The output is the structure of the generated molecule and its evaluation results. Specifically, the generative model performs structural simulations and physical property evaluations.

[0592] Step 4:

[0593] The device collects user emotional data. Inputs include vital data and facial recognition data from smartwatches and webcams. This data is acquired and aggregated in real time and sent to a server. The output is a dataset representing the user's current emotional state.

[0594] Step 5:

[0595] The server analyzes the emotional data sent from the terminal. The input is the emotional data collected in step 4, which is analyzed using Python or R. This allows the server to identify the user's emotional state and adjust the interface accordingly. The output is an adaptive strategy for the interface based on the user's state. Specifically, it dynamically updates the information presentation format according to the emotional state.

[0596] Step 6:

[0597] Users advance new drug development through an interface based on the analysis results. They receive the output results from Step 5 as input and can work efficiently with the optimized interface. Outputs include user feedback and progress information regarding new drug development. Specific actions include UX adjustments such as content highlighting and the presentation of additional support tools.

[0598] (Application Example 2)

[0599] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0600] In conventional drug development processes, effectively collecting and analyzing biodata and chemical information to select candidate substances was crucial. However, the lack of consideration for emotional states resulted in a heavy user burden and difficulty in efficient process management. Furthermore, there is the issue of insufficient care support that incorporates the emotions of the subjects.

[0601] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0602] In this invention, the server includes means for automatically collecting biodata and chemical information, means for analyzing the data and predicting new drug candidates using machine learning algorithms, and means for dynamically presenting information based on the user's emotional state by collecting and analyzing emotional information. This makes it possible to efficiently and interactively advance new drug development in accordance with the user's emotional state.

[0603] "Biodata" refers to information related to living organisms, and in particular, data that includes molecular biological or biochemical information.

[0604] "Chemical substance information" refers to scientific information related to chemical substances, such as their properties, structure, and reactivity.

[0605] A "machine learning algorithm" is a computational method used to analyze large amounts of data and find patterns and trends.

[0606] "Emotional information" refers to data that indicates an individual's emotional state, and includes things like facial expressions, tone of voice, and heart rate.

[0607] "Generative AI technology" is a technology that uses artificial intelligence to generate new data and information and creatively solve problems.

[0608] "Care support" refers to activities and processes that provide assistance with daily life for the elderly and those who require care.

[0609] The system realizing this invention features a program in which various software components work in coordination. The server primarily automatically collects biodata and chemical information and analyzes this data using machine learning algorithms. The analyzed data is then used to automatically generate molecular structures using generative AI technology and evaluate them. This makes it possible to efficiently select and evaluate new drug candidates.

[0610] Furthermore, using emotional information collected from the device, the server activates an emotion engine to understand the user's emotional state in real time. Based on this information, it dynamically presents information appropriate to the user's current situation. In addition, in care support settings, it is designed to flexibly adjust care procedures based on emotion analysis to reduce the user's burden.

[0611] A concrete example is when an elderly person shows anxiety; the device suggests calming exercises or music. In this invention, an example of a prompt utilizing a generative AI model is: "Analyze the elderly person's current emotional state and generate appropriate care advice. If the user shows anxiety, suggest calming exercises."

[0612] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0613] Step 1:

[0614] The server automatically collects data related to living organisms and information related to chemical substances. Inputs are data from external databases and sensors, and the output is integrated, analyzable data. This data is then formatted into a specific form for subsequent processing by machine learning algorithms.

[0615] Step 2:

[0616] The server uses machine learning algorithms to analyze the collected data. The input is the data formatted in step 1. Through data patterns and hypothesis building, it predicts potential new drug candidates. This process yields an output in the form of a drug candidate list.

[0617] Step 3:

[0618] The device collects emotional information from the user. The input consists of real-time emotional data such as the user's facial expressions, voice, and heart rate. An emotion engine analyzes this data, outputting the user's emotional state. This analysis result is used to present effective support information to the user.

[0619] Step 4:

[0620] The server automatically generates and evaluates the molecular structures of predicted drug candidates using generative AI technology. The input is the list of drug candidates generated in step 2, and the output is a list of refined new drug candidates along with the evaluation results for each structure. This process selects high-quality drug candidates.

[0621] Step 5:

[0622] The device dynamically displays information optimized for the user's emotional state. The input is the result of the emotion analysis obtained in step 3, and the output is the customized information and interface adjustments presented to the user. Specific actions include displaying a calming interface and suggesting relaxation techniques.

[0623] Step 6:

[0624] Users make decisions based on the provided information on new drug development and care support alerts. Input is information dynamically presented from the terminal, and output is the user's response and feedback. This feedback is reflected in the next prompt.

[0625] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0626] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0627] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0628] [Fourth Embodiment]

[0629] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0630] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0631] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0632] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0633] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0634] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0635] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0636] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0637] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0638] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0639] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0640] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0641] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] This invention is a system that supports new drug development using biodata and chemical information. This system enables an efficient new drug development process through the coordinated operation of the server, terminals, and users.

[0643] First, the server collects biodata and chemical information. This includes a function to obtain the latest data in conjunction with a database, and data collection can be performed according to the user's requests. The collected data is preprocessed on the server and formatted into a format suitable for analysis.

[0644] Next, the server uses machine learning algorithms to analyze the pre-processed data. This builds a predictive model for potential new drug candidates. Based on existing drug efficacy data, this model can predict the effectiveness of unknown compounds with high accuracy.

[0645] Subsequently, the server utilizes generative AI technology to automatically generate molecular structures. By analyzing the structures of promising compounds and further evaluating their properties, it supports the selection of new candidate substances.

[0646] As a thought experiment, the server performs in silico simulations to evaluate the dynamics and reactions of compounds in a virtual environment. The results are displayed on the user's terminal and used for further analysis. The user can visually review this data through the terminal and select the most suitable new drug candidate.

[0647] Furthermore, the server analyzes past trial data to optimize clinical trials and proposes trial designs suitable for new drug candidates. This allows users to plan efficient and effective clinical trials.

[0648] As a concrete example, let's assume a user wants to develop a treatment for a specific type of cancer. The server collects relevant genetic data and data on the reactivity of cancer cells, and proposes an optimal molecular structure. Subsequently, based on the simulation results, the user further refines the candidate substance before bringing it to market.

[0649] This series of processes is expected to enable faster and more accurate new drug development than before, thereby supporting innovation in the medical industry.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server accesses external biodatabases and chemical information systems to collect necessary data. It utilizes APIs to acquire information in real time and selects the type of data according to the user's research topic.

[0653] Step 2:

[0654] The server preprocesses the collected data. Specifically, it corrects missing values, removes noisy data, and normalizes the data. This prepares the data for analysis by machine learning algorithms.

[0655] Step 3:

[0656] The server executes machine learning algorithms and performs data analysis. In this process, it builds a predictive model for selecting new drug candidates. As algorithms, it applies random forests and deep neural networks, and verifies the accuracy of the model.

[0657] Step 4:

[0658] The server automatically generates new molecular structures using generative AI technology. It designs candidate substances and sets evaluation criteria considering their chemical and biological properties. This makes it possible to automatically select promising compounds.

[0659] Step 5:

[0660] The server performs in silico simulations to evaluate the properties of selected compounds in detail. The simulations utilize molecular dynamics and quantum chemical analysis to virtually verify how the new drug candidates function in living organisms.

[0661] Step 6:

[0662] The terminal receives simulation results and analysis data sent from the server and displays them visually to the user. This allows the user to make a final selection of drug candidates based on the analyzed information.

[0663] Step 7:

[0664] The server analyzes past clinical trial data and proposes trial designs that match the new drug candidate. It also provides functions to support the optimization of clinical trials, such as selecting trial participants and setting up trial groups.

[0665] Step 8:

[0666] Users review the proposed clinical trial design via their device and consider further details. This allows the development to proceed to the next stage based on sufficient data regarding the drug's safety and efficacy.

[0667] (Example 1)

[0668] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0669] In recent years, the effective use of vast amounts of biodata and chemical information has become essential in new drug development. However, it is difficult to consistently automate the process of efficiently collecting, preprocessing, and analyzing this data to predict new drug candidates, and a great deal of time and resources are spent on trial and error. Furthermore, because there is a lack of sufficient systems to automatically propose molecular structures using generation technologies and to evaluate their properties in a virtual environment, there is a need to rapidly perform tasks from candidate substance identification to the optimization of clinical trial designs.

[0670] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0671] In this invention, the server includes means for automatically collecting biodata and chemical information; means for preprocessing the data and formatting it into an analyzable form; means for predicting new drug candidates using machine learning algorithms; means for automatically generating and evaluating molecular structures using generation technology; means for performing simulations in a virtual environment based on the predictions and evaluating the properties of the new drug candidates; means for visually displaying the data for user analysis; and means for analyzing past clinical trial data and optimizing the trial design for the new drug candidates. This automates the entire process from data collection to candidate substance selection and trial design proposal, enabling faster and more efficient new drug development.

[0672] "Biodata" refers to biological data such as genetic information, protein structure, and clinical trial results used in biological research and medicine.

[0673] "Chemical substance information" refers to data on the structure, properties, and reactivity of compounds, and plays a particularly important role in new drug development.

[0674] "Automated data collection" refers to the process of obtaining necessary information from databases or online resources without human intervention.

[0675] "Preprocessing" refers to data cleaning and formatting work to convert collected data into an analyzable format.

[0676] A "machine learning algorithm" refers to a computer program that learns patterns by analyzing past data and uses that knowledge to make predictions and classifications about future data.

[0677] A "new drug candidate substance" refers to a compound that shows promise as a therapeutic effect and is being considered as a component of a newly developed drug.

[0678] "Generative techniques" refer to a group of algorithms that generate new data or patterns based on known data, and are particularly used for molecular structure generation.

[0679] A "virtual environment" refers to a computer setting used to simulate and evaluate real-world phenomena through computer simulation.

[0680] "Visual display" refers to presenting data and simulation results to users in the form of images, graphs, 3D models, etc.

[0681] "Study design optimization" refers to the process of analyzing past data and proposing the most effective and efficient implementation plan for a clinical trial.

[0682] The system in this invention supports new drug development through the collaborative efforts of a server, terminal, and user. The server has means for effectively collecting biodata and chemical information. In this process, necessary information is automatically obtained via APIs through integration with databases. In particular, it uses data provided from gene sequencing databases and chemical library databases.

[0683] Upon user request, the server preprocesses the collected data and prepares it for analysis. During this process, data cleaning software is used to impute missing values ​​and normalize the data.

[0684] Next, the server uses machine learning algorithms to analyze the preprocessed data. This analysis utilizes open-source machine learning libraries (e.g., TensorFlow and scikit-learn) to build a model for predicting new drug candidates. Using this model, the effectiveness of new molecules is predicted based on existing drug efficacy data.

[0685] Furthermore, the server automatically generates molecular structures of potential new drugs using generative AI models. This process employs techniques such as variational autoencoders (VAEs) and generative adversarial networks (GANs) to generate structures of potentially promising compounds.

[0686] The created molecular structures are evaluated through in silico simulations, and the server uses molecular dynamics software (e.g., GROMACS or AMBER) to simulate the dynamics and reactions of compounds in a virtual environment. Based on these results, the server sends the data to a terminal, which the user then analyzes visually. The terminal is equipped with software that enables 3D visualization of the data, allowing the user to select the most suitable new drug candidates.

[0687] Furthermore, the server utilizes statistical analysis software to analyze past clinical trial data and propose the optimal trial design for new drug candidates. This proposal allows users to plan more efficient clinical trials.

[0688] For example, if a user wants to develop a new cancer treatment drug, the server will collect gene databases and cancer cell response data and propose an optimal molecular structure. An example of a prompt to be input into the generating AI model would be, "Please propose a novel molecular structure for a cancer treatment drug. Genetic data and efficacy data are available." This system is expected to accelerate the new drug development process with high accuracy, thereby promoting innovation in the medical field.

[0689] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0690] Step 1:

[0691] The server automatically collects biodata and chemical information from databases. It takes information from gene sequencing databases and chemical library APIs as input. By extracting this data, it outputs the latest biodataset required. Specifically, the server periodically calls the APIs to ensure updated data is available.

[0692] Step 2:

[0693] The server preprocesses the collected data. It uses the raw biodata obtained in step 1 as input. The server outputs the preprocessed data, imputing missing values ​​and performing a normalization process to convert it into a format suitable for analysis. Specifically, the server uses data cleaning software to correct incomplete data items.

[0694] Step 3:

[0695] The server uses pre-processed data to predict potential new drug candidates. It receives pre-processed data as input and analyzes it using machine learning algorithms. The server applies a model trained on existing drug efficacy data and outputs a list of promising new drug candidates. Specifically, the server uses TensorFlow to operate its predictive model through supervised learning.

[0696] Step 4:

[0697] The server automatically generates molecular structures using a generative AI model. The features of the new drug candidate obtained in step 3 are used as input. The AI ​​model performs molecular generation and outputs new molecular structure data. Specifically, the server unfolds a variational autoencoder and generates a new compound from the latent space.

[0698] Step 5:

[0699] The server performs simulations to evaluate the generated molecular structure in a virtual environment. The molecular structure generated in step 4 is used as input. The server performs molecular dynamics simulations and outputs evaluation results for chemical stability and reactivity. Specifically, the server uses GROMACS to simulate molecular dynamics on a computer.

[0700] Step 6:

[0701] The terminal visually displays the simulation results to the user. It uses evaluation results sent from the server as input. The terminal outputs visual analysis results by displaying 3D structures and graphs in a user-friendly format. Specifically, the terminal provides an interactive user interface using 3D rendering software.

[0702] Step 7:

[0703] The server analyzes historical clinical trial data and proposes optimized trial designs. It combines existing trial data and simulation results for analysis. The server presents efficient clinical trial plans and outputs proposed trial designs. Specifically, the server uses statistical analysis software and applies data trends and optimization algorithms.

[0704] (Application Example 1)

[0705] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0706] The objective of this invention is to streamline the new drug development process and support the identification of highly accurate and predictable new drug candidates. Furthermore, it aims to improve the quality of health management by rapidly providing individually optimized preventive measures and treatment plans through integration with personal health data. Additionally, it aims to optimize clinical trials by effectively visualizing clinical trial information and post-market safety information.

[0707] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0708] This invention includes a server that automatically collects biodata and chemical information, analyzes the data and predicts new drug candidates using machine learning algorithms, performs in silico simulations based on the predictions to evaluate the characteristics of the new drug candidates, and links with individual health data to present optimal preventive measures and treatment plans. This increases the efficiency of new drug development and enables the provision of individually optimized health management. Furthermore, it can automatically generate and evaluate molecular structures using generative AI technology, select new drug candidates, and propose treatment methods based on them. Through this series of functions, it is possible to analyze past clinical trial data and optimize trial designs while visualizing clinical trial information and post-market safety information.

[0709] "Biodata" is a general term for information originating from living organisms, primarily data that indicates biological processes and states.

[0710] "Chemical substance information" refers to data concerning the chemical properties of a compound, such as its structure, properties, and reactivity.

[0711] A "machine learning algorithm" is a computer program that analyzes large amounts of data to find patterns, and is a method for making appropriate predictions and classifications from new data.

[0712] "In silico simulation" is a simulation performed in a virtual environment on a computer, and is a means of evaluating the properties of compounds and other substances without conducting physical experiments.

[0713] "Generative AI technology" refers to techniques that use artificial intelligence to automatically generate new data and structures, and is a method that supports creative work.

[0714] "Health data" is a general term for information about an individual's health status and medical history, and is used for medical care and health management.

[0715] A "treatment plan" refers to a set of medical procedures and care plans designed to improve a person's health.

[0716] "Clinical trial information" refers to information about clinical trials conducted to confirm the effectiveness and safety of new drugs.

[0717] "Post-market safety information" refers to information about side effects and effects of a drug that is reported after it has been released to the market.

[0718] "Past clinical trial data" refers to data collected from clinical trials conducted in the past, and this information can be used in future trial design and new drug development.

[0719] "Study design optimization" is the process of improving a study plan to ensure that information is obtained efficiently and effectively when planning and conducting a clinical trial.

[0720] The system implementing this invention is primarily realized through the coordinated operation of a server, terminals, and users. The server automatically collects biodata and chemical information and links it with a database to obtain the latest information. The collected data is analyzed using machine learning algorithms to predict potential new drug candidates. In this process, a program written in Python assists the analysis.

[0721] The server further utilizes generative AI technology to automatically generate and evaluate new molecular structures. These generated molecular structures, combined with the user's health data, enable the creation of individually optimized preventative measures and treatment plans. This improves the quality of health management.

[0722] The device visually displays collected and analyzed data to the user and suggests optimal treatment methods based on health data. Users can then formulate specific treatment plans based on this information. This enables the practice of medical care tailored to individual needs.

[0723] As a concrete example, individual residents of a smart city can use this system to monitor their health on a daily basis and identify the most suitable medication for preventing seasonal influenza. Furthermore, this system visualizes clinical trial information and post-market safety information, contributing to raising residents' awareness of drug safety.

[0724] Examples of prompts to input into a generative AI model include:

[0725] "Based on recent health data, please suggest the most suitable medication for the symptoms of [specific symptom]."

[0726] "Please generate a list of medications suitable for vaccination, taking into account the current health status."

[0727] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0728] Step 1:

[0729] The server collects biodata and chemical information via the internet and databases. Inputs are various databases, and output is the collected raw data. Scripts on the server periodically update the information.

[0730] Step 2:

[0731] The server preprocesses the collected data. Preprocessing includes data standardization and cleaning. The input is raw data, and the output is data in a format suitable for analysis. In this process, a Python library is used to unify the data format.

[0732] Step 3:

[0733] The server runs machine learning algorithms on preprocessed data to predict potential new drug candidates. The input is standardized data, and the output is a list of potential drug candidates. Existing drug data is used to train the model, and then predictions are made on unknown data.

[0734] Step 4:

[0735] The server utilizes generative AI technology to generate and evaluate new molecular structures for proposed candidate substances. The input is a list of new drug candidates, and the output is the evaluated molecular structures. Simulations are then performed using a generative model to conduct characterization.

[0736] Step 5:

[0737] The server generates personalized treatment and preventative measures based on the user's health data. The input is individual health data and AI analysis results, and the output is a personalized medical plan. This process involves inputting prompts into an AI model to obtain a specific plan.

[0738] Step 6:

[0739] The device visually displays the generated results to the user, providing further insights. The input is an individualized medical plan, and the output is easy-to-understand information displayed in the user interface. Specifically, information is communicated through a health dashboard.

[0740] Step 7:

[0741] Users make appropriate decisions and implement treatment plans based on the information provided. The output is a record of medical actions, useful for subsequent data analysis and feedback. Users regularly update their health status through the in-app feedback function.

[0742] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0743] This invention is a new drug development support system incorporating an emotion engine, which allows for the smoother and more effective development process by recognizing the user's emotional state in real time and dynamically adjusting the system's behavior.

[0744] The server automatically collects existing biodata and chemical information. The collected data is analyzed using machine learning algorithms and used to predict potential new drug candidates. Next, generative AI technology is used to generate and evaluate the structures of candidate molecules, leading to advanced drug candidate selection.

[0745] Furthermore, the server uses emotional data transmitted from the user's terminal to activate an emotion engine and understand the user's current emotional state. The emotion engine has the ability to dynamically change the format of information presented by the system to assess how stressed the user is using the system and to maintain the user's interest and concentration.

[0746] For example, if the system detects that a user is feeling tired, it simplifies the interface on the device and highlights important information. Similarly, if a user is feeling confused or stressed, the system improves the user experience by providing support tools and detailed help information.

[0747] Regarding clinical trials, the server analyzes past trial data and proposes more effective trial designs. This process is also optimized by the emotion engine, enabling flexible suggestions based on user feedback. The emotion engine builds an optimization loop based on user feedback, effectively incorporating user preferences during the development process.

[0748] In this way, this system combines emotion recognition technology with the new drug development process to provide users with a less stressful, efficient, and supportive development environment.

[0749] The following describes the processing flow.

[0750] Step 1:

[0751] The server collects necessary biodata and chemical information from external biodatabases. This utilizes API connections to retrieve data in real time and performs filtering according to user requests.

[0752] Step 2:

[0753] The server preprocesses the collected data and formats it into a format suitable for analysis by machine learning algorithms. In this stage, missing values ​​are imputed, noisy data is removed, and normalization is performed.

[0754] Step 3:

[0755] The server analyzes data using machine learning algorithms to predict potential new drug candidates. Here, random forests and deep learning are utilized as algorithms to build models that predict the effectiveness of new drugs with high accuracy.

[0756] Step 4:

[0757] The server utilizes generative AI technology to generate new molecular structures. By evaluating the structures of promising compounds and selecting new candidates based on these evaluations, the accuracy of the search is improved.

[0758] Step 5:

[0759] The server performs in silico simulations on the generated candidate substances. This process uses molecular dynamics simulations and quantum chemical calculations to virtually analyze the behavior of the drugs in vivo.

[0760] Step 6:

[0761] The device collects emotional data from the user and sends it to a server. This data is analyzed using facial recognition and voice analysis technologies with a camera and microphone to detect emotions and provide real-time feedback to the server.

[0762] Step 7:

[0763] The server analyzes the received emotional data using an emotion engine. This evaluates the user's stress level and concentration level, and dynamically adjusts the system interface and feedback format based on the results.

[0764] Step 8:

[0765] Based on the analysis results from the emotion engine, the server provides users with appropriate information and optimizes the interface. For example, if the server determines that the user is in a high-stress state, it will provide a more intuitive interface and detailed help.

[0766] Step 9:

[0767] The server analyzes past clinical trial data and proposes a suitable trial design for the new drug candidate. Based on user feedback and emotional state, it customizes the trial plan and provides the appropriate support the user needs.

[0768] Step 10:

[0769] Users can review the analysis results and trial designs provided through their devices and revise the development direction as needed. This enables users to achieve efficient and less stressful new drug development.

[0770] (Example 2)

[0771] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0772] In the new drug development process, there is a need to efficiently and effectively analyze vast amounts of data to identify promising drug candidates more quickly. Furthermore, optimizing the interface to consider the user's emotional state is a challenge in reducing developer stress and improving work efficiency.

[0773] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0774] In this invention, the server includes means for automatically collecting information, means for analyzing the data and predicting substances using an algorithm, and means for evaluating based on the prediction. This makes it possible to streamline the new drug development process and optimally support the user's work.

[0775] "Means of automatically collecting information" refers to technologies for continuously acquiring necessary information from networks and databases through automated processes.

[0776] "Methods for analyzing data and predicting substances using algorithms" refers to methods for analyzing collected data using analytical techniques and predicting the properties and effectiveness of new chemical substances using machine learning algorithms.

[0777] "Methods for evaluation based on predictions" refer to the process of examining the results predicted by an algorithm according to various evaluation criteria, and confirming their effectiveness and safety based on those criteria.

[0778] "Means for the automatic generation and evaluation of structures using technology" refers to technologies that automatically create molecular structures of materials using generative algorithms, simulate the results, and determine their usefulness.

[0779] "A means of analyzing past data and proposing optimized test designs" refers to a system that analyzes accumulated test results to date, makes suggestions to help design new tests, and enables more efficient test implementation.

[0780] The implementation of this invention involves a series of systems for streamlining the new drug development process through the interaction of servers, terminals, and users.

[0781] The server first connects to the network and automatically collects biometric and chemical information from public databases and specialized information sources. The server particularly utilizes cloud platforms such as Google Cloud and AWS, collecting data using APIs and web scraping techniques. The collected data is analyzed using machine learning libraries such as TensorFlow and PyTorch, and algorithms are used to predict the properties of potential new drugs. The algorithmic models are built upon existing scientific knowledge and data-driven methods.

[0782] Furthermore, the server utilizes generative AI technology to automatically generate and evaluate the molecular structures of materials. This process employs specialized chemical simulation software to understand how the molecules created by the generative AI model behave physically and chemically.

[0783] The device functions as a tool for collecting user emotional data. It uses vital information from a smartwatch and facial recognition technology via a webcam to collect and send the user's emotional state to a server. The server analyzes this emotional data in real time using Python or R. Based on the analyzed emotional state, it adaptively adjusts how the user optimally interacts with the digital interface.

[0784] For example, if the device detects that the user is feeling fatigued, it simplifies the displayed content and uses highlighted important information to attract the user's attention. Furthermore, if confusion or stress is detected, the system proactively improves the user experience by providing detailed help information and support tools.

[0785] Examples of prompt statements include:

[0786] "To streamline the new drug development process, we would like to evaluate potential drug candidates using generative AI models. Furthermore, please teach us methods for analyzing users' emotional states and adjusting the system accordingly."

[0787] Thus, this invention provides a system that comprehensively supports new drug development by combining data collection, machine learning, and sentiment analysis.

[0788] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0789] Step 1:

[0790] The server automatically collects biometric and chemical information over the network. It requires data retrieval requests from public databases and specialized information sources using APIs or web scraping techniques as input. The server then outputs a structured dataset.

[0791] Step 2:

[0792] The server analyzes the collected data. The dataset obtained in Step 1 is used as input. Machine learning algorithms, particularly TensorFlow and PyTorch, are used to process the data and predict potential drug candidates. The output of this process is the predicted characteristics of the potential drug candidates. Specifically, this data is used to score and rank promising compounds.

[0793] Step 3:

[0794] The server uses a generative AI model to automatically generate structures for new drug candidate molecules. Using the prediction results from step 2 as input, the generative AI model generates new molecular candidates. The output is the structure of the generated molecule and its evaluation results. Specifically, the generative model performs structural simulations and physical property evaluations.

[0795] Step 4:

[0796] The device collects user emotional data. Inputs include vital data and facial recognition data from smartwatches and webcams. This data is acquired and aggregated in real time and sent to a server. The output is a dataset representing the user's current emotional state.

[0797] Step 5:

[0798] The server analyzes the emotional data sent from the terminal. The input is the emotional data collected in step 4, which is analyzed using Python or R. This allows the server to identify the user's emotional state and adjust the interface accordingly. The output is an adaptive strategy for the interface based on the user's state. Specifically, it dynamically updates the information presentation format according to the emotional state.

[0799] Step 6:

[0800] Users advance new drug development through an interface based on the analysis results. They receive the output results from Step 5 as input and can work efficiently with the optimized interface. Outputs include user feedback and progress information regarding new drug development. Specific actions include UX adjustments such as content highlighting and the presentation of additional support tools.

[0801] (Application Example 2)

[0802] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0803] In conventional drug development processes, effectively collecting and analyzing biodata and chemical information to select candidate substances was crucial. However, the lack of consideration for emotional states resulted in a heavy user burden and difficulty in efficient process management. Furthermore, there is the issue of insufficient care support that incorporates the emotions of the subjects.

[0804] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0805] In this invention, the server includes means for automatically collecting biodata and chemical information, means for analyzing the data and predicting new drug candidates using machine learning algorithms, and means for dynamically presenting information based on the user's emotional state by collecting and analyzing emotional information. This makes it possible to efficiently and interactively advance new drug development in accordance with the user's emotional state.

[0806] "Biodata" refers to information related to living organisms, and in particular, data that includes molecular biological or biochemical information.

[0807] "Chemical substance information" refers to scientific information related to chemical substances, such as their properties, structure, and reactivity.

[0808] A "machine learning algorithm" is a computational method used to analyze large amounts of data and find patterns and trends.

[0809] "Emotional information" refers to data that indicates an individual's emotional state, and includes things like facial expressions, tone of voice, and heart rate.

[0810] "Generative AI technology" is a technology that uses artificial intelligence to generate new data and information and creatively solve problems.

[0811] "Care support" refers to activities and processes that provide assistance with daily life for the elderly and those who require care.

[0812] The system realizing this invention features a program in which various software components work in coordination. The server primarily automatically collects biodata and chemical information and analyzes this data using machine learning algorithms. The analyzed data is then used to automatically generate molecular structures using generative AI technology and evaluate them. This makes it possible to efficiently select and evaluate new drug candidates.

[0813] Furthermore, using emotional information collected from the device, the server activates an emotion engine to understand the user's emotional state in real time. Based on this information, it dynamically presents information appropriate to the user's current situation. In addition, in care support settings, it is designed to flexibly adjust care procedures based on emotion analysis to reduce the user's burden.

[0814] A concrete example is when an elderly person shows anxiety; the device suggests calming exercises or music. In this invention, an example of a prompt utilizing a generative AI model is: "Analyze the elderly person's current emotional state and generate appropriate care advice. If the user shows anxiety, suggest calming exercises."

[0815] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0816] Step 1:

[0817] The server automatically collects data related to living organisms and information related to chemical substances. Inputs are data from external databases and sensors, and the output is integrated, analyzable data. This data is then formatted into a specific form for subsequent processing by machine learning algorithms.

[0818] Step 2:

[0819] The server uses machine learning algorithms to analyze the collected data. The input is the data formatted in step 1. Through data patterns and hypothesis building, it predicts potential new drug candidates. This process yields an output in the form of a drug candidate list.

[0820] Step 3:

[0821] The device collects emotional information from the user. The input consists of real-time emotional data such as the user's facial expressions, voice, and heart rate. An emotion engine analyzes this data, outputting the user's emotional state. This analysis result is used to present effective support information to the user.

[0822] Step 4:

[0823] The server automatically generates and evaluates the molecular structures of predicted drug candidates using generative AI technology. The input is the list of drug candidates generated in step 2, and the output is a list of refined new drug candidates along with the evaluation results for each structure. This process selects high-quality drug candidates.

[0824] Step 5:

[0825] The device dynamically displays information optimized for the user's emotional state. The input is the result of the emotion analysis obtained in step 3, and the output is the customized information and interface adjustments presented to the user. Specific actions include displaying a calming interface and suggesting relaxation techniques.

[0826] Step 6:

[0827] Users make decisions based on the provided information on new drug development and care support alerts. Input is information dynamically presented from the terminal, and output is the user's response and feedback. This feedback is reflected in the next prompt.

[0828] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0829] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0830] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0831] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0832] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0833] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0834] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0835] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0836] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0837] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0838] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0839] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0840] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0841] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0842] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0843] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0844] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0845] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0846] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0847] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0848] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0849] The following is further disclosed regarding the embodiments described above.

[0850] (Claim 1)

[0851] Means for automatically collecting biodata and chemical information,

[0852] A means for analyzing the aforementioned data and predicting new drug candidate substances using a machine learning algorithm,

[0853] A means for evaluating the characteristics of a new drug candidate by performing in silico simulations based on the prediction,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, comprising means for automatically generating and evaluating molecular structures using generation AI technology and selecting new drug candidate substances.

[0857] (Claim 3)

[0858] The system according to claim 1, comprising means for analyzing past clinical trial data and optimizing and proposing a trial design for a new drug candidate.

[0859] "Example 1"

[0860] (Claim 1)

[0861] Means for automatically collecting biodata and chemical information,

[0862] Means for preprocessing the aforementioned data and formatting it into an analyzable format,

[0863] A method for predicting new drug candidates using machine learning algorithms,

[0864] A method for automatically generating and evaluating molecular structures using generation technology,

[0865] A means for performing simulations in a virtual environment based on the prediction to evaluate the characteristics of a new drug candidate,

[0866] A means of visually displaying data and enabling users to perform analysis,

[0867] A method for analyzing past clinical trial data to optimize the trial design for new drug candidates,

[0868] A system that includes this.

[0869] (Claim 2)

[0870] The system according to claim 1, which evaluates automatically generated structures based on a molecular structure prediction model and selects new drug candidate substances.

[0871] (Claim 3)

[0872] The system according to claim 1, which visualizes 3D structures using a terminal based on generated data, thereby facilitating the comparison and evaluation of new drug candidates.

[0873] "Application Example 1"

[0874] (Claim 1)

[0875] Means for automatically collecting biodata and chemical information,

[0876] A means for analyzing the aforementioned data and predicting new drug candidate substances using a machine learning algorithm,

[0877] A means for evaluating the characteristics of a new drug candidate by performing in silico simulations based on the prediction,

[0878] A means of linking with individual health data to suggest optimal preventive measures and treatment plans,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, comprising means for automatically generating and evaluating molecular structures using generation AI technology, selecting new drug candidate substances, and proposing individually optimal treatment methods.

[0882] (Claim 3)

[0883] The system according to claim 1, comprising means for analyzing past clinical trial data and optimizing and proposing trial designs for new drug candidates, and means for visualizing clinical trial information and post-marketing safety information.

[0884] "Example 2 of combining an emotion engine"

[0885] (Claim 1)

[0886] Means for automatically collecting information,

[0887] A means for analyzing the aforementioned data and predicting the substance using an algorithm,

[0888] A means for evaluating based on the prediction,

[0889] A means of collecting and analyzing information sent from users,

[0890] A means for dynamically adjusting the information presentation format based on the aforementioned analysis results,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, comprising means for automatically generating and evaluating structures using technology and for selecting materials.

[0894] (Claim 3)

[0895] The system according to claim 1, comprising means for analyzing past data and proposing an optimized test design.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] Means for automatically collecting biodata and chemical information,

[0899] A means for analyzing the aforementioned data and predicting new drug candidate substances using a machine learning algorithm,

[0900] A means for evaluating the characteristics of a new drug candidate by conducting simulations in a virtual environment based on the prediction,

[0901] By collecting and analyzing emotional information, a means of dynamically presenting information based on the user's emotional state is provided.

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, comprising means for automatically generating and evaluating molecular structures using generative AI technology to select new drug candidate substances, and further comprising means for adjusting care procedures based on emotion analysis for care support.

[0905] (Claim 3)

[0906] The system according to claim 1, comprising means for analyzing past clinical trial data and optimizing and proposing trial designs for new drug candidates, and further comprising means for incorporating feedback from user reactions using an emotion engine to improve the development process. [Explanation of Symbols]

[0907] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for automatically collecting biodata and chemical information, A means for analyzing the aforementioned data and predicting new drug candidate substances using a machine learning algorithm, A means for evaluating the characteristics of a new drug candidate by performing in silico simulations based on the prediction, A system that includes this.

2. The system according to claim 1, comprising means for automatically generating and evaluating molecular structures using generation AI technology and selecting new drug candidate substances.

3. The system according to claim 1, comprising means for analyzing past clinical trial data and proposing an optimized trial design for a new drug candidate.

Images