50 results about "Molecular Bank" patented technology

The invention discloses a high-flux molecular modeling method of an asphalt binder. The method comprises the following steps: creating an asphalt binder component molecular library; according to given modeling requirements, component molecules of the asphalt binder component molecule library are randomly extracted, and an asphalt binder model is generated through modeling; on the basis of topological information of an asphalt binder model, according to a molecular simulation CVFF empirical force field, determining bonding categories of component atoms of the asphalt binder so as to determine atomic simulation force field parameters; and finally, outputting a data file of the asphalt binder model according to a set format requirement. According to the method, the initial model construction of the asphalt binder model and the automatic generation of the atomic scale simulation file are realized, the workload of manual modeling is reduced, the modeling requirement can be automatically processed, the asphalt binder molecular model can be automatically generated, and the model creation speed is improved.

Disclosed are systems and methods for identifying a target molecule by receiving a molecule dataset from a library of molecules comprising chemical-structural representations of candidate molecules for a material application; determining one or more target molecular property values derived from a set of predictive molecular descriptor values determined from a candidate molecule of the molecular dataset applied to a trained machine learning model, wherein the trained ML model is configured to output the set of predictive molecular descriptor values for a given molecule data input, and wherein the trained ML model was trained for a set of training data and the set of molecular descriptors generated from a molecular descriptor modeling application; and outputting, via a report or to a data store, the one or more target molecular property values for each of the molecular dataset.

The invention relates to the field of drug discovery and delivery collaboration, in particular to an autonomous evolutionary drug discovery and delivery collaboration method and system based on a large language model. The method comprises the following steps: aiming at a given biological target three-dimensional structure, generating a candidate molecular library which is complementary with a target pocket and gives consideration to druggability through an SE (3) isovariant hybrid generation model; according to a two-stage funnel type high-throughput virtual screening process, screening out the molecule with the highest comprehensive potential from the candidate molecule library; generating a customized delivery scheme through a three-stage process; in a digital twinborn model for simulating a real in-vivo tumor microenvironment, a targeted delivery process of a drug and carrier complex is simulated, and efficiency is evaluated; atomic-scale performance confirmation is carried out on a medicine, carrier and target point ternary system through molecular dynamics simulation. The invention is suitable for drug research and development.

The invention discloses a monomolecular structure design and generation method based on a large language model, and relates to the crossing field of monomolecular electronics and artificial intelligence. In order to solve the problems of low single molecule design efficiency and insufficient data, SingMolT5 is obtained through field fine tuning on the basis of MolT5, and generation from a natural language to a molecular SMILES is realized. According to the method, data are collected from literatures in the single molecule field and an existing disclosed molecule library, a fine tuning data set containing 329 high-quality instructions is constructed, and the fine tuning data set comprises three basic data types including a molecular skeleton, an anchoring group and molecules. The model is initialized by a MolT5 check point, and a cross entropy loss function is used in the fine tuning process; reasoning, generating and using a beam search strategy; the follow-up evaluation indexes comprise BLEU, Levenshtein, MACCS, RDK, Morga and effectiveness. The method provides an innovative technical path for'low experience and data dependent type single molecule design 'in the field of single molecule electronics, and is particularly suitable for aided design of a single molecule device core function unit and a single molecule sensing probe molecule, namely, a target molecular structure can be quickly converted through a natural language, the design threshold of researchers is reduced, and the design efficiency is improved. And a traceable technical basis can be provided for screening and iteration of a monomolecular structure based on a high-quality data set and rigorous evaluation logic.

The invention discloses a cancer targeted drug generation method based on differential geometry and reinforcement learning, and belongs to the technical field of intelligent control. Molecular surface geometric characteristics are accurately described through differential geometry, diversified and chemically reasonable molecular conformations are generated by using DDPM, and a molecular library is expanded in combination with a genetic algorithm; and the binding affinity of the molecule and the mutation target protein is optimized through reinforcement learning. According to the cancer targeted drug generation method based on differential geometry and reinforcement learning, complex post-processing of a traditional method is not needed, the structure is simple, efficiency is high, and a brand new technical normal form is provided for cancer targeted drug design.

The application provides a drug virtual screening method and device based on deep learning, wherein the method comprises the following steps: inputting all candidate compound small molecules in a candidate molecule database into a pre-trained molecular encoder respectively to obtain molecular vectorization representation of the candidate compound small molecules; constructing an index structure corresponding to the candidate compound small molecules based on the molecular vectorization representation of the candidate compound small molecules; inputting a protein target to be matched into a pre-trained protein target encoder to obtain protein target vectorization representation corresponding to the protein target; and matching the protein target vectorization representation based on the index structure to obtain a target compound small molecule corresponding to the protein target. The method establishes a full-amount mapping function of the target and the molecule through a vector calculation mode, realizes high-throughput virtual screening in a second-level calculation time, realizes rapid virtual screening of a full-amount candidate molecule library, improves the precision of the virtual screening, and increases the possibility of drug discovery.

The present disclosure is directed to compositions and methods that use the principles of DNA origami to package and archive data stored in multiple indexed DNA oligonucleotides. These structures allow for selective physical data access and retrieval from a molecular pool of DNA origami (DNAO) nanostructures comprising the data bearing oligonucleotides.

The invention relates to the technical field of petrochemical production, and discloses a molecular-level method and system for predicting the quality of any stream in petrochemical production. The method comprises the following steps: carrying out online spectral analysis on a feed stream to obtain carbon number distribution and hydrocarbon composition data, and establishing a dynamic molecular library through structural unit coding; establishing a reaction rule library according to a reaction mechanism, and matching with the molecular library to generate a reaction network; establishing a reaction kinetics equation set in which the feed composition correction factor is introduced, and optimizing parameters; and performing gas-liquid phase equilibrium calculation on the reaction product to obtain stream molecular composition, extracting a structure descriptor, inputting the structure descriptor into a neural network model, introducing a component interaction item, and outputting a stream quality prediction result. The problems that stream quality prediction lags behind, precision is low, and feeding fluctuation cannot be adapted in real time in the prior art are solved.

The invention relates to the technical field of semiconductor packaging materials, and particularly discloses a TLCP molecular design method suitable for chip packaging of a low-temperature BGA solder ball, and the method comprises the following specific steps: 1, constructing a target-driven TLCP molecular structure space; 2, establishing a molecular digital characterization and performance prediction model; 3, performing multi-objective reverse design and optimization screening; 4, structure-activity relationship analysis and experimental verification are carried out; a target driving molecular structure space with the melting temperature and the dielectric constant as core performance indexes is constructed, a quantitative prediction model between a TLCP molecular structure and Tm and Dk is established through machine learning, and global search is conducted in a virtual TLCP molecular library through a multi-target optimization algorithm. The Pareto optimal molecular structure capable of realizing synergistic balance between high Tm and low Dk is obtained. The invention further constructs a TLCP material research and development normal form of application requirements, performance objectives, AI reverse design and experimental verification, and the method can be popularized and applied to design of other electronic packaging high polymer materials.

The invention discloses a construction method and device of an SAM type molecule library, electronic equipment, a storage medium and a product, SAM type molecules comprise parent fragments, intermediate fragments and tail fragments, and the method comprises the following steps: obtaining the intermediate fragments, and constructing an intermediate molecule library based on the intermediate fragments; based on the intermediate fragment, determining a first site for connecting a parent fragment and a second site for connecting a tail fragment of the intermediate fragment; splicing and combining the parent fragment, the intermediate fragment and the tail fragment to obtain a plurality of first SAM molecules; a primary molecular library is obtained based on a plurality of first SAM-class molecules. In the implementation process of the construction method provided by the embodiment of the invention, the whole process is low in artificial participation degree, high in splicing efficiency and more in splicing combination types, site omission of artificial splicing is reduced, a large number of SAM molecules can be obtained, the cost of obtaining a plurality of SAM molecules is reduced, and the convenience of knowing the basic attributes of the SAM molecules in the primary molecule library is improved.

The invention discloses a molecular property prediction and drug design system based on graph comparative learning. The molecular property prediction and drug design system comprises a data preprocessing module, a graph coding module, a comparative learning module, a property prediction module and an interpretability analysis module. According to the method, molecules are modeled into an atom-bond graph structure, a self-supervised contrast learning mechanism is adopted to learn general representation from a large-scale unlabeled molecule library, and a graph neural network with multi-view graph enhancement, a molecule similarity keeping mechanism and substructure perception is combined to obtain a multi-view graph structure; accurate prediction of molecular properties, drug-target interaction prediction and molecular optimization design based on property targets are realized.

The present application relates to a screening method, apparatus, computer device, storage medium, and computer program product. The method includes: obtaining a plurality of molecules from a molecular library and obtaining the structural information of the plurality of molecules; inputting the structural information of the plurality of molecules into a cell activity prediction model, and performing a first screening process on the plurality of molecules based on the output of the cell activity prediction model to obtain a first molecule; inputting the structural information of the first molecule into a main protease activity prediction model, and performing a second screening process on the first molecule based on the output of the main protease activity prediction model to obtain a second molecule; inputting the structural information of the second molecule into an ADMET prediction model, and performing a third screening process on the second molecule based on the output of the ADMET prediction model to obtain a third molecule; determining a target molecule based on the third molecule. Using this method can effectively improve the working efficiency of the screening task.

The application discloses a data-driven phenol-amine composite antioxidant screening method and a storage medium. The method comprises the following steps: taking amine antioxidant molecules and phenolic antioxidant molecules as parent bodies, selecting different groups into different sites in each molecular combination, generating new molecules and constructing a virtual molecular library; performing structure optimization on the generated new molecules to obtain the lowest energy spatial configuration thereof; based on the hydrogen atom transfer mechanism and the single electron transfer mechanism of the antioxidant, calculating the frontier orbital energy level difference, the ionization potential and the minimum hydrogen atom partition charge of the new molecules, and taking the three performance indexes as the performance indexes of the antioxidant; according to the three performance indexes, a molecular performance thermodynamic diagram under different molecular core-functional group combinations is drawn, and a representative antioxidant molecule is screened according to the analysis result of the molecular performance thermodynamic diagram. Through the above method, high-performance phenol-amine composite antioxidants can be quickly and efficiently designed and screened.

The embodiment of the invention relates to a processing method and device for generating an MR-TADF molecular library. The method comprises the following steps: taking a preset benzene ring structure as an initial molecular skeleton; performing molecular skeleton deduction based on the initial molecular skeleton to obtain a corresponding molecular skeleton library; carrying out heteroatom substitution and hydrogen atom addition treatment on molecular skeletons in the molecular skeleton library to obtain a corresponding preselected molecular library; and performing MR-TADF molecular screening on the molecular structure of the preselected molecular library to obtain a corresponding MR-TADF molecular library. According to the method, a molecular database with massive MR-TADF molecular structures can be constructed, and the purpose of effectively increasing MR-TADF molecular types and the number of molecular structures is achieved.

In a method of molecular scaffold hopping an interface of a scheduler computer sends instructions, prepared by the scheduler computer, to a job runner computer to perform a plurality of separate computational tasks. Each of the separate computational tasks includes calculating one or more chemical properties for a query molecule or molecules in a library of molecules. One or more of the plurality of separate computational tasks performed on the job runner computer are preemptible computing instances. Status indicators sent from the job runner computer are received by the interface for each of the plurality of separate computational tasks. The indicators are one of: incomplete, completed, or failed computing instances. The interface resends the instructions to the job runner computer that correspond to the separate computational tasks having the failed computing instance indicator to increase fault-tolerance against the separate computational tasks not attaining the completed computing instance indicator.

The application discloses a cancer targeting drug generation method based on differential geometry and reinforcement learning, belongs to the intelligent control technical field, and accurately describes the geometric characteristics of a molecular surface through differential geometry, generates diversified and chemically reasonable molecular conformations through DDPM, expands a molecular library in combination with a genetic algorithm, and optimizes the binding affinity of a molecule and a mutant target protein through reinforcement learning. The cancer targeting drug generation method based on differential geometry and reinforcement learning provided by the application does not need the complex post-processing of traditional methods, has a simple structure, is high in efficiency, and provides a brand-new technical paradigm for cancer targeting drug design.

The application relates to a virtual screening method, device and electronic equipment. The method comprises the following steps: performing molecular docking on ligand molecules in a molecule library and target proteins to obtain at least one molecular conformation after the ligand molecules contact the target proteins; determining a first binding free energy of the molecular conformation after the ligand molecules contact the target proteins by using a preset scoring function, and screening a molecular conformation whose first binding free energy meets a first preset condition; and determining a second binding free energy of the molecular conformation whose first binding free energy meets the first preset condition after the ligand molecules contact the target proteins based on a semi-empirical molecular orbital method, and screening a molecular conformation whose second binding free energy meets a second preset condition. The scheme provided by the application can quickly predict the binding free energy of the molecular conformation, improve the accuracy of the prediction result, and thus improve the success rate of screening active compounds.

The invention relates to the technical field of DNA (deoxyribonucleic acid) coding molecular libraries, and particularly discloses a synthetic method and application of a DNA-ketoamide conjugate. Wherein an oxidizing agent is added into a solution containing the DNA-hydroxyamide conjugate as shown in the general formula (I) in the specification, reaction is performed for at least 1 hour under the condition of-5 DEG C to 5 DEG C, and the DNA-ketoamide conjugate as shown in the general formula (II) in the specification is obtained. The synthesis method has the characteristics of high selectivity, mild reaction conditions, biological system compatibility and the like, effectively ensures that other sensitive groups in DNA molecules are not influenced in the reaction process, and has a relatively high conversion rate.

The application discloses a library sequencing method for determining methylation difference of positive and negative strands of DNA molecules. The application provides a library sequencing method for determining methylation difference of positive and negative strands of DNA molecules, comprising the following steps: 1) using molecular tags UMI to label positive and negative strands of a plurality of DNA double-stranded molecules to obtain a DNA molecule library labeled with molecular tags; 2) performing bisulfite conversion on DNA molecules in the DNA molecule library, converting unmethylated modified C bases in the DNA molecules into U bases to obtain converted DNA molecules; 3) sequentially performing PCR amplification, constructing a sequencing library and sequencing on the converted DNA molecules; and determining the difference in methylation modification of positive and negative strands of the same DNA molecule. Compared with traditional whole genome methylation sequencing, the application can more accurately detect the methylation difference of DNA molecules, and more accurately detect the dynamic change of methylation.

The present invention discloses a hierarchical screening method, device, system and medium for 3D compound similarity. The method comprises the following steps: inputting three-dimensional information of a query compound; preprocessing the query information of the query compound, comparing the query compound with compounds in a molecular library, screening the search range in the molecular library, and reducing the input scale; and calculating the similarity between the query compound and molecules in the molecular library based on the preprocessed search range and query information.

The present application relates to the field of drug discovery and delivery synergy, in particular to an autonomous evolutionary drug discovery and delivery synergy method and system based on a large language model. The method comprises: for a given biological target three-dimensional structure, generating a candidate molecule library complementary to the target pocket and taking into account drugability through an SE(3) equivariant mixture generation model; screening the highest comprehensive potential molecules from the candidate molecule library according to a two-stage funnel high-throughput virtual screening process; generating a customized delivery scheme through a three-stage process; simulating the drug and carrier complex targeting delivery process and evaluating the efficiency in a simulated real in vivo tumor microenvironment digital twin model; and performing atomic-level performance verification on the drug, carrier and target three-element system through molecular dynamics simulation. The present application is suitable for drug research and development.

The invention discloses a covalent warhead screening method and system based on multi-factor weighted scoring, and belongs to the technical field of computer-aided drug discovery. The method comprises the following steps: on the basis of a chemical synthesis feasibility rule, combining a covalent warhead template, an aromatic ring fragment and a linker, automatically generating a candidate molecular library, and standardizing an SMILES character string; on the basis of the SMARTS pattern library, matching and identifying reactive groups in the candidate molecules, and endowing a corresponding reactive score Wr; calculating quantitative drug effect scores of the candidate molecules as drug-likeness scores SQED; a nonlinear penalty function is introduced, and a penalty term LogP penalty of the LogP is calculated; carrying out weighted fusion on the Wr, the SQED and the LogPpenalty to obtain a covalent warhead final score Sfinal of the candidate molecule; and screening the candidate molecules according to a preset threshold value and a target suitability rule. According to the method, by constructing a comprehensive evaluation model of reactivity, drug-likeness and physicochemical properties, efficient and accurate screening of covalent drug candidate molecules is achieved, and the success rate and transformability of covalent inhibitor design are improved.

The embodiment of the invention provides a molecular-level oil refining whole-process model construction method and device and computer equipment. The method comprises the steps that an SOL molecular library is constructed according to input SOL molecular data; constructing a reaction rule base according to the reaction rules; constructing a single device model according to the SOL molecular library, the reaction rule library and the reaction parameter library, and storing the single device model in a whole-process model construction system; and according to the constructed single device model in the construction system or the single device model obtained by importing the drawing and the logistics connection line between the single device models, a whole-process model is constructed and obtained. According to the method, the single device model can be constructed and stored as a system resource, and in the construction process of the whole-process model, the existing single device model can be reused, so that the manual operation of a user is reduced, and the modeling cost of the whole-process model is effectively reduced. And a single device model can be obtained by supporting a drawing import mode, so that the requirements of various whole-process model construction scenes are met.

The application discloses a new method for high-throughput detection of metabolites based on direct injection high-resolution mass spectrometry, and relates to the fields of detection of small molecule metabolites and high-resolution mass spectrometry. The application is based on direct injection high-resolution mass spectrometry technology, and first, a high-coverage and high-quality-accuracy serum metabolite molecular formula database is constructed by using direct injection Fourier transform ion cyclotron resonance ultra-high-resolution mass spectrometry; second, according to the distribution of the number of molecular formulas in different mass-to-charge ratio ranges in the self-built database, a high-throughput metabolome detection method based on direct injection nanoliter spray ionization high-resolution mass spectrometry is established; finally, non-targeted metabolite data obtained by the high-throughput detection method is searched in the self-built database, and high-throughput molecular annotation of metabolites is realized. The application adopts a two-step acquisition strategy, takes a high-reliability and high-coverage metabolome molecular library as a bridge, and takes into account the detection throughput, coverage and reliability. The method has higher reliability, wider metabolome coverage range and is suitable for large-scale metabolome data analysis.

The invention belongs to the field of guiding air-gap membrane distillation to recycle organic solvents, and discloses a method and a system for membrane material screening and process parameter optimization based on machine learning, and the method comprises the following steps: collecting pervaporation document data and air-gap membrane distillation experimental data, cleaning and aligning, and constructing a heterogeneous data set; generating an SMILES sequence code and a molecular fingerprint of the solvent, and carrying out standardization processing on process parameters to generate multi-modal input data; based on a deep learning regression model of a Transform architecture, executing a pre-training task based on pervaporation data and a transfer learning fine tuning task based on air gap type membrane distillation data; and performing high-throughput prediction on the chemical molecule library, and outputting an optimal solvent list and recommended process parameters. According to the method, historical data prediction and reverse optimization are utilized through machine learning, so that the experiment cost and trial and error times of membrane distillation organic solvent separation process optimization are remarkably reduced.

The invention discloses a strategy library based on expert knowledge and deep learning and application of the strategy library in molecular optimization. With expert knowledge and deep learning as a dual-drive core, a molecular optimization strategy is extracted from drug molecular optimization core periodical literatures, and a standardized expert strategy library is constructed; a MolOpt deep learning framework is built, and diversity expansion and rationality enhancement of strategies are realized through large-scale compound database pre-training and expert strategy fine adjustment; according to the method, an expert strategy library and an extension strategy generated by MolOpt are integrated into an AutoOptimizer automatic molecule optimization platform built on the basis of a Pipeline Pilot tool, initial molecules are input, the strategy library is called to execute multiple rounds of iterative optimization, and efficient generation from a single initial molecule to a large-scale candidate molecule library is achieved. According to the method, the limitation that a traditional method depends on artificial experience, strategy coverage is insufficient and the automation degree is low is overcome, the discovery efficiency and druggability of the lead compound are remarkably improved, and the method has wide drug research and development application prospects.

The invention relates to the technical field of crude oil molecular-level physical analysis, and particularly discloses a process simulation optimization method and system of a molecular-level atmospheric and vacuum distillation unit, which breaks through the limitation of traditional virtual component simulation by constructing a full-fraction molecular library and molecular-level composition model and establishing accurate mapping of virtual components and molecules. The method has the remarkable advantages that two-way conversion between the molecular level and the macroscopic level is achieved, the reliability of mapping rules is quantified through mapping accuracy coefficients, and the product molecular composition prediction precision is improved; real-time data dynamic regulation and control are combined, macroscopic properties and molecular compositions of all lateral line products are accurately predicted, working condition visualization is achieved, and the operation stability of the device is enhanced; and thirdly, an optimal scheme is efficiently screened based on a multi-dimensional process scheme matrix and parallel calculation, the yield and quality of products are considered, downstream process requirements are met, and the method promotes an atmospheric and vacuum distillation device to be refined and optimized from macroscopic simulation to molecular level, so that the process regulation and control efficiency is remarkably improved.

The present invention relates to a method for identifying which members of a barcode-free library of small molecules bind to a target and elucidating their molecular structure, the method comprising: a) mixing the members of at least one subset of the library with the target; b) separating the members that do not bind to the target (nonbinders) from the members that bind to the target (binders); c) analysing the binders using tandem mass spectrometry (MS / MS) to generate MS / MS spectra of the binders; and d) analysing the MS / MS spectra by computational analysis to elucidate the molecular structure of the binders.

The application relates to the technical field of petrochemical production, and discloses a method and system for molecular-level prediction of the quality of any flow in petrochemical production. The method comprises the following steps: performing online spectrum analysis on a feed flow to obtain carbon number distribution and hydrocarbon composition data, and establishing a dynamic molecular library through structural unit coding; establishing a reaction rule library according to a reaction mechanism, and matching the reaction rule library with the molecular library to generate a reaction network; establishing a reaction kinetics equation group with an introduced feed composition correction factor and optimizing parameters; performing gas-liquid phase equilibrium calculation on reaction products to obtain flow molecular composition, inputting structural descriptors into a neural network model to introduce component interaction terms, and outputting flow quality prediction results. The application solves the problems of lagging flow quality prediction, low precision and incapability of real-time adaptation to feed fluctuations in the prior art.