54 results about "In silico" patented technology

To provide an insilico toxicity risk evaluation method in which high prediction accuracy is compatible with the explicitness of a prediction basis.SOLUTION: A machine learning model for predicting the intensity of the toxicity risk of a chemical substance by an information processing system is constructed using a molecular descriptor based on a chemical structure and inchemico or invitro test data, the prediction result of the toxicity risk intensity output by the information processing system by the machine learning model is used as an index of similarity specific to toxicity, and the toxicity risk is evaluated by a Reed-Acros method based on the similarity by the index.SELECTED DRAWING: Figure 1

Methods, systems, and apparatus for generating synthetic patient data and simulating clinical studies. In one aspect, a method includes obtaining a disease of interest for an in silico clinical study and obtaining historic patient data associated with the disease of interest. The historic patient data includes patient attributes for each patient. The method includes, based on the patient attributes, generating synthetic patient data. The synthetic patient data reproduce statistical properties of the historic patient data. The method includes applying the synthetic patient data to the in silico clinical study configured to predict a clinical study outcome and providing, based on the predicted clinical study outcome, feedback data that specify one or more parameters used in generating the synthetic patient data.

A device may receive, by the computer system, a digital chemical structure for each of a plurality of ligand-drug conjugate compounds. A device may calculate by said one or more processors, an aggregation number for each of said plurality of ligand-drug conjugate compounds. A device may rank, by the computer system, at least a portion of said plurality of ligand-drug conjugate compounds based on said aggregation number. A device may identify, by the computer system, a plurality of low aggregation ligand-drug conjugate compounds based on said ranking, wherein said plurality of low aggregation ligand-drug conjugate compounds is a portion of said plurality of ligand-drug conjugate compounds having an aggregation number indicative of a predicted molecular aggregation lower than the predicted molecular aggregation of a remaining ligand-drug conjugate compounds within said plurality of ligand-drug conjugate compounds.

A method for confirming the sequence of a nucleic acid is provided, comprising: (i) hydrolytic cleavage of predetermined phosphodiester bonds in the nucleic acid to generate a plurality of oligonucleotides; (ii) ionization of the plurality of oligonucleotides to provide a gas phase of ionized oligonucleotides, wherein a majority of the ionized oligonucleotides are singly charged; (iii) isolation of the ionized oligonucleotides using a plurality of mass-to-charge ratio (m / z) windows; (iv) detection of the isolated ionized oligonucleotides of each m / z window using a high-resolution mass spectrometer (HRMS) with a resolution of more than 30.000 at m / z 200, thereby obtaining a mass spectrum; (v) Confirming the sequence of the nucleic acid by comparing the mass spectrum obtained in step (iv) with a mass spectrum determined in silico after the same hydrolytic cleavage of the nucleic acid as in step (i), the confirmation comprising a comparison of the signal intensities of one or more mass envelopes resulting from the ionized oligonucleotides.

Disclosed herein are methods of in silico generation of polypeptide structures using time-based data generated from molecular dynamics simulations. Also disclosed herein are methods of predicting an epitope or binding surface of a polypeptide using in silico methods. Also disclosed herein are compositions containing polypeptide therapeutics designed to bind to a predicted epitope structure of a polypeptide, as well as methods of treating a subject by administering to the subject compositions containing the same.

A computational system and method for digital modeling of biochemical reactions within cardiac cells are disclosed. The system comprises processors and a computer-readable storage device with instructions to maintain biological data related to cardiac cell reactions and receive user selections via a user interface to configure a simulation. The user can select a cardiac cell class, and functions to load cellular components, generate enzyme activity, load specific enzymes, and perform enzymatic reactions. The system performs in silico experiments, predicts new biological data, and compiles this into configuration data. An enzyme activity model is generated and simulated under various conditions, including user-defined enzymatic dysregulation, to replicate and study cardiac physiology and pathology. The results, such as changes in energy metabolism parameters like glucose consumption and ATP usage, are outputted. The system provides a detailed and interactive platform for research and education in cardiac electrophysiology and disease.

A device may receive, by the computer system, a digital chemical structure for each of a plurality of ligand-drug conjugate compounds. A device may calculate by said one or more processors, an aggregation number for each of said plurality of ligand-drug conjugate compounds. A device may rank, by the computer system, at least a portion of said plurality of ligand-drug conjugate compounds based on said aggregation number. A device may identify, by the computer system, a plurality of low aggregation ligand-drug conjugate compounds based on said ranking, wherein said plurality of low aggregation ligand-drug conjugate compounds is a portion of said plurality of ligand-drug conjugate compounds having an aggregation number indicative of a predicted molecular aggregation lower than the predicted molecular aggregation of a remaining ligand-drug conjugate compounds within said plurality of ligand-drug conjugate compounds.

Inventors followed an untargeted approach by screening a single chain variable fragment (scFv) library via phage display against recombinant human full-length wild-type (wt)TDP-43. They identified four wtTDP-43-specific scFv, two of which were retained following cellular expression and colocalization with TDP-43 in vitro. In silico binding site prediction on TDP-43 suggested the pathologically-relevant C-terminal and RRM1 domains as potential targets. One scFv diminished the amount of the insoluble 35-kDa C-terminal fragment of TDP-43 when the wildtype protein was overexpressed. Another scFv inhibited NF-κB activation associated with TDP-43 overexpression. Both scFv seemed to reverse some metabolic alterations caused by TDP-43 overexpression. Their findings offer two scFv molecules that bind wtTDP-43, alter its aggregation, and modify cellular pathways associated with TDP-43 proteinopathies. Accordingly, the present invention relates to scFv intrabodies targeting TDP-43 and their uses in diagnosis and treatment methods.

The disclosure notably relates to a computer-implemented method for processing in silica chemical compounds, the method comprising: for each connected molecule and each non-coordinating molecule, assigning to each atom a respective formal charge and computing the sum of the respective formal charge assigned to each respective atom. The method also comprises determining an output from the input, including: removing each non- coordinating molecule having a respective total charge equal to zero; and removing at least one connected molecule having a respective total charge of zero and having one and only one bond with a metal atom.

Introduced here is an approach to developing molecules and molecule groups via a simulated mutagenesis process that is performed as part of in silico experimentation. Due to its initiation of the simulation based on a known binding interface or predicted binding interface between two structures—whether biological or synthetic—with known sequences, the approach introduced here can accomplish linear iteration of sequences. This can be accomplished whether these sequences relate to proteins, biological amino acids, synthetic amino acids, biological nucleic acids, synthetic nucleic acids, unnatural variants thereof, or any other molecules with a three-dimensional (“3D”) structure to evaluate the thermodynamic binding and affinity of the interaction as individual nucleic acids, amino acids or individual units of a polymer are mutated one at a time.

This disclosure provides T7 RNA polymerase mutants generated using the large language program EVOLVE-Pro. EVOLVE-Pro substantially enhances the efficiency and effectiveness of in silico protein evolution, surpassing current state-of-the-art methods and yielding proteins with enhanced properties.

Provided herein are artificial intelligence architecture for gene network analysis and related organoid-based systems and methods for in vitro and in silico disease modeling and identification of disease-modifying target gene and therapeutic candidates.

The invention relates to a computer-implemented method performed by one or more data processing apparatus for assessing a biological feature of a biological macromolecule, preferably a protein molecule, by providing an electrostatic data based in silico representation of the biological macromolecule. The biological feature may be, without limitation, multiple function-related states of the macromolecule, differences in the conformation, e.g. in the secondary structure, patterns based on primary structure, folded nature of the protein including, among others, π-π relationships and relationship between the genetic code and the electrostatic state of the environment of the encoded amino acid(s). The invention can be used among others in the field of drug research, medical diagnosis, genetic engineering and macromolecular modeling.

A method for optimizing at least one process parameter of a separation process for at least one target substance from at least one impurity using a chromatography system, comprising the steps of: a) providing a set of preliminary system-specific parameters suitable for describing the concentration transport of at least one target substance and at least one impurity in a preliminary chromatography system using a system-specific transport model, wherein the preliminary chromatography system does not include any chromatography column but includes a column shortcut; b) providing a set of preliminary column-specific parameters suitable for describing the concentration transport of at least one target substance and at least one impurity in only a preliminary chromatography column containing a preliminary chromatography matrix using a column-specific transport model; c) using an sorption model, the set of preliminary system-specific parameters, and the set of preliminary column-specific parameters to optimize at least one process parameter of the separation of at least one target substance into or from a preliminary chromatography matrix contained in a preliminary chromatography column. A step of determining a set of sorption-specific parameters suitable for describing the adsorption and / or desorption of one target substance and at least one impurity, wherein the preliminary chromatography system includes the preliminary chromatography column of step b) instead of the column shortcut of step a), d) a set of system-specific parameters suitable for describing the concentration transport of at least one target substance and at least one impurity in the chromatography system using a system-specific transport model, wherein the chromatography system does not include any chromatography column but includes a column shortcut, e) a set of column-specific parameters suitable for describing the concentration transport of at least one target substance and at least one impurity in chromatography columns including a chromatography matrix using a column-specific transport model, f) the following parameters: using the set of system-specific parameters of step d), the set of column-specific parameters of step e), and the set of sorption-specific parameters of step c),A step for optimizing at least one process parameter in silico, wherein the chromatography system includes a step of step e) with a chromatography column instead of a column shortcut in step d), and the sum of the volume of the chromatography system without any chromatography column and the volume of the chromatography column is different from the sum of the volume of the spare chromatography system without any chromatography column and the volume of the spare chromatography column.

The present invention relates to a computer implementation method for predicting site-directed mutagenesis of an antigen, the method comprising: (a) providing in silico at least one three-dimensional structure of the antigen, preferably an ensemble of three-dimensional structures of the antigen; (b) providing in silico at least one three-dimensional structure of at least one antibody or fragment thereof that is binding to or specific to the antigen, preferably an ensemble of three-dimensional structures of the antibody or fragment thereof; and (c) determining in silico the accessibility of the structure of (a) to the structure of (b), indicating that higher accessibility indicates higher mutagenesis, particularly under the selective pressure exerted by the antibody or fragment thereof, thereby predicting the site-directed mutagenesis.

The present invention provides in vitro, in silico, and in vivo methods, and combinations thereof, for optimizing dosages of combination therapies for treating cancer. The present invention additionally provides therapeutic methods and compositions for treating cancer using optimized dosages of the combination therapies.

Described herein are materials for, and methods of, breeding that allow for efficient increases in crop improvement. The methods include one or more machine learning (ML) models to predict and / or select which plants or genomes from at least one pool of plants are useful for continuing forward in the breeding program. Another approach that can be utilized is to assess in silico the desirability of simulated progeny from plants in the pool to decide which plants would produce desired progeny.

In some embodiments, a method(s) generates, in silico with a machine-learning model, multiple candidate amino acid sequences based on a reference amino acid sequence and sequence-to-function model(s) that measure binding to and neutralization of a first target. In some embodiments, a method(s) forms a sequence-to-function model for each in vitro evaluation of function(s) of each respective candidate amino acid sequence. In some embodiments, evaluated function(s) measure binding to and neutralization of a related target to a first target. In some embodiments, a method(s) selects a set of candidate amino acid sequences based on function(s) of each respective candidate amino acid sequence. In some embodiments, each candidate amino acid sequence in a selected set binds to a first target and related target(s) and neutralizes a first target and / or related target(s). In some embodiments, a method(s) retrains a machine-learning model(s) with a selected set of candidate amino acid sequences and their respective functional evaluation.

The present disclosure provides methods and systems for building generative biological sequence models and synthesizing samples from those models at petascale. A library of nucleic acids or peptides can be designed in silico and a library can be synthesized in vitro.

This disclosure provides protein mutants generated using the large language program EVOLVE-Pro, which is designed for a wide range of applications. Examples of protein mutants include miniature CRISPR nucleases. EVOLVE-Pro substantially enhances the efficiency and effectiveness of in silico protein evolution, surpassing current state-of-the-art methods and yielding proteins with more than 100-fold improvement of desired properties. EVOLVE-Pro demonstrates the necessity for protein engineering models to zoom in on desired functional properties rather than predicted fitness, paving the way for broader applications of AI-guided protein engineering in biology and medicine.

The present disclosure relates to an integrated system for generating optimized primer probe pair design for one or more quantitative polymerase chain reaction (qPCR) assays using a sequence alignment free design approach. The system includes a processor; and a computer-readable medium storing instructions which, when executed by the processor, cause the processor to: receive data including a genomic dataset; generate one or more k-mers from the genomic dataset; cluster the one or more k-mers to identify one or more targeted genomic regions; generate a plurality of primer-probe pair candidates corresponding to the one or more targeted genomic regions, wherein the one or more primer-probe pairs include degenerate primers; and perform one or more in silico operations using the one or more primers, wherein the one or more in silico operations comprise at least one of primer-probe pair optimization, specificity testing, secondary structure analysis, and in silico PCR simulation.

Computer systems for check point identification for a subject through in silico modeling are provided. One or more conditions and a plurality of contacts associated with the subject are identified in a data repository. A subset of decision rules is discovered from among a plurality of decision rules through alignment of a condition in the one or more conditions against the decision rules. The subset of decision rules models a response to the first condition at a first entity. A first decision rule in the subset of decision rules is activated using an evaluation module when a corresponding triggering condition for the decision rule arises in the data repository. A notification rule actionable upon the activating of the first decision rule is identified. A notification is communicated using a computer network to a notification path, consisting of a subset of the plurality of contacts, in accordance with the notification rule.

The present disclosure relates to systems, methods and computer program products for drug development using in silico techniques. An aspect of the disclosure is directed to an in silico method for determining drug activity of a plurality of drug targets by determining biomarker stratifier effects, calculating a biomarker stratifier score for a chosen disease phenotype; and calculating a pharmacomimetic genetic score using molecular biomarker stratifier data.

The present disclosure relates to systems, methods, and computer program products for drug development using in silico techniques. One aspect of the disclosure relates to an in silico method for determining drug activity for multiple drug targets by determining biomarker stratification factor effects, calculating biomarker stratification factor scores for a selected disease phenotype, and calculating pharmacomimetic gene scores using molecular biomarker stratification factor data.

The present disclosure relates to systems, methods and computer program products for drug development for chronic liver disease (CLD) or non-alcoholic steatohepatitis (NASH) using in silico techniques. An aspect of the disclosure is directed to an in silico method for determining drug activity of a plurality of drug targets by determining biomarker stratifier effects, calculating a biomarker stratifier score for a chosen disease phenotype; and calculating a pharmacomimetic genetic score using molecular biomarker stratifier data.

In silico tools are used to determine possibly effective therapies for treating a patient's cancer based on patient, drug, and cancer information. Functional assays can be performed on living cancer cells from the patient to evaluate the possibly effective therapies along with subsequent genomic or other more destructive assays to provide additional information from a single sample. Drug, patient, cancer, and outcome information can be recorded and updated iteratively and analyzed using machine learning to identify correlations between various patient, cancer, and drug characteristics and expected outcomes and drug efficacies.

The present invention provides in vitro, in silico, and in vivo methods, and combinations thereof, for optimizing dosages of combination therapies for treating cancer. The present invention additionally provides therapeutic methods and compositions for treating cancer using optimized dosages of the combination therapies.

Methods for identifying multi-targeting molecules by analyzing their interactions with multiple partner elements within given reference structures are provide. In certain embodiments, the methodology includes providing reference structures and an in silico library of candidate molecules, and assessing the interactions between candidate and partner molecules. Molecules that bind with multiple partners are identified as multi-targeting molecules. The library can include different types of molecules, such as polypeptide molecules. The methods, in some embodiments, further involves predicting the structure of candidate molecules and evaluating their structure in the context of the reference structure. The invention also provides systems configured to execute this methodology and the multi -targeting molecule identified through this process.

The dosage of the active ingredient in a treatment provided to or under consideration for providing to a subject is specified. The level of local amyloid beta is predicted based on the dosage of the active ingredient. T 2 The severity of amyloid-related imaging abnormalities (ARIA) (ARIA-E) that appear as high signal in fluid-attenuated inversion recovery (FLAIR) images is predicted based on the predicted amount of removal of local amyloid beta, and predicting the severity of ARIA-E includes predicting the degree of blood vessel wall damage. A result corresponding to the predicted ARIA-E severity is output.