A system and method for feedback-driven automated drug discovery which combines machine learning algorithms with automated research facilities and equipment to make the process of drug discovery more data driven and less reliant on intuitive decision-making by experts. In an embodiment, the system comprises automated research equipment configured to perform automated assays of chemical compounds, a data platform comprising drug databases and an analysis engine, a bioactivity and de novo modules operating on the data platform, and a retrosynthesis system operating on the drug discovery platform, all configured in a feedback loop that drives drug discovery by using the outcome of assays performed on the automated research equipment to feed the bioactivity module and retrosynthesis systems, which identify new molecules for testing by the automated research equipment.

The invention belongs to the technical field of the molecular force field and particularly relates to a computing task management and analysis system for molecular force field parameter building and an operation method thereof. The system comprises a computing result analysis module and a computing task management module, the computing result analysis module is connected with the computing task management module, and the computing task management module is connected with a force field building computing server through a cloud computing interface. The operation method comprises: (1) selecting a molecular force field building computing templates; (2) selecting a computing task submitting platform and submitting computing tasks; (3) retrieving computing results; and (4) analyzing the computing results. According to the invention, since force field building system users mainly including researchers do not have powerful open interface development capacity commonly, a convenient cloud computing calling interface is provided, and the force field building speed is improved; the system provides full-view and visual effects; an interactive analysis mode is provided for the force field building computing results, which facilitates quick location of a computing exception; and automatic task processing and analysis are supported.

The invention belongs to the technical field of the molecular force field and particularly relates to a computing task management and analysis system for molecular force field parameter building and an operation method thereof. The system comprises a computing result analysis module and a computing task management module, the computing result analysis module is connected with the computing task management module, and the computing task management module is connected with a force field building computing server through a cloud computing interface. The operation method comprises: (1) selecting a molecular force field building computing templates; (2) selecting a computing task submitting platform and submitting computing tasks; (3) retrieving computing results; and (4) analyzing the computing results. According to the invention, since force field building system users mainly including researchers do not have powerful open interface development capacity commonly, a convenient cloud computing calling interface is provided, and the force field building speed is improved; the system provides full-view and visual effects; an interactive analysis mode is provided for the force field building computing results, which facilitates quick location of a computing exception; and automatic task processing and analysis are supported.

A system and method for optimizing the latent space in generative machine learning models, and applications of the optimizations for use in the de novo generation of molecules for both ligand-based and pocket-based generation. The ligand-based optimizations comprise a tunable reward system based on a multi-property model and further define new measurable metrics: molecular novelty and uniqueness. The pocket-based optimizations comprise an initial multi-property optimization followed up by either a seed-based optimization or a relaxed-based optimization.

A system and method for optimizing the latent space in generative machine learning models, and applications of the optimizations for use in the de novo generation of molecules for both ligand-based and pocket-based generation. The ligand-based optimizations comprise a tunable reward system based on a multi-property model and further define new measurable metrics: molecular novelty and uniqueness. The pocket-based optimizations comprise an initial multi-property optimization followed up by either a seed-based optimization or a relaxed-based optimization.

A discrete attribute value dataset is obtained that is associated with a plurality of probe spots each assigned a different probe spot barcode. The dataset comprises spatial projections, each comprising images of a biological sample. Each image includes a corresponding plurality of discrete attribute values for the probe spots. Each such value is associated with a probe spot in the plurality of probes spots based on the probe spot barcodes. The dataset is clustered using the discrete attribute values, or dimension reduction components thereof, for a plurality of loci at each respective probe spot across the images of the projections thereby assigning each probe spot to a cluster in a plurality of clusters. Morphological patterns are identified from the spatial arrangement of the probe spots in the various clusters.

A discrete attribute value dataset is obtained that is associated with a plurality of probe spots each assigned a different probe spot barcode. The dataset comprises spatial projections, each comprising images of a biological sample. Each image includes a corresponding plurality of discrete attribute values for the probe spots. Each such value is associated with a probe spot in the plurality of probes spots based on the probe spot barcodes. The dataset is clustered using the discrete attribute values, or dimension reduction components thereof, for a plurality of loci at each respective probe spot across the images of the projections thereby assigning each probe spot to a cluster in a plurality of clusters. Morphological patterns are identified from the spatial arrangement of the probe spots in the various clusters.

This disclosure relates to a method and an apparatus for classification model training. The method includes: obtaining a support set and a query set, the support set comprising support sample feature vectors and corresponding drug resistance category labels, and the query set comprising query sample feature vectors and corresponding drug resistance category labels; inputting the support set and the query set into an initial drug resistance classification model; performing drug resistance-related feature screening to obtain target support feature vectors and target query feature vectors; calculating an initial category representation vector corresponding to a drug resistance category; determining training drug resistance category information corresponding to the query sample feature vectors; updating the initial drug resistance classification model based on the training drug resistance category information and the corresponding drug resistance category labels; and obtaining a target drug resistance classification model in response to training being completed.

This disclosure relates to a method and an apparatus for classification model training. The method includes: obtaining a support set and a query set, the support set comprising support sample feature vectors and corresponding drug resistance category labels, and the query set comprising query sample feature vectors and corresponding drug resistance category labels; inputting the support set and the query set into an initial drug resistance classification model; performing drug resistance-related feature screening to obtain target support feature vectors and target query feature vectors; calculating an initial category representation vector corresponding to a drug resistance category; determining training drug resistance category information corresponding to the query sample feature vectors; updating the initial drug resistance classification model based on the training drug resistance category information and the corresponding drug resistance category labels; and obtaining a target drug resistance classification model in response to training being completed.

A method for generating binding peptides presented by any given Major Histocompatibility Complex (MHC) protein is presented. The method includes, given a peptide and an MHC protein pair, enabling a Reinforcement Learning (RL) agent to interact with and exploit a peptide mutation environment by repeatedly mutating the peptide and observing an observation score of the peptide, learning to form a mutation policy, via a mutation policy network, to iteratively mutate amino acids of the peptide to obtain desired presentation scores, and generating, based on the desired presentation scores, qualified peptides and binding motifs of MHC Class I proteins.