Abstract: A protein virtual screening method and device, equipment, and a storage medium, falling within the field of drug discovery. The method comprises: acquiring a training sample set, wherein the set comprises source and sample data corresponding to the source data; performing unsupervised pre-training on a Transformer model with the source data as input and the sample data as verification, and generating a one-dimensional or multi-dimensional symmetric matrix for the protein sequence and the ligand sequence; coupling two matrices for the protein sequence and the ligand sequence into a multi-dimensional symmetric matrix, and using the matrix as an input of an hidden layer of a BILSTM network model; fitting the experimental measurement classification and regression value of protein and small molecule interaction by the Bilstm network model to obtain to a trained screening model; and predicting different protein prediction tasks by the screening model to output prediction results.

Abstract: The present invention enables the prediction of both the ligand type for protein-ligand binding sites and their druggability scores. The invention provides a computational method to investigate the ligand type and druggability of protein-ligand binding sites. The invention has two distinct training sets for two different prediction methods. The method leverages attention-based deep learning models for both ligand type and druggability prediction tasks. Deep learning models incorporate both channel-based and spatial-based attention mechanisms. The training phase focuses on the coordinates of known ligand binding sites to enhance the accuracy of druggability prediction. The method also provides the capability to update the training set with new data, thereby ensuring continued improvement in the prediction performance. The invention also details a computer device with a memory and processor, storing a computer program to implement the method.

Abstract: A system and method for predicting physical and chemical properties of eco-friendly materials is disclosed. The method includes receiving 3D structures and DFT calculated energy data associated with one or more sesquioxides via one or more electronic devices associated with a user or an external database, and predicting a formation energy and a bandgap energy of each of the one or more sesquioxides based on the received 3D structures and the DFT calculated energy data by using a property prediction-based AI model. Further, the method includes determining a best sesquioxide from the one or more sesquioxides based on the predicted formation energy, and the predicted bandgap energy by using the property prediction-based AI model, and outputting the predicted formation energy, the predicted bandgap energy, and the determined best sesquioxide on user interface screen of the one or more electronic devices associated with the user.

Abstract: A system and method for drug discovery is disclosed. The method includes receiving patient multiomics raw data, extracting one or more reports from the patient multiomics raw data, and detecting one or more genome variants in the patient. Further, the method includes determining if the one or more genome variants are one or more known variants or one or more unknown variants, determining if the one or more genome variants are one or more coding variants or one or more non-coding variants, and determining if the patient is suffering from a functional loss or a functional excess. The method includes generating one or more rescue recommendations, determining one or more medical therapies for the patient, and outputting the one or more rescue recommendations and the one or more medical therapies to one or more electronic devices associated with the user.

Abstract: The present invention provides a cleaning method for drug-target interaction data, which comprises the following steps: provide an original collection of drug-target interaction data; screen and filter the original drug-target interaction data set according to a predetermined cleaning rule to obtain a drug-target interaction data set to be studied; wherein, the predetermined cleaning rule is based on the data structure of the adjacency matrix of the graph. The present invention further provides a cleaning system for drug-target interaction data. The present invention provides a method and system for properly describing and comparing the structure, function, etc. of drug target proteins, so as to the differences in target proteins can be quantified.

Abstract: A system and method for collaborative smart evidence gathering and investigation for incident response attack surface management and forensics in a computing environment is disclosed. The system obtains evidence data from multiple sources with various entry points, capturing contextual information. Further, the system processes the data using an artificial intelligence (AI) root cause analysis, graph augmented retrieval, semantic classifier, meaning extraction, and causal discovery model. Furthermore, the system performs similarity analysis to assess evidence quality, sufficiency, and completeness. Based on the evaluation, the system determines appropriate actions to be taken on the processed evidence data. Additionally, the system executes the actions to resolve the incidents effectively by using a smart expert system, a human agent participation, or an AI co-pilot, as a first-class investigator and collaborator in the process.

Abstract: The present invention provides a data preprocessing method for cleaning a small molecule compound, the data preprocessing method comprising: an S1 text preprocessing step including: preprocessing an original SMILES text of a small molecule compound into a standardized SMILES text of the small molecule compound; and an S2 chemical graph formatting step including: splitting in a format each text element of the standardized SMILES text of the small molecule compound of S1 to obtain chemical graph information of the small molecule compound. The present invention also provides a data preprocessing system for cleaning a small molecule compound. The present invention enables the cleaning, deduplication, and standardization of global datasets, providing an efficient, fast, accurate integration method for the cleaning of end-to-end small molecule compounds.

Abstract: A ligand screening model construction method, a ligand screening model construction device, and a drug ligand screening method for drug screening, comprising that obtain a drug ligand training set, and the drug ligand training set includes a drug ligand chemical formula and a classification label; a ligand graph network is drawn, in which atoms are nodes and chemical bonds are edges connecting nodes; use a random initialization vector to identify the weight vector of each node in the ligand graph network; reconstruct each node of the ligand graph network to obtain a reconstruction network, and repeat the reconstruction steps to obtain at least two layers of reconstruction networks; perform deep learning on the ligand graph network and the at least two-layer reconstruction graph network according to the classification labels, and construct a ligand screening model.

Abstract: A drug screening model construction method and device, a screening method, apparatus and a medium, in the field of drug screening that includes obtaining a drug training set, where the set comprises a chemical formula of a drug protein, a chemical formula of a small molecule and a classification label; drawing an initial graph network of drug protein and small molecule, in which atoms are nodes and chemical bonds are edges connecting nodes; using a random initialization vector to identify the weight vector of each node; reconstructing each node of the initial graph network according to the connection relationship of the initial graph network to obtain a reconstruction network, and repeating the reconstruction steps to obtain at least two layers of reconstruction networks; performing deep learning on the initial graph network and the reconstruction graph network according to the classification labels, and constructing a drug screening model.

Abstract: The present application provides a data processing method, system, electronic equipment and storage medium based on a cloud platform, which are applied to the technical field of cloud computing processing, wherein the data processing method comprises the following steps: obtaining task processing requests submitted by several target users through a distributed system, wherein the task processing requests are requests for processing scientific computing tasks; Determining whether the number of the obtained task processing requests reaches a preset capacity expansion threshold, and if so, generating a workload capacity expansion request; Performing capacity expansion processing on the computing node according to the capacity expansion request; The workload is redeployed based on the computing nodes after capacity expansion processing, so as to execute the scientific computing task based on the redeployed workload.

Abstract: The present application provides a method, a device, and a system for compound clustering and a storage medium, including acquiring samples of compounds to be identified, and segmenting the samples of the compounds into a subset of samples including an initial identification tag; obtaining a sample legend according to the sample subset; and obtaining target identification tag results corresponding to the samples of the compounds according to the sample legend and the identification tag, wherein the identification tag includes the initial identification tag. The present invention provides an efficient, rapid and accurate method for small molecule compound clustering based on statistical compound clustering, improving the accuracy of small molecule compound clustering, reducing the processing space of clustering and breaking through the limitations of small molecule clustering, thereby making the processing of small molecule compound clustering more efficient and accurate.

Abstract: A PROTAC target molecule generation method, system, and storage medium where the method includes obtaining parameters; extract the target protein ligand structure corresponding to the first parameter in the target protein ligand database to form a first subset, extract the degradation agent fragment structure corresponding to the parameter in the degradation agent fragment database to form a second subset, and extract the linker fragment structure corresponding to the parameter in the linker fragment database to form a third subset; permute and combine each fragment structure in the subsets to generate PROTAC target molecules. The extract required fragment structures from various databases, then permute and combine the three groups of fragment structure, and use big data and computational processing to be used for experiments, avoids the omission of the combination of structural fragments, improves the accuracy of molecular design and speeds up drug research and development processes.

Abstract: The present invention provides an affinity modification system of antibody/macromolecular drug, wherein the affinity modification system comprises: an interaction module, set to: input template sequence information of antibody/macromolecular drugs, modification requirements of single/multi-targets of antibody/macromolecular drugs and optional user-defined screening requirements to generate interaction antibody/macromolecular drug sequence information; affinity modification module, set to: according to the interaction antibody/macromolecular drug sequence information, perform corresponding partial or exhaustive numeration of possible sequence in a part of the full variable range to obtain a mutation library, and perform sequence-based affinity prediction on the mutation library based on a deep learning model, so as to obtain the sequence information of the modified antibody/macromolecular drug; an output module, designed to: according to the sequence information of the modified antibody/macromolecular drug, ou