3082results about "Molecular structures" patented technology

The invention discloses a genomics-based Parkinson's disease drug target prediction model construction method, and relates to the technical field of drug research and development, and the method comprises the following steps: collecting genomics, transcriptomics and proteomics data related to Parkinson's disease patients, and carrying out quality control and standardization processing; through differential expression analysis and function enrichment, key genes and signal pathways related to Parkinson's disease are identified, and a potential drug target range is determined. By integrating genomics, transcriptomics and proteomics data of patients with Parkinson's disease, molecular mechanisms related to Parkinson's disease can be comprehensively analyzed, multi-target combination is optimized in combination with the ant colony algorithm, the limitation that a traditional single-target model is difficult to capture complex disease network comprehensiveness is effectively overcome, and the method is suitable for popularization and application. The accuracy of target spot prediction is remarkably improved, a more reliable action target spot is provided for drug research and development, and the failure rate of clinical tests is reduced.

The invention discloses a drug target affinity prediction method and system based on a multi-scale protein attention mechanism, and belongs to the crossing field of bioinformatics and artificial intelligence. The method comprises the following steps: firstly, extracting protein sequence features through an ESM2 pre-training model, predicting that a three-dimensional structure is converted into a two-dimensional contact graph, and extracting spatial topological information in combination with a graph convolutional network; a two-dimensional attention mechanism is innovatively designed, structural features are taken as query vectors, sequence features are taken as key value pairs, and cross-modal feature fusion is realized by dynamically associating sequence semantics and spatial proximity relationships through multiple attention. Drug molecules are characterized by adopting MACCS fingerprints, are spliced with protein multi-modal features and then are optimized through a deep network, and finally an affinity value is output through a regression prediction module. According to the technology, the problem of protein heterogeneous data fusion is effectively solved, the generalization ability to unknown targets is remarkably improved, an efficient calculation tool is provided for new drug research and development and drug relocation, and the drug research and development cost can be reduced.

The invention discloses a drug and target interaction prediction method based on multi-scale convolution feature fusion, which comprises the following steps: acquiring drug molecule data, target protein data and drug and target interaction data, constructing a drug molecule map according to the drug molecule data, and coding a target protein sequence according to the target protein data; inputting the drug molecular map into a model, and obtaining drug features through a multi-scale map convolutional network and a dynamic gating attention mechanism; inputting a target protein sequence into the model, and obtaining target features through hierarchical cavity convolution and a bidirectional gating cycle unit; through multi-head cross attention, the drug features are aligned with the target features, local and global cross-modal fusion is carried out, and drug target fusion features are obtained; based on the drug target fusion features, outputting a drug and target interaction prediction probability; and training the model according to the drug and target interaction data and the prediction probability, and applying the trained model to drug and target interaction prediction.

The invention discloses a drug target activation and inhibition relation prediction method based on a depth map neural network, and aims to improve the modeling precision and prediction performance of an activation or inhibition action mechanism between a drug and a target. According to the method, on the basis of a fine-grained graph interaction modeling mechanism, multi-scale structural characteristics of drug molecules and three-dimensional space structural information of protein residue levels are fused, and a heterogeneous interaction graph between drugs and proteins is constructed. The method comprises the following steps: firstly, acquiring a drug-target sample with an activation / inhibition tag through a public database, predicting a protein structure by utilizing AlphaFold2, and constructing a protein residue map and a drug molecular map; multi-scale structure semantic representation is obtained through sub-graph decomposition, atomic-scale feature extraction and graph neural network coding of drug graph features; protein graph node features are combined with context embedding generated by a pre-training language model, DSSP coding, secondary structure spectrum and atomic structure features are constructed, and edge features are designed based on the geometrical relationship between residues. Then, based on constraints such as spatial distance and biochemical similarity, a fine-grained mapping relation between drug atoms and protein residues is established, an interaction graph is constructed, and coding is carried out through a GraphSAGE network; and finally, fusing the interacted multi-source embedding, and completing the prediction of the activation / suppression relationship through a multi-layer perceptron. A cross entropy loss function, an Adam optimizer and hyper-parameter grid search are adopted in model training; in the evaluation stage, five-fold cross validation and an independent test set are adopted, and indexes such as the accuracy rate, the recall rate, the F1 score, the specificity and the Morse correlation coefficient are used for comprehensively evaluating the performance of the model. Experimental results show that compared with an existing method, the method has the advantages that the prediction accuracy and mechanism interpretability are remarkably improved, and the method has good generalization ability and application prospects and is suitable for multiple fields of drug action mechanism research, new drug discovery and the like.

The invention discloses a drug resistance prediction method and system based on comparative learning and multi-modal fusion, and the method comprises the steps: firstly generating a molecular map and a molecular fingerprint based on the SMILES of a target drug, and extracting the molecular features of the drug through a comparative learning model constructed through combining a map attention network and a map convolution network; and then, acquiring protein expression, gene expression and metabolic expression data from the target tissue cells, extracting modal features through a deep convolutional network, a Transform encoder and a multi-dimensional attention network, and realizing adaptive fusion of the multi-modal features through a heterogeneous interactive attention mechanism. And finally, jointly inputting the fused multi-modal features and drug molecular features into a multi-layer sensor to realize high-precision prediction of the drug resistance of cells to drugs. By introducing a contrast learning and multi-modal feature fusion mechanism, the characterization capability and prediction precision of the model are effectively improved, and efficient and reliable support can be provided for drug screening and clinical decision making.

Systems and methods described herein include embodiments for generating a geometrical structure of a binding complex formed between a plurality of macromolecules, comprising: processing an input representation comprising a plurality of representations of the plurality of macromolecules to generate a geometry prior; sampling an initial geometrical structure of the binding complex based on the geometry prior; and processing, using a neural network, the initial geometrical structure to generate the geometrical structure of the binding complex formed by the plurality of macromolecules.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for embedding perturbation data via a machine learning model and filtering, aligning, and aggregating the embeddings to generate a genome-wide perturbation database for real-time generation of perturbation heatmaps. In particular, in one or more embodiments, the disclosed systems can receive a plurality of perturbation images portraying cells from a plurality of wells corresponding to a plurality of cell perturbations. Further, the systems can generate, utilizing a machine learning model, a plurality of well-level image embeddings from the plurality of perturbation images. Moreover, the systems can align, utilizing an alignment model, the plurality of well-level image embeddings to generate aligned well-level image embeddings. Additionally, the systems can aggregate, according to perturbations of one or more perturbation experiments, the well-level image embeddings to generate perturbation-level image embeddings. Furthermore, the systems can generate perturbation comparisons utilizing the perturbation-level image embeddings.

The invention discloses a molecular binding prediction model training method and device, equipment and a storage medium. Relates to the technical field of artificial intelligence. The method comprises the following steps: performing feature extraction on a sequence of a first biomolecule sample through a molecular binding prediction model to obtain a first feature; performing feature extraction on the sequence of the second biomolecule sample through a molecule combination prediction model to obtain a second feature; obtaining an interaction feature based on the first feature and the second feature through a molecular binding prediction model; obtaining a combination probability based on the first feature, the second feature and the interaction feature through a molecular combination prediction model; and adjusting parameters of the molecular binding prediction model based on the binding probability to obtain a trained molecular binding prediction model. By means of the method, the molecular binding prediction model can learn the interaction relation between the sequences of the biomolecules, and then the binding probability between the biomolecules can be predicted more accurately.

The invention relates to the technical field of pharmaceutical knowledge maps, in particular to a pharmaceutical knowledge map construction method and system based on artificial intelligence, and the method comprises the following steps: querying and collecting a molecular structure of a drug and a corresponding target protein sequence through a database, and carrying out the numerical coding of the molecular structure data of the drug, molecular fingerprints and protein structural domain features are extracted, and a drug and protein feature set is formed by combining drug chemical attributes and protein sequence features. According to the invention, through accurate analysis of the molecular structure of the drug and the target protein sequence thereof, the innovative scheme significantly enhances the understanding of the interaction of the drug and the protein, so that researchers can directly extract key features from data and monitor the dynamic change of the drug effect, thereby not only accelerating the development process of the drug, but also improving the development efficiency of the drug. By dynamically tracking the interaction between the side effect of the medicine and the pathological characteristics, the scheme provides powerful data support for personalized medical treatment.

According to the intelligent training method, the prediction method, the equipment and the medium for the pharmacokinetic properties of the polypeptide drugs, based on the prediction model obtained through training, the pharmacokinetic properties of at least two polypeptide drugs can be predicted, and compared with a traditional experiment method, the intelligent training method has the advantages of being efficient, accurate and comprehensive in effect and high in practicability. And the comprehensive systematic prediction platform can promote the unification of model data standards developed by different research teams, and effectively ensures the actual value of the polypeptide drug in early screening and optimization.

A system is disclosed for encoding a data string of a first modality into a hierarchical tokenized representation for processing by a text-based deep neural network (DNN) trained on a second modality. The data string comprises multiple units, each having one or more attributes. Each attribute is represented in the tokenized string as a sequence of hierarchical tokens, with a first hierarchical token encoding one or more most significant bits and a subsequent hierarchical token encoding one or more less significant bits. The DNN processes the data string bidirectionally, across the sequence of units and within the token hierarchy, to select tokens that capture attribute information. The selected hierarchical tokens output by the DNN from a representation of the original data string that preserves attribute detail while enabling cross-modal processing using models trained on text.

The invention provides a drug target binding affinity prediction method based on multi-modal data fusion. The method comprises the following steps: firstly, extracting sequence feature information of drug SMILES and target FASTA, then constructing an affinity graph, modeling drug molecules and target protein molecules into an undirected graph, and extracting molecular-level features of atoms, bonds, residues and contact. And fusing the hierarchical graph structure information of the affinity graph and the molecular graph to obtain the graph structure feature representation of the drug-target spot. The sequence feature information and the graph structure feature representation are further fused by using intramolecular and intermolecular attention fusion mechanisms. And finally, performing affinity prediction by using the fused features, and outputting a drug-target binding affinity score. According to the method, sequence and structural information are effectively fused, the accuracy of drug target affinity prediction is improved, and the problems of insufficient information fusion and insufficient structural information utilization in an existing method are solved.

The invention discloses a small molecule ligand drug screening method and system based on affinity prediction, and belongs to the technical field of biological medicine. The invention aims to solve the technical problem of low drug screening precision caused by molecular expression limitation, geometric invariance deficiency and insufficient multi-modal information fusion when virtual drug screening is carried out by using protein-ligand affinity. Comprising the following steps: acquiring ligand and protein structure information, and preprocessing to obtain coordinates and a feature matrix of ligand / pocket / residue; performing comprehensive representation, multi-feature flow self-adaption, geometric algebraic multi-layer perception and feature alignment processing on the feature matrix to obtain corresponding feature space representation; performing cross attention fusion and multi-scale interactive learning processing on the feature space representation in sequence to obtain fusion features; inputting the fused features into a multi-scale interactive learning module, and outputting final features; and finally, predicting the binding affinity of the ligand and the protein according to the fusion characteristics to obtain a binding affinity value.

The invention discloses a colorectal cancer drug relocation method based on multi-omics integration. The system comprises a multi-omics data acquisition and preprocessing module, a tumor microenvironment analysis module, a specific disease network construction module, a multi-dimensional drug relocation module and a result evaluation module. And the tumor microenvironment analysis module comprises cell heterogeneity identification, cell map construction, cell annotation and tumor cell subset annotation. The specific disease network construction module comprises tumor feature expression program extraction, expression program screening, meta-program construction, clinical related meta-program recognition and specific disease protein interaction network construction. And the multi-dimensional drug relocation module comprises a module for identifying diseases by using a random walk algorithm, carrying out drug screening based on disturbance data, carrying out drug screening based on network proximity and carrying out comprehensive drug relocation. From the perspective of single cell data, element programs related to colorectal cancer survival are excavated, corresponding modules are designed, and the efficiency and precision of colorectal cancer targeted drug screening are improved.

Methods and apparatus for obtaining representations of proteins and small molecule drugs for synthesis; wherein pre-trained mixed modality protein and natural language fusion models are further trained by supervised fine tuning using reasoning-oriented query—chain-of-thought (CoT) response pairs. The resulting reasoning-oriented neural network is then used to obtain representations of output proteins or small molecule drugs, in response to mixed modality reasoning-oriented input queries specifying conditions on the output. In one embodiment, the neural network is an autoregressive multicapitate transformer whose decoder output heads correspond to the represented modalities. The method returns mixed modality output representations of proteins or small molecule drugs for synthesis or manufacture.

The present disclosure provides in some embodiments, a multi -objective binder design framework by aligning autoregressive molecular foundation models (e.g., protein language models (pLMs)) to different objectives, such as binding and developability considerations. In some embodiments, direct preference optimization (DPO) can be utilized in the methods and systems described herein to encode multiple design objectives in the language model through direct optimization on expert curated preference sequence datasets comprising preferred and dispreferred distributions. In some embodiments, utilizing the described framework can enable molecular foundation models (e.g., protein language models), such as ProtGPT2, to effectively design binders conditioned on specified receptors and one or more drug developability criteria. Besides being multi -objective, in some embodiments, the methods and systems provided herein conceive online lab-in-the-loop design pipelines by actively incorporating experimental feedback.

The invention belongs to the field of bioinformatics, and relates to an improved integrated deep learning cell communication ligand-receptor interaction prediction method. The method comprises the following steps: firstly, carrying out extraction and dimensionality reduction on biological sequence features of a ligand and a receptor, and constructing multi-modal feature input; secondly, constructing an improved deep neural network branch, introducing a batch normalization layer and a Leaky ReLU activation function, solving the problems of gradient disappearance and neuronal necrosis, and improving regularization strength to prevent overfitting; meanwhile, an enhanced heterogeneous graph auto-encoder branch is constructed, the graph embedding dimension is remarkably expanded to improve the feature capacity, and full convergence of the model is ensured by increasing training rounds; thirdly, fusing the improved deep network with the prediction probability of a heterogeneous graph auto-encoder by adopting a weighted integration strategy; and finally, outputting a potential interaction relationship based on the fusion probability. By optimizing the architecture and the strategy, the prediction accuracy and robustness are remarkably improved, and a reliable tool is provided for analyzing a complex cell communication network.

The invention relates to the technical field of bioinformatics and computational biology, and provides an anti-cancer drug target screening method and system based on hypergraph-knowledge graph dual-channel, a hypergraph-knowledge graph dual-channel architecture is constructed through a feature extraction module, a self-adaptive multi-modal fusion module dynamically integrates multi-source heterogeneous data, and the anti-cancer drug target screening method and system based on the hypergraph-knowledge graph dual-channel architecture are obtained. The method comprises the following steps: adaptively fusing high-order interaction features and semantic association features of a gene, generating a high-quality negative sample by using a generative adversarial network to optimize a training process, finally optimizing feature representation through a discriminator, and calculating a synthetic lethal probability score between any gene pair. According to the application, firstly, the extracted multi-dimensional features are normalized through the feature extraction module, then the importance of different features is dynamically weighted based on the attention mechanism, finally, the synthesis lethal relationship prediction probability of the gene pair is output through the multi-layer sensor, and under the theoretical framework of the gene synthesis lethal effect, the synthesis lethal effect of the gene pair is predicted. And an innovative solution is provided for anti-cancer drug target screening.

A protein complex model interface quality evaluation method based on a multi-scale isovariant graph neural network comprises the following steps: firstly, screening out a co-crystallized natural protein complex structure from a non-redundant protein interaction database PRISM, and generating a bait structure by using a HDock docking algorithm; the method comprises the following steps: firstly, extracting molecular surface interaction fingerprints, atomic-level features and residue-level features on the basis of each compound bait structure, obtaining graph representation of the compound bait structures, then fully capturing and fusing multi-scale information through a depth isotropic graph neural network, and finally obtaining an interface mass fraction through prototype comparison prediction. According to the method, the interface quality evaluation of the protein compound model can be accurately carried out, and the problems of low precision and poor generalization of the interface quality evaluation of the protein compound model are effectively solved.

The invention discloses a protein active site multi-classification identification method based on multi-modal deep learning. According to the method, protein sequence information, three-dimensional structure information and functional text information are fused, a pre-trained protein language model, an isotropic graph neural network and a biomedical language model are utilized, an innovative multi-modal feature extraction and fusion mechanism is designed, and the model performance is optimized through a self-adaptive weighted fusion strategy. According to the method provided by the invention, accurate prediction of protein active sites can be realized through acquisition of a high-quality data set, construction of a cross-modal feature fusion module, setting of a weighted fusion mechanism and design of a composite loss function.

According to the pre-training language model-based drug-target interaction prediction method designed by the invention, natural language processing and graph neural network technologies are fused, context semantic features are automatically extracted from drug molecule SMILES character strings and protein sequences, and by constructing a graph structure taking drug-target pairs as nodes, the drug-target interaction is predicted. The weight of an edge is defined according to the similarity between embedded vectors, and a simplified graph convolutional network is adopted to carry out graph structure modeling to realize complex relation learning, so that the accuracy, generalization and interpretability of prediction are improved, the limitation of a traditional method on the problems of sparse feature expression, mutual information loss and'words outside a vocabulary 'is overcome, and the prediction accuracy, generalization and interpretability are improved. And finally, the accuracy of predicting the drug-target interaction relationship is improved.

Methods and apparatus for obtaining representations of proteins and small molecule drugs for synthesis; wherein pre-trained mixed modality protein and natural language fusion models are further trained by supervised fine tuning using reasoning-oriented query—chain-of-thought (CoT) response pairs. The resulting reasoning-oriented neural network is then used to obtain representations of output proteins or small molecule drugs, in response to mixed modality reasoning-oriented input queries specifying conditions on the output. In one embodiment, the neural network is an autoregressive multicapitate transformer whose decoder output heads correspond to the represented modalities. The method returns mixed modality output representations of proteins or small molecule drugs for synthesis or manufacture.

The invention relates to a method for classifying antihypertensive peptides by fusing sequence and structure multi-modal features and combining contrast-generative combined optimization. The method comprises the following steps: extracting sequence feature representation and structure feature representation of peptide fragments; performing multi-modal feature enhancement of comparison-generative joint optimization on the sequence feature representation and the structural feature representation; and performing peptide classification on the enhanced feature representation by using a preset Kan-Conv structure and tag smooth joint optimization classification model. According to the method, high-precision recognition of the functional activity of the antihypertensive peptide is achieved, information in the three aspects of the sequence, the structure and the generative potential space is creatively and comprehensively utilized, the blank that the structure-sequence synergistic effect is ignored in the existing peptide function prediction field is filled, and the screening efficiency and prediction reliability of the antihypertensive peptide are remarkably improved.

The invention provides a method for identifying PFAS in an environment based on machine learning pseudo-targeted screening, which comprises the following steps: calling mass spectrum data containing PFAS compounds from a preset mass spectrum database, and performing interference peak elimination processing on the mass spectrum data to obtain a model training data set; extracting a feature data set for model training from the model training data set based on a feature extraction standard; training a plurality of machine learning classification models based on the feature data set, and performing performance evaluation on each machine learning classification model based on a training result to determine an optimal machine learning classification model; and analyzing the optimal machine learning classification model, determining key features when the PFAS is screened and identified, and carrying out PFAS screening identification verification on the optimal machine learning classification model according to the key features based on an actual environment sample. The method has the advantages of saving analysis cost, improving analysis efficiency and improving compound recognition accuracy.

The invention provides a drug-target interaction prediction method and device based on a dynamic heterogeneous double-flow graph neural network, and belongs to the field of drug research and development. The method solves the problems of low prediction accuracy and weak generalization ability caused by insufficient graph structure construction and feature expression in the prior art, and comprises the following steps: constructing a graph structure according to feature data of drugs and targets, and dynamically adjusting weights of the graph structure and edges according to data change to obtain a dynamic heterogeneous graph; the double-flow graph neural network is utilized to process feature information of the medicine and the target spot at the same time, and a complex mode of medicine-target spot interaction is effectively captured; in combination with long-range dependency modeling and random walk feature learning, on the basis of heterogeneous graph convolutional network learning, processing a remote dependency relationship between a drug and a target spot, and capturing multi-hop information in an isomorphic network by using random walk to further optimize interaction prediction; designing a decoder based on matrix completion; training and optimizing the model; the method is applied to drug-target interaction prediction.

The invention discloses a luciferase high-throughput optimization screening method and system based on artificial intelligence. The method comprises the following steps: simulating and constructing a protein high-throughput mutation sequence library; carrying out prediction and evaluation on physicochemical properties, enzyme function indexes and mutation adaptability on protein sequences in the protein high-throughput mutation sequence library from the sequence level through a sequence level evaluation model and a tool; carrying out protein structure prediction on protein sequences in the protein high-throughput mutation sequence library from a structure level through a plurality of structure prediction models and tools so as to predict and evaluate various structure prediction indexes, physicochemical information, protein-substrate binding force and protein-substrate affinity of proteins; and customizing a screening scheme by adopting a mode of combining threshold filtering and dynamic weighted scoring so as to optimize and screen the protein high-throughput mutation sequence library according to different screening targets to obtain a high-quality mutation sequence. According to the method, the protein optimization screening efficiency can be remarkably improved, and the requirements of different application scenes can be met.

The invention provides a drug-target correlation prediction method based on a hierarchical representation learning framework, and the method comprises the steps: screening high-information-density nodes based on a dynamic fluctuation threshold value, reducing low-noise nodes, and reconstructing topological connection according to a virtual edge weight formula; performing tensor splicing on the drug molecular features extracted by the dynamic neighborhood search framework and the protein semantic features generated by the denoising auto-encoder to form drug-protein pair joint feature representation; a multi-head attention mechanism is utilized to allocate dynamic weights for multi-view features based on drug-protein pairs, multi-view feature vectors are spliced, after key information is screened through the attention mechanism, the key information is input into a full-connection neural network, and a correlation prediction value is output based on the full-connection neural network. The association prediction method solves the problems that the prediction precision of the model on the complex biological interaction is poor, and the understanding ability of the model on the multilevel feature learning association in the complex biological network is seriously limited.

The invention discloses a method for identifying the effectiveness of a Cas target spot by combining a gene large model and ML, and belongs to the field of biotechnology and artificial intelligence. The method comprises the following steps: constructing a detection array of A types of combined sequences and targeted combined sequences, wherein the detection array is provided with A detection units; respectively adding a combined sequence into each detection unit, carrying out incubation reaction, obtaining a fluorescence value of each detection unit, and carrying out normalization processing; carrying out key feature extraction on each combined sequence by adopting a feature extraction model; constructing a label set and a training set, constructing an integrated model, and training by adopting the label set and the training set; forming a machine learning model by the feature extraction model and the trained integrated model; and combining the new target sequence and the PAM sequence into a to-be-analyzed combined sequence, inputting the to-be-analyzed combined sequence into the machine learning model to obtain a predicted fluorescence value, and judging the recognition capability of the Cas protein on the combined sequence based on the fluorescence value. The method can assist in targeted therapy detection.

The invention discloses a protein generation model optimization method based on deep learning, and relates to the technical field of protein generation. The optimization method comprises the following steps: generating a candidate protein electron density distribution diagram based on the structural characteristics of a target spot by adopting a pre-trained diffusion model; converting the candidate protein electron density distribution diagram into a corresponding amino acid sequence; determining a functional index value corresponding to the amino acid sequence, and constructing a feedback data set; setting a reward threshold value, and marking the feedback data set as a positive sample data set and a negative sample data set according to the reward threshold value; constructing a utility function taking the reward threshold as a reference point, and respectively calculating utility values of the positive sample data set and the negative sample data set; and performing iterative optimization on the diffusion model according to the utility value. By adopting the technology provided by the invention, the dependence on preference paired data of large-scale and high-quality protein sequences can be avoided, and the performance of the protein generation model can be effectively and continuously improved.

The invention discloses a drug target affinity prediction system based on cross-modal feature fusion, and relates to the technical field of biological information. The invention aims to solve the problem of low prediction precision of the existing DTA prediction method. The method comprises the following steps: preprocessing a drug SMILES character string and a protein amino acid sequence to obtain a drug molecular map, a drug SMILES sequence embedding characteristic, a protein contact map and a protein amino acid sequence embedding characteristic; according to the drug molecular diagram and the protein contact diagram, drug diagram modal characteristics and protein diagram modal characteristics are obtained; obtaining drug sequence modal characteristics and protein sequence modal characteristics by using drug SMILES sequence embedding characteristics and protein amino acid sequence embedding characteristics; fusing the drug pattern modal features and the drug sequence modal features to obtain drug fusion features, and fusing the protein pattern modal features and the protein sequence modal features to obtain protein fusion features; and acquiring the drug target affinity by using the drug fusion feature and the protein fusion feature. The method is used for predicting the affinity of the drug target.