79 results about "Functional prediction" patented technology

The invention relates to the technical field of tumor treatment, in particular to an intelligent decision-making system for tumor precise targeted medication based on individual mutation information, which comprises a data processing layer, a variation annotation and function prediction layer, a knowledge base integration layer and a scheme decision-making engine and report visualization module. According to the intelligent decision-making system for tumor precise targeted medication based on individual mutation information, a rule engine and a prediction model are combined, dynamic priority ranking is output, multi-model fusion decision making is achieved, and clinical scene deep adaptation is achieved by predicting primary and secondary drug resistance, calculating liver and kidney function adjusting dosage and generating a combined medication time sequence scheme; through an individualized drug delivery scheme, combination drug use optimization is achieved, a visual clinical report is generated, clinical executable operation is further strengthened, and through algorithm quantification, a dynamic knowledge graph, AI auxiliary decision making and a clinical operation closed loop, the next-generation technical research direction of a tumor precise drug use system can be represented.

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 liver function prediction method and device, electronic equipment and a medium, and the method comprises the steps: obtaining original clinical data of a plurality of pneumonia patients, and grouping an original clinical database according to the liver injury degree; performing significance evaluation on characteristic variables in the data, and finding out a first characteristic variable related to the liver injury degree; extracting a first feature variable in the data, and constructing a first data set; respectively training and evaluating the plurality of machine learning models, and selecting the machine learning model with the optimal evaluation result as a liver function prediction model; carrying out interpretability analysis on the liver function prediction model; extracting a second feature variable in each piece of original clinical data to construct a second data set; training a liver function prediction model based on the second data set to obtain a trained liver function prediction model; and predicting the liver function of the target pneumonia patient based on the trained liver function prediction model. The method can be used for rapidly predicting the liver function of the pneumonia patient.

The invention relates to the technical field of artificial intelligence, and provides a protein function prediction method and device based on multi-modal protein data, and the method comprises the steps: obtaining protein multi-source data, carrying out the feature extraction of a protein sequence in the protein multi-source data, and obtaining a protein sequence feature; constructing a heterogeneous graph based on the protein multi-source data; performing feature coding on the heterogeneous graph by adopting a graph attention mechanism to obtain protein graph features; performing multi-modal fusion on the protein sequence features and the protein map features by adopting a gating fusion mechanism to obtain fusion features; and performing multi-label classification prediction based on the fusion features to obtain a protein function annotation result. The accuracy and robustness of protein function prediction can be improved, and the problems that in the prior art, multi-source protein data cannot be effectively integrated, and the method is sensitive to data noise are solved.

The invention discloses a new mutation-oriented pathogenicity prediction method, which comprises the following steps of: acquiring new mutation site data to be analyzed, and generating a numerical feature vector containing evolution conservative property, function prediction score and quantitative clinical evidence; constructing a feature extractor through the numerical feature vector; inputting a training data set containing a label sample and a label-free sample into the feature extractor, and updating the network parameters of the feature extractor and each header; and predicting target variation by using the feature extractor after parameter updating and the supervised classification head to obtain a pathogenicity probability, and calculating a contribution value of each feature in the numerical feature vector to the pathogenicity probability. According to the technical scheme provided by the invention, the auxiliary decision-making information conforming to the diagnosis habit of a doctor is output, the workload of manually interpreting the variation with unclear meaning is greatly reduced, and the end-to-end intelligent processing from the original sequencing data to the clinical auxiliary diagnosis is realized.

The invention provides a method and a system for predicting a cell type-specific non-coding variation function, and belongs to the technical field of bioinformatics. Comprising the steps that a DINOSNN prediction model is constructed, model training is carried out, and the model is composed of a convolution and attention mixed neural network model and a non-coding variation prediction model; obtaining all non-coding variations corresponding to each brain mental disease, inputting the non-coding variations into a DINOSNN prediction model, predicting the probability that each non-coding variation is a functional non-coding variation through a trained gradient boosting tree model, and predicting a cell type set influenced by the variation, further establishing a corresponding relationship among the brain and mental diseases, the non-coding variation and the cell type set influenced by the non-coding variation; and selecting a cell type set corresponding to the non-coding variation with the highest probability of functional non-coding variation from the non-coding variations corresponding to the brain and mental disease to be analyzed as a targeted cell set corresponding to the brain and mental disease to be analyzed.

The invention provides a gene function prediction method and system based on multi-label active learning, and the method comprises the steps: selecting gene-function pairs forming an initial set from an unlabeled data set according to an initial information score quantified by the uncertainty of gene function prediction, label correlation and label distribution imbalance; according to a selection standard of feature diversity, label space diversity and sample-label pair interaction diversity, a standby set is selected in combination with the initial information score; the gene function prediction efficiency and accuracy are remarkably improved, reliable technical support is provided for large-scale gene function research, and the method is particularly suitable for complex function prediction scenes such as research fields of new gene function discovery, disease-related gene function annotation and the like and has important practical application value.

The invention provides an RNA sequence classification method based on a Mangbar model and semi-supervised learning, and belongs to the field of bioinformatics. Firstly, multi-scale sparse features are extracted from an RNA sequence, high-dimensional features are compressed to low-dimensional potential space vectors through an encoder network, and L2 normalization is carried out to enhance feature separability. Secondly, a Mangbar model based on a selective state space model is introduced into a residual structure, and the long-range dependency relationship is efficiently modeled with low complexity; and finally, realizing unsupervised feature reconstruction and semi-supervised learning of supervised classification by constructing an encoder-decoder structure, and improving the generalization performance of the model under a small sample condition by adopting a weighted loss function. Experimental results show that the method significantly improves the F1 score in a classification task of multiple types of RNA sequences. According to the method, the long sequence modeling and labeling cost is reduced, and the method is suitable for the fields of RNA function prediction, biomedical research, disease diagnosis and the like.

The invention discloses a cell image segmentation and function prediction method and device and computer equipment. The method comprises the steps of obtaining a to-be-processed cell image; inputting the to-be-processed cell image into the segmentation model for segmentation to obtain physical morphological features; inputting the physical morphological characteristics into a function prediction model to predict relevant parameters of the cell biological characteristics and relevant indexes of a set type of curative effect so as to obtain the parameters of the cell biological characteristics and the relevant indexes; and outputting physical morphological characteristics, cell biological characteristic parameters and related indexes. By implementing the method provided by the invention, the undyed bright field cell image can be effectively processed, the cell morphology and function are associated, the method is specially used for segmenting the mesenchymal stem cells, and the problem of instance segmentation under the condition of cell overlapping is solved.

The invention relates to the technical field of biological function prediction, in particular to a biological reagent function prediction method and system. The method comprises the following steps: carrying out biomolecule information acquisition on a biological reagent public database to obtain a biological reagent biomolecule information set; performing biological characteristic analysis on the biological reagent biomolecule information set to obtain biological reagent protein sequence comparison characteristics, biological reagent molecular structure domain characteristics and biological reagent specific molecular function domain characteristics; constructing a biological reagent function prediction network framework and performing function prediction model training construction to generate a biological reagent function prediction model; obtaining molecular characteristics of the biological reagent to be predicted and performing target function prediction to obtain a target biological reagent function prediction result; and performing function verification optimization according to the target biological reagent function prediction result to generate a target biological reagent function optimization result. According to the invention, effective pre-judgment and screening of biological reagent functions can be realized.

The invention discloses a low-efficiency land use redevelopment function prediction method based on a graph neural network, and the method comprises the steps: S1, obtaining the land use benefit of each space unit in a learning region, dividing each space unit into a high land use benefit type, a middle land use benefit type and a low land use benefit type, selecting a space unit with a high land utilization benefit type as an urban land use configuration case library; s2, taking the urban land use configuration case library obtained in the step S1 as a sample set, and constructing and training a functional feature learning model based on a graph neural network according to the sample set; and S3, obtaining each space unit in the prediction area, inputting the space units into the functional feature learning model obtained in the step S2, and performing low-efficiency land use redevelopment function prediction. By simulating urban space function interaction and mechanism innovation, a traditional land utilization prediction normal form based on static rules and spatio-temporal evolution is broken through, and scientific support is provided for land benefit improvement and function replacement decision in urban updating.

The invention belongs to the technical field of protein function prediction, and relates to a recognition system for a natural disordered functional region. The system receives a protein sequence, converts the protein sequence into a sequence representation vector based on a protein language model, and outputs the sequence representation vector to a disordered binding region prediction model and a flexible connection region prediction model respectively. The disordered binding region prediction model is composed of a multi-scale feature processing module and a multifunctional classifier, and the disordered binding region and the binding molecule type thereof are speculated by predicting the probability that each residue in the sequence is located in a disordered region and is bound with five types of molecules including protein, nucleic acid and the like. The flexible connection region prediction model is composed of a single feature processing module and a single classifier, and can predict the probability that each residue in the sequence is located in the flexible connection region. The method has the beneficial effects that on a blind test data set provided by the natural disordered protein and the function prediction evaluation platform CAID of the natural disordered protein, the prediction precision is in the front, so that the method can realize accurate prediction of the disordered functional region.

The invention belongs to the crossing field of marine biotechnology and bioinformatics, and particularly relates to a method for high-throughput identification of natural functional oligopeptides. At present, bottlenecks still exist in development and application of various functional oligopeptides such as penetrating peptides and antibacterial peptides in non-model species, and the high adaptability of the existing functional oligopeptides in complex and diverse non-model organisms is limited mainly due to differences (amino acid preference and receptor specificity) among species. Therefore, the invention provides a method for high-throughput identification of functional oligopeptides from natural sequences of organisms by means of machine learning. According to the method, based on a biological natural protein sequence, an oligopeptide sequence set meeting a preset length condition is generated through a sliding window strategy system, a deep machine learning model is utilized to perform high-throughput functional prediction on the oligopeptide sequence, and on the basis of performing'interruption-prediction-re-comparison 'on existing functional oligopeptides, the functional oligopeptide sequence set meeting the preset length condition is obtained. The comparison threshold value for accurately identifying the functional oligopeptide can be determined, and the natural functional oligopeptide existing in the protein sequence can be effectively identified based on the threshold value. The functional oligopeptide obtained by the method has strict screening of physicochemical properties of a machine learning model and high-adaptability biological characteristics formed in species evolution. According to the method, the direct application capability of the functional oligopeptide in non-model species is remarkably improved, and an accurate and high-throughput technical means is provided for efficient development and application of the functional oligopeptide in non-model organisms.

The application discloses a Zanthoxylum bungeanum protein characteristic data-driven modeling method and system for functional expression, belongs to the technical field of food protein data modeling, obtains protein characteristic indexes, functional expression indexes and impurity interference indexes of Zanthoxylum bungeanum protein samples under different processing conditions, forms corresponding data and carries out standardization and abnormal data processing; based on the correlation degree of the protein characteristic indexes, the functional expression indexes and the impurity interference indexes, functional contribution factors and impurity domination factors are determined respectively, and comprehensive weights are generated; the protein characteristic data is weighted by using the comprehensive weights to obtain function-oriented protein characteristic data; then principal component extraction is carried out, and function-oriented principal components are screened according to the correlation between the principal components and the functional expression data and the impurity interference data; finally, a Zanthoxylum bungeanum protein functional expression prediction model is established; the application can weaken the influence of interference information such as pigments, turbidity, residual oil rate and non-protein particles on modeling, and improve the functional prediction stability.

The present invention belongs to the technical field of protein function prediction, and is an identification system for natural disordered functional regions. The system receives a protein sequence, converts it into a sequence representation vector based on a protein language model, and outputs it to the disordered binding region and flexible connection region prediction models respectively. The disordered binding region prediction model consists of a multi-scale feature processing module and a multifunctional classifier. By predicting the probability that each residue in the sequence is located in the disordered region and binds to five types of molecules such as proteins and nucleic acids, the disordered binding region and its binding molecule type are inferred. The flexible connection region prediction model consists of a single feature processing module and a single classifier, which can predict the probability that each residue in the sequence is located in the flexible connection region. The beneficial effects of the present invention: On the blind test data set provided by CAID, a platform for predicting and evaluating natural disordered proteins and their functions, the prediction accuracy ranks among the top, so this method can achieve accurate prediction of disordered functional regions.

The invention discloses a bombyx mori protein function prediction multi-modal fusion method based on a deep residual network, and the method comprises the steps: collecting the sequences and high-resolution three-dimensional structure data of bombyx mori proteins of different varieties and at different development stages from databases of bombyx mori genomes, protein crystal structures and the like by employing a data crawling and interface calling technology; and constructing a multi-modal data source. The sequence data are cleaned and coded in a one-hot mode, and the structural data are optimized and converted into a graph structure. Sequence and structure features are respectively extracted through a convolutional neural network and a GraphSAGE graph neural network, and the features are dynamically fused through an adaptive weight fusion strategy. And building a deep residual network training model, and realizing accurate prediction of the protein function category and confidence of the bombyx mori with unknown functions. According to the method, the precision and the high robustness of silkworm protein function prediction are improved through full-process technical optimization, and an efficient tool is provided for silkworm molecular breeding and functional genomics research.

The invention discloses a microbial data semantic processing method and system based on a graph model, and relates to the technical field of knowledge graph and microbial information processing, and the method comprises the steps: obtaining microbial data from a heterogeneous data source, and carrying out the standardization processing; constructing a domain ontology model conforming to microbial taxonomy specifications; implementing entity disambiguation and unified identifier mapping by utilizing a pre-training language model; a semantic relation triple is extracted in a mode of combining remote supervision and deep learning; constructing a microorganism knowledge attribute graph and storing the graph in a graph database; knowledge reasoning and function prediction are carried out by using a graph attention network; the method supports natural language semantic retrieval, and solves the problems that heterogeneous microorganism data integration is difficult, the naming disambiguation precision is insufficient and the function association mining capacity is limited.

The invention discloses a peptide function prediction method based on artificial intelligence, and belongs to the technical field of biomedical artificial intelligence, and the method comprises the following steps: S1, obtaining a training data set for training an artificial intelligence model; s2, obtaining a prediction model; s3, obtaining a to-be-predicted data set; s4, obtaining a prediction result; and S5, judging the prediction result obtained in the step S4. According to the peptide function prediction method based on artificial intelligence, the peptide chain with the preset function can be efficiently and accurately identified, so that the economic cost of functional peptide screening is remarkably reduced, and the efficiency of the screening process is greatly improved.

This invention provides a method for detecting the TLR10rs11096957 genotype and its application in assessing transplanted liver function. The method includes the following steps: extracting genomic DNA from whole blood of liver transplant patients, adjusting the concentration, and performing PCR amplification; treating the amplified PCR product with SAP and then performing a single-base extension reaction; purifying the single-base extension reaction product, detecting it using time-of-flight mass spectrometry, and performing genotyping. This invention discovers that TLR10rs11096957 can be used to predict the function of transplanted livers in liver transplant patients, thereby guiding clinical treatment to improve transplant survival rates. Therefore, the method for detecting the TLR10rs11096957 genotype provided by this invention can improve the sensitivity of predicting transplanted liver function in liver transplant patients, providing a strategy for preparing corresponding predictive or assessment products, and has significant social and economic benefits.

The application provides a method and system for generating and predicting the function of mRNA untranslated region sequence based on coding sequence. The method comprises: constructing a pre-training data set and a downstream task data set; using the pre-training data set to perform autoregressive training on the constructed conditional generation model to obtain a UTR sequence generation model; using the downstream task data set to fine-tune the UTR sequence generation model to obtain a downstream task function prediction model; generating candidate UTR sequences based on the UTR sequence generation model, and evaluating the generation ability of the UTR sequence generation model in the non-coding region sequence generation task; and predicting the function attribute of the UTR sequence based on the downstream task function prediction model, and evaluating the prediction ability of the downstream task function prediction model in multiple UTR related downstream tasks. The application considers the synergistic relationship between UTR and CDS in the UTR sequence generation process, and improves the efficiency and rationality of UTR sequence design.

The present invention discloses a method for predicting olfactory receptor function based on transfer learning and molecular docking, comprising: obtaining a source domain dataset and a target domain dataset; using a feature extraction module to build a function prediction model by merging feature vectors and inputting them into a fully connected neural network; pre-training the function prediction model using the source domain dataset, and fine-tuning the function prediction model using the target domain dataset to obtain a first-step transfer learning model; determining whether the target species for which the olfactory receptor function is to be predicted is consistent with the species corresponding to the target domain dataset; if so, using the first-step transfer learning model to predict the olfactory receptor function; if not, performing one or more fine-tuning steps on the first-step transfer learning model until a second-step transfer learning model for predicting the olfactory receptor function is obtained. The method of the present invention effectively combines experimental data, molecular simulation, and deep learning technology to achieve rapid and accurate prediction of large-scale olfactory receptor function.

The application provides an RNA sequence classification method based on a Mamba model and semi-supervised learning, and belongs to the field of bioinformatics. First, multi-scale sparse features are extracted from the RNA sequence, high-dimensional features are compressed into low-dimensional potential space vectors through an encoder network, and L2 normalization is performed to enhance feature separability. Second, a Mamba model based on a selective state space model is introduced in a residual structure to efficiently model long-range dependencies with low complexity. Finally, a semi-supervised learning of unsupervised feature reconstruction and supervised classification is realized by constructing an encoder-decoder structure, and a weighted loss function is used to improve the generalization performance of the model under small sample conditions. Experimental results show that the method significantly improves the F1 score in the multi-class RNA sequence classification task. The application reduces the cost of long sequence modeling and labeling, and is suitable for the fields of RNA function prediction, biomedical research and disease diagnosis.

The application relates to a cerebral hemorrhage post-function prediction model establishment method, in particular to a cerebral hemorrhage post-function prediction model establishment method based on a multi-knowledge fusion model. The method is used for predicting various function grades of a cerebral hemorrhage patient after 48 hours of operation. The prediction model establishment method realizes the prediction of the function rehabilitation grade by building a multi-knowledge fusion network model. The method comprises the following steps: data preprocessing, multi-knowledge fusion network model construction, model training and prediction.

The invention discloses an enzyme function prediction method based on three-dimensional point cloud characterization and multi-modal fusion. The method comprises the following steps: extracting point cloud features on the surface of protein by using dMaSIF to characterize geometric and chemical characteristics; the point cloud features are coded through the pre-trained Point Net + +; a decoupling cross attention mechanism is adopted to fuse PointNet + + point cloud coding, Sapot network structure coding and ESM-2 sequence coding, and the network is optimized through comparison learning based on sorting loss. The invention also provides an enzyme function prediction system based on three-dimensional point cloud representation and multi-modal fusion, and the system comprises a point cloud feature extraction module, a point cloud coding module, a multi-modal fusion module and an optimization module, and is used for realizing the method. By integrating the protein three-dimensional structure, sequence and multi-source information of surface physicochemical characteristics, the functional prediction accuracy and robustness are remarkably improved, and the method has excellent performance in enzyme classification (EC number prediction) tasks.

The present application relates to a unified protein modification method, apparatus and computer equipment, which fine-tune the initial protein representation model based on a text-protein pair data set, align the human language large model and the initial protein representation model in the semantic space, and obtain a target protein representation model; input the obtained optimization target into the human language large model to obtain a first representation; based on the obtained key mutation sites, generate a set of protein mutants; input the set of protein mutants into the target protein representation model to obtain a second representation corresponding to each of the protein mutants; based on the second representation matching the first representation, obtain a protein mutant that meets the optimization target, solve the problem of poor generalization of protein function prediction, improve the function prediction performance of unknown proteins and mutants, and achieve efficient protein modification effect.

The present disclosure provides a rational modification method of spermidine synthase (SpeE) in Bacillus subtilis, which relates to the technical fields of enzyme engineering and computational structural biology. The modification method comprises the following steps: constructing a high-confidence three-dimensional model of Bacillus subtilis SpeE, determining the key action scope by double-substrate (S-adenosyl methionine and putrescine) docking, performing virtual saturation mutation on the residues in the region, screening the optimal mutant by combining function prediction, stability analysis, molecular dynamics simulation and binding free energy calculation, and explaining the mutation mechanism from the atomic level. The SpeE mutant (such as G85S, G85A) obtained by the modification method has significantly improved catalytic efficiency and substrate binding affinity, and when applied to a whole-cell catalytic system, it can greatly improve the yield of spermidine, and is suitable for the industrialized green biosynthesis of spermidine.

The invention relates to the field of bioengineering and genetic engineering, and particularly provides a rapid digging method of isomerase genes. According to the method, on the basis of big data analysis and bioinformatics technologies, in combination with means of sequence alignment, gene expression analysis, function prediction and the like, rapid and accurate mining of isomerase genes is achieved, and powerful technical support is provided for development and application of the enzyme engineering field.

The invention relates to the technical field of gene analysis, and discloses an intelligent cancer-related gene analysis method based on weighted voting. According to the method, firstly, different calculation biological tools are used for performing preliminary prediction on a to-be-detected gene, then prediction scores of the multiple calculation biological tools are fused in a non-linear feature construction mode, and finally the prediction scores, confidence coefficients and non-linear extension features of to-be-detected variation points are input into a plurality of pre-trained first-level models. And obtaining output results of the plurality of primary models. And fusing output results of different primary models by adopting a weighted fusion method, and analyzing to obtain a function prediction result corresponding to the to-be-tested gene data based on a final fusion result. Therefore, the to-be-detected gene data can be analyzed more comprehensively, analysis results of different analysis tools and different models are integrated, and finally the reliability of the analysis results is improved on the whole.

The invention relates to a wheat low-phosphorus response transcription factor TaERF112 and application thereof, and belongs to the technical field of plant bioengineering. The low-phosphorus response transcription factor TaERF112 gene is cloned from wheat, the CDS region sequence of the gene is 882bp, 294 amino acids are encoded, the molecular weight is 31 and 572.92 Da, and the gene is hydrophilic protein. By analyzing the TaERF112 gene structure, protein physicochemical properties, subcellular localization and species evolution characteristics, the characteristics and function prediction of the gene are known. Furthermore, a wheat taerf112 mutant is created by using a CRISPR / Cas9 technology, phenotypic characters, biomass and phosphorus utilization characteristics of a transformed strain under different phosphorus conditions are evaluated, and the important effect of the wheat taerf112 mutant in regulation and control of a wheat root system and phosphorus homeostasis is preliminarily revealed. Theoretical basis and gene resources are provided for efficient genetic improvement of wheat phosphorus.

This invention relates to a method for targeted design and optimization of the 5′ untranslated region (UTR) of mRNA based on generative language models and reinforcement learning. The method includes: constructing pre-training data for the 5′ UTR; obtaining a prediction task dataset; calculating the minimum free energy (MFE) corresponding to the pre-training data; constructing a generative language model and performing phased pre-training on the generative language model using the pre-training data and the MFE to obtain a generative model and a prediction task fine-tuning model; fine-tuning the prediction task fine-tuning model based on the prediction task dataset to obtain a functional prediction model; evaluating the generative model's generation capability in the 5′ UTR sequence generation task; and performing targeted optimization design of the 5′ UTR sequence based on a reinforcement learning framework, combining the generative model and the functional prediction model. This invention can efficiently generate 5′ UTR sequences with specific biological functions, providing strong support for functional mRNA design and showing broad application prospects.