35 results about "Functional prediction" patented technology

Predicting software product quality. Real-time and historic software code metrics, software code defect data for the software product, and test case-related data for the software product are received. A feature predicted fallibility that estimates the number of code defects for a new feature of the software product, a product version projected fallibility that estimates the number of code defects for a new version of a software product, a test case related quality coefficient that estimates the likelihood of discovery of code defects in a new feature, a feature quality and a product quality indexes that are qualitative indications of quality of the new code of a feature and the new product version, are calculated. A report is then output that includes at least the calculated values, whereby developer resources are directed to features of the software product for which the calculated values indicate likelihoods of a high defect densities.

A data processing apparatus includes an input unit that receives input data, a calculating unit that calculates a feature vector, a selection receiving unit that presents processing options to a user and receives a user selection, a storing unit stores processing history information, and a predictor constructing unit that constructs a predictor for an identifying algorithm that predicts optimal processing for input data based on processing history information stored in a history database. An optimal function predicting unit predicts optimal processing based on a feature vector calculated for new data by using the predictor and an evaluating unit evaluates work efficiency for the predicted optimal processing, wherein the evaluating unit is configured to evaluate work efficiency for the optimal processing based on a prediction accuracy of the predictor and a user specific working time that is required for each user to select one of the processing options with the selection receiving unit. Finally, a presenting unit presents the optimal processing to a user when an evaluation result obtained by the evaluating unit is equal to or greater than a threshold.

A method for predicting gene function based on R-SVM and TPR rules relates to a method for predicting gene function. The invention can realize the prediction of the gene function, and can solve the multi-label problem and the hierarchical constraint problem existing when the classification algorithm is used to realize the prediction of the gene function. The present invention firstly uses genes with known functions as training samples to form a training set; for each node in the GO annotation scheme, a positive sample set and a negative sample set are constructed; for each node in the GO annotation scheme, select the node The attribute that contributes a lot to the classification of the function; through training, a set of R-SVM classifiers is obtained and the unknown samples are classified and predicted, and a set of preliminary R-SVM classification results are obtained; the classification results are converted into posterior probability values, using A weighted TPR ensemble algorithm for directed acyclic graph hierarchy to realize gene function prediction. The invention is applicable to the prediction of gene function.

The present invention is a method for predicting the functional impact of cancer somatic mutation. The invention constructs a comprehensive mutation feature set, integrates the mutation frequencies of different populations together; performs conservative estimation based on the mutation sites of multiple species, and estimates the probability that these mutations are harmful mutations; and constructs mutation network features based on the interaction of gene products. , complete the construction of mutation network features; build a deep random forest prediction model based on multiple sampling and hierarchical structure, and make functional predictions for cancer somatic mutations.

The embodiment of the present application discloses a method and device for protein feature extraction, function model generation, and function prediction; the protein feature extraction method includes: obtaining the amino acid sequence of the target protein and the residue interaction site on the amino acid sequence of the target protein, Obtain the target amino acid sequence and target residue interaction site; intercept an amino acid abbreviation code or multiple consecutive amino acid abbreviation codes from the target amino acid sequence to obtain a target string including the target residue interaction site; extract the target string in the target The text features in the amino acid sequence, using the feature of the residue interaction site on the amino acid sequence as the expression of protein function, can provide high-quality feature input for the subsequent use of machine learning algorithms for protein function prediction, which is conducive to abandoning time-consuming The powerful manual prediction method improves the efficiency and accuracy of protein function prediction.

The present invention is applicable to the technical field of biological information, and provides a protein function prediction method, device, equipment, and storage medium. The method includes: obtaining a protein sequence to be predicted, dividing the protein sequence, obtaining corresponding amino acid fragments, and training Query the word vectors corresponding to the amino acid fragments in a good dictionary, generate the eigenvalues ​​of the protein sequence based on these word vectors, predict the function of the protein sequence according to the eigenvalues ​​of the protein sequence and the trained machine learning model, and generate and output the eigenvalues ​​of the protein sequence Therefore, by obtaining the eigenvalues ​​of protein sequences with context characteristics and performing machine learning on these eigenvalues, the accuracy and efficiency of protein function prediction are effectively improved, and the effect of protein function prediction is improved.

The invention discloses a gene BI-1 of cell withering inhibition factors for regulating and controlling symbiotic nodulation of leguminous plants, and provides application of the gene in regulating and controlling number of root nodules of leguminous plant. A nucleotide sequence of the gene is shown in SEQ ID NO:1 in a sequence list. The gene has the advantages that a yeast two-hybrid technique isutilized to screen in a soybean root nodule AD-cDNA library, a kind of new protein which interacts with receptor protein of nodulation factor is found, and the gene is proofed to be a cell apoptosisinhibition factor gene through methods of sequence comparison, function prediction and the like; an over-expression technique is utilized to study the function of the gene in the symbiotic nodulationprocess of crowtoe of the leguminous plant; proofed by results, the protein encoded by the gene participates in the symbiotic nodulation process, the number of the root nodules is obviously increasedafter over-expression, and the application prospect on the symbiotic nitrogen immobilizing of the leguminous plant is realized.

The present invention relates to the discovery of a method for identifying a treatment regimen for a patient diagnosed with cancer, predicting patient resistance to therapeutic agents and identifying new therapeutic agents. Specifically, the present invention relates to the use of an algorithm to identify a mutation in a kinase, determine if the mutation is an activation or resistance mutation and then to suggest an appropriate therapeutic regimen. The invention also relates to the use of a pattern matching algorithm and a crystal structure library to predict the functionality of a gene mutation, predict the specificity of small molecule kinase inhibitors and for the identification of new therapeutic agents.