10 results about "Test protein" patented technology

The invention provides a method for training an aptamer generation model and a method for generating an aptamer, and the method comprises the steps: inputting the sequence features and structural features of a training protein nucleic acid pair into an initial generation model, and generating a training prediction nucleic acid based on the initial generation model; calculating generation loss based on the training predicted nucleic acid, and performing parameter correction on the initial generation model based on the generation loss to obtain a to-be-optimized generation model; and carrying out adversarial training on the basis of the to-be-optimized generation model, the test protein nucleic acid pair and the combined nucleic acid discrimination model, and optimizing to obtain the nucleic acid aptamer generation model. According to the method provided by the invention, the generative adversarial training is carried out on the to-be-optimized generation model through the nucleic acid discrimination model to optimize the model parameters of the to-be-optimized generation model so as to obtain the final nucleic acid aptamer generation model, so that the ability of the nucleic acid aptamer generation model to generate the nucleic acid aptamer interacting with protein is ensured; and the generation of the nucleic acid aptamer with higher efficiency, higher accuracy and higher affinity is realized.

The present invention relates to a method of screening for peptides capable of binding to a ubiquitin protein ligase (E3), successful binding being determined by detecting the amount of a test protein in the cell. The invention relates to a method for determining if a peptide binds or is capable of binding to a ubiquitin protein ligase (E3) and thereby leads to degradation of a test protein, wherein the peptide is between about 7 and 110 amino acids in length, the method comprising: providing in a eukaryotic cell a candidate peptide functionally linked to a test protein, under conditions enabling ubiquitination of proteins by an E3; and detecting the amount of test protein present in the cell; whereby, a reduced amount of the test protein determines the candidate peptide as a peptide that binds or is capable of binding to an E3 (an E3-binding peptide).

The present disclosure relates to a higher throughput, medium scale, semi-automated protein expression and screening platform useful, for example, in drug discovery studies and in addition for testing protein expression conditions, among other uses. In some embodiments, the workflows described herein also enable a comprehensive expression and purification screening assessment of challenging or difficult-to-express recombinant proteins in a faster and efficient manner by delivering small but sufficient amounts of high quality proteins.

The present application relates to a protein drug reaction prediction method based on EM fusion learning, comprising: 1) constructing a data set containing protein nodes, drug nodes and intermediate nodes into a text attribute graph; 2) embedding the protein amino acid sequence and the drug molecule SMILES sequence to obtain corresponding sequence representations; 3) constructing a transformer-based protein-drug reaction prediction model; 4) constructing a GNN-based protein-drug reaction prediction model; 5) using a variational EM framework to alternately update the above two models to obtain an EM fusion protein-drug reaction prediction model; 6) inputting the to-be-tested protein amino acid sequence and the to-be-tested drug SMILES sequence into the above prediction model to output the reaction prediction result of the to-be-tested protein-drug pair. The present application learns the topological information in the protein-drug network to realize protein-drug reaction prediction.

This application provides a protein stability detection probe based on ascorbate peroxidase 2 and its application. The detection probe includes ascorbate peroxidase 2 displayed on the cell surface and an anchoring protein that anchors ascorbate peroxidase 2 to the cell. Ascorbate peroxidase 2 has an insertion site for the target protein, into which the target protein inserts. Ascorbate peroxidase 2 is divided into N-terminal and C-terminal ascorbate peroxidase 2, and the target protein is linked to both ends of the C-terminal ascorbate peroxidase 2 via flexible linkers. The intensity of the fluorescence signal generated by the cascade reaction catalyzed by the probe in this application has a good linear relationship with the stability of the inserted test protein mutant, enabling high-throughput identification of protein mutant stability and showing promising application prospects.

A method for determining or verifying the identity of a protein based on a melting curve obtained from a nano-differential scanning fluorimeter (nanoDSF). The method uses a machine learning model trained on a set of proteins of known identity and includes acquiring, through use of nanoDSF, a set of data points representative of a thermal denaturation curve (melting curve) of a test protein, generating a set of features derived from the melting curve, and providing the set of features as inputs to the trained machine learning model to obtain a corresponding output indicative of an identity of the test protein. Methods for training the machine learning model are provided, as well as systems including processor-executable instructions that, when executed by a processor, cause the system to perform the method for determining or verifying protein identity.

The present disclosure relates to a higher-throughput, mid-scale, semi-automated protein expression and screening platform that can be used, for instance, for drug discovery research and otherwise for testing protein expression conditions, among other uses. The workflow described here also in some embodiments enables comprehensive expression and purification screening assessment of challenging or difficult-to-express recombinant proteins in a faster and efficient manner by delivering small but sufficient amounts of high-quality proteins.

The application discloses a protein phase separation prediction method and system based on a physical information neural network, an electronic device and a storage medium, and relates to the technical field of bioinformatics. The method comprises the following steps: obtaining an amino acid sequence of a to-be-tested protein, and extracting multi-dimensional physicochemical features of the amino acid sequence to construct a feature vector; inputting the feature vector into a pre-trained physical information neural network; the physical information neural network comprises a shared hidden layer, a first output branch and a second output branch which are connected with the shared hidden layer respectively; a prediction probability of phase separation of the to-be-tested protein is output through the first output branch, and a continuous scalar value is output as a thermodynamic score through the second output branch; and a phase separation prediction result of the to-be-tested protein is output according to the prediction probability. The method can effectively overcome the excessive dependence of a traditional sequence prediction model on intrinsic disorder degree, reduce the prediction false positive rate, and improve the interpretability of the result through physical mechanism constraint.

The application provides a kit for identifying pig Y sperm and application thereof. Specifically, the kit takes pig membrane protein PPP4C or pig membrane protein CSNK2A2 as a molecular marker, tests protein expression amount by Western blotting or immunofluorescence, and identifies pig X and Y sperm according to the difference of the protein expression amount, and the specific identification standard is that the expression of pig membrane protein PPP4C or pig membrane protein CSNK2A2 in Y sperm is higher than that in X sperm. The application provides an effective scheme for realizing the identification of pig X and Y sperm by immunization, realizes the identification of pig X and Y sperm with low cost, high efficiency and simplicity, helps the sustainable development of animal husbandry, improves economic benefits, helps to alleviate the future food shortage problem, solves a series of animal welfare problems, and has important application value.

The present invention generally relates to a high-throughput system and method for concurrent measurements of a plurality of protein reactions. In embodiments, the high-throughput system is advantageously designed and configured to efficiently test the interactions between a set of proteins and chemical compounds. For example, by utilizing mass spectrometry and intelligent sample pooling strategies, the system generates a massive and diverse dataset of protein-compound interactions while minimizing resource usage. Advantageously, the system is capable of obtaining interaction data on a wide variety of different protein classes and is particularly suited for generating comprehensive bioactivity data for use in downstream applications such as machine learning model training for drug discovery and protein function prediction.