17 results about "ESA Protein" patented technology

A target protein drug binding prediction method based on meta learning and subgraph matching, by constructing protein structure, drug small molecule structure and its binding energy value, the meta learning training task is established according to protein grouping, that is, as the main model of the meta model; the sub model and its loss function for the protein prediction task are obtained after fine tuning of the meta model; then the task self-adaptive self-attention model is established to balance the optimization contribution of the sub model of each protein prediction task to the meta model, the weighted average is used for the loss function of the sub model of each protein prediction task to obtain the meta model loss function; then the meta model loss function is used to calculate the gradient, the meta model parameters are updated and optimized based on the preset learning rate, and after the training is completed, the trained meta model is used for fine tuning of the test set of new protein samples, the prediction sub model of the new protein is obtained, the sub model is used for prediction of the protein test set, and the evaluation result is obtained. The training method combining meta learning and subgraph matching can effectively avoid shortcut learning, enhance the generalization effect, and also solve the problem that the previous prediction model is difficult to predict the newly discovered protein.

The application discloses application of a micro cryptosporidium cgd6_660 protein as an oocyst outer wall marker protein, and discloses that the inventors find that the cryptosporidium cgd6_660 protein is an oocyst outer wall protein, and the protein is located on the outer surface of the cryptosporidium oocyst wall. The inventors confirm the feasibility of the protein as a detection antigen. The antibody of the protein recombinant protein (as shown in a sequence table SEQ ID N0.2) can be used for immunological detection of unbroken cryptosporidium oocysts (live cryptosporidium oocysts), and the application further provides a specific polypeptide of the protein.

The present invention relates to a disease-specific biomarker for early prediction and diagnosis of preeclampsia and use thereof, and a composition for prediction or diagnosis of preeclampsia according to an aspect or a method of providing information for prediction or diagnosis thereof, can simply and effectively predict or diagnose the disease by measuring and comparing the mRNA level of a disease-specific protein or a gene encoding the protein changed in a patient.

Methods, compositions, kits, and systems are provided for identifying protein-binding regions in genomic DNA. The method may include contacting genomic DNA with an adenine methyltransferase (A-MTase), wherein the A-MTase methylates adenine residues in a region of the genomic DNA that is not protein-binding; and performing single-molecule long-read sequencing on the contacted genomic DNA to detect locations in the genomic DNA lacking methylated adenine residues, thereby identifying regions in the genomic DNA that are protein-binding. The bound region may be a nucleosome location, and the method can determine the nucleosome location in the genomic DNA. A method is also provided for visualizing chromatin regions that are not protein-binding and spatially serve as substrates for the A-MTase within the cell by visualizing the location of methylated adenine after contacting the cell with the adenine methyltransferase (A-MTase).

Embodiments of the present disclosure provides a method, an electronic device and a storage medium. In the method, a number of residues of a protein structure is obtained, a protein backbone of the protein structure in a first scale is generated, and the protein structure in a second scale is generated based on the number and the protein backbone, where the second scale is larger than the first scale.

An in vitro method for assessing or predicting the response of human patients to treatment of periodontal disease is disclosed. This method is based on insights into identifying biomarker proteins. Therefore, the concentration of a specific combination of proteins is measured in a saliva sample from the patient. One such combination is at least one of interleukin-1-β (IL-1β) and matrix metalloproteinase-8 (MMP-8), and α-1-acid glycoprotein (A1AGP). Based on the measured concentrations, at least one value reflecting the combined concentration of these proteins is determined. This at least one value can indicate the likelihood that the human patient has been or will be successfully treated for periodontitis. This at least one value can be compared to at least one threshold, which in the same manner reflects the combined concentration associated with successful treatment of periodontitis. This comparison allows assessment of whether the test value is an indicator of the patient's periodontal treatment status.

Protein complexes targeting CD47, PD-L1, and / or TIGIT are provided, as well as methods for using the same. In one embodiment, the protein complex comprises a CD47-binding domain having all or part of the SIRPα extracellular domain, a PD-L1-binding domain having all or part of the PD-1 extracellular domain, and a TIGIT ligand-binding domain having all or part of the TIGIT extracellular domain.

Provided is a chemical recycling method for nylon using an enzyme reaction instead of depolymerization. A mutant, which is a protein that is the following (4), (5), or (6) and in which an amino acid corresponding to at least one selected from among D304, R52, D99, and G111 of the sequence of SEQ ID NO: 1 is mutated, is used. (4) is a protein composed of the amino acid sequence of SEQ ID NO: 1. (5) is a protein composed of a sequence obtained by deleting, substituting, or adding 1-35 amino acids in the amino acid sequence of the protein described in (4), and having 6-aminohexanoic acid oligomer endo-type hydrolase (NylC) activity. (6) is a protein composed of a sequence that shares a sequence identity of at least 90% with the protein described in (4), and having NylC activity.

[Problem] To provide a conjugate comprising a protein and a nucleic acid moiety, and an immunodetection method using said conjugate. [Solution] A conjugate comprising a protein and a nucleic acid moiety that includes a first nucleic acid bound to the protein and a second nucleic acid containing a sequence complementary to the first nucleic acid is produced. The first nucleic acid and the second nucleic acid form a complementarily bound double-stranded portion, the second nucleic acid includes a single-stranded overhang portion, and the double-stranded portion includes a photo-crosslink using cnvK that crosslinks the first nucleic acid and the second nucleic acid. The conjugate can be used in the detection of a target substance by isothermal amplification and in nucleic acid medicine and gene therapy drugs.

The application discloses a multi-point protein directed evolution design method based on a graph neural network, and designs protein directed evolution through a trained protein directed evolution model based on a graph neural network, and comprises the following steps: protein data preparation, representing a protein structure as a protein graph, wherein each node in the graph represents an amino acid, and nodes close to each other are connected by edges; and binding amino acid feature data on the nodes or edges of the graph. The protein directed evolution design method is used for guiding a directed evolution task in protein engineering and designing an effective multi-point protein mutation scheme.

The present invention relates to an allele designated alpha-WOLF 31 which confers resistance to at least one Peronospora effusa race, wherein the protein encoded by said allele is a CC-NBS-LRR protein that comprises in its amino acid sequence: a) the motif "MAEIGYSVC" at its N-terminus; and b) the motif "KWMCLR"; and wherein the protein has an amino acid sequence that in order of increased preference has at least 97% sequence similarity to SEQ ID NO: 11. The allele when present in a spinach plant confers complete resistance to at least Peronospora effusa race Pe:1, Pe:2, Pe:4, Pe:5, Pe:6, Pe:7, Pe:10, Pe:12, Pe:13, Pe:14, Pe:15, Pe:16, Pe:18, Pe:19, and Pe:20.

Disclosed is a novel composition and method for treating hemophilia incorporating a gain-of-function human Factor VIII variant in which serine may replace arginine at amino-acid position 590 (R590S). The variant can exhibit reduced sensitivity to activated protein C and / or produces thrombin at rates exceeding those of wild-type Factor VIII while maintaining normal antigen levels. The invention may comprise: (i) an isolated polypeptide comprising the R590S substitution, optionally with B-domain deletion; (ii) a nucleic-acid molecule encoding the variant; and / or (iii) recombinant vectors, including adeno-associated virus constructs, that may express the variant in host cells. The novel composition further may be synthesized by encoding nucleic acid, expressing the variant in mammalian cells, recovering the protein, and / or administering therapeutically effective amounts of the polypeptide and / or vector to restore coagulation.

Training a protein diffusion model includes receiving a representation of a protein as training data, the representation comprising at least three dimensions. It further includes training a protein diffusion model at least in part by performing rotational diffusion based at least in part on the representation of the protein.Generating proteins includes receiving protein conditioning information. It further includes, based at least in part on the protein conditioning information, performing conditional sampling of a protein diffusion model. The protein diffusion model is trained at least in part by performing rotational diffusion. Based at least in part on the conditional sampling of the protein diffusion model, the protein diffusion model generates one or more of a protein structure or a protein sequence.

The present invention relates to a recombinant plasmid comprising a gene encoding a protein toxic to an organism and a gene encoding an ELP linked thereto. By using the recombinant plasmid, it is possible to produce a fusion protein in an organism in which the toxicity of the protein is mitigated due to fusion with the ELP.

A protein structure prediction method is applied to the technical field of artificial intelligence. According to the prediction method of the protein structure, experimental data obtained by detecting the protein structure through various experimental modes are obtained firstly, various experimental data are converted into constraint data of the protein structure in a unified mode, and the constraint data can indicate distance constraint conditions required to be met by residues on the protein structure. Then, the constraint data and the amino acid sequence of the protein are jointly used as input of a neural network model, prediction of the protein structure is executed, and therefore the constraint data obtained by converting different types of experimental data is used for assisting the model to predict the protein structure, and the precision of the protein structure obtained through model prediction is improved. Moreover, according to the scheme, the prediction of the protein structure is realized through the model, manual participation is not needed, and the prediction efficiency of the protein structure can be effectively improved.

Disclosed is a novel composition and method for treating hemophilia incorporating a gain-of-function human Factor VIII variant in which serine may replace arginine at amino-acid position 590 (R590S). The variant can exhibit reduced sensitivity to activated protein C and / or produces thrombin at rates exceeding those of wild-type Factor VIII while maintaining normal antigen levels. The invention may comprise: (i) an isolated polypeptide comprising the R590S substitution, optionally with B-domain deletion; (ii) a nucleic-acid molecule encoding the variant; and / or (iii) recombinant vectors, including adeno-associated virus constructs, that may express the variant in host cells. The novel composition further may be synthesized by encoding nucleic acid, expressing the variant in mammalian cells, recovering the protein, and / or administering therapeutically effective amounts of the polypeptide and / or vector to restore coagulation.

The present disclosure proposes a protein language model processing device that generates a chimeric protein language model on the basis of an existing protein language model in order to efficiently and highly accurately achieve the fine tuning of a protein language model. The protein language model processing device executes: processing for referring to a given natural protein database and generating, with respect to known sequence data representing known chimeric proteins, an extended sequence data group which represents a plurality of closely-related proteins that share homology equal to or higher than a predetermined threshold value with each other; and processing for generating a chimeric protein language model by re-training an existing protein language model by using the extended sequence data group as training data (see FIG. 1).