32 results about "Anticancer peptide" patented technology

The invention relates to an anticancer peptide prediction method and system based on feature fusion and a cross attention mechanism. The method comprises the following steps: constructing a data set containing each protein sequence; inputting the protein sequence into a protein language model ESM-2 to extract peptide structure features; inputting the protein sequence into a feature extraction model to extract peptide physical and chemical features; carrying out dimension transformation processing on the peptide structural characteristics, and carrying out serialization on discrete peptide physical and chemical characteristics by using BiLSTM (Bidirectional Long Short Term Memory); and carrying out feature fusion by using a cross attention mechanism to obtain a target feature, inputting the target feature into a multi-layer perceptron (MLP), and obtaining an anticancer peptide prediction result. According to the method, peptide structural features are extracted by using a protein language model, peptide physical and chemical features are extracted by using a traditional feature extraction model, feature fusion is performed by using a cross attention mechanism, time consumption is not needed, high cost is provided, the extracted features are correlated, and anticancer peptide prediction can be performed quickly, efficiently and accurately.

The invention relates to an anticancer peptide prediction method and system based on a protein language model. The method comprises the following steps: collecting and screening out anti-cancer peptide samples and non-anti-cancer peptide samples to construct a data set; inputting the data set into a protein language model for feature processing, and extracting high-dimensional biological features in the sample sequence; performing convolution operation on the high-dimensional biological characteristics by using a convolutional neural network through a protein language model, dynamically adjusting the weight of the high-dimensional biological characteristics through a self-attention mechanism, and capturing global characteristics in the peptide sequence; and performing anticancer peptide prediction through a full connection layer in the protein language model to obtain a prediction result. According to the method, feature processing is performed through the protein language model, global features are captured based on the convolutional neural network and the self-attention mechanism, complex feature engineering steps are not needed, and key information in a peptide sequence can be fully excavated, so that the anticancer peptide prediction performance of the model is improved, and the anticancer peptide can be rapidly predicted with low cost and high accuracy.

The present invention is applicable to the field of peptide recognition technology and provides an anticancer peptide recognition method and system. The recognition method includes the following steps: inputting a given peptide sequence, performing data enhancement on the peptide sequence to obtain an original sequence; the first channel uses Bi-LSTM to extract features from the original sequence; the second channel converts the original sequence into a chemical formula, and uses SMILES to simplify the chemical formula, and inputs the sequence represented by SMILES into a pre-trained BERT model to obtain deep abstract features; the third channel fuses four features, BPF, DPC, PAAC, and K-mer, to jointly extract features at different levels of the original sequence; splicing the features extracted by the three channels, and classifying the input peptide sequence through a fully connected layer. The ACP-BC model in the present invention has strong robustness and versatility, and has great potential in predicting ACP and non-ACP.

The present invention constructs a method and system for identifying anticancer peptides based on an attention mechanism and multi-granularity hierarchical features. This method is of great significance in the field of anticancer peptide identification technology. First, atomic-level features are learned through transfer learning, revealing potential features that were difficult to discover in previous work. Secondly, the ChouFasman algorithm is used to represent the secondary structure in the amino acid sequence layer extraction process, which increases the richness of information. Next, the problem that the existing technology cannot capture the high-order structural similarity of anticancer peptide sequences is solved by constructing a hypergraph, and the importance of subsequences to the overall sequence is learned through the attention mechanism. Finally, the multi-granularity hierarchical features are fused, so that the model can fully understand and describe the characteristics of the anticancer peptide sequence. This invention provides a more accurate and comprehensive analysis tool for the discovery and design of anticancer peptides, and can contribute to the development of anticancer drugs.

The invention discloses an anti-cancer peptide JZTX-66 sourced from chilobrachys guangxiensis and application thereof, and belongs to the field of biological medicine, the novel natural anti-cancer peptide JZTX-66 is separated from spider venom by taking the chilobrachys guangxiensis as a material, the novel natural anti-cancer peptide JZTX-66 has 66 amino acid residues, is alkaline polypeptide containing a plurality of positively charged amino acid residues, has an isoelectric point of 9.15, and has a molecular weight of 90000-90000. 8 cysteine residues are contained, 4 pairs of disulfide bonds are formed, and the C-terminal is amidated and modified. And the molecular weight of the polypeptide is 6766.1643 Da. The natural anti-cancer peptide JZTX-66 disclosed by the invention has relatively strong cytotoxic activity on a mouse melanoma cell line B16-F10, and the half inhibitory concentration IC50 of the natural anti-cancer peptide JZTX-66 is 2.06 mu M. The natural anti-cancer peptide JZTX-66 disclosed by the invention is a natural anti-cancer peptide. Researches find that cell death is caused by high-concentration induction of cell apoptosis or direct destruction of cell membranes; and proliferation, migration and invasion of B16-F10 cells are inhibited at low concentration. The cytotoxic activity of JZTX-66 can be inhibited by metal cations such as Ca < 2 + > and the like, and can be reversed by EDTA (Ethylene Diamine Tetraacetic Acid). The invention provides a novel anti-cancer peptide, a high-quality lead molecule is provided for research and development of innovative anti-cancer polypeptide drugs, and a potential drug is provided for treatment of cancers.

The invention discloses a polypeptide function prediction method based on machine learning. The method comprises the following steps: collecting data information of wound healing peptides, hypoglycemic peptides, antioxidant peptides and anticancer peptides, analyzing different characterization data of polypeptide sequences by utilizing biological new informatics software, constructing a polypeptide characterization database, and dividing training, verification and test data sets; important features for determining polypeptide function classification are obtained through data preprocessing and feature screening; based on the important feature data, performing model construction on the data by using different machine learning algorithms to obtain an algorithm with the best performance for model optimization; and further performing performance verification on the optimization model on the verification set and the test set. The invention constructs a polypeptide function prediction tool based on a C50 algorithm, and the function of the position function polypeptide can be efficiently and accurately evaluated.

The invention relates to preparation of an anti-cancer peptide inhibitor GLP2 with good biocompatibility, stability and excellent anti-cancer activity and application of the anti-cancer peptide inhibitor GLP2 in tumor treatment, and belongs to the field of medicine. The amino acid sequence of the anticancer peptide inhibitor GLP2 is C12H23O-Tyr-Cys-Pro-Tyr-Lys-Ser-Arg-Tyr-Lys-Lys-Pro-Arg-Arg-Pro-Val-Arg-Asn-Tyr-C6H12NO5, the anticancer peptide inhibitor GLP2 is designed on the basis of several important biological characteristics (net positive charge, amphipathy and a PPII spiral structure) of an anticancer peptide, and fatty acid C12H24O2 and monosaccharide C6H13NO5 are coupled to the N end and the C end of the anticancer peptide inhibitor GLP2 respectively. The invention provides a technical scheme for solid-phase synthesis of an anticancer peptide inhibitor skeleton. The GLP2 has excellent in-vitro anticancer activity, good pancreatin stability and biocompatibility. In-vivo anti-cancer experiments show that the designed anti-cancer peptide inhibitor can play an excellent anti-cancer role in a mouse tumor model and is a potential anti-cancer inhibitor with a good application prospect.

An anticancer peptide comprehensive prediction and screening method based on multi-modal deep learning relates to the technical field of anticancer peptide screening, and obtains a to-be-detected sequence set, and inputs the to-be-detected sequence set into a pre-constructed multi-modal deep learning framework, the multi-modal deep learning framework comprises a dichotomy model, a multi-label classification model and an active regression model, selecting one of the models or sequentially combined three models to process a to-be-detected sequence set, obtaining a plurality of second activity values when the to-be-detected sequence set is sequentially processed by the dichotomy model, the multi-label classification model and the activity regression model, and obtaining candidate anti-cancer peptides according to the second activity values, the method has the advantages of high accuracy, strong generalization and good interpretability, and the calculation and screening efficiency of the candidate anticancer peptide can be obviously improved.

To provide a novel anticancer agent having improved selectivity for cancer cells so as not to damage healthy tissues.SOLUTION: A peptide having a sequence comprising the motif GLLxLLxLLLxAAG, wherein x is independently selected from arginine (R), histidine (H), lysine (K), aspartic acid (D), or glutamic acid (E); a pharmaceutically acceptable composition comprising the peptide; a kit comprising the composition; nucleotides encoding the peptide; and vectors expressing the peptide.SELECTED DRAWING: None

The first aspect of the present application provides an anticancer peptide classification method based on a graph convolution network, comprising: S1, obtaining an anticancer peptide training data set and a test data set; S2, constructing an anticancer peptide sequence into a graph structure network with amino acid nodes as vertices and encoding to obtain graph structure data; S3, constructing a graph convolution collapse pooling and residual network model, inputting the graph structure data into the model for training; and S4, applying the trained model to classify anticancer peptides. Wherein the graph convolution collapse pooling and residual network model comprises a stacked graph convolution network module, a graph collapse pooling module and a residual network module. The above scheme regards the anticancer peptide data as a kind of data similar to the graph structure, uses the graph convolution neural network to process the classification problem of the anticancer peptide, effectively distinguishes the anticancer peptide and the non-anticancer peptide, and avoids the problems of low recognition accuracy, insufficient generalization ability, lack of large-scale evaluation of features and prediction model of the existing model.

Embodiments of the current invention provide a solution to the problems associated with balancing patient toxicity with broad efficacy of cancer therapy. In particular, embodiments are directed to anti-cancer peptides that demonstrate a broad anti-cancer efficacy with a limited toxicity to normal or non-cancer cells.

The application discloses an anticancer peptide generation and screening method and system based on a diffusion model and a seed synchronous autoencoder, and comprises the following steps: preprocessing original anticancer peptide and non-anticancer peptide sequences and extracting multi-dimensional physicochemical features; training a diffusion model in a continuous numerical space based on sequence mapping based on a global random seed, adding noise through forward diffusion and learning the potential distribution of anticancer peptide data features through reverse denoising; based on a reverse seed synchronization strategy, training an autoencoder using the same random seed and environment state, and establishing a mapping from continuous random noise to discrete biological sequences; using the diffusion model to sample and generate potential vectors in the latent space and mapping them into candidate anticancer peptide sequences through the decoded synchronously trained decoder; inputting an integrated learning classifier based on grouping features, selecting the optimal feature group and predicting the anticancer activity probability, and outputting the anticancer characteristic peptide chain; the application solves the mapping contradiction between continuous space and discrete sequences and can efficiently screen anticancer peptides with high activity sequences.

The application relates to an anticancer peptide prediction method and system based on feature fusion and cross attention mechanism. The method comprises the following steps: constructing a data set containing various protein sequences; inputting the protein sequence into a protein language model ESM-2 to extract peptide structure features; inputting the protein sequence into a feature extraction model to extract peptide physical and chemical features; performing dimension transformation processing on the peptide structure features, using BiLSTM to continuously process discrete peptide physical and chemical features; using a cross attention mechanism for feature fusion to obtain target features input into a multilayer perception machine (MLP) to obtain an anticancer peptide prediction result. By using a protein language model to extract peptide structure features, using a traditional feature extraction model to extract peptide physical and chemical features, and using a cross attention mechanism for feature fusion, time-consuming and high cost can be avoided, and the extracted features are related to each other, so that anticancer peptide prediction can be quickly, efficiently and accurately performed.

The present disclosure is based on the development of improved clinical protocols for administering an anti-cancer peptide having the sequence of SEQ ID NO: 1, or a pharmaceutically acceptable salt thereof ("Peptide A"), to a subject (e.g., for the treatment of a skin cancer, such as basal cell carcinoma (BCC)). Methods provided herein allow for the safe and effective treatment of skin cancers, including BCC, in a minimally invasive manner. In certain embodiments, methods provided herein allow for administration of Peptide A to a skin cancer lesion (e.g., BCC lesion) on a subject with no significant treatment-related adverse events (TRAEs), e.g, TRAEs such as burning and / or pain at the injection site.

The invention relates to an intelligent anti-cancer peptide recognition method based on a Transform deep learning framework. The problems that in the prior art, an anti-cancer peptide screening method is serious in feature redundancy, poor in model interpretability and prone to over-fitting are solved. The method comprises the following steps: S1, data preprocessing: obtaining a sequence and carrying out data set division; s2, feature extraction: automatically extracting a plurality of sequence features; s3, feature screening: carrying out importance evaluation on the extracted features; s4, model construction: designing a deep learning classifier and constructing a traditional machine learning and classical deep learning architecture for comparison; and S5, performance evaluation and optimization: performing parameter optimization on each model in the training set by adopting five-fold cross validation, and finally evaluating the performance on the independent test set. The method has the advantages that the accuracy and the stability of anticancer peptide prediction are remarkably improved, redundant features are effectively removed, the model complexity is reduced, the calculation efficiency is improved, the reliability of a prediction result is ensured, and the labor cost and the time cost are greatly reduced.

The invention provides an antibacterial peptide de novo design method and system based on a spectrum structure-activity relationship. The method comprises the following steps: obtaining structures, sequences and simulated spectrum data of functional peptides including antibacterial peptides, anti-cancer peptides, anti-inflammatory peptides and the like; constructing a spectral diffusion generation model, and generating spectral data corresponding to the target function; mapping the spectrum into a CA atomic distance matrix through a neural network model, and generating an initial three-dimensional structure in combination with PyRosetta; optimizing the initial structure by using an RFdiffusion model to obtain a high-resolution full-atomic structure; inputting the optimized structure into a retrained ProteinMPNN model, and generating a candidate polypeptide sequence in combination with a function guidance strategy; and finally, performing function screening and structure verification on the sequence by using a deep learning model. The technical problems that an existing antibacterial peptide design method neglects peptide three-dimensional structure information and lacks an optimal design strategy for multiple functions such as antibiosis, anticancer and anti-inflammation, so that design flexibility and functional diversity are low are solved.

The application discloses a kind of anti-cancer peptide generation model training methods, comprising: obtaining general polypeptide sequence data, anti-cancer peptide sequence data and non-anti-cancer peptide sequence data, and according to amino acid glossary general polypeptide sequence data, anti-cancer peptide sequence data and non-anti-cancer peptide sequence data are digitally encoded, to obtain general polypeptide sequence data set, anti-cancer peptide sequence data set and non-anti-cancer peptide sequence data set, general polypeptide sequence data set, anti-cancer peptide sequence data set and non-anti-cancer peptide sequence data set are respectively divided according to training set and test set 8:2 ratio, to obtain general polypeptide sequence training set and test set, anti-cancer peptide sequence training set and test set and non-anti-cancer peptide sequence training set and test set, general polypeptide sequence training set is input into the generation module of anti-cancer peptide generation model, and the weight parameter and bias parameter of each layer in generation module are updated and optimized using back propagation algorithm, to obtain pre-trained generation module.

The present invention relates to a method and system for predicting anticancer peptides based on a protein language model. The method comprises: collecting and screening anticancer peptide samples and non-anticancer peptide samples to construct a data set; inputting the data set into a protein language model for feature processing to extract high-dimensional biological features from the sample sequence; performing convolution operations on the high-dimensional biological features using a convolutional neural network through the protein language model, and dynamically adjusting the weights of the high-dimensional biological features through a self-attention mechanism to capture global features in the peptide sequence; and predicting anticancer peptides through a fully connected layer in the protein language model to obtain prediction results. By performing feature processing through a protein language model and capturing global features based on a convolutional neural network and a self-attention mechanism, the method eliminates the need for complex feature engineering steps, fully exploits key information in the peptide sequence, and thereby improves the model's anticancer peptide prediction performance. Anticancer peptides can be predicted quickly, at low cost, and with high accuracy.

The invention discloses a therapeutic polypeptide generation method and system based on function prompt in the technical field of artificial intelligence assisted biological medicine. According to the therapeutic polypeptide generation method based on the function prompt, biological association between antibacterial peptides and anti-cancer peptides is utilized, a function prompt tag hard tag is introduced to carry out prompt type fine tuning on a ProGen2 protein language model, an AMP and ACP combined task fine tuning scheme is adopted, controlled generation of functional peptides is achieved, and the therapeutic polypeptide generation method based on the function prompt has the advantages of being simple in structure, convenient to operate and high in practicability. The problem that the capacity of an existing protein language model for generating the peptide with the specific biological function is limited is solved, data sets are integrated for unified training, the modeling process is simplified, cross-task knowledge transfer is promoted, and the generated peptide sequence has high diversity, sequence stability and function correlation.