COMPUTER-ASSISTED METHOD AND SYSTEM FOR EVALUATING AND MODIFYING IMMUNOGENICITY OF PROTEIN SEQUENCES USING A PROTEIN LARGE LANGUAGE MODEL
The embodiment discloses a computer-assisted method for evaluating and modifying immunogenicity, as well as related computer systems and storage media. The method includes using unsupervised learning of a protein large language model on all human sequences and a supervised deep learning neural networks to establish a predictive scoring model for the humanness score of peptide chains based on the data from the model training dataset to achieve classification between human and non-human species. This involves cutting protein sequences into all possible peptide chains of a preset length using a dynamic window method and importing these chains into the predictive scoring, thereby evaluating their immunogenicity in terms of humanness score. Peptide chains with scores above a certain threshold undergo all possible single-point virtual mutations to generate a set of modified peptide chains which are then reassessed using the model, selecting those with scores above the threshold of humanness for further consideration.
1 . A computer-assisted method for evaluating immunogenicity of protein sequences using a protein large language model, characterized by:
establishing a predictive scoring model for the humanness score of protein sequences using a deep learning neural network, including a protein large language model, based on data from a model training dataset comprising various human and non-human species protein sequence information.
obtaining protein sequences and processing them into peptide chains of a preset length using a dynamic window method.
importing these peptide chains into the protein large language model for scoring each chain's humanness score, thereby evaluating their immunogenicity.
2 . The method according to claim 1 , further characterized by:
storing peptide chains whose humanness score, as determined by the protein large language model, are smaller than or equal to a first preset threshold; and/or
marking cutting sites on the protein sequence where the humanness scores are smaller than or equal to a first preset threshold.
3 . The method according to claim 1 , wherein obtaining protein sequences includes translating protein sequences into FASTA format files and importing these files into the protein large language model through tokenization.
4 . The method according to claim 1 , where the data of the model training dataset is processed through the protein large language model.
5 . The method according to claim 1 , wherein the protein large language model is part of a unsupervised deep learning model, which is integrated with a combination of supervised learning models including CNN, RNN, GNN, VAE and Transformer models, all tailored for analyzing protein sequences.
6 . A computer-assisted method for modifying immunogenicity of protein sequences using a protein large language model, characterized by:
implementing the method for evaluating immunogenicity as described in claims 1 to 5 ;
identifying, via the protein large language model that includes CNN, RNN, GNN, VAE and Transformer models, peptide chains whose humanness scores are smaller than or equal to a second preset threshold;
performing all possible single-point virtual mutations on these identified peptide chains to generate a set of modified peptide chains;
scoring the humanness score of each modified peptide chain using the protein large language model that includes CNN, RNN, GNN, VAE and Transformer models; and
selecting modified peptide chains whose humanness scores are more than the second preset threshold.
7 . A computer system for evaluating and/or modifying immunogenicity of protein sequences, characterized by including a processor and a memory connected to the processor, wherein the memory stores a program executable by the processor to implement the method for evaluating and/or modifying immunogenicity using a protein large language model, as described in any one of claims 1 to 6 , wherein the protein large language model followed by a combination of CNN, RNN, GNN, VAE and Transformer models for comprehensive protein sequence analysis.
8 . A computer-readable storage medium, characterized by storing a computer program, which, when executed by a processor, implements the method for evaluating and/or modifying immunogenicity of protein sequences using a protein large language model, according to any one of claims 1 to 6 , wherein the protein large language model includes CNN, RNN, GNN, VAE and Transformer models as part of its deep learning architecture.