Dea Gogishvili, Emmanuel Minois-Genin, Jan van Eck, Sanne Abeln
{"title":"PatchProt:利用蛋白质基础模型预测疏水斑块。","authors":"Dea Gogishvili, Emmanuel Minois-Genin, Jan van Eck, Sanne Abeln","doi":"10.1093/bioadv/vbae154","DOIUrl":null,"url":null,"abstract":"<p><strong>Motivation: </strong>Hydrophobic patches on protein surfaces play important functional roles in protein-protein and protein-ligand interactions. Large hydrophobic surfaces are also involved in the progression of aggregation diseases. Predicting exposed hydrophobic patches from a protein sequence has shown to be a difficult task. Fine-tuning foundation models allows for adapting a model to the specific nuances of a new task using a much smaller dataset. Additionally, multitask deep learning offers a promising solution for addressing data gaps, simultaneously outperforming single-task methods.</p><p><strong>Results: </strong>In this study, we harnessed a recently released leading large language model Evolutionary Scale Models (ESM-2). Efficient fine-tuning of ESM-2 was achieved by leveraging a recently developed parameter-efficient fine-tuning method. This approach enabled comprehensive training of model layers without excessive parameters and without the need to include a computationally expensive multiple sequence analysis. We explored several related tasks, at local (residue) and global (protein) levels, to improve the representation of the model. As a result, our model, PatchProt, cannot only predict hydrophobic patch areas but also outperforms existing methods at predicting primary tasks, including secondary structure and surface accessibility predictions. Importantly, our analysis shows that including related local tasks can improve predictions on more difficult global tasks. This research sets a new standard for sequence-based protein property prediction and highlights the remarkable potential of fine-tuning foundation models enriching the model representation by training over related tasks.</p><p><strong>Availability and implementation: </strong>https://github.com/Deagogishvili/chapter-multi-task.</p>","PeriodicalId":72368,"journal":{"name":"Bioinformatics advances","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2024-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525051/pdf/","citationCount":"0","resultStr":"{\"title\":\"PatchProt: hydrophobic patch prediction using protein foundation models.\",\"authors\":\"Dea Gogishvili, Emmanuel Minois-Genin, Jan van Eck, Sanne Abeln\",\"doi\":\"10.1093/bioadv/vbae154\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Motivation: </strong>Hydrophobic patches on protein surfaces play important functional roles in protein-protein and protein-ligand interactions. Large hydrophobic surfaces are also involved in the progression of aggregation diseases. Predicting exposed hydrophobic patches from a protein sequence has shown to be a difficult task. Fine-tuning foundation models allows for adapting a model to the specific nuances of a new task using a much smaller dataset. Additionally, multitask deep learning offers a promising solution for addressing data gaps, simultaneously outperforming single-task methods.</p><p><strong>Results: </strong>In this study, we harnessed a recently released leading large language model Evolutionary Scale Models (ESM-2). Efficient fine-tuning of ESM-2 was achieved by leveraging a recently developed parameter-efficient fine-tuning method. This approach enabled comprehensive training of model layers without excessive parameters and without the need to include a computationally expensive multiple sequence analysis. We explored several related tasks, at local (residue) and global (protein) levels, to improve the representation of the model. As a result, our model, PatchProt, cannot only predict hydrophobic patch areas but also outperforms existing methods at predicting primary tasks, including secondary structure and surface accessibility predictions. Importantly, our analysis shows that including related local tasks can improve predictions on more difficult global tasks. This research sets a new standard for sequence-based protein property prediction and highlights the remarkable potential of fine-tuning foundation models enriching the model representation by training over related tasks.</p><p><strong>Availability and implementation: </strong>https://github.com/Deagogishvili/chapter-multi-task.</p>\",\"PeriodicalId\":72368,\"journal\":{\"name\":\"Bioinformatics advances\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-10-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11525051/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioinformatics advances\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/bioadv/vbae154\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"MATHEMATICAL & COMPUTATIONAL BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics advances","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/bioadv/vbae154","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"MATHEMATICAL & COMPUTATIONAL BIOLOGY","Score":null,"Total":0}
PatchProt: hydrophobic patch prediction using protein foundation models.
Motivation: Hydrophobic patches on protein surfaces play important functional roles in protein-protein and protein-ligand interactions. Large hydrophobic surfaces are also involved in the progression of aggregation diseases. Predicting exposed hydrophobic patches from a protein sequence has shown to be a difficult task. Fine-tuning foundation models allows for adapting a model to the specific nuances of a new task using a much smaller dataset. Additionally, multitask deep learning offers a promising solution for addressing data gaps, simultaneously outperforming single-task methods.
Results: In this study, we harnessed a recently released leading large language model Evolutionary Scale Models (ESM-2). Efficient fine-tuning of ESM-2 was achieved by leveraging a recently developed parameter-efficient fine-tuning method. This approach enabled comprehensive training of model layers without excessive parameters and without the need to include a computationally expensive multiple sequence analysis. We explored several related tasks, at local (residue) and global (protein) levels, to improve the representation of the model. As a result, our model, PatchProt, cannot only predict hydrophobic patch areas but also outperforms existing methods at predicting primary tasks, including secondary structure and surface accessibility predictions. Importantly, our analysis shows that including related local tasks can improve predictions on more difficult global tasks. This research sets a new standard for sequence-based protein property prediction and highlights the remarkable potential of fine-tuning foundation models enriching the model representation by training over related tasks.
Availability and implementation: https://github.com/Deagogishvili/chapter-multi-task.