{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mgpfusion-predicting-protein-stability","title":"mGPfusion: Predicting protein stability changes with Gaussian process kernel learning and data fusion","arxiv_id":"1802.02852","date":"2018-02-08","proceeding":null,"authors":["Emmi Jokinen","Markus Heinonen","Harri Lähdesmäki"],"abstract":"Proteins are commonly used by biochemical industry for numerous processes.\nRefining these proteins' properties via mutations causes stability effects as\nwell. Accurate computational method to predict how mutations affect protein\nstability are necessary to facilitate efficient protein design. However,\naccuracy of predictive models is ultimately constrained by the limited\navailability of experimental data. We have developed mGPfusion, a novel\nGaussian process (GP) method for predicting protein's stability changes upon\nsingle and multiple mutations. This method complements the limited experimental\ndata with large amounts of molecular simulation data. We introduce a Bayesian\ndata fusion model that re-calibrates the experimental and in silico data\nsources and then learns a predictive GP model from the combined data. Our\nprotein-specific model requires experimental data only regarding the protein of\ninterest and performs well even with few experimental measurements. The\nmGPfusion models proteins by contact maps and infers the stability effects\ncaused by mutations with a mixture of graph kernels. Our results show that\nmGPfusion outperforms state-of-the-art methods in predicting protein stability\non a dataset of 15 different proteins and that incorporating molecular\nsimulation data improves the model learning and prediction accuracy.","url_abs":"http://arxiv.org/abs/1802.02852v2","url_pdf":"http://arxiv.org/pdf/1802.02852v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mgpfusion-predicting-protein-stability","repo_url":"https://github.com/emmijokinen/mgpfusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"protein-design","task_name":"Protein Design"},{"task_slug":"protein-stability-prediction","task_name":"Protein Stability Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.02852","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}