MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types

Abstract Protein phosphorylation plays a crucial role in regulating a wide range of biological processes, and its dysregulation is strongly linked to various diseases. While many phosphorylation sites have been identified so far, their functionality and regulatory effects are largely unknown. Here,...

Full description

Saved in:
Bibliographic Details
Main Authors: Juan Xie, Ruihan Dong, Jintao Zhu, Haoyu Lin, Shiwei Wang, Luhua Lai
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Advanced Science
Subjects:
Online Access:https://doi.org/10.1002/advs.202410981
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849471687387512832
author Juan Xie
Ruihan Dong
Jintao Zhu
Haoyu Lin
Shiwei Wang
Luhua Lai
author_facet Juan Xie
Ruihan Dong
Jintao Zhu
Haoyu Lin
Shiwei Wang
Luhua Lai
author_sort Juan Xie
collection DOAJ
description Abstract Protein phosphorylation plays a crucial role in regulating a wide range of biological processes, and its dysregulation is strongly linked to various diseases. While many phosphorylation sites have been identified so far, their functionality and regulatory effects are largely unknown. Here, a deep learning model MMFuncPhos, based on a multi‐modal deep learning framework, is developed to predict functional phosphorylation sites. MMFuncPhos outperforms existing functional phosphorylation site prediction approaches. EFuncType is further developed based on transfer learning to predict whether phosphorylation of a residue upregulates or downregulates enzyme activity for the first time. The functional phosphorylation sites predicted by MMFuncPhos and the regulatory types predicted by EFuncType align with experimental findings from several newly reported protein phosphorylation studies. The study contributes to the understanding of the functional regulatory mechanism of phosphorylation and provides valuable tools for precision medicine, enzyme engineering, and drug discovery. For user convenience, these two prediction models are integrated into a web server which can be accessed at http://pkumdl.cn:8000/mmfuncphos.
format Article
id doaj-art-387fc25f9ee24e8eb75a7633fe28fff8
institution Kabale University
issn 2198-3844
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Advanced Science
spelling doaj-art-387fc25f9ee24e8eb75a7633fe28fff82025-08-20T03:24:44ZengWileyAdvanced Science2198-38442025-03-01129n/an/a10.1002/advs.202410981MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory TypesJuan Xie0Ruihan Dong1Jintao Zhu2Haoyu Lin3Shiwei Wang4Luhua Lai5Center for Quantitative Biology Academy for Advanced Interdisciplinary Studies Peking University Beijing 100871 ChinaPTN Graduate Program Academy for Advanced Interdisciplinary Studies Peking University Beijing 100871 ChinaCenter for Quantitative Biology Academy for Advanced Interdisciplinary Studies Peking University Beijing 100871 ChinaPeking‐Tsinghua Center for Life Sciences at BNLMS College of Chemistry and Molecular Engineering Peking University Beijing 100871 ChinaPeking University Chengdu Academy for Advanced Interdisciplinary Biotechnologies Chengdu Sichuan 610213 ChinaCenter for Quantitative Biology Academy for Advanced Interdisciplinary Studies Peking University Beijing 100871 ChinaAbstract Protein phosphorylation plays a crucial role in regulating a wide range of biological processes, and its dysregulation is strongly linked to various diseases. While many phosphorylation sites have been identified so far, their functionality and regulatory effects are largely unknown. Here, a deep learning model MMFuncPhos, based on a multi‐modal deep learning framework, is developed to predict functional phosphorylation sites. MMFuncPhos outperforms existing functional phosphorylation site prediction approaches. EFuncType is further developed based on transfer learning to predict whether phosphorylation of a residue upregulates or downregulates enzyme activity for the first time. The functional phosphorylation sites predicted by MMFuncPhos and the regulatory types predicted by EFuncType align with experimental findings from several newly reported protein phosphorylation studies. The study contributes to the understanding of the functional regulatory mechanism of phosphorylation and provides valuable tools for precision medicine, enzyme engineering, and drug discovery. For user convenience, these two prediction models are integrated into a web server which can be accessed at http://pkumdl.cn:8000/mmfuncphos.https://doi.org/10.1002/advs.202410981drug discoveryenzyme engineeringfunctional phosphorylation sitesmulti‐modal deep learning frameworkphosphorylation regulation typesprecision medicine
spellingShingle Juan Xie
Ruihan Dong
Jintao Zhu
Haoyu Lin
Shiwei Wang
Luhua Lai
MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
Advanced Science
drug discovery
enzyme engineering
functional phosphorylation sites
multi‐modal deep learning framework
phosphorylation regulation types
precision medicine
title MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
title_full MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
title_fullStr MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
title_full_unstemmed MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
title_short MMFuncPhos: A Multi‐Modal Learning Framework for Identifying Functional Phosphorylation Sites and Their Regulatory Types
title_sort mmfuncphos a multi modal learning framework for identifying functional phosphorylation sites and their regulatory types
topic drug discovery
enzyme engineering
functional phosphorylation sites
multi‐modal deep learning framework
phosphorylation regulation types
precision medicine
url https://doi.org/10.1002/advs.202410981
work_keys_str_mv AT juanxie mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes
AT ruihandong mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes
AT jintaozhu mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes
AT haoyulin mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes
AT shiweiwang mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes
AT luhualai mmfuncphosamultimodallearningframeworkforidentifyingfunctionalphosphorylationsitesandtheirregulatorytypes