A Systematic Evaluation of Protein Phase Separation Predictors Across Diverse Protein Landscapes

背景(考古学) 计算生物学 生物 内在无序蛋白质 选择(遗传算法) 水准点(测量) 计算机科学 机器学习 蛋白质-蛋白质相互作用 人类蛋白质 鉴定(生物学) 蛋白质法 预测建模 序列(生物学) 计算模型 生物信息学 人工智能 灵敏度(控制系统) 数据挖掘 突变 蛋白质测序 结构蛋白 特征选择 蛋白质结构预测 航程(航空) 钥匙(锁) 蛋白质结构域 蛋白质结构
作者
Kate Gilroy,John Barr
出处
期刊: [Cold Spring Harbor Laboratory]
标识
DOI:10.64898/2026.01.20.700394
摘要

Abstract Background Liquid–liquid phase separation (LLPS) plays a central role in cellular regulation, with its dysregulation linked to numerous disease outcomes. LLPS has also being increasingly implicated as critical in various biological contexts, with a key example being virus replication. These findings have driven the development of numerous computational predictors to screen and identify phase-separating proteins from sequence and/or structural models. Despite the growing need for these tools, their comparative performance across diverse biological contexts remains incompletely understood, complicating tool selection and result interpretation. Results A systematic comparative analysis of nine LLPS prediction algorithms was conducted using multiple curated datasets comprising both LLPS-positive (LLPS+) and -negative (LLPS-) proteins. The datasets span a range of biologically relevant scenarios, including intrinsically disordered proteins, folded proteins, proteins with LLPS-abolishing variants, benchmark datasets, and viral proteins. Substantial variability in predictive performance was observed across algorithms when assessing proteins of different structural classes. Numerous showed reduced accuracy in distinguishing LLPS+ and LLPS- folded proteins. Sensitivity to the impact of small LLPS-abolishing mutations also varied markedly between predictors, with structure-informed algorithms generally outperforming most sequence-based predictors. Similar decreases in predictive capability were also observed across several algorithms when analysing viral proteins, which are often-under-represented in predictor training datasets. Conclusions These results demonstrate that LLPS predictor performance is strongly context dependent, leading to different predictors being optimal for different biological questions. For overall protein assessment, DeePhase and Molphase provided the most consistently accurate predictions, being the least impacted by structural bias. For assessing the impact of small mutations on LLPS propensity, PSPHunter, a built-for-purpose algorithm, reliably predicts mutation impacts with structure-informed algorithms PSPire and PICNIC also providing strong insight. Across all evaluated datasets, the findings highlight the need for well-benchmarked training and testing data that encompasses a broad and diverse range of protein classes.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
山丘完成签到,获得积分10
1秒前
orixero的应助被675675采纳,获得10
1秒前
RWcreator完成签到 ,获得积分10
1秒前
Pomelo完成签到,获得积分10
1秒前
1秒前
LLL发布了新的文献求助10
1秒前
Wedg完成签到 ,获得积分10
2秒前
2秒前
XuNan完成签到,获得积分10
2秒前
youyouka完成签到,获得积分20
3秒前
3秒前
3秒前
3秒前
自觉谷蓝发布了新的文献求助10
3秒前
卡黄99完成签到,获得积分10
4秒前
天际完成签到,获得积分10
4秒前
杰帅完成签到,获得积分10
4秒前
斯文败类的应助被CC采纳,获得100
4秒前
5秒前
cc发布了新的文献求助10
5秒前
5秒前
科研通AI6.4的应助被淡淡嘟采纳,获得10
5秒前
5秒前
FashionBoy的应助被称心匕采纳,获得10
5秒前
5秒前
ECHO完成签到 ,获得积分10
6秒前
tangli完成签到 ,获得积分10
6秒前
清秀的碧彤完成签到,获得积分10
6秒前
树522发布了新的文献求助10
6秒前
淮雨晚完成签到,获得积分10
6秒前
7秒前
小月完成签到,获得积分10
7秒前
7秒前
yu完成签到,获得积分10
7秒前
FF完成签到,获得积分10
7秒前
小陈发布了新的文献求助10
7秒前
yuqinghui98发布了新的文献求助10
7秒前
7秒前
7秒前
皮卡路发布了新的文献求助10
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180531
求助须知:如何正确求助?哪些是违规求助? 9570507
关于积分的说明 21812974
捐赠科研通 7776619
什么是DOI,文献DOI怎么找? 3433286
关于科研通互助平台的介绍 2557539
邀请新用户注册赠送积分活动 2479185