End-to-end multitask learning, from protein language to protein features without alignments

作者
Ahmed Elnaggar,Michael Heinzinger,Christian Dallago,Burkhard Rost
出处
期刊: [Cold Spring Harbor Laboratory]
被引量:18
标识
DOI:10.1101/864405
摘要

Abstract Correctly predicting features of protein structure and function from amino acid sequence alone remains a supreme challenge for computational biology. For almost three decades, state-of-the-art approaches combined machine learning and evolutionary information from multiple sequence alignments. Exponentially growing sequence databases make it infeasible to gather evolutionary information for entire microbiomes or meta-proteomics. On top, for many important proteins (e.g. dark proteome and intrinsically disordered proteins ) evolutionary information remains limited. Here, we introduced a novel approach combining recent advances of Language Models (LMs) with multi-task learning to successfully predict aspects of protein structure (secondary structure) and function (cellular component or subcellular localization) without using any evolutionary information from alignments. Our approach fused self-supervised pre-training LMs on an unlabeled big dataset (UniRef50, corresponding to 9.6 billion words) with supervised training on labelled high-quality data in one single end-to-end network. We provided a proof-of-principle for the novel concept through the semi-successful per-residue prediction of protein secondary structure and through per-protein predictions of localization (Q10=69%) and the distinction between integral membrane and water-soluble proteins (Q2=89%). Although these results did not reach the levels obtained by the best available methods using evolutionary information from alignments, these less accurate multi-task predictions have the advantage of speed: they are 300-3000 times faster (where HHblits needs 30-300 seconds on average, our method needed 0.045 seconds). These new results push the boundaries of predictability towards grayer and darker areas of the protein space, allowing to make reliable predictions for proteins which were not accessible by previous methods. On top, our method remains scalable as it removes the necessity to search sequence databases for evolutionary related proteins.

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
研二就毕业完成签到,获得积分10
刚刚
晚霞跌落星河的应助被master采纳,获得30
1秒前
4yjmngbfd发布了新的文献求助10
1秒前
星辰大海的应助被稳重的馒头采纳,获得10
2秒前
4秒前
李健的应助被牧百川采纳,获得10
6秒前
风吹麦浪的应助被ping采纳,获得10
7秒前
天青色等烟雨完成签到,获得积分10
7秒前
vbmc发布了新的文献求助30
7秒前
英俊的铭的应助被张会采纳,获得10
7秒前
风吹麦浪的应助被文艺雁兰采纳,获得10
7秒前
Zhangtao完成签到,获得积分0
8秒前
聪慧雪糕发布了新的文献求助10
8秒前
kitty完成签到,获得积分10
8秒前
Ryan完成签到,获得积分10
9秒前
9秒前
丘比特的应助被4yjmngbfd采纳,获得10
9秒前
9秒前
xiaot驳回了Jun的应助
10秒前
10秒前
张娜发布了新的文献求助10
10秒前
禾十完成签到,获得积分10
11秒前
康利萍完成签到,获得积分20
11秒前
12秒前
牧长一完成签到 ,获得积分0
12秒前
13秒前
w0304hf完成签到,获得积分10
13秒前
路星辞完成签到 ,获得积分10
13秒前
ShawnJohn发布了新的文献求助10
13秒前
14秒前
14秒前
禾十发布了新的文献求助10
14秒前
大个的应助被Ann采纳,获得10
15秒前
16秒前
16秒前
康利萍发布了新的文献求助10
16秒前
16秒前
DW的应助被小博士328采纳,获得10
17秒前
pengnanhao完成签到,获得积分10
17秒前
18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
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
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 8183621
求助须知:如何正确求助?哪些是违规求助? 9572918
关于积分的说明 21828010
捐赠科研通 7780809
什么是DOI,文献DOI怎么找? 3434031
关于科研通互助平台的介绍 2558243
邀请新用户注册赠送积分活动 2480496