How we choose to represent our data has a fundamental impact on our ability to subsequently extract information from them. Machine learning promises to automatically determine efficient representations from large unstructured datasets, such as those arising in biology. However, empirical evidence suggests that seemingly minor changes to these machine learning models yield drastically different data representations that result in different biological interpretations of data. This begs the question of what even constitutes the most meaningful representation. Here, we approach this question for representations of protein sequences, which have received considerable attention in the recent literature. We explore two key contexts in which representations naturally arise: transfer learning and interpretable learning. In the first context, we demonstrate that several contemporary practices yield suboptimal performance, and in the latter we demonstrate that taking representation geometry into account significantly improves interpretability and lets the models reveal biological information that is otherwise obscured.
学习有意义的蛋白质表示对于各种生物下游任务(如基于结构的药物设计)非常重要。在蛋白质序列预训练取得成功之后,对信息量更大的结构数据进行预训练成为一个很有前途的研究课题。然而,蛋白质结构预训练面临三大挑战:样本多样性不足,物理上不切实际的建模,以及缺乏蛋白质特定的借口任务。为了解决这些挑战,我们提出了3D几何预训练。在本文中,我们提出了一个统一的蛋白质预训练框架和一个基于3D几何的,数据高效的,蛋白质特定的借口任务:RefineDiff(Refine the Diffused Protein Structure Decoy)。在有限的数据(不到SOTA模型的1%)上对我们的几何感知模型进行预训练后,我们获得了信息丰富的蛋白质表示,可以在各种下游任务中实现相当的性能。
Do Protein Transformers Have Biological Intelligence?
University of Delaware(德克萨斯大学);Beijing University of Posts and Telecommunications(北京邮电大学);Yale University(耶鲁大学);University of Louisiana at Lafayette(路易斯安那州立大学)
Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning
Peking University(北京大学);Tsinghua University(清华大学);Massachusetts Institute of Technology(麻省理工学院);Stanford University(斯坦福大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Helixon Ltd.(Helixon有限公司)
Comprehensive classification of the plant non-specific lipid transfer protein superfamily towards its Sequence -Structure -Function analysis
背景非特异性脂质转移蛋白(Non-specific Lipid Transfer Proteins,nsLTP)广泛分布于植物界,是一个相关蛋白超家族。到目前为止,已经鉴定了800多个不同的序列,但它们的生物学功能仍不清楚。多年来,很明显,它们对农学和营养问题产生了一定的兴趣。破译它们的功能意味着收集和分析从基因序列到蛋白质结构,从细胞定位到生理作用的各种数据。随着大量新的蛋白质序列的出现,从序列-结构-功能关系中提取有意义的知识需要开发新的工具和方法。由于nsLTP显示出高度的进化分歧,但保守的共同右手超螺旋结构折叠,并且由于它们参与了植物发育和防御中的大量关键作用,因此它们是验证这种方法的一个令人兴奋的案例研究。
Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
Shanghai AI Laboratory(上海人工智能实验室);Mila, Université de Montréal(蒙特利尔大学米拉研究所);Zelixir Biotech(泽列西尔生物科技公司);Fudan University(复旦大学);The Chinese University of Hong Kong(香港中文大学)
From Supervision to Exploration: What Does Protein Language Model Learn During Reinforcement Learning?
The Chinese University of Hong Kong(香港中文大学);Peking University(北京大学);Stanford University(斯坦福大学);Nanjing University(南京大学);University of Pennsylvania(宾夕法尼亚大学);National University of Singapore(新加坡国立大学);University of Illinois Urbana-Champaign(伊利诺伊大学香槟分校);Toyota Technological Institute at Chicago(芝加哥丰田技术研究所)
AF2-Mutation: Adversarial Sequence Mutations against AlphaFold2 on Protein Tertiary Structure Prediction
Shanghai AI Laboratory(上海人工智能实验室);Research Institute of Intelligent Complex Systems, Fudan University(复旦大学智能复杂系统研究院);Institute of Metabolism and integrative biology, Fudan University(复旦大学代谢与整合生物学研究所);Zelixir Biotech(泽里瑟生物科技公司);WAVES, Ghent University(根特大学WAVES机构)
Representing local protein environments with machine learning force fields
IST Austria(IST奥地利研究院);Technion, Israel(技术学院,以色列);University of Oxford, UK(牛津大学,英国);Princeton University(普林斯顿大学);Broad Institute of MIT and Harvard(哈佛大学与麻省理工学院Broad研究所)