DeepProteomics: Protein family classification using Shallow and Deep Networks
Center for Computational Engineering and Networking (CEN)(计算工程与网络中心(CEN));Amrita School of Engineering(阿姆里塔工程学院);Amrita Vishwa Vidyapeetham(阿姆里塔维什瓦维迪亚佩瑟姆大学)
The knowledge regarding the function of proteins is necessary as it gives a clear picture of biological processes. Nevertheless, there are many protein sequences found and added to the databases but lacks functional annotation. The laboratory experiments take a considerable amount of time for annotation of the sequences. This arises the need to use computational techniques to classify proteins based on their functions. In our work, we have collected the data from Swiss-Prot containing 40433 proteins which is grouped into 30 families. We pass it to recurrent neural network(RNN), long short term memory(LSTM) and gated recurrent unit(GRU) model and compare it by applying trigram with deep neural network and shallow neural network on the same dataset. Through this approach, we could achieve maximum of around 78% accuracy for the classification of protein families.
A robust methodology for inferring physiology of a protein family: application to K+-ion channel family
We are interested in the subtle variations of function among the members of a protein family. A protein family is usually subdivided into subfamilies based on functional differences. Existence of this functional diversity is essential for the successful performance of physiological roles expected of the family. This presents a unique problem: there must be preservation of the active site; simultaneously there should be specificity of protein action according to subfamily. Though the classification into subfamilies is by no means a formalized one, it is most times based on the character of regu…
A Fusion-Driven Approach of Attention-Based CNN-BiLSTM for Protein Family Classification -- ProFamNet
School of Computer Science and IT, Institute of Management Sciences(管理科学学院计算机科学与信息技术学院);National University of Computer and Emerging Sciences(国家计算机与新兴科学大学);Ghulam Ishaq Institute of Emerging Sciences(古拉姆·伊沙克新兴科学学院)
MRFalign: Protein Homology Detection through Alignment of Markov Random Fields
Toyota Technological Institute at Chicago(芝加哥丰田技术研究所)
基于序列的蛋白质同源性检测已经被广泛研究,并且迄今为止最灵敏的方法是基于蛋白质序列谱的比较,所述蛋白质序列谱来自于蛋白质家族中序列同源物的多个序列比对(MSA)。序列谱通常表示为位置特异性评分矩阵(PSSM)或HMM(隐马尔可夫模型),因此PSSM-PSSM或HMM-HMM比较用于同源物检测。本文提出了一种新的同源性检测方法MRFalign,该方法由三个关键部分组成:1)一个蛋白质家族的马尔可夫随机场(MRF)表示; 2)一个衡量两个MRF相似性的评分函数; 3)一个高效的ADMM(Alternating Direction Method of Multipliers)算法。与只能模拟非常短距离残基相关性的HMM相比,MRF可以模拟长距离残基相互作用模式,从而编码蛋白质家族的全局3D结构信息。因此,用于远程同源性检测的MRF-MRF比较应比HMM-HMM或PSSM-PSSM比较灵敏得多。实验证实,MRFalign优于几个流行的HMM或PSSM为基础的方法在比对精度和远程同源性检测方面,MRFalign工程特别好,主要是β蛋白。例如,在用于同源性检测的基准SCOP 40(8353种蛋白质)上测试,PSSM-PSSM和HMM-HMM在超家族水平上分别对48%和52%的蛋白质成功,并且在倍数水平上分别对15%和27%的蛋白质成功。相比之下,MRFalign在超家族和折叠水平上的成功率分别…
Evolutionary Profiles for Protein Fitness Prediction
Zhejiang University(浙江大学);Peking University(北京大学);East China University of Science and Technology(华东理工大学);Chengdu University of Information Technology(成都信息工程大学);Massachusetts Institute of Technology(麻省理工学院);Zhejiang University of Technology(浙江工业大学)
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 Scarce Functional Labels to Label-Aware Generation in Homologous Protein Families
École Normale Supérieure, CNRS, Laboratoire de Physique - LPENS(巴黎高等师范学院,法国国家科学研究中心,物理实验室);Sorbonne Université, CNRS, Dept. of Computational, Quantitative and Synthetic Biology - CQSB(索邦大学,法国国家科学研究中心,计算、定量与合成生物学系);Institut Universitaire de France (IUF)(法兰西学院);Dipartimento di Fisica, Sapienza Università di Roma(罗马智慧大学物理系)
PUMA: Learning a Mutation-Aware Vocabulary of Protein Units
Department of Computer Engineering, Boğaziçi University(计算机工程系,博雅大学);C. Eugene Bennett Department of Chemistry, West Virginia University(C. Eugene Bennett化学系,西弗吉尼亚大学);Department of Pharmaceutical Chemistry, Istanbul Medipol University, Faculty of Pharmacy(药学系,伊斯坦布尔Medipol大学);Istanbul Medipol University, Research Institute for Health Sciences and Technologies (SABITA)(伊斯坦布尔Medipol大学,健康科学与技术研究所)
RegimeFormer: A Large Protein Model of Global Perturbation Regimes
Nanyang Technological University(南洋理工大学);National University of Singapore(新加坡国立大学);Alibaba-NTU Global e-Sustainability CorpLab (ANGEL)(阿里巴巴-南洋理工大学全球电子可持续发展联合实验室);Shanghai Jiao Tong University(上海交通大学);Zhejiang A&F University(浙江农林大学);University of Oxford(牛津大学);Shanghai East Hospital, Tongji University School of Medicine(同济大学医学院附属东方医院);University of Southern California(南加州大学);Zhejiang University(浙江大学);Jinan University(暨南大学);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Selection of sequence motifs and generative Hopfield-Potts models for protein familiesilies
进化相关蛋白质家族的统计模型最近引起了人们的兴趣:特别是成对Potts模型,如直接耦合分析所推断的那些,已经能够提取有关折叠蛋白质的三维结构的信息,以及蛋白质中氨基酸取代的影响。这些模型通常被要求再现蛋白质家族中氨基酸使用的单点和两点统计,{ \em,即}~以捕获所谓的残基保守和协变统计的共同进化起源的蛋白质。成对Potts模型是实现这一目标的最大熵模型。虽然是成功的,这些模型依赖于大量的{ \em ad hoc}引入的参数,这些参数必须从有限数量的数据中估计,并且其生物物理解释仍然不清楚。在这里,我们提出了一种方法来减少参数,这是基于选择集体序列基序。它自然导致制定的统计序列模型的Hopfield-Potts模型。这些模型可以准确地推断使用映射到限制玻尔兹曼机和持续的对比发散。我们发现,当应用于蛋白质数据时,即使是20-40个模式也足以获得统计上接近生成的模型。Hopfield模式形成可解释的序列基序,并可用于将氨基酸序列聚类为功能亚家族。然而,这些图案的分布式集体本质上限制了Hopfield-Potts模型在预测接触图的能力,显示出开发超越这里讨论的Hopfield-Potts模型的必要性。