Filters








2,407 Hits in 6.7 sec

Interpretable Structured Learning with Sparse Gated Sequence Encoder for Protein-Protein Interaction Prediction [article]

Kishan KC, Feng Cui, Anne Haake, Rui Li
2020 arXiv   pre-print
Predicting protein-protein interactions (PPIs) by learning informative representations from amino acid sequences is a challenging yet important problem in biology.  ...  Our model incorporates a bidirectional gated recurrent unit to learn sequence representations by leveraging contextualized and sequential information from sequences.  ...  Finally, we demonstrate that the learned sparse gate values correspond to the biologically interpretable protein motifs.  ... 
arXiv:2010.08514v1 fatcat:npycv5jm6bcyvmpffxzjxippwq

A Review on Compound-Protein Interaction Prediction Methods: Data, Format, Representation and Model

Sangsoo Lim, Yijingxiu Lu, Chang Yun Cho, Inyoung Sung, Jungwoo Kim, Youngkuk Kim, Sungjoon Park, Sun Kim
2021 Computational and Structural Biotechnology Journal  
There has recently been a rapid progress in computational methods for determining protein targets of small molecule drugs, which will be termed as compound protein interaction (CPI).  ...  For the CPI methods, we grouped prediction methods into five categories from traditional machine learning techniques to state-of-the-art deep learning techniques.  ...  Target proteins Various formats and encoding schemes are available for protein sequences and structures.  ... 
doi:10.1016/j.csbj.2021.03.004 pmid:33841755 pmcid:PMC8008185 fatcat:x3xk3b566vh6ljpeffojtusda4

An Interpretable Framework for Drug-Target Interaction with Gated Cross Attention [article]

Yeachan Kim, Bonggun Shin
2021 arXiv   pre-print
Specifically, deep learning-based DTI approaches have been shown promising results in terms of accuracy and low cost for the prediction.  ...  In this study, we propose a novel interpretable framework that can provide reasonable cues for the interaction sites.  ...  Most recent studies for predicting the interaction focus on representation learning for drugs and targets.  ... 
arXiv:2109.08360v1 fatcat:lbq5hbngxjdwllz2nogfe5uoj4

Incorporating Machine Learning into Established Bioinformatics Frameworks

Noam Auslander, Ayal B. Gussow, Eugene V. Koonin
2021 International Journal of Molecular Sciences  
Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease  ...  We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics  ...  Integrating Machine-Learning with Protein Structure Analysis In the study of proteins, numerous methods have been developed to process the amino acid sequence, and predict the protein structure, function  ... 
doi:10.3390/ijms22062903 pmid:33809353 pmcid:PMC8000113 fatcat:ssfoobbtcjhidbaffbkakqbwfe

ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding

Junjie Wang, NaiFeng Wen, Chunyu Wang, Lingling Zhao, Liang Cheng
2022 Journal of Cheminformatics  
Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset.  ...  This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding.  ...  Acknowledgements We thank the anonymous reviewers very much for their effort in evaluating our paper.  ... 
doi:10.1186/s13321-022-00591-x pmid:35292100 pmcid:PMC8922401 fatcat:m3sbqcyg7fgmphlxaha3nwtwhu

DeepACLSTM: deep asymmetric convolutional long short-term memory neural models for protein secondary structure prediction

Yanbu Guo, Weihua Li, Bingyi Wang, Huiqing Liu, Dongming Zhou
2019 BMC Bioinformatics  
Protein secondary structure (PSS) is critical to further predict the tertiary structure, understand protein function and design drugs.  ...  Conclusions: Experiments demonstrate that DeepACLSTM is an efficient predication method for predicting 8category PSS and has the ability to extract more complex sequence-structure relationships between  ...  WL and BW provided valuable insights on biomolecular interactions and systems biology modeling. HL participated in result interpretation and manuscript preparation.  ... 
doi:10.1186/s12859-019-2940-0 fatcat:6aqjk2jcmngnvd2d2k32sfhrgy

Deep learning for drug repurposing: methods, databases, and applications [article]

Xiaoqin Pan, Xuan Lin, Dongsheng Cao, Xiangxiang Zeng, Philip S. Yu, Lifang He, Ruth Nussinov, Feixiong Cheng
2022 arXiv   pre-print
Next, we discuss recently developed sequence-based and graph-based representation approaches as well as state-of-the-art deep learning-based methods.  ...  In this review, we introduce guidelines on how to utilize deep learning methodologies and tools for drug repurposing.  ...  For example, with the novel representations of structurally annotated protein sequences (SPS), Karimi et al. proposed a semi-supervised deep learning model called DeepAffinity.  ... 
arXiv:2202.05145v1 fatcat:5oqujy2daffdpa33b4cbrg6hqy

Exploring chemical space using natural language processing methodologies for drug discovery

Hakime Öztürk, Arzucan Özgür, Philippe Schwaller, Teodoro Laino, Elif Ozkirimli
2020 Drug Discovery Today  
Text-based representations of chemicals and proteins can be thought of as unstructured languages codified by humans to describe domain-specific knowledge.  ...  in the processing of spoken languages accelerated the application of NLP to elucidate hidden knowledge in textual representations of these biochemical entities and then use it to construct models to predict  ...  well as for protein fold prediction [87] to learn representations for proteins from aminoacid sequences.  ... 
doi:10.1016/j.drudis.2020.01.020 pmid:32027969 fatcat:5dhdhn5pxrffnegbqf73cym3kq

Deep Learning in Virtual Screening: Recent Applications and Developments

Talia B Kimber, Yonghui Chen, Andrea Volkamer
2021 International Journal of Molecular Sciences  
This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing.  ...  Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed.  ...  The PADME model, an acronym for "Protein And Drug Molecule interaction prEdiction" [156] , suggests two variants for ligand encoding in the regression context of drug-target interaction prediction.  ... 
doi:10.3390/ijms22094435 pmid:33922714 fatcat:uecx2a7rarb2hdyui6m3kg5vge

A modular kernel approach for integrative analysis of protein domain boundaries

Paul D Yoo, Bing Zhou, Albert Y Zomaya
2009 BMC Genomics  
In this paper, we introduce a novel inter-range interaction integrated approach for protein domain boundary prediction.  ...  One of the key features of this profiling technique is the use of multiple structural alignments of remote homologues to create an extended sequence profile and combines the structural information with  ...  set, to create a model; (7) simulation of each model on the test set, to obtain predicted outputs; and (8) post-processing to find predicted domain boundary locations.  ... 
doi:10.1186/1471-2164-10-s3-s21 pmid:19958485 pmcid:PMC2788374 fatcat:dhkowfzqnrdajivnum255ugsue

High-resolution de novo structure prediction from primary sequence [article]

Ruidong Wu, Fan Ding, Rui Wang, Rui Shen, Xiwen Zhang, Shitong Luo, Chenpeng Su, Zuofan Wu, Qi Xie, Bonnie Berger, Jianzhu Ma, Jian Peng
2022 bioRxiv   pre-print
Recent breakthroughs have used deep learning to exploit evolutionary information in multiple sequence alignments (MSAs) to accurately predict protein structures.  ...  Here, we introduce OmegaFold, the first computational method to successfully predict high-resolution protein structure from a single primary sequence alone.  ...  Previous deep learning models usually sample a sub-sequence with fixed length (20) . Adjacent residues in a protein sequence are usually closed in the 3D structure.  ... 
doi:10.1101/2022.07.21.500999 fatcat:2bl27gvagrbdvloldhavlvoisi

AttentionSiteDTI: Attention Based Model for Predicting Drug-Target Interaction Using 3D Structure of Protein Binding Sites [article]

Mehdi Yazdani-Jahromi, Niloofar Yousefi, Aida Tayebi, Ozlem Ozmen Garibay, Sudipta Seal, Elayaraja Kolanthai, Craig Neal
2021 bioRxiv   pre-print
To achieve this, we first computationally predict binding interaction of some candidate compounds with a target protein, and then experimentally validate the binding interactions for these pairs in the  ...  This, indeed, complements the black-box nature of deep learning-based methods and enables interpretability, while achieving state of the art results in drug target interaction prediction task on three  ...  We thank Ms.Katalina Biondi for discussions and her valuable feedback and comments on earlier versions of the manuscript.  ... 
doi:10.1101/2021.12.07.471693 fatcat:gulukrznljf2vn2kcqlzwg2apy

AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification

Mehdi Yazdani-Jahromi, Niloofar Yousefi, Aida Tayebi, Elayaraja Kolanthai, Craig J Neal, Sudipta Seal, Ozlem Ozmen Garibay
2022 Briefings in Bioinformatics  
In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem  ...  To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in  ...  Acknowledgments We thank Ms.Katalina Biondi for discussions and her valuable feedback and comments on earlier versions of the manuscript.  ... 
doi:10.1093/bib/bbac272 pmid:35817396 pmcid:PMC9294423 fatcat:fey2qrqhxreixp37khjk6dabzq

Conjoint Feature Representation of Gene Ontology and Protein Sequence for Protein-Protein Interaction Prediction Based on an Inception RNN Attention Network

Lingling Zhao, Junjie Wang, Yang Hu, Liang Cheng
2020 Molecular Therapy: Nucleic Acids  
Protein-protein interactions (PPIs) are pivotal for cellular functions and biological processes.  ...  We propose a deep-learning-based PPI prediction methodology conjointly featuring sequence information and GO annotation.  ...  We thank all of the reviewers for their valuable comments and suggestions.  ... 
doi:10.1016/j.omtn.2020.08.025 pmid:33230427 pmcid:PMC7515979 fatcat:nzj2d3klg5ebhheoqu66ih3my4

A hybrid model combining evolutionary probability and machine learning leverages data-driven protein engineering [article]

Alexander-Maurice Illig, Niklas E. Siedhoff, Ulrich Schwaneberg, Mehdi D. Davari
2022 bioRxiv   pre-print
Our method achieves high performance in predicting a proteins fitness based on its sequence regardless of the number of sequences-fitness pairs in the training dataset.  ...  Besides reducing the computational effort compared to state-of-the-art methods, it outperforms them for sparse data situations, i.e., 50-250 labeled sequences available for training.  ...  Model performance studies were performed with computing resources granted by JARA-HPC from RWTH Aachen University under project p0020054. We thank André Breuer for the lively discussions.  ... 
doi:10.1101/2022.06.07.495081 fatcat:m6cjogwljnfxnerqblcjc6pe5m
« Previous Showing results 1 — 15 out of 2,407 results