Filters








28,841 Hits in 4.3 sec

Learning Models for Aligning Protein Sequences with Predicted Secondary Structure [chapter]

Eagu Kim, Travis Wheeler, John Kececioglu
2009 Lecture Notes in Computer Science  
We introduce several new models for scoring alignments of protein sequences with predicted secondary structure, which use the predictions and their confidences to modify both the substitution and gap cost  ...  Accurately aligning distant protein sequences is notoriously difficult. A recent approach to improving alignment accuracy is to use additional information such as predicted secondary structure.  ...  Acknowledgements We thank Matt Cordes and Chuong Do for helpful discussions, and the reviewers for their suggestions.  ... 
doi:10.1007/978-3-642-02008-7_36 fatcat:bnpnmye4nfcw7ctebwuloai5pi

Evaluating Protein Transfer Learning with TAPE

Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S Song
2019 Advances in Neural Information Processing Systems  
Machine learning applied to protein sequences is an increasingly popular area of research.  ...  This gap in performance suggests a huge opportunity for innovative architecture design and improved modeling paradigms that better capture the signal in biological sequences.  ...  We thank the AWS Educate program for providing us with the resources to train our models.  ... 
pmid:33390682 pmcid:PMC7774645 fatcat:s57yq2xvpzhdjn4un3nt6p6qsa

Learning protein sequence embeddings using information from structure [article]

Tristan Bepler, Bonnie Berger
2019 arXiv   pre-print
We train bidirectional long short-term memory (LSTM) models on protein sequences with a two-part feedback mechanism that incorporates information from (i) global structural similarity between proteins  ...  Structures are not known for the vast majority of protein sequences, but structure is critical for understanding function.  ...  PROTEIN STRUCTURE COMPARISON The primary task we consider for training the sequence embedding model with structural information is the prediction of global structural similarity between protein sequences  ... 
arXiv:1902.08661v2 fatcat:mujq6uyhsbc65bvii754mpgpwi

Evaluating Protein Transfer Learning with TAPE [article]

Roshan Rao, Nicholas Bhattacharya, Neil Thomas, Yan Duan, Xi Chen, John Canny, Pieter Abbeel, Yun S. Song
2019 bioRxiv   pre-print
Protein modeling is an increasingly popular area of machine learning research.  ...  This gap in performance suggests a huge opportunity for innovative architecture design and improved modeling paradigms that better capture the signal in biological sequences.  ...  We thank the AWS Educate program for providing us with the resources to train our models.  ... 
doi:10.1101/676825 fatcat:hd7zpclltnbq3ifruwwa7ppu3u

Prediction of α-turns in proteins using PSI-BLAST profiles and secondary structure information

Harpreet Kaur, G.P.S. Raghava
2004 Proteins: Structure, Function, and Bioinformatics  
It has been observed that ANN with multiple sequence alignment and predicted secondary structure information outperforms other methods.  ...  Most of the commonly used approaches in the field of protein structure prediction have been tried in this study, which includes statistical approach "Sequence Coupled Model" and machine learning approaches  ...  ACKNOWLEDGMENT The authors are thankful to Council of Scientific and Industrial Research (CSIR) and Department of Biotechnology (DBT), Govt. of India for financial assistance.  ... 
doi:10.1002/prot.10569 pmid:14997542 fatcat:xolcpc2uwrduzg2katksrdox4y

An extension of Wang protein design model using Blosum62 substitution matrix [article]

Amin Rahmani, Fatemeh Zare-Mirakabad
2021 bioRxiv   pre-print
One of the problems that help us understand the relation between protein structure is the well-known protein design problem which attempts to find an amino acid sequence that can fold into a desired tertiary  ...  This paper presents an extension to Wang's deep learning model, which uses evolutionary information in the Blosum62 substitution matrix to take amino acid replacement probability into account while designing  ...  Analyzing sequences quality using PSI-Blast alignment with natural sequence Table 3 : 3 Comparison of predicted structures with the natural structure I-Tasser and TM-Align Secondary structures, dihedral  ... 
doi:10.1101/2021.06.07.447415 fatcat:xg5uct6aeje5raunj2t2croet4

A neural-network based method for prediction of γ-turns in proteins from multiple sequence alignment

Harpreet Kaur, G.P.S. Raghava
2003 Protein Science  
In the first step, a sequence-to-structure network is used to predict the ␥-turns from multiple alignment of protein sequence.  ...  First, we have implemented the commonly used statistical and machine-learning techniques in the field of protein structure prediction, for the prediction of ␥-turns.  ...  This article must therefore be hereby marked "advertisement" in accordance with 18 USC section 1734 solely to indicate this fact.  ... 
doi:10.1110/ps.0241703 pmid:12717015 pmcid:PMC2323863 fatcat:wqelegtnfvdcfinzkikaomc4jq

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, Rob Fergus
2021 Proceedings of the National Academy of Sciences of the United States of America  
Protein language modeling at the scale of evolution is a logical step toward predictive and generative artificial intelligence for biology.  ...  features for long-range contact prediction.  ...  We thank Jinbo Xu for sharing RaptorX features and help with CASP13. We thank Michael Klausen for providing the NetSurf training code. A.R. was supported at New York University by NSF Grant #1339362.  ... 
doi:10.1073/pnas.2016239118 pmid:33876751 pmcid:PMC8053943 fatcat:3bdyww5e75csbazdbf3ur4vcfu

From local structure to a global framework: recognition of protein folds

A. P. Joseph, A. G. de Brevern
2014 Journal of the Royal Society Interface  
The huge amount of available sequence and structural information provides hints to identify the putative fold for a given sequence.  ...  Here, we review the developments in the field of local structure prediction and especially their implication in protein fold recognition.  ...  They are trained to learn the amino acid preferences associated with different secondary structures and make predictions for new sequences.  ... 
doi:10.1098/rsif.2013.1147 pmid:24740960 pmcid:PMC4006237 fatcat:b7tyzbe3jrh6lf57t6cxxpw7lq

PREDICTION OF CONTACT MAPS USING SUPPORT VECTOR MACHINES

YING ZHAO, GEORGE KARYPIS
2005 International journal on artificial intelligence tools  
Our study showed that predicted secondary structure features play an important roles for the proteins containing beta structures.  ...  Our study also suggests that models learned separately for different protein fold families may achieve better performance than a unified model.  ...  Yiannis Kaznessis for introducing us to the contact-map prediction problem and the use of the AAindex for CMA calculations.  ... 
doi:10.1142/s0218213005002429 fatcat:teoi2gs5lnhrxdql75brw4loca

DNSS2: improved ab initio protein secondary structure prediction using advanced deep learning architectures [article]

Jie Hou, Zhiye Guo, Jianlin Cheng
2019 bioRxiv   pre-print
Most of the deep learning architectures are novel for protein secondary structure prediction.  ...  secondary structure, and (ii) using more sensitive profile features inferred from Hidden Markov model (HMM) and multiple sequence alignment (MSA).  ...  Meanwhile, the machine learning algorithms for protein secondary structure prediction also continued to improve.  ... 
doi:10.1101/639021 fatcat:wbttv5kszrg2zniteeejyjzpke

Are the Hidden Markov Models Promising in Protein Research?

Kiyoshi Asai, Hidetoshi Tanaka, Katunobu Itou, Kentaro Onizuka
1993 Genome Informatics Series  
In the field of protein research, HMMs have been used to represent stochastic motifs of protein sequences, to model the structural patterns of protein, to predict the secondary structures and upper level  ...  structures, to make multiple sequence alignments, and to classify the protein sequences.  ...  HMMs were used for structure predictions , f or structure modeling, for multiple sequence alignment , for protein classification and for motif extraction.  ... 
doi:10.11234/gi1990.4.130 fatcat:kgzafnbg7nejpecnjx3tziwwly

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

Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Burkhard Rost
2019 bioRxiv   pre-print
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  ...  For almost three decades, state-of-the-art approaches combined machine learning and evolutionary information from multiple sequence alignments.  ...  Acknowledgements 43 The authors thank primarily to Tim Karl and Jian Kong for invaluable help with hardware and 44 software and to Inga Weise for support with many other aspects of this work.  ... 
doi:10.1101/864405 fatcat:6i5sr524zrd6nk27xf7tbas3ye

Improvement of the GenTHREADER method for genomic fold recognition

L. J. McGuffin, D. T. Jones
2003 Bioinformatics  
The improved version incorporates PSI-BLAST searches, which have been jumpstarted with structural alignment profiles from FSSP, and now also makes use of PSIPRED predicted secondary structure and bi-directional  ...  The neural network has also been expanded to accommodate the secondary structure element alignment (SSEA) score as an extra input and it is now trained to learn the FSSP Z -score as a measurement of similarity  ...  We would like to thank Alejandro Schaffer at the National Institutes for Health, USA for his useful comments concerning PSI-BLAST.  ... 
doi:10.1093/bioinformatics/btg097 pmid:12724298 fatcat:arb26ewea5c2pne5ivmckkrfx4

SPOT-1D-LM: Reaching Alignment-profile-based Accuracy in Predicting Protein Secondary and Tertiary Structural Properties without Alignment [article]

Jaspreet Singh, Kuldip Paliwal, Jaswinder Singh, Yaoqi Zhou
2021 bioRxiv   pre-print
Protein language models have emerged as an alternative to multiple sequence alignment for enriching sequence information and improving downstream prediction tasks such as biophysical, structural, and functional  ...  The high-accuracy prediction in both secondary and tertiary structural properties indicates that it is possible to make highly accurate prediction of protein structures without homologous sequences, the  ...  We also gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPU used for this research. The support of Shenzhen Science and Technology Program (Grant No.  ... 
doi:10.1101/2021.10.16.464622 fatcat:7ve2a6knvbbfboac4373tvmnbi
« Previous Showing results 1 — 15 out of 28,841 results