Filters








335 Hits in 6.4 sec

Optimization of a new score function for the detection of remote homologs

Maricel Kann, Bin Qian, Richard A. Goldstein
2000 Proteins: Structure, Function, and Bioinformatics  
We describe a new method of determining a score function, optimizing the ability to discriminate between homologs and non-homologs.  ...  We find that this new score function performs better than standard score functions for the identification of distant homologies. Proteins 2000;41:498 -503.  ...  ACKNOWLEDGMENTS We thank Stephen Altschul, Ting-Lan Chiu, William Pearson, Romesh Saigal, Stephen Bryant, and John Spouge for helpful discussions, and Todd Raeker and Michael Kitson for computational assistance  ... 
doi:10.1002/1097-0134(20001201)41:4<498::aid-prot70>3.0.co;2-3 pmid:11056037 fatcat:lexopv2ogvekbagi5bkrhstvxe

Performance evaluation of a new algorithm for the detection of remote homologs with sequence comparison

Maricel G. Kann, Richard A. Goldstein
2002 Proteins: Structure, Function, and Bioinformatics  
The studies were made with several score functions in current use including OPTIMA, a new score function originally developed to detect remote homologs with the Smith Waterman algorithm.  ...  The advantage of producing accurate score statistics with only a few simulations may overcome the small differences in performance and make this new algorithm suitable for detection of homologs in conjunction  ...  We also thank Stephen Altschul, Ralf Bundschuh, Yi-Kuo Yu, and Terry Hwa for providing us with preprints of their manuscripts and copies of their software.  ... 
doi:10.1002/prot.10117 pmid:12112703 fatcat:qqzrvts27nc7lclbxmvcbd5oka

Detection of homologous proteins by an intermediate sequence search

B. John
2004 Protein Science  
We developed a variant of the intermediate sequence search method (ISS new ) for detection and alignment of weakly similar pairs of protein sequences.  ...  In contrast, ISS new assigned a correct homolog as the top hit for 121 of these 1619 sequences, while incorrectly assigning homologs for only nine targets; it did not assign homologs for the remainder  ...  The publication costs of this article were defrayed in part by payment of page charges.  ... 
doi:10.1110/ps.03335004 pmid:14691221 pmcid:PMC2286512 fatcat:pf7iklb5dvdhlk4dvpxer3jsya

Protein sequence comparison and fold recognition: progress and good-practice benchmarking

Johannes Söding, Michael Remmert
2011 Current Opinion in Structural Biology  
In combination with a domaincentered approach to function and structure prediction, modern remote homology detection methods have a great and largely underexploited potential for elucidating protein functions  ...  Advances during the last few years include nonlinear scoring functions combining various sequence features, the use of sequence context information, and powerful new software packages.  ...  Acknowledgements We acknowledge financial support by the Deutsche Forschungsgemeinschaft and SFB646. We thank Julian Gough, Ceslovas Venclovas, and Jinbo Xu for comments and discussions.  ... 
doi:10.1016/j.sbi.2011.03.005 pmid:21458982 fatcat:m3xcvvmmerh6nbewcchdrd4nxy

morFeus: a web-based program to detect remotely conserved orthologs using symmetrical best hits and orthology network scoring

Ines Wagner, Michael Volkmer, Malvika Sharan, Jose M Villaveces, Felix Oswald, Vineeth Surendranath, Bianca H Habermann
2014 BMC Bioinformatics  
a network score for the resulting network of orthologs that is a measure of orthology independent of the E-value.  ...  Detecting remotely conserved orthologs of a protein using morFeus thus requires no manual intervention.  ...  Acknowledgements The authors thank Assa Yeroslaviz, Corinna Klein, Thomas Wiehe, James Stewart and Carolin Meharg for critical input and reading of the manuscript.  ... 
doi:10.1186/1471-2105-15-263 pmid:25096057 pmcid:PMC4137093 fatcat:gwblyxlqbjet5m4tukdni7wevm

MRFy: Remote Homology Detection for Beta-Structural Proteins Using Markov Random Fields and Stochastic Search

Noah M. Daniels, Andrew Gallant, Norman Ramsey, Lenore J. Cowen
2015 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
Both methods achieve improvements over the state of the art in remote homology detection for beta-structural protein folds.  ...  Given the amino acid sequence of a protein, researchers often infer its structure and function by finding homologous, or evolutionarily-related, proteins of known structure and function.  ...  for remote homology detection.  ... 
doi:10.1109/tcbb.2014.2344682 pmid:26357074 fatcat:6wo3cmou5jcqdhd4bm7hpm634m

Automatic Prediction of Protein 3D Structures by Probabilistic Multi-template Homology Modeling

Armin Meier, Johannes Söding, Nir Ben-Tal
2015 PLoS Computational Biology  
By far the most widely used computational approach for protein structure prediction relies on detecting a homologous relationship with a protein of known structure and using this protein as a template  ...  Our new theoretical approach allowed us to improve the quality of homology models by 11% over a baseline single-template approach and by 6.5% over a multi-template approach.  ...  Author Contributions Conceived and designed the experiments: JS AM. Analyzed the data: AM. Wrote the paper: JS AM.  ... 
doi:10.1371/journal.pcbi.1004343 pmid:26496371 pmcid:PMC4619893 fatcat:2cszcebyg5fllp4dqf72ozlsna

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  
Semi-supervised learning for proteins has emerged as an important paradigm due to the high cost of acquiring supervised protein labels, but the current literature is fragmented when it comes to datasets  ...  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

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
This gap in performance suggests a huge opportunity for innovative architecture design and improved modeling paradigms that better capture the signal in biological sequences.  ...  To facilitate progress in this field, we introduce the Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein  ...  We thank the AWS Educate program for providing us with the resources to train our models.  ... 
doi:10.1101/676825 fatcat:hd7zpclltnbq3ifruwwa7ppu3u

PFASUM: a substitution matrix from Pfam structural alignments

Frank Keul, Martin Hess, Michael Goesele, Kay Hamacher
2017 BMC Bioinformatics  
These tasks usually require a substitution matrix for modeling evolutionary substitution events derived from a set of aligned sequences.  ...  We address these aspects by presenting a new substitution matrix series called PFASUM.  ...  Edgar for providing a convenient collection of MSA tools and benchmark datasets at www.drive5.com. We also thank M. Vingron and T. Müller for making the VTML source code available to us. Funding  ... 
doi:10.1186/s12859-017-1703-z pmid:28583067 pmcid:PMC5460430 fatcat:3lowthphnbfwvfhuubzfjfybiu

The ranging of amino acids substitution matrices of various types in accordance with the alignment accuracy criterion

Valery Polyanovsky, Alexander Lifanov, Natalia Esipova, Vladimir Tumanyan
2020 BMC Bioinformatics  
Optimization of a combination of matrices and the penalty parameters was carried out for local and global alignment on the values of penalty function parameters.  ...  The quality of this procedure is determined by the substitution matrix and parameters of the insertion-deletion penalty function.  ...  Authors' contributions VP and VT jointly developed a concept of the paper. VP performed the data generation, alignment and analysis of results, and wrote the manuscript.  ... 
doi:10.1186/s12859-020-03616-0 pmid:32921315 fatcat:4mtshqc5gnabtjtkdeg3em22eq

Unified rational protein engineering with sequence-only deep representation learning [article]

Ethan C. Alley, Grigory Khimulya, Surojit Biswas, Mohammed AlQuraishi, George M. Church
2019 bioRxiv   pre-print
AbstractRational protein engineering requires a holistic understanding of protein function.  ...  Our data-driven approach reaches near state-of-the-art or superior performance predicting stability of natural and de novo designed proteins as well as quantitative function of molecularly diverse mutants  ...  To make our model comparable with the scores of previously developed remote homology detection models in the literature, we used two standard metrics -ROC score (normalized area under the receiver operating  ... 
doi:10.1101/589333 fatcat:2i2u2cjre5dgbbo4ndadhtyfi4

Gradient-based optimization of hyperparameters for base-pairing profile local alignment kernels

Kengo Sato, Yutaka Saito, Yasubumi Sakakibara
2009 Genome Informatics Series  
We have recently proposed novel kernel functions, called base-pairing profile local alignment (BPLA) kernels for discrimination and detection of functional RNA sequences using SVMs.  ...  Our experiments show that the proposed method can find a nearly optimal set of parameters much faster than the grid search on all parameter combinations.  ...  Acknowledgments This work was supported in part by a grant from "Functional RNA Project" funded by the New Energy and Industrial Technology Development Organization (NEDO) of Japan, and was also supported  ... 
pmid:20180268 fatcat:6mnro4t5djcb7c4gqpgudjz3pa

HINT-KB: The Human Interactome Knowledge Base [chapter]

Konstantinos Theofilatos, Christos Dimitrakopoulos, Dimitrios Kleftogiannis, Charalampos Moschopoulos, Stergios Papadimitriou, Spiros Likothanassis, Seferina Mavroudi
2012 IFIP Advances in Information and Communication Technology  
for their retrieval, estimates a set of features of interest and computes a confidence score for every candidate protein interaction using a modern computational hybrid methodology.  ...  Proteins and their interactions are considered to play a significant role in many cellular processes. The identification of Protein-Protein interactions (PPIs) in human is an open research area.  ...  This research has been co-financed by the European Union (European Social Fund -ESF) and Greek national funds through the Operational Program "Education and Lifelong Learning" of the National Strategic  ... 
doi:10.1007/978-3-642-33412-2_63 fatcat:a3cdjyfzjncu5blspxdb5nus5y

Extraction and Three-Dimensional Reconstruction of Isolated Buildings in Urban Scenes From High-Resolution Optical and SAR Spaceborne Images

Hélène Sportouche, Florence Tupin, Léonard Denise
2011 IEEE Transactions on Geoscience and Remote Sensing  
A qualification of each reconstructed building by a score of confidence is then proposed. Good results of building detection are obtained, and relevant height estimations are retrieved.  ...  A sequence of processing, exploring the complementarities of both optical and SAR data, is developed for building reconstruction.  ...  In [47] , a new process for the detection of building outlines, based on the fusion of optical and SAR features, is presented.  ... 
doi:10.1109/tgrs.2011.2132727 fatcat:bp6jab4kc5beba3fxhbcoj3lnm
« Previous Showing results 1 — 15 out of 335 results