15,390 Hits in 7.0 sec

Using Short-Range Interactions and Simulated Genetic Strategy to Improve the Protein Contact Map Prediction [chapter]

Cosme E. Santiesteban Toca, Milton García-Borroto, Jesus S. Aguilar Ruiz
2012 Lecture Notes in Computer Science  
The proposed solution predicts protein contact maps by the combination of a forest of 400 decision trees with an input codification for short-range interactions and a genetic-based edition method.  ...  For a globulin data set the method can predict contacts with a maximal accuracy of 43%.  ...  Model Architecture On previous papers, decision trees have been proved to be a successful method for prediction of contact maps of proteins [15, 16] .  ... 
doi:10.1007/978-3-642-31149-9_17 fatcat:bz54pyh675achg6elj7pwyti6a

Predicting protein contact maps by bagging decision trees

Chuqiao Ren, Brian R. King
2014 Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics - BCB '14  
Instead, many methods aim to predict a protein contact map from sequence. We introduce an ensemble method for protein contact map prediction based on bagging multiple decision trees.  ...  A random sampling method is used to address the large class imbalance in contact maps. Our results show that our technique performs favorably against existing methods.  ...  We introduce a prediction method based on the C4.5 decision tree method [6] .  ... 
doi:10.1145/2649387.2660818 dblp:conf/bcb/RenK14 fatcat:2yk4p7ymozahzkhsfauwzyass4

Improving the Efficiency of MECoMaP: A Protein Residue-Residue Contact Predictor [chapter]

Alfonso E. Márquez Chamorro, Federico Divina, Jesús S. Aguilar-Ruiz, Cosme E. Santiesteban Toca
2013 Lecture Notes in Computer Science  
This work proposes an improvement of the multi-objective evolutionary method for the protein residue-residue contact prediction called MECoMaP.  ...  This method bases its prediction on physicochemical properties of amino acids, structural features and evolutionary information of the proteins.  ...  An useful, and commonly used, representation for protein 3D structure is the protein contact map, which represents binary proximities (contact or noncontact) between each pair of amino acids of a protein  ... 
doi:10.1007/978-3-642-41827-3_21 fatcat:gvrasfysdnaclcmhjyhunfass4

Building Protein Atomic Models from Cryo-EM Density Maps and Residue Co-Evolution

Guillaume Bouvier, Benjamin Bardiaux, Riccardo Pellarin, Chiara Rapisarda, Michael Nilges
2022 Biomolecules  
To tackle these issues, we have developed a graph-based method to thread most of the C-α trace of the protein backbone into the EM density map.  ...  By complementing experimental EM maps with contact predictions from sequence co-evolutionary information, we demonstrate that this approach can correctly segment EM maps into individual subunits and assign  ...  Acknowledgments: We would like to thank Rémi Fronzes (IECB, Bordeaux) for his contribution to the segmentation of the T6SS baseplate cryo-EM density map.  ... 
doi:10.3390/biom12091290 pmid:36139128 pmcid:PMC9496541 fatcat:4gbloca3n5duppyn7crzjtb4im

ROSEFW-RF: The winner algorithm for the ECBDL'14 big data competition: An extremely imbalanced big data bioinformatics problem

Isaac Triguero, Sara del Río, Victoria López, Jaume Bacardit, José M. Benítez, Francisco Herrera
2015 Knowledge-Based Systems  
Moreover, in many of these problems such as contact map prediction, the problem tackled in this paper, it is difficult to collect representative positive examples.  ...  In this work we describe the methodology that won the ECBDL'14 big data challenge for a bioinformatics big data problem.  ...  Contact map prediction Contact Map (CM) prediction is a bioinformatics (and specifically a protein structure prediction) classification task that is an ideal test case for a big data challenge for several  ... 
doi:10.1016/j.knosys.2015.05.027 fatcat:iwuatu7hrbcrbcfgaczzz52fiy

Feature Selection Methods for Improving Protein Structure Prediction with Rosetta

Ben Blum, Michael I. Jordan, David Kim, Rhiju Das, Philip Bradley, David Baker
2007 Neural Information Processing Systems  
In this paper we present a resampling technique for structure prediction of small alpha/beta proteins using Rosetta.  ...  Rosetta is one of the leading algorithms for protein structure prediction today. It is a Monte Carlo energy minimization method requiring many random restarts to find structures with low energy.  ...  In the second (referred to henceforth as "decision- tree"), three subpopulations were defined for each protein using a decision tree, and within each subpopulation 15 LARS-predicted torsion features were  ... 
dblp:conf/nips/BlumJKDBB07 fatcat:eknti2s3sbc3ndz6voqsowpus4

Protein structural features predict responsiveness to pharmacological chaperone treatment for three lysosomal storage disorders

Jaie Woodard, Wei Zheng, Yang Zhang, Piero Fariselli
2021 PLoS Computational Biology  
Using both a single decision tree and an advanced machine learning approach based on the larger Fabry dataset, we correctly predict responsiveness of three Gaucher disease variants, and we provide predictions  ...  Many variants are predicted to be responsive to treatment, suggesting that drug-based treatments may be effective for a number of variants in Gaucher disease.  ...  Acknowledgments The authors thank Cameron Fen for help with Auto-ML, Eric Bell for helpful discussions, and Dr. Gil Omenn for comments on the manuscript.  ... 
doi:10.1371/journal.pcbi.1009370 pmid:34529671 pmcid:PMC8478239 fatcat:cemjwzhewzc3po634yfwgrwmne


2006 Biocomputing 2007  
LTHREADER uses a profile of secondary structure and solvent accessibility predictions with residue contact maps to guide and constrain alignments.  ...  Using a decision tree classifier and low-throughput experimental data for training, it combines information inferred from statistical interaction potentials, energy functions, correlated mutations and  ...  Thanks to Andrew Macdonnell, Rohit Singh, and Jinbo Xu for helpful discussions and computational assistance. Pacific Symposium on Biocomputing 12:64-75(2007)  ... 
doi:10.1142/9789812772435_0007 fatcat:si3iwkmtyrc7rcnke3brlr3nce

A comparative study of machine-learning methods to predict the effects of single nucleotide polymorphisms on protein function

V.G. Krishnan, D.R. Westhead
2003 Bioinformatics  
Here, two different machine-learning methods, decision trees and support vector machines (SVMs), are applied for the first time to this problem.  ...  SVMs show better generalization performance, but decision trees have the advantage of generating interpretable rules with robust estimates of prediction confidence.  ...  ACKNOWLEDGEMENTS We thank Ian Hope, Matthew Woodwark and Cary O'Donnell for valuable discussions.  ... 
doi:10.1093/bioinformatics/btg297 pmid:14630648 fatcat:5r375gvcszerbj2zc6fxgxoouq

Structure-Based Function Prediction using Graph Convolutional Networks [article]

Vladimir Gligorijevic, P. Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Kyunghyun Cho, Tommi Vatanen, Daniel Berenberg, Bryn C Taylor, Ian M Fisk, Ramnik J Xavier, Rob Knight, Richard A Bonneau
2019 bioRxiv   pre-print
We use our method to annotate all proteins in the PDB, making several new confident function predictions spanning both fold and function trees.  ...  Using class activation mapping, we can automatically identify structural regions at the residue-level that lead to each function prediction for every protein confidently predicted, advancing site-specific  ...  Discussion In this work, we proposed a novel deep learning-based method for predicting protein function from both protein sequences and contact map representations of protein structures.  ... 
doi:10.1101/786236 fatcat:ymvyktg4ljac7b2i62kx2uwhuu

Structural Protein Function Prediction - A Comprehensive Review

Huda A. Maghawry, Mostafa G. M. Mostafa, Mohamed H. Abdul-Aziz, Tarek F. Gharib
2015 International Journal of Modern Education and Computer Science  
The large amounts of available protein structures emerges the need for computational methods for protein function prediction.  ...  However, structure-based computational methods provide additional accuracy and reliability of protein function prediction.  ...  [58] used contact maps to predict protein folds.  ... 
doi:10.5815/ijmecs.2015.10.07 fatcat:xvvm2j7zjranhngr2eqpx7jf4y

Accurate prediction of helix interactions and residue contacts in membrane proteins

Peter Hönigschmid, Dmitrij Frishman
2016 Journal of Structural Biology  
In this work we present a new contact 20 prediction method for a-helical transmembrane proteins, MemConP, in which evolutionary couplings 21 are combined with a machine learning approach.  ...  For both methods an accelerated implementation called 76 Freecontact (Kajan et al., 2014) is available. Recently improved methods to predict residue contacts 77  ...  The output of the random forest is a value between 0 and 1, representing 209 the fraction of decision trees voting for the residue pair to be in contact.  ... 
doi:10.1016/j.jsb.2016.02.005 pmid:26851352 fatcat:f4aww3vbnrhwno2gihlj3wryqe

A new ensemble coevolution system for detecting HIV-1 protein coevolution

Guangdi Li, Kristof Theys, Jens Verheyen, Andrea-Clemencia Pineda-Peña, Ricardo Khouri, Supinya Piampongsant, Mónica Eusébio, Jan Ramon, Anne-Mieke Vandamme
2015 Biology Direct  
This system allowed combinations of different sequence-based methods for coevolution predictions.  ...  Using HIV-1 protein structures and experimental data, we evaluated the performance of individual and combined sequence-based methods in the prediction of HIV-1 intra-and inter-protein coevolution.  ...  Acknowledgements We thank Fossie Ferreira and Jasper Edgar Neggers for technical assistance and valuable contributions to the analysis. This work was supported by the  ... 
doi:10.1186/s13062-014-0031-8 pmid:25564011 pmcid:PMC4332441 fatcat:ygddtqpshfaozltgrlyncwjgky

LTHREADER: Prediction of extracellular ligand-receptor interactions in cytokines using localized threading

Vinay Pulim, Jadwiga Bienkowska, Bonnie Berger
2008 Protein Science  
LTHREADER uses a profile of secondary structure and solvent accessibility predictions with residue contact maps to guide and constrain alignments.  ...  Using a decision tree classifier and low-throughput experimental data for training, it combines information inferred from statistical interaction potentials, energy functions, correlated mutations, and  ...  Acknowledgments We thank Jinbo Xu for providing assistance with RAPTOR and suggesting the use of PSI-BLAST for localized threading.  ... 
doi:10.1110/ps.073178108 pmid:18096641 pmcid:PMC2222721 fatcat:expvchvnjjemzbqxua4nfevgeq

Integrated structure-based protein interface prediction

M. Walder, E. Edelstein, M. Carroll, S. Lazarev, J. E. Fajardo, A. Fiser, R. Viswanathan
2022 BMC Bioinformatics  
ISPIP is a method that integrates these approaches through simple linear or logistic regression models and more complex decision tree models.  ...  Results We describe the development of an integrated method for protein interface prediction (ISPIP) to explore the hypothesis that the efficacy of a computational prediction method of protein binding  ...  The other tree-based model employed for ISPIP involved gradient boosting. Like RF, gradient boosting constructs an ensemble of decision trees to generate an interface probability score.  ... 
doi:10.1186/s12859-022-04852-2 pmid:35879651 pmcid:PMC9316365 fatcat:e2yij5capzbnhkgtntcxkprtbe
« Previous Showing results 1 — 15 out of 15,390 results