Filters








5,418 Hits in 3.0 sec

Protein Fold Pattern Recognition Using Bayesian Ensemble of RBF Neural Networks

Homa Baradaran Hashemi, Azadeh Shakery, Mahdi Pakdaman Naeini
2009 2009 International Conference of Soft Computing and Pattern Recognition  
Experimental results imply that RBF Neural Network holds better Correct Classification Rate (CCR) compared to other common classification methods such as MLP networks.  ...  Our experiments also show that the Bayesian fusion method can improve the correct classification rate of proteins up to 20% with the final CCR of 59% by reducing both bias and variance error of the RBF  ...  Artificial Neural Networks The neural network is a very applicable regression and classification tool which has the capability of representing complex relationships among inputs and outputs of a system  ... 
doi:10.1109/socpar.2009.91 dblp:conf/socpar/HashemiSN09 fatcat:34awm2regzditdc7nik7jhmqry

Adaptive machine learning for protein engineering [article]

Brian L. Hie, Kevin K. Yang
2021 arXiv   pre-print
However, when using these models to suggest new protein designs, one must deal with the vast combinatorial complexity of protein sequences.  ...  First, we discuss how to select sequences through a single round of machine-learning optimization.  ...  B.L.H. acknowledges the support of the Stanford Science Fellows program.  ... 
arXiv:2106.05466v2 fatcat:x724wxzwkbfh5pjdpakthqmow4

Machine learning in bioinformatics

Pedro Larrañaga, Borja Calvo, Roberto Santana, Concha Bielza, Josu Galdiano, Iñaki Inza, José A. Lozano, Rubén Armañanzas, Guzmán Santafé, Aritz Pérez, Victor Robles
2006 Briefings in Bioinformatics  
A review of deterministic and stochastic heuristics for optimization in the same domain is presented. Applications in genomics, proteomics, systems biology, evolution and text mining are also shown.  ...  Applications in genomics, proteomics, systems biology, evolution and text mining are also shown.  ...  Acknowledgements The authors are grateful to the anonymous reviewers for their comments, which have helped us to greatly improve this article.  ... 
doi:10.1093/bib/bbk007 pmid:16761367 fatcat:4oss26occvhkjnetcr3sesnkcu

Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction

QHwan Kim, Joon-Hyuk Ko, Sunghoon Kim, Nojun Park, Wonho Jhe, Pier Luigi Martelli
2021 Bioinformatics  
Second, we use a Bayesian neural network to make a robust model by estimating the data uncertainty.  ...  Results At first, we use transfer learning in encoding protein sequences with a pretrained model, which trains general sequence representations in an unsupervised manner.  ...  The Bayesian neural network model is also a good predictor for an unbalanced dataset, a common problem in real drug-protein interaction applications.  ... 
doi:10.1093/bioinformatics/btab346 pmid:33978713 pmcid:PMC8545317 fatcat:3g5ivbdlevb2hpyoxdxusrsyxa

Bayesian analysis, pattern analysis, and data mining in health care

Peter Lucas
2004 Current Opinion in Critical Care  
Recent findings: Bayesian networks and other probabilistic graphical models are beginning to emerge as methods for discovering patterns in biomedical data and also as a basis for the representation of  ...  Purpose of review: To discuss the current role of data mining and Bayesian methods in biomedicine and heath care, in particular critical care.  ...  Neural networks and support vector machines A neural network is a computational representation that takes as input a sequence of numbers, say encoded patient features, and outputs another sequence of numbers  ... 
doi:10.1097/01.ccx.0000141546.74590.d6 pmid:15385759 fatcat:dodreho355hthmsjyf2c5b3qh4

Protein Secondary Structure Prediction using Bayesian Inference method on Decision fusion algorithms

Somasheker Akkaladevi, Ajay K Katangur
2007 2007 IEEE International Parallel and Distributed Processing Symposium  
Prediction of protein secondary structure (alpha-helix, beta-sheet, coil) from primary sequence of amino acids is a very challenging task, and the problem has been approached from several angles.  ...  Previously research was performed in this field using several techniques such as neural networks, Simulated annealing (SA) and Genetic algorithms (GA) for improving the protein secondary structure prediction  ...  Initially we feed the sequence profiles of amino acids into the profilebased neural network to predict the protein secondary structure.  ... 
doi:10.1109/ipdps.2007.370430 dblp:conf/ipps/AkkaladeviK07 fatcat:hugcawgrizfqbf5dhq6htiodae

Predicting secondary structure of Oxidoreductase protein family using Bayesian Regularization Feed-forward Backpropagation ANN Technique

Brijesh Singh Yadav, Mayank Pokhariyal, Barkha Ratta, Gaurava Rai, Meeta Saxena
2010 Journal of Proteomics & Bioinformatics  
The neural network has been trained using Bayesian Regularization Feed-forward Backpropagation Neural Network Technique to predict the -helix, -sheet and coil regions of this protein family.  ...  Feed-forward neural network have been trained by analyzing windows of 25 parameters for predicting the central residue of protein sequence. PSI-BLAST has been used for multiple-sequence alignment.  ...  Work is also under way to improve the sequence-to-structure prediction produced by the neural network and can be applied to other families of protein.  ... 
doi:10.4172/jpb.1000137 fatcat:umngwr3gr5gv7lc5j7jvtxys3q

Bayesian neural network with pretrained protein embedding enhances prediction accuracy of drug-protein interaction [article]

QHwan Kim, Joon-Hyuk Ko, Sunghoon Kim, Nojun Park, Wonho Jhe
2020 arXiv   pre-print
Second, we use a Bayesian neural network to make a robust model by estimating the data uncertainty.  ...  The characterization of drug-protein interactions is crucial in the high-throughput screening for drug discovery.  ...  All authors participated in the discussion of the results. Q.K and W.J wrote the manuscript. All authors reviewed the manuscript.  ... 
arXiv:2012.08194v2 fatcat:52iiq2wacjgstbjz7bwpdp5be4

Intelligent mining of large-scale bio-data: Bioinformatics applications

Farahnaz Sadat Golestan Hashemi, Mohd Razi Ismail, Mohd Rafii Yusop, Mahboobe Sadat Golestan Hashemi, Mohammad Hossein Nadimi Shahraki, Hamid Rastegari, Gous Miah, Farzad Aslani
2017 Biotechnology & Biotechnological Equipment  
The present paper argues how artificial intelligence can assist bio-data analysis and gives an up-to-date review of different applications of bio-data mining.  ...  Today, there is a collection of a tremendous amount of bio-data because of the computerized applications worldwide.  ...  Applications References Back-propagation artificial neural networks [127] Bayesian networks [128] Bayesian confidence propagation neural networks [129] Feed forward neural networks [130] Flow  ... 
doi:10.1080/13102818.2017.1364977 fatcat:qmbiss53wfggtc7ayj2ysgt5rq

Classification and Sequential Pattern Analysis for Improving Managerial Efficiency and Providing Better Medical Service in Public Healthcare Centers

Keunho Choi, Sukhoon Chung, Hyunsill Rhee, Yongmoo Suh
2010 Healthcare Informatics Research  
Then, in the first stage of classification task, we used 5 classification techniques such as decision tree, artificial neural networks, logistic regression, Bayesian networks, and Naïve Bayes to build  ...  [22] analyzed protein sequence and classify proteins into the folds. That is, they extracted sequential patterns of proteins, which were then used to classify the unknown proteins. Chiang et al.  ...  Conflict of Interest No potential conflict of interest relevant to this article was reported.  ... 
doi:10.4258/hir.2010.16.2.67 pmid:21818426 pmcid:PMC3089866 fatcat:prnnqu3zl5dthmrse5tez3mj3u

The Development and Application of Bayesian Networks Used in Data Mining Under Big Data

JINGWEI ZHANG
2018 DEStech Transactions on Social Science Education and Human Science  
Therefore, this paper starts with the Bayesian networks, stretching out the Bayesian formula, Bayesian network technology, as well as the advantages of the combination of data mining and the Bayesian networks  ...  It also has great applications in the fields of the Internet, finance, natural language, biology, among which the Bayesian network has experienced significant development last year and has become a kind  ...  of lower nodes and branches. (3) Neural network method: neural network attempts to build the neural structure of human brain.  ... 
doi:10.12783/dtssehs/adess2017/17888 fatcat:cwkmc5glrjbdxolpiac6gf4rke

An Equivariant Bayesian Convolutional Network predicts recombination hotspots and accurately resolves binding motifs [article]

Gerton Lunter, Richard Brown
2018 bioRxiv   pre-print
We use our network to predict recombination hotspots from sequence, and identify high-resolution binding motifs for the recombination- initiation protein PRDM9, which were recently validated by high-resolution  ...  Results: Here we show how to combine equivariant networks, a general mathematical framework for handling exact symmetries in CNNs, with Bayesian dropout, a version of MC dropout suggested by a reinterpretation  ...  To improve on this situation, we showed how to combine equivariant neural networks (here, neural networks that exhibit exact reverse-complement symmetry) with Bayesian dropout.  ... 
doi:10.1101/351254 fatcat:xm2ic6zbjfctrmzzril4uku25q

An equivariant Bayesian convolutional network predicts recombination hotspots and accurately resolves binding motifs

Richard C Brown, Gerton Lunter, John Hancock
2018 Bioinformatics  
We use our network to predict recombination hotspots from sequence, and identify binding motifs for the recombination-initiation protein PRDM9 previously unobserved in this data, which were recently validated  ...  Convolutional neural networks (CNNs) have been tremendously successful in many contexts, particularly where training data are abundant and signal-to-noise ratios are large.  ...  Conflict of Interest: none declared.  ... 
doi:10.1093/bioinformatics/bty964 pmid:30481258 pmcid:PMC6596897 fatcat:qbiuy4toqrgxvaxbxfq2sffhfu

Comparison of reversible-jump Markov-chain-Monte-Carlo learning approach with other methods for missing enzyme identification

Bo Geng, Xiaobo Zhou, Jinmin Zhu, Y.S. Hung, Stephen T.C. Wong
2008 Journal of Biomedical Informatics  
Computational identification of missing enzymes plays a significant role in accurate and complete reconstruction of metabolic network for both newly sequenced and well-studied organisms.  ...  Robust full Bayesian learning for radial basis networks 2001;13:2359-407.]) is adopted to estimate the model order and the parameters.  ...  They would like to thank other members of the Life Science Imaging Group of the Center for Bioinformatics, Harvard Center for Neurodegeneration and Repair (HCNR) and Brigham and Women's Hospital, HMS for  ... 
doi:10.1016/j.jbi.2007.09.002 pmid:17950040 fatcat:clzp2ezn3jgh3pr3x5plmq5jna

Predicting solvent accessibility: Higher accuracy using Bayesian statistics and optimized residue substitution classes

Michael J. Thompson, Richard A. Goldstein
1996 Proteins: Structure, Function, and Bioinformatics  
These results demonstrate the applicability of this relatively simple Bayesian approach to structure prediction and illustrate the utility of the classification methodology previously developed to extract  ...  We introduce a novel Bayesian probabilistic method for predicting the solvent accessibilities of amino acid residues in globular proteins.  ...  We extend a general thanks to those who solve protein structures and make this information available, and to those who construct and maintain databases of protein sequences and structures.  ... 
doi:10.1002/(sici)1097-0134(199605)25:1<38::aid-prot4>3.3.co;2-h pmid:8727318 fatcat:grlqntgl3nfnrjdsxjylkn33o4
« Previous Showing results 1 — 15 out of 5,418 results