7,142 Hits in 4.0 sec

Multi-class protein fold classification using a new ensemble machine learning approach

Aik Choon Tan, David Gilbert, Yves Deville
2003 Genome Informatics Series  
classifiers, and we illustrate this idea in classifying multi-class SCOP protein fold data.  ...  We have compared our approach with PART and show that our method improves the sensitivity of the classifier in protein fold classification.  ...  Acknowledgments We would like to thank Gilleain Torrance and Ali Al-Shahib for their useful comments. AC Tan was funded by a University of Glasgow studentship.  ... 
pmid:15706535 fatcat:mxasp4wvtzg63me6pabnanp57e

Mining protein database using machine learning techniques

Renata da Silva Camargo, Mahesan Niranjan
2008 Journal of Integrative Bioinformatics  
With a large amount of information relating to proteins accumulating in databases widely available online, it is of interest to apply machine learning techniques that, by extracting underlying statistical  ...  cross validation and feature selection based studies quantify the average limits and uncertainties with which such predictions may be made.  ...  There have been other similar attempts to use machine learning methods to automatically associate proteins to SCOP families.  ... 
doi:10.2390/biecoll-jib-2008-106 pmid:20134071 fatcat:3rc254v7zvhrzjqoegheb73kra

Mining Protein Databases using Machine Learning Techniques

Renata da Silva Camargo, Mahesan Niranjan
2008 Journal of Integrative Bioinformatics  
and functional relationships between pairs of proteins, and from extensive cross validation and feature selection based studies quantify the average limits and uncertainties with which such predictions  ...  SummaryWith a large amount of information relating to proteins accumulating in databases widely available online, it is of interest to apply machine learning techniques that, by extracting underlying statistical  ...  There have been other similar attempts to use machine learning methods to automatically associate proteins to SCOP families.  ... 
doi:10.1515/jib-2008-106 fatcat:q362fesju5fznjlxcergnmy6li

Recent Progress in Machine Learning-Based Methods for Protein Fold Recognition

Leyi Wei, Quan Zou
2016 International Journal of Molecular Sciences  
In this review, we conduct a comprehensive survey of recent computational methods, especially machine learning-based methods, for protein fold recognition.  ...  With such a great number of proteins, the use of experimental techniques to determine protein folding is extremely difficult because these techniques are time consuming and expensive.  ...  Machine learning aims to build a prediction model by learning the differences between different protein fold categories and use the learned model to automatically assign a query protein to a specific protein  ... 
doi:10.3390/ijms17122118 pmid:27999256 pmcid:PMC5187918 fatcat:epqch4vj3nhr7dlgfieysqu2ta

A Study of Hierarchical and Flat Classification of Proteins

Arthur Zimek, Fabian Buchwald, Eibe Frank, Stefan Kramer
2010 IEEE/ACM Transactions on Computational Biology & Bioinformatics  
Automatic classification of proteins using machine learning is an important problem that has received significant attention in the literature.  ...  One feature of this problem is that expert-defined hierarchies of protein classes exist and can potentially be exploited to improve classification performance.  ...  The aim is to build a classification model using machine learning techniques that can be used to predict the class label for a new instance (i.e. protein).  ... 
doi:10.1109/tcbb.2008.104 pmid:20671325 fatcat:gdpm3ixtvbdnrik45ocyqfkvsu

Supervised machine learning algorithms for protein structure classification

Pooja Jain, Jonathan M. Garibaldi, Jonathan D. Hirst
2009 Computational biology and chemistry  
We explore automation of protein structural classification using supervised machine learning methods on a set of 11,360 pairs of protein domains (up to 35% sequence identity) consisting of three secondary  ...  The boosted random forest, a collection of decision trees, is found to be the most accurate, with a cross-validated accuracy of 97.0% and F-measures of 0.97, 0.85, 0.93 and 0.98 for classification of proteins  ...  We thank Craig Bruce for technical assistance. PJ is supported by the BIOPTRAIN Marie Curie Action MEST-CT-2004-7597 under the Sixth Framework Programme of the European Community.  ... 
doi:10.1016/j.compbiolchem.2009.04.004 pmid:19473879 fatcat:3iyyaliujjfhtcwn3i3xfn2n3y

Prediction of protein function using a deep convolutional neural network ensemble

Evangelia I. Zacharaki
2017 PeerJ Computer Science  
learning techniques for automatic protein function prediction.  ...  Each of the multi-channel feature maps is introduced into a deep convolutional neural network (CNN) for function prediction and the outputs are fused through support vector machines or a correlation-based  ...  N Paragios from the Center for Visual Computing, CentraleSupélec, Paris, for providing the means to complete this study and Dr.  ... 
doi:10.7717/peerj-cs.124 fatcat:gozkaelzgvhyhb2tp2cdl7ayu4

Multi-Site Protein Subcellular Localization Based on Deep Convolutional Neural Network

Hanhan Cong, Hong Liu, Yuehui Chen, Yaou Zhao, Lei Wang
2019 Journal of Nutritional Biology  
Besides ensemble learning and features fusion are effective for improving classification result.  ...  In order to further improve the classification result of the algorithm, it was combined ensemble learning and features fusion.  ...  At present, the machine learning algorithms for multisite protein subcellular localization include multi-label k-nearest neighbor algorithm (ML-kNN) [16] , multi-label support vector machine algorithm  ... 
doi:10.18314/jnb.v5i1.1580 fatcat:ice4fvofsjh6vgxmowxd4vgik4

Protein fold classification with Grow-and-Learn network

Özlem POLAT, Zümray DOKUR
2017 Turkish Journal of Electrical Engineering and Computer Sciences  
Protein fold classification is an important subject in computational biology and 8 a compelling work from the point of machine learning.  ...  To deal with such a challenging 9 problem, in this study, we propose a solution method for the classification of protein folds 10 using Grow and Learn neural network (GAL) together with one-versus-others  ...  et al. [23] proposed a novel 20 margin-based ensemble classifier, called MarFold, for multi-class protein fold 21 recognition task where multiple heterogeneous feature spaces were available.  ... 
doi:10.3906/elk-1506-126 fatcat:bkodnbzhe5hizbwjlzqsgvxtdy

ProFET: Feature engineering captures high-level protein functions

Dan Ofer, Michal Linial
2015 Bioinformatics  
We hypothesize that a universal feature engineering approach can yield classification of high-level functions and unified properties when combined with machine learning approaches, without requiring external  ...  ProFET was applied on 17 established and novel protein benchmark datasets involving classification for a variety of binary and multi-class tasks. The results show state of the art performance.  ...  Acknowledgements We thank Michael Doron for extensive collaboration, aid and programming expertise in setting up the framework. Nadav Rappoprt supported Psi-Blast comparisons.  ... 
doi:10.1093/bioinformatics/btv345 pmid:26130574 fatcat:fp6xosy23bf2binhvmrbu6gbz4

Detecting experimental techniques and selecting relevant documents for protein-protein interactions from biomedical literature

Xinglong Wang, Rafal Rak, Angelo Restificar, Chikashi Nobata, CJ Rupp, Riza Theresa B Batista-Navarro, Raheel Nawaz, Sophia Ananiadou
2011 BMC Bioinformatics  
Conclusions: Our novel approach that converts the multi-class, multi-label classification problem to a binary classification problem showed much promise in IMT.  ...  ACT aimed to automatically select relevant documents for PPI curation, whereas the goal of IMT was to recognise the methods used in experiments for identifying the interactions in full-text articles.  ...  He also worked on text cleaning, linguistic pre-processing and feature extraction. RR worked on the m-SVM method for IMT, the thresholding strategies, and preliminary versions of the ACT systems.  ... 
doi:10.1186/1471-2105-12-s8-s11 pmid:22151769 pmcid:PMC3269934 fatcat:qmfgoxabnbd5nctdbokyn7jlfq

A Critical Study of Selected Classification Algorithms for Liver Disease Diagnosis

Bendi Venkata Ramana, M.Surendra Prasad Babu, N.B Venkateswarlu
2011 International Journal of Database Management Systems  
Automatic classification tools may reduce burden on doctors. This paper evaluates the selected classification algorithms for the classification of some liver patient datasets.  ...  The classification algorithms considered here are Naïve Bayes classifier, C4.5, Back propagation Neural Network algorithm, and Support Vector Machines.  ...  ACKNOWLEDGEMENTS We take this opportunity with much pleasure to thank Dr. Bevera. Lakshmana Rao for his help during the collection of data and in labeling samples.  ... 
doi:10.5121/ijdms.2011.3207 fatcat:m2edofobabbslkz55vwt7mbwcq

Design of the 2015 ChaLearn AutoML challenge

Isabelle Guyon, Kristin Bennett, Gavin Cawley, Hugo Jair Escalante, Sergio Escalera, Tin Kam Ho, Nuria Macia, Bisakha Ray, Mehreen Saeed, Alexander Statnikov, Evelyne Viegas
2015 2015 International Joint Conference on Neural Networks (IJCNN)  
ChaLearn is organizing for IJCNN 2015 an Automatic Machine Learning challenge (AutoML) to solve classification and regression problems from given feature representations, without any human intervention  ...  This is a challenge with code submission: the code submitted can be executed automatically on the challenge servers to train and test learning machines on new datasets.  ...  [y ik ] in {0, 1}, for multi-class or multi-label classification problems (one per class k).  ... 
doi:10.1109/ijcnn.2015.7280767 dblp:conf/ijcnn/GuyonBCEEHMRSSV15 fatcat:c2yo3f73bzcfnntoluvcm454nu

PrESOgenesis: A two-layer multi-label predictor for identifying fertility-related proteins using support vector machine and pseudo amino acid composition approach

Mohammad Reza Bakhtiarizadeh, Maryam Rahimi, Abdollah Mohammadi-Sangcheshmeh, Vahid Shariati J, Seyed Alireza Salami
2018 Scientific Reports  
Moreover, by using feature selection methods, important properties of fertility-related proteins were identified that allowed for their accurate classification.  ...  The results of five-fold cross validation, as well as the independent test demonstrated that this method is capable of predicting the fertility-related proteins and their classes with accuracy of more  ...  Feature importance. In machine-learning methods, not all features are equally important for the performance of the trained model, especially for high dimension data.  ... 
doi:10.1038/s41598-018-27338-9 pmid:29899414 pmcid:PMC5998058 fatcat:qkkafaqhdjblbjfmnpfbyn5vsi

A high performance profile-biomarker diagnosis for mass spectral profiles

Henry Han
2011 BMC Systems Biology  
We propose multi-resolution independent component analysis, a novel feature selection algorithm to tackle the large dimensionality of mass spectra, by following our local and global feature selection framework  ...  Methods: In this study, we present a novel machine learning approach to achieve a clinical level disease diagnosis for mass spectral data.  ...  Acknowledgements The author wants to thank the anonymous reviewers for their valuable comments in improving this manuscript.  ... 
doi:10.1186/1752-0509-5-s2-s5 pmid:22784576 pmcid:PMC3287485 fatcat:ab22i7wimvhpbkvzblrzhgdihe
« Previous Showing results 1 — 15 out of 7,142 results