Cargando…

Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network

The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes...

Descripción completa

Detalles Bibliográficos
Autores principales: Naik, Pradeep Kumar, Mishra, Viplav Shankar, Gupta, Mukul, Jaiswal, Kunal
Formato: Texto
Lenguaje:English
Publicado: Biomedical Informatics Publishing Group 2007
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2248448/
https://www.ncbi.nlm.nih.gov/pubmed/18288334
_version_ 1782151007769198592
author Naik, Pradeep Kumar
Mishra, Viplav Shankar
Gupta, Mukul
Jaiswal, Kunal
author_facet Naik, Pradeep Kumar
Mishra, Viplav Shankar
Gupta, Mukul
Jaiswal, Kunal
author_sort Naik, Pradeep Kumar
collection PubMed
description The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes and non-enzymes from its amino-acid sequence using artificial neural network (ANN). Using 61 sequence derived features alone we have been able to achieve 79 percent correct prediction of enzymes/non-enzymes (in the set of 660 proteins). For the complete set of 61 parameters using 5-fold cross-validated classification, ANN model reveal a superior model (accuracy = 78.79 plus or minus 6.86 percent, Q(pred) = 74.734 plus or minus 17.08 percent, sensitivity = 84.48 plus or minus 6.73 percent, specificity = 77.13 plus or minus 13.39 percent). The second module of ANN is based on PSSM matrix. Using the same 5-fold cross-validation set, this ANN model predicts enzymes/non-enzymes with more accuracy (accuracy = 80.37 plus or minus 6.59 percent, Q(pred) = 67.466 plus or minus 12.41 percent, sensitivity = 0.9070 plus or minus 3.37 percent, specificity = 74.66 plus or minus 7.17 percent).
format Text
id pubmed-2248448
institution National Center for Biotechnology Information
language English
publishDate 2007
publisher Biomedical Informatics Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-22484482008-02-20 Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network Naik, Pradeep Kumar Mishra, Viplav Shankar Gupta, Mukul Jaiswal, Kunal Bioinformation Prediction Model The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes and non-enzymes from its amino-acid sequence using artificial neural network (ANN). Using 61 sequence derived features alone we have been able to achieve 79 percent correct prediction of enzymes/non-enzymes (in the set of 660 proteins). For the complete set of 61 parameters using 5-fold cross-validated classification, ANN model reveal a superior model (accuracy = 78.79 plus or minus 6.86 percent, Q(pred) = 74.734 plus or minus 17.08 percent, sensitivity = 84.48 plus or minus 6.73 percent, specificity = 77.13 plus or minus 13.39 percent). The second module of ANN is based on PSSM matrix. Using the same 5-fold cross-validation set, this ANN model predicts enzymes/non-enzymes with more accuracy (accuracy = 80.37 plus or minus 6.59 percent, Q(pred) = 67.466 plus or minus 12.41 percent, sensitivity = 0.9070 plus or minus 3.37 percent, specificity = 74.66 plus or minus 7.17 percent). Biomedical Informatics Publishing Group 2007-12-05 /pmc/articles/PMC2248448/ /pubmed/18288334 Text en © 2007 Biomedical Informatics Publishing Group This is an open-access article, which permits unrestricted use, distribution, and reproduction in any medium, for non-commercial purposes, provided the original author and source are credited.
spellingShingle Prediction Model
Naik, Pradeep Kumar
Mishra, Viplav Shankar
Gupta, Mukul
Jaiswal, Kunal
Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title_full Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title_fullStr Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title_full_unstemmed Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title_short Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network
title_sort prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and pssm matrix using artificial neural network
topic Prediction Model
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2248448/
https://www.ncbi.nlm.nih.gov/pubmed/18288334
work_keys_str_mv AT naikpradeepkumar predictionofenzymesandnonenzymesfromproteinsequencesbasedonsequencederivedfeaturesandpssmmatrixusingartificialneuralnetwork
AT mishraviplavshankar predictionofenzymesandnonenzymesfromproteinsequencesbasedonsequencederivedfeaturesandpssmmatrixusingartificialneuralnetwork
AT guptamukul predictionofenzymesandnonenzymesfromproteinsequencesbasedonsequencederivedfeaturesandpssmmatrixusingartificialneuralnetwork
AT jaiswalkunal predictionofenzymesandnonenzymesfromproteinsequencesbasedonsequencederivedfeaturesandpssmmatrixusingartificialneuralnetwork