Shou-Hui Guo1, En-Ze Deng1, Li-Qin Xu1, Hui Ding1, Hao Lin2, Wei Chen2, Kuo-Chen Chou2. 1. Key Laboratory for Neuro-Information of Ministry of Education, Center of Bioinformatics, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China, Gordon Life Science Institute, Belmont, Massachusetts, USA, Department of Physics, School of Sciences, Center for Genomics and Computational Biology, Hebei United University, Tangshan 063000, China and Center of Excellence in Genomic Medicine Research (CEGMR), King Abdulaziz University, Jeddah, Saudi Arabia. 2. Key Laboratory for Neuro-Information of Ministry of Education, Center of Bioinformatics, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China, Gordon Life Science Institute, Belmont, Massachusetts, USA, Department of Physics, School of Sciences, Center for Genomics and Computational Biology, Hebei United University, Tangshan 063000, China and Center of Excellence in Genomic Medicine Research (CEGMR), King Abdulaziz University, Jeddah, Saudi ArabiaKey Laboratory for Neuro-Information of Ministry of Education, Center of Bioinformatics, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu 610054, China, Gordon Life Science Institute, Belmont, Massachusetts, USA, Department of Physics, School of Sciences, Center for Genomics and Computational Biology, Hebei United University, Tangshan 063000, China and Center of Excellence in Genomic Medicine Research (CEGMR), King Abdulaziz University, Jeddah, Saudi Arabia.
Abstract
MOTIVATION: Nucleosome positioning participates in many cellular activities and plays significant roles in regulating cellular processes. With the avalanche of genome sequences generated in the post-genomic age, it is highly desired to develop automated methods for rapidly and effectively identifying nucleosome positioning. Although some computational methods were proposed, most of them were species specific and neglected the intrinsic local structural properties that might play important roles in determining the nucleosome positioning on a DNA sequence. RESULTS: Here a predictor called 'iNuc-PseKNC' was developed for predicting nucleosome positioning in Homo sapiens, Caenorhabditis elegans and Drosophila melanogaster genomes, respectively. In the new predictor, the samples of DNA sequences were formulated by a novel feature-vector called 'pseudo k-tuple nucleotide composition', into which six DNA local structural properties were incorporated. It was observed by the rigorous cross-validation tests on the three stringent benchmark datasets that the overall success rates achieved by iNuc-PseKNC in predicting the nucleosome positioning of the aforementioned three genomes were 86.27%, 86.90% and 79.97%, respectively. Meanwhile, the results obtained by iNuc-PseKNC on various benchmark datasets used by the previous investigators for different genomes also indicated that the current predictor remarkably outperformed its counterparts. AVAILABILITY: A user-friendly web-server, iNuc-PseKNC is freely accessible at http://lin.uestc.edu.cn/server/iNuc-PseKNC.
MOTIVATION: Nucleosome positioning participates in many cellular activities and plays significant roles in regulating cellular processes. With the avalanche of genome sequences generated in the post-genomic age, it is highly desired to develop automated methods for rapidly and effectively identifying nucleosome positioning. Although some computational methods were proposed, most of them were species specific and neglected the intrinsic local structural properties that might play important roles in determining the nucleosome positioning on a DNA sequence. RESULTS: Here a predictor called 'iNuc-PseKNC' was developed for predicting nucleosome positioning in Homo sapiens, Caenorhabditis elegans and Drosophila melanogaster genomes, respectively. In the new predictor, the samples of DNA sequences were formulated by a novel feature-vector called 'pseudo k-tuple nucleotide composition', into which six DNA local structural properties were incorporated. It was observed by the rigorous cross-validation tests on the three stringent benchmark datasets that the overall success rates achieved by iNuc-PseKNC in predicting the nucleosome positioning of the aforementioned three genomes were 86.27%, 86.90% and 79.97%, respectively. Meanwhile, the results obtained by iNuc-PseKNC on various benchmark datasets used by the previous investigators for different genomes also indicated that the current predictor remarkably outperformed its counterparts. AVAILABILITY: A user-friendly web-server, iNuc-PseKNC is freely accessible at http://lin.uestc.edu.cn/server/iNuc-PseKNC.