Spanish 
Chinese 
Russian 
German 
French 
Japanese 
Portuguese 
Hindi Our Group organises 3000+ Global Conferenceseries Events every year across USA, Europe & Asia with support from 1000 more scientific Societies and Publishes 700+ Open Access Journals which contains over 50000 eminent personalities, reputed scientists as editorial board members.
Open Access Journals gaining more Readers and Citations
700 Journals and 15,000,000 Readers Each Journal is getting 25,000+ Readers
Google Scholar citation report
Citations : 3314
Journal of Biotechnology & Biomaterials received 3314 citations as per Google Scholar report
Indexed In
- Index Copernicus
- Google Scholar
- Sherpa Romeo
- Open J Gate
- Genamics JournalSeek
- Academic Keys
- ResearchBible
- China National Knowledge Infrastructure (CNKI)
- Access to Global Online Research in Agriculture (AGORA)
- Electronic Journals Library
- RefSeek
- Hamdard University
- EBSCO A-Z
- OCLC- WorldCat
- SWB online catalog
- Virtual Library of Biology (vifabio)
- Publons
- Geneva Foundation for Medical Education and Research
- Euro Pub
- ICMJE
Useful Links
Recommended Journals
Related Subjects
Share This Page
In Association with
A hybrid approach for identifying 5� splicing junction with higher accuracy
6th World Congress on Biotechnology
Prabina Kumar Meher
ICAR-Indian Agricultural Statistics Research Institute, India
ScientificTracks Abstracts: J Biotechnol Biomater
Abstract
Identification of splice site is essential for annotation of genes. Though existing approaches have achieved an acceptable level of accuracy, still there is a need for improvement in the accuracy. Besides, most of the approaches are species-specific and have used longer sequence motif to train the classification model. Therefore, it is required to develop an approach compatible with short sequence motif as well as provide higher accuracy across the species. The real and pseudo splice site sequences on human, bovine, fish and worm were collected from public domain. Then, each splice site sequence of 15 nucleotides long was transformed into a numeric vector of length 49, out of which 4 were positional, 4 were dependency and 41 were compositional features. Using transformed real and pseudo splice site dataset, prediction was made through SVM with radial basis kernel function. Using balanced training set, the proposed approach achieved AUC-ROC of 96.05%, 96.96%, 96.95%, 96.24% and AUC-PR of 97.64%, 97.89%, 97.91%, 97.90%, while tested on human, bovine, fish and worm datasets respectively. On the other hand, AUC-ROC of 97.21%, 97.45%, 97.41%, 98.06% and AUC-PR of 93.24%, 93.34%, 93.38% and 92.29% were obtained, while imbalanced training datasets were used. Further, the proposed approach outperformed most of the splice site prediction approaches while compared using bench mark NN269 dataset. Thus, we believe that the proposed approach can be used as a complementary method to the existing methods.Biography
Prabina Kumar Meher has completed his PhD in the year 2014 from Indian Agricultural Research Institute, New Delhi. He is currently working as a Scientist in the Division of Statistical Genetics at Indian Agricultural Statistics Research Institute, a premier institute in the field of agricultural statistics. His area of interest is Statistical Genetics/Genomics and Computational Biology. He is currently working in the area of splice site prediction in eukaryotes. He has published 7 research papers in the last year.
Email: meherprabin@yahoo.com
