S1: DNA-­binding protein predictions

Integrating sequence, gene expression and multi-scope annotations improves DNA-binding protein predictions

S1: DNA-­binding protein predictions, OpenTox Asia 2017
PRESENTING AUTHOR: 

Shandar Ahmad 

INSTITUTION / COMPANY : 

JawaharlalNehru University, New Delhi

POSITION: 

Professor 

ABSTRACT CONTENT / DETAILS: 

DNA-­binding proteins form an important class of proteins of which many members remain unknown. Amino acid sequence contains useful information about identifying novel DBPs but remains inadequate due to many false positives and also because the size of the binding sites varies widely across DBPs.  On the other hand the current annotations of DBPs are available with various scope and confidence levels, posing challenges for suitable machine learning models. We have shown that integrating multi-­level annotations,  global  gene  expression  profiles and sequence information into predictive models can account for many  DBPs, which could not be predicted by individual approaches.