PredPSD: A Gradient Tree Boosting Approach for Single-Stranded and Double-Stranded DNA Binding Protein Prediction.

ABSTRACT: Interactions between proteins and DNAs play essential roles in many biological processes. DNA binding proteins can be classified into two categories. Double-stranded DNA-binding proteins (DSBs) bind to double-stranded DNA and are involved in a series of cell functions such as gene expression and regulation. Single-stranded DNA-binding proteins (SSBs) are necessary for DNA replication, recombination, and repair and are responsible for binding to the single-stranded DNA. Therefore, the effective classification of DNA-binding proteins is helpful for functional annotations of proteins. In this work, we propose PredPSD, a computational method based on sequence information that accurately predicts SSBs and DSBs. It introduces three novel feature extraction algorithms. In particular, we use the a

SUBMITTER: Tan C 

PROVIDER: S-EPMC6982935 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature