iTIS-PseTNC: a sequence-based predictor for identifying translation initiation site in human genes using pseudo...

Area of Science:

• Genomics and Bioinformatics
• Molecular Biology
• Computational Biology

Background:

• Translation initiation site (TIS) identification is crucial for gene expression and genome analysis.
• Existing computational methods for TIS prediction have limitations due to not considering long-range DNA sequence-order effects.
• The increasing volume of genomic data necessitates rapid and effective automated TIS identification tools.

Purpose of the Study:

• To develop a novel computational predictor for accurately identifying translation initiation sites (TIS).
• To incorporate global and long-range sequence-order effects of DNA into TIS prediction.
• To provide a user-friendly web server for experimental scientists to facilitate TIS identification.

Main Methods:

• Developed iTIS-PseTNC, a predictor incorporating physicochemical properties into pseudo trinucleotide composition (PseTNC).
• Utilized a methodology analogous to the pseudo amino acid composition (PseAAC) approach from computational proteomics.
• Validated the predictor through rigorous cross-validation tests on a benchmark dataset.

Main Results:

• The iTIS-PseTNC predictor achieved an overall success rate exceeding 97% in identifying TIS locations.
• The method effectively accounts for sequence-order effects, improving prediction accuracy.
• A freely accessible web server (http://lin.uestc.edu.cn/server/iTIS-PseTNC) was established.

Conclusions:

• iTIS-PseTNC offers a significant advancement in computational TIS identification.
• The predictor's high accuracy and consideration of sequence-order effects make it valuable for genome analysis.
• The provided web server enhances accessibility for researchers, simplifying TIS prediction workflows.