PromID: human promoter prediction by deep learning

TL;DR

PromID is a deep learning-based tool that accurately predicts the exact positions of transcription start sites in human genomic sequences, significantly reducing false positives compared to previous methods.

Contribution

This work advances promoter prediction by developing deep learning models that precisely locate TSS positions and iteratively improve discrimination using adaptive negative sets.

Findings

Achieved recall of 0.76, precision of 0.77, MCC of 0.76

Outperformed previous tools like FPROM in accuracy and false positive reduction

Provided a publicly available tool for human promoter prediction

Abstract

Computational identification of promoters is notoriously difficult as human genes often have unique promoter sequences that provide regulation of transcription and interaction with transcription initiation complex. While there are many attempts to develop computational promoter identification methods, we have no reliable tool to analyze long genomic sequences. In this work we further develop our deep learning approach that was relatively successful to discriminate short promoter and non-promoter sequences. Instead of focusing on the classification accuracy, in this work we predict the exact positions of the TSS inside the genomic sequences testing every possible location. We studied human promoters to find effective regions for discrimination and built corresponding deep learning models. These models use adaptively constructed negative set which iteratively improves the models discriminative ability. The developed promoter identification models significantly outperform the previously developed promoter prediction programs by considerably reducing the number of false positive predictions. The best model we have built has recall 0.76, precision 0.77 and MCC 0.76, while the next best tool FPROM achieved precision 0.48 and MCC 0.60 for the recall of 0.75. Our method is available at http://www.cbrc.kaust.edu.sa/PromID/.