Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification

TL;DR

This paper introduces Prototype Matching Networks, a novel deep learning architecture that models TF binding mechanisms and interactions for large-scale multi-label genomic sequence classification, significantly improving prediction accuracy.

Contribution

The paper presents the first deep learning model combining prototype learning and TF-TF interaction modeling for large-scale TFBS prediction.

Findings

Significantly outperforms baseline models on a dataset with 2.1 million sequences.

Effectively models biological TF binding mechanisms and interactions.

Demonstrates the importance of prototype learning in genomics.

Abstract

One of the fundamental tasks in understanding genomics is the problem of predicting Transcription Factor Binding Sites (TFBSs). With more than hundreds of Transcription Factors (TFs) as labels, genomic-sequence based TFBS prediction is a challenging multi-label classification task. There are two major biological mechanisms for TF binding: (1) sequence-specific binding patterns on genomes known as "motifs" and (2) interactions among TFs known as co-binding effects. In this paper, we propose a novel deep architecture, the Prototype Matching Network (PMN) to mimic the TF binding mechanisms. Our PMN model automatically extracts prototypes ("motif"-like features) for each TF through a novel prototype-matching loss. Borrowing ideas from few-shot matching models, we use the notion of support set of prototypes and an LSTM to learn how TFs interact and bind to genomic sequences. On a reference TFBS dataset with $2.1$ $million$ genomic sequences, PMN significantly outperforms baselines and validates our design choices empirically. To our knowledge, this is the first deep learning architecture that introduces prototype learning and considers TF-TF interactions for large-scale TFBS prediction. Not only is the proposed architecture accurate, but it also models the underlying biology.