Deep Learning and Random Forest-Based Augmentation of sRNA Expression Profiles

TL;DR

This paper explores deep learning and random forest methods to automatically augment small RNA-seq data annotations, significantly improving accuracy and handling unseen datasets better than traditional text mining approaches.

Contribution

It formulates annotation augmentation as a classification problem and demonstrates high accuracy in tissue and sex prediction using DL and RF methods.

Findings

Deep learning achieves up to 98% accuracy in tissue annotation.

DL outperforms RF in classification tasks.

The approach improves annotation quality for unseen datasets.

Abstract

The lack of well-structured annotations in a growing amount of RNA expression data complicates data interoperability and reusability. Commonly - used text mining methods extract annotations from existing unstructured data descriptions and often provide inaccurate output that requires manual curation. Automatic data-based augmentation (generation of annotations on the base of expression data) can considerably improve the annotation quality and has not been well-studied. We formulate an automatic augmentation of small RNA-seq expression data as a classification problem and investigate deep learning (DL) and random forest (RF) approaches to solve it. We generate tissue and sex annotations from small RNA-seq expression data for tissues and cell lines of homo sapiens. We validate our approach on 4243 annotated small RNA-seq samples from the Small RNA Expression Atlas (SEA) database. The average prediction accuracy for tissue groups is 98% (DL), for tissues - 96.5% (DL), and for sex - 77% (DL). The "one dataset out" average accuracy for tissue group prediction is 83% (DL) and 59% (RF). On average, DL provides better results as compared to RF, and considerably improves classification performance for 'unseen' datasets.