DIFFUSE: predicting isoform functions from sequences and expression profiles via deep learning

Abstract

Motivation Alternative splicing generates multiple isoforms from a single gene, greatly increasing the functional diversity of a genome. Although gene functions have been well studied, little is known about the specific functions of isoforms, making accurate prediction of isoform functions highly desirable. However, the existing approaches to predicting isoform functions are far from satisfactory due to at least two reasons: (i) unlike genes, isoform-level functional annotations are scarce. (ii) The information of isoform functions is concealed in various types of data including isoform sequences, co-expression relationship among isoforms, etc. Results In this study, we present a novel approach, DIFFUSE (Deep learning-based prediction of IsoForm FUnctions from Sequences and Expression), to predict isoform functions. To integrate various types of data, our approach adopts a hybrid framework by first using a deep neural network (DNN) to predict the functions of isoforms from their genomic sequences and then refining the prediction using a conditional random field (CRF) based on co-expression relationship. To overcome the lack of isoform-level ground truth labels, we further propose an iterative semi-supervised learning algorithm to train both the DNN and CRF together. Our extensive computational experiments demonstrate that DIFFUSE could effectively predict the functions of isoforms and genes. It achieves an average area under the receiver operating characteristics curve of 0.840 and area under the precision–recall curve of 0.581 over 4184 GO functional categories, which are significantly higher than the state-of-the-art methods. We further validate the prediction results by analyzing the correlation between functional similarity, sequence similarity, expression similarity and structural similarity, as well as the consistency between the predicted functions and some well-studied functional features of isoform sequences. Availability and implementation https://github.com/haochenucr/DIFFUSE. Supplementary information Supplementary data are available at Bioinformatics online.

Computational Methods for Predicting Functions at the mRNA Isoform Level

“…For instance, alternative splicing of mouse transcription factors changed domain composition of the mRNA isoforms, leading to tissue-specific isoforms with distinct functions [ 52 ]. Deep learning-based prediction of IsoForm FUnctions from Sequences and Expression (DIFFUSE) [ 32 ] uses both mRNA isoform sequence specific features and information from expression profiles to predict mRNA isoform functions.…”

“…Previously, machine learning methods have been used to address a multitude of problems, some of which include, drug target discovery, gene function prediction, protein–protein interaction (PPI) prediction, protein structure and functional site prediction, and subcellular localization protein prediction [ 21 , 22 , 23 , 24 , 25 , 26 , 27 ]. More recently, several machine learning and recommendation system methods have also been developed to predict the biological functions of mRNA isoforms [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 ]. These methods have been successful in predicting gene functions at the level of mRNA isoforms and provide an added advantage over experimental approaches in terms of time and resources.…”

Isoform-Disease Association Prediction by Data Fusion

“…The above equation can simultaneously distribute GDAs to individual isoforms and induce a classifier to predict IDAs. However, it ignores the important genomics data, which carry important information to boost the performance of isoform function prediction and to identify the genetic determinants of disease [3,37]. Similarly, the incorporation of genomic data can also improve the performance of predicting IDAs.…”

“…The co-expression pattern of isoforms also carry important information about the functions of isoforms [3,40], whose usage also boosts the prediction of IDAs. In addition, the expression of isoforms has tissue specificity [7,38].…”

“…In fact, such lack also exists in functional analysis of isoforms [13]. To bypass this issue, some researchers take a gene as a bag and its spliced isoforms as instances of that bag, and adapt multiple instance learning (MIL) [2,17] to distribute the readily available functional annotations of a gene to its isoforms [3,6,14,26,34,40].…”