A proteogenomic approach to understand splice isoform functions through sequence and expression-based computational modeling

Exploring the functional impact of alternative splicing on human protein isoforms using available annotation sources

In recent years, the emphasis of scientific inquiry has shifted from whole-genome analyses to an understanding of cellular responses specific to tissue, developmental stage or environmental conditions. One of the central mechanisms underlying the diversity and adaptability of the contextual responses is alternative splicing (AS). It enables a single gene to encode multiple isoforms with distinct biological functions. However, to date, the functions of the vast majority of differentially spliced protein isoforms are not known. Integration of genomic, proteomic, functional, phenotypic and contextual information is essential for supporting isoform-based modeling and analysis. Such integrative proteogenomics approaches promise to provide insights into the functions of the alternatively spliced protein isoforms and provide high-confidence hypotheses to be validated experimentally. This manuscript provides a survey of the public databases supporting isoform-based biology. It also presents an overview of the potential global impact of AS on the human canonical gene functions, molecular interactions and cellular pathways.

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

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.

ASV-ID, a Proteogenomic Workflow To Predict Candidate Protein Isoforms on the Basis of Transcript Evidence

One of the goals of the Chromosome-Centric Human Proteome Project (C-HPP) is to map and characterize the functions of protein isoforms produced by alternative splicing of genes. However, identifying alternative splice variants (ASVs) via mass spectrometry remains a major challenge, because ASVs usually contain highly homologous peptide sequences. A routine protein sequence analysis suggests that more than half of the investigated proteins do not generate two or more uniquely mapping peptides that would enable their isoforms to be distinguished. Here, we develop a new proteogenomics method, named "ASV-ID" (alternative splicing variants identification), which enables identification of ASVs by using a cell type-specific protein sequence database that is supported by RNA-Seq data. Using this workflow, we identify 1935 distinct proteins under highly stringent conditions. In fact, transcript evidence on these 841 proteins helps us distinguish them from other isoforms, despite the fact that these proteins are not predicted to make 2 or more uniquely mapping peptides. We also demonstrate that ASV-ID enables detection of 19 differently expressed isoforms present in several cell lines. Thus, a new workflow using ASV-ID has the potential to map yet-to-be-identified difficult protein isoforms in a simple and robust way.

Systematic Protein Prioritization for Targeted Proteomics Studies through Literature Mining

There are more than 3.7 million published articles on the biological functions or disease implications of proteins, constituting an important resource of proteomics knowledge. However, it is difficult to summarize the millions of proteomics findings in the literature manually and quantify their relevance to the biology and diseases of interest. We developed a fully automated bioinformatics framework to identify and prioritize proteins associated with any biological entity. We used the 22 targeted areas of the Biology/Disease-driven (B/D)-Human Proteome Project (HPP) as examples, prioritized the relevant proteins through their Protein Universal Reference Publication-Originated Search Engine (PURPOSE) scores, validated the relevance of the score by comparing the protein prioritization results with a curated database, computed the scores of proteins across the topics of B/D-HPP, and characterized the top proteins in the common model organisms. We further extended the bioinformatics workflow to identify the relevant proteins in all organ systems and human diseases and deployed a cloud-based tool to prioritize proteins related to any custom search terms in real time. Our tool can facilitate the prioritization of proteins for any organ system or disease of interest and can contribute to the development of targeted proteomic studies for precision medicine.

Progress on the HUPO Draft Human Proteome: 2017 Metrics of the Human Proteome Project

The Human Proteome Organization (HUPO) Human Proteome Project (HPP) continues to make progress on its two overall goals: (1) completing the protein parts list, with an annual update of the HUPO draft human proteome, and (2) making proteomics an integrated complement to genomics and transcriptomics throughout biomedical and life sciences research. neXtProt version 2017-01-23 has 17 008 confident protein identifications (Protein Existence [PE] level 1) that are compliant with the HPP Guidelines v2.1 ( https://hupo.org/Guidelines ), up from 13 664 in 2012-12 and 16 518 in 2016-04. Remaining to be found by mass spectrometry and other methods are 2579 "missing proteins" (PE2+3+4), down from 2949 in 2016. PeptideAtlas 2017-01 has 15 173 canonical proteins, accounting for nearly all of the 15 290 PE1 proteins based on MS data. These resources have extensive data on PTMs, single amino acid variants, and splice isoforms. The Human Protein Atlas v16 has 10 492 highly curated protein entries with tissue and subcellular spatial localization of proteins and transcript expression. Organ-specific popular protein lists have been generated for broad use in quantitative targeted proteomics using SRM-MS or DIA-SWATH-MS studies of biology and disease.