FFPred 3: feature-based function prediction for all Gene Ontology domains

Abstract

Predicting protein function has been a major goal of bioinformatics for several decades, and it has gained fresh momentum thanks to recent community-wide blind tests aimed at benchmarking available tools on a genomic scale. Sequence-based predictors, especially those performing homology-based transfers, remain the most popular but increasing understanding of their limitations has stimulated the development of complementary approaches, which mostly exploit machine learning. Here we present FFPred 3, which is intended for assigning Gene Ontology terms to human protein chains, when homology with characterized proteins can provide little aid. Predictions are made by scanning the input sequences against an array of Support Vector Machines (SVMs), each examining the relationship between protein function and biophysical attributes describing secondary structure, transmembrane helices, intrinsically disordered regions, signal peptides and other motifs. This update features a larger SVM library that extends its coverage to the cellular component sub-ontology for the first time, prompted by the establishment of a dedicated evaluation category within the Critical Assessment of Functional Annotation. The effectiveness of this approach is demonstrated through benchmarking experiments, and its usefulness is illustrated by analysing the potential functional consequences of alternative splicing in human and their relationship to patterns of biological features.

The Ortholog Conjecture Revisited: the Value of Orthologs and Paralogs in Function Prediction

“…The prediction of gene function generally proceeds by the transfer of function from genes with experimental evidence to unannotated, or less-annotated, genes that are similar by some measure [42]. While several methods use multiple data types to carry out predictions [31,47,11], many solely rely on evolutionary relationships [16,24,6,10] and are the focus of the current study.…”

Structure-Based Protein Function Prediction using Graph Convolutional Networks

“…MouseFunc 25 , have also played a key role in the development of these methods and have shown that integrative machine learning and statistical methods outperform traditional sequence alignmentbased methods (e.g., BLAST) 22 . However, the performance of these methods is typically strongly affected by the quality of manually-engineered features constructed from either sequence or structure (features that rely heavily on heuristics that in turn require domain-expert knowledge, and in some cases unstable assumptions, thresholds and preprocessing pipelines) 26 . Here, we focus on methods that can take as inputs sequence and features that are readily derived from sequence (such as predicted structure) and do not focus on, or compare to, the many methods that rely on protein networks like GeneMANIA 27 , Mashup 28 , DeepNF 29 , and other integrative network prediction methods.…”

UDSMProt: Universal Deep Sequence Models for Protein Classification

“…Here, Table 3. Gene ontology (molecular function) prediction performance evaluated on the DeepGO [Kulmanov et al, 2017] benchmark set in comparison to literature results from DeeProtein [zu Belzen et al, 2019], DeepGO [Kulmanov et al, 2017], FFPred3 [Cozzetto et al, 2016], and GoFDR [Gong et al, 2016]. we focus on the domain of molecular function prediction.…”

“…we focus on the domain of molecular function prediction. Similar to enzyme class prediction, the first proposed approaches in this field relied on handcrafted features like functionally discriminating residues (FDR) with PSSM [Gong et al, 2016] and classification models consisting of an array of Support Vector Machines [Cozzetto et al, 2016]. Recently, deep learning approaches have raised the bar by using convolutional neural networks [Kulmanov et al, 2017] and residual neural networks [zu Belzen et al, 2019].…”

“…There is a large body of literature on methods to infer protein properties, most of which make use of additional handcrafted features in addition to the primary sequence alone [Shen and Chou, 2007, Håndstad et al, 2007, Gong et al, 2016, Cozzetto et al, 2016, Li et al, 2017, Dalkiran et al, 2018. These include experimentally determined functional annotations (such as Pfam [El-Gebali et al, 2018]) as well as features incorporating information from homologous (evolutionary related) proteins that are typically inferred from well-motivated but still heuristic methods such as the basic local alignment search tool (BLAST) [Madden, 2013], that searches a database for proteins that are homologous to a given query protein, via multiple sequence alignment.…”