ProFET: Feature engineering captures high-level protein functions

Ofer, Dan; Linial, Michal

doi:10.1093/bioinformatics/btv345

Cited by 93 publications

(60 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For comparison purposes under difficult working conditions with limited or completely missing homology information, additional predictions were generated by a baseline method (Naïve), which ranks GO terms by prevalence in UniProtKB-GOA, and by a sequence similarity-based approach (BLAST), which can transfer annotations only from distantly related and experimentally characterized proteins as detailed in Methods. Other machine-learning based tools for GO term prediction from patterns of biological features could not be included in the study: ProtFun15 has not been updated in a very long time and only covers a handful of currently valid GO terms, whereas ProFET18 requires training from scratch classifiers for all GO categories of interest.…”

Section: Resultsmentioning

confidence: 99%

“…The observation that the length and position of intrinsically disordered protein regions strongly correlates with some molecular activities and biological processes led to an expanded set of sequence-derived features, which FFPred scans through a library of GO term-specific SVMs to annotate protein chains1617. A more recent study has confirmed the effectiveness of this feature-based approach with the use of random forests for supervised learning18.…”

mentioning

confidence: 97%

See 1 more Smart Citation

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

Cozzetto

Minneci

Currant

et al. 2016

Sci Rep

107

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

mentioning

confidence: 97%

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

Cozzetto

Minneci

Currant

et al. 2016

Sci Rep

107

View full text Add to dashboard Cite

show abstract

“…In addition to homology, there exist many AFP methods that exploit additional information extracted from the genome sequence, e.g., conserved gene neighborhoods (Ling et al, 2009), phylogenetic distribution (Pellegrini et al, 1999), protein motifs and biophysical properties (Ofer and Linial, 2015), codon usage biases (Kriško et al, 2014), remote homology (Hawkins et al, 2009;Sokolov and Ben-Hur, 2010), and composition of protein domains (Hunter et al, 2011;Punta et al, 2011). Moreover, inference using genomic information can be further supplemented by experimental data: gene expression (Tian et al, 2008), protein-protein interactions (Cao and Cheng, 2015) or protein structure (Wass et al, 2012), and also by text-mining the scientific literature .…”

Section: Introductionmentioning

confidence: 99%

Extensive complementarity between gene function prediction methods

2016

View full text Add to dashboard Cite

Motivation: The number of sequenced genomes rises steadily, but we still lack the knowledge about the biological roles of many genes. Automatic function prediction (AFP) is thus a necessity. We hypothesize that AFP approaches which draw on distinct genome features may be useful for predicting different types of gene functions, motivating a systematic analysis of the benefits gained by obtaining and integrating such predictions. Results: Our pipeline amalgamates 5,133,543 genes from 2,071 genomes in a single massive analysis that evaluates five established genomic AFP methodologies. While 1,227 Gene Ontology terms yielded reliable predictions, the majority of these functions were accessible to only one or two of the methods. Moreover, different methods tend to assign a GO term to non-overlapping sets of genes. Thus, inferences made by diverse AFP methods display a striking complementary, both gene-wise and function-wise. Because of this, a viable integration strategy is to simply rely on a single mostconfident prediction per gene/function, instead of enforcing agreement across multiple AFP methods. Using an information-theoretic approach, we estimate that current databases contain 29.2 bits/gene of known E. coli gene functions. This can be increased by up to 5.5 bits/gene using individual AFP methods, or by 11 additional bits/gene upon integration, thereby providing a highly-ranking predictor on the CAFA2 community benchmark. Availability of more sequenced genomes boosts the predictive accuracy of AFP approaches and also the benefit from integrating them.

show abstract

“…The main features included are: i) the location of the variant within the protein sequence, ii) the identities of the reference and alternative amino-acids, iii) the score of the amino-acid substitution under various BLOSUM matrices, iv) an abundance of annotations extracted from UniProt, v) amino-acid scales (i.e. various numeric values assigned to amino-acids, as described elsewhere 71,72 ), vi) Pfam domains and Pfam clans. The full specification of all extracted features is available in Supplementary Table S4.…”

Section: Proteomic Features Used By the Prediction Modelmentioning

confidence: 99%

Modeling Functional Genetic Alteration in Cancer Reveals New Candidate Driver Genes

Brandes

Linial

2018

Preprint

Self Cite

View full text Add to dashboard Cite

Compiling the catalogue of genes actively involved in tumorigenesis (known as cancer drivers) is an ongoing endeavor, with profound implications to the understanding of tumorigenesis and treatment of the disease. An abundance of computational methods have been developed to screening the genome for candidate driver genes based on genomic data of somatic mutations in tumors. Most methods rely on detecting genes displaying excessive mutation rates compared to some background model. This approach is susceptible to false discoveries, due to its sensitivity to the assumptions of the background model, such as the need to account for hyper-mutated samples, cancer types and genomic loci. We present a fundamentally different approach. Instead of focusing on the number of mutations, we examine their content, and their expected effects on the functions of genes. We use a machine-learning model to predict functional effect scores of somatic mutations. For each gene, we compare the distribution of observed effect scores with the distribution expected at random, and report genes showing significant bias. By applying our framework on the ~20k protein-coding human genes, we detected 593 genes showing significant bias towards harmful mutations in the context of cancer. In contrast, we found only 6 significant genes biased in the opposite direction. The list of 593 genes, constructed without any prior knowledge of their role in cancer, shows an overwhelming overlap with known cancer driver genes, but also highlights many overlooked genes. These overlooked genes are promising candidates for novel cancer drivers. Our model is generic and is not restricted to the context of cancer. Applying the same framework to data of human-population genetic variation reveals the opposite trend. Unlike cancer, which is dominated by a bias towards harmful mutations, long-term evolution in healthy individuals results a bias towards less harmful mutations. The underlying assumptions of our framework are minimal, making it ideal for analyzing genetic data in search of genes subjected to positive or negative selection. It is fully open sourced and available for installation and use. Our framework presents a substantial development towards the application of state-of-the-art machine-learning algorithms in genetic studies.

show abstract

ProFET: Feature engineering captures high-level protein functions

Abstract: Supplementary data are available at Bioinformatics online.

Cited by 93 publications

References 65 publications

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

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

Extensive complementarity between gene function prediction methods

Modeling Functional Genetic Alteration in Cancer Reveals New Candidate Driver Genes

Contact Info

Product

Resources

About