Gene function prediction in five model eukaryotes based on gene relative location through machine learning

Motiviation: The function of most genes is unknown. The best results in gene function prediction are obtained with machine learning-based methods that combine multiple data sources, typically sequence derived features, protein structure and interaction data. Even though there is ample evidence showing that a gene's function is not independent of its location, the few available examples of gene function prediction based on gene location relay on sequence identity between genes of different organisms and are thus subjected to the limitations of the relationship between sequence and function. Results: Here we predict thousands of gene functions in five eukaryotes (Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster, Mus musculus and Homo sapiens) using machine learning models trained with features derived from the location of genes in the genomes to which they belong. To the best of our knowledge this is the first work in which gene function prediction is successfully achieved in eukaryotic genomes using predictive features derived exclusively from the relative location of the genes. Contact: [email protected] Supplementary information: http://gfpml.bnd.edu.uy

Download Full-text

Gene Function Prediction in Five Model Eukaryotes Exclusively Based on Gene Relative Location Through Machine Learning

10.21203/rs.3.rs-1199974/v1 ◽

2022 ◽

Author(s):

Flavio Pazos Obregón ◽

Diego Silvera ◽

Pablo Soto ◽

Patricio Yankilevich ◽

Gustavo Guerberoff ◽

...

Keyword(s):

Machine Learning ◽

Gene Function ◽

Homo Sapiens ◽

Function Prediction ◽

Gene Location ◽

Gene Function Prediction ◽

Ample Evidence ◽

Multiple Data ◽

And Function ◽

The Relationship

Abstract The function of most genes is unknown. The best results in automated function prediction are obtained with machine learning-based methods that combine multiple data sources, typically sequence derived features, protein structure and interaction data. Even though there is ample evidence showing that a gene’s function is not independent of its location, the few available examples of gene function prediction based on gene location rely on sequence identity between genes of different organisms and are thus subjected to the limitations of the relationship between sequence and function. Here we predict thousands of gene functions in five model eukaryotes (Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster, Mus musculus and Homo sapiens) using machine learning models exclusively trained with features derived from the location of genes in the genomes to which they belong. Our aim was not to obtain the best performing method to automated function prediction but to explore the extent to which a gene's location can predict its function in eukaryotes. We found that our models outperform BLAST when predicting terms from Biological Process and Cellular Component Ontologies, showing that, at least in some cases, gene location alone can be more useful than sequence to infer gene function.

Download Full-text

Accurate and efficient gene function prediction using a multi-bacterial network

Bioinformatics ◽

10.1093/bioinformatics/btaa885 ◽

2020 ◽

Author(s):

Jeffrey N Law ◽

Shiv D Kale ◽

T M Murali

Keyword(s):

Gene Function ◽

Bacterial Species ◽

Heterogeneous Data ◽

Function Prediction ◽

Label Propagation ◽

Supplementary Information ◽

Gene Function Prediction ◽

Functional Annotations ◽

A Genome ◽

Multiple Species

Abstract Motivation Nearly 40% of the genes in sequenced genomes have no experimentally or computationally derived functional annotations. To fill this gap, we seek to develop methods for network-based gene function prediction that can integrate heterogeneous data for multiple species with experimentally based functional annotations and systematically transfer them to newly sequenced organisms on a genome-wide scale. However, the large sizes of such networks pose a challenge for the scalability of current methods. Results We develop a label propagation algorithm called FastSinkSource. By formally bounding its rate of progress, we decrease the running time by a factor of 100 without sacrificing accuracy. We systematically evaluate many approaches to construct multi-species bacterial networks and apply FastSinkSource and other state-of-the-art methods to these networks. We find that the most accurate and efficient approach is to pre-compute annotation scores for species with experimental annotations, and then to transfer them to other organisms. In this manner, FastSinkSource runs in under 3 min for 200 bacterial species. Availability and implementation An implementation of our framework and all data used in this research are available at https://github.com/Murali-group/multi-species-GOA-prediction. Supplementary information Supplementary data are available at Bioinformatics online.

Download Full-text

Machine learning: A powerful tool for gene function prediction in plants

Applications in Plant Sciences ◽

10.1002/aps3.11376 ◽

2020 ◽

Vol 8 (7) ◽

Cited By ~ 5

Author(s):

Elizabeth H. Mahood ◽

Lars H. Kruse ◽

Gaurav D. Moghe

Keyword(s):

Machine Learning ◽

Gene Function ◽

Function Prediction ◽

Gene Function Prediction

Download Full-text

Non-Homology-Based Prediction of Gene Functions

10.1101/730473 ◽

2019 ◽

Author(s):

Xiuru Dai ◽

Zheng Xu ◽

Zhikai Liang ◽

Xiaoyu Tu ◽

Silin Zhong ◽

...

Keyword(s):

Machine Learning ◽

Gene Function ◽

Functional Annotation ◽

Function Prediction ◽

Classification Algorithms ◽

Gene Function Prediction ◽

Machine Learning Classification ◽

New Gene ◽

Go Terms ◽

Annotation Errors

AbstractAdvances in genome sequencing and annotation have eased the difficulty of identifying new gene sequences. Predicting the functions of these newly identified genes remains challenging. Genes descended from a common ancestral sequence are likely to have common functions. As a result homology is widely used for gene function prediction. This means functional annotation errors also propagate from one species to another. Several approaches based on machine learning classification algorithms were evaluated for their ability to accurately predict gene function from non-homology gene features. Among the eight supervised classification algorithms evaluated, random forest-based prediction consistently provided the most accurate gene function prediction. Non-homology-based functional annotation provides complementary strengths to homology-based annotation, with higher average performance in Biological Process GO terms, the domain where homology-based functional annotation performs the worst, and weaker performance in Molecular Function GO terms, the domain where the accuracy of homology-based functional annotation is highest. Non-homology-based functional annotation based on machine learning may ultimately prove useful both as a method to assign predicted functions to orphan genes which lack functionally characterized homologs, and to identify and correct functional annotation errors which were propagated through homology-based functional annotations.

Download Full-text

Editorial: Machine Learning Techniques on Gene Function Prediction

Frontiers in Genetics ◽

10.3389/fgene.2019.00938 ◽

2019 ◽

Vol 10 ◽

Author(s):

Quan Zou ◽

Arun Kumar Sangaiah ◽

Dariusz Mrozek

Keyword(s):

Machine Learning ◽

Gene Function ◽

Function Prediction ◽

Machine Learning Techniques ◽

Gene Function Prediction ◽

Learning Techniques

Download Full-text

Accurate and Efficient Gene Function Prediction using a Multi-Bacterial Network

10.1101/646687 ◽

2019 ◽

Cited By ~ 1

Author(s):

Jeffrey Law ◽

Shiv Kale ◽

T. M. Murali

Keyword(s):

Gene Function ◽

Bacterial Species ◽

Heterogeneous Data ◽

Function Prediction ◽

Label Propagation ◽

Supplementary Information ◽

Supplementary File ◽

Gene Function Prediction ◽

Functional Annotations ◽

Multiple Species

AbstractMotivationNearly 40% of the genes in sequenced genomes have no experimentally- or computationally-derived functional annotations. To fill this gap, we seek to develop methods for network-based gene function prediction that can integrate heterogeneous data for multiple species with experimentally-based functional annotations and systematically transfer them to newly-sequenced organisms on a genomewide scale. However, the large size of such networks pose a challenge for the scalability of current methods.ResultsWe develop a label propagation algorithm called FastSinkSource. By formally bounding its the rate of progress, we decrease the running time by a factor of 100 without sacrificing accuracy. We systematically evaluate many approaches to construct multi-species bacterial networks and apply FastSinkSource and other state-of-the-art methods to these networks. We find that the most accurate and efficient approach is to pre-compute annotation scores for species with experimental annotations, and then to transfer them to other organisms. In this manner, FastSinkSource runs in under three minutes for 200 bacterial species.Availability and ImplementationPython implementations of each algorithm and all data used in this research are available at http://bioinformatics.cs.vt.edu/~jeffl/supplements/[email protected] InformationA supplementary file is available at bioRxiv online.

Download Full-text