1
|
Bromberg Y, Prabakaran R, Kabir A, Shehu A. Variant Effect Prediction in the Age of Machine Learning. Cold Spring Harb Perspect Biol 2024; 16:a041467. [PMID: 38621825 PMCID: PMC11216171 DOI: 10.1101/cshperspect.a041467] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/17/2024]
Abstract
Over the years, many computational methods have been created for the analysis of the impact of single amino acid substitutions resulting from single-nucleotide variants in genome coding regions. Historically, all methods have been supervised and thus limited by the inadequate sizes of experimentally curated data sets and by the lack of a standardized definition of variant effect. The emergence of unsupervised, deep learning (DL)-based methods raised an important question: Can machines learn the language of life from the unannotated protein sequence data well enough to identify significant errors in the protein "sentences"? Our analysis suggests that some unsupervised methods perform as well or better than existing supervised methods. Unsupervised methods are also faster and can, thus, be useful in large-scale variant evaluations. For all other methods, however, their performance varies by both evaluation metrics and by the type of variant effect being predicted. We also note that the evaluation of method performance is still lacking on less-studied, nonhuman proteins where unsupervised methods hold the most promise.
Collapse
Affiliation(s)
- Yana Bromberg
- Department of Biology, Emory University, Atlanta 30322, Georgia, USA
- Department of Computer Science, Emory University, Atlanta 30322, Georgia, USA
| | - R Prabakaran
- Department of Biology, Emory University, Atlanta 30322, Georgia, USA
| | - Anowarul Kabir
- Department of Computer Science, George Mason University, Fairfax 22030, Virginia, USA
| | - Amarda Shehu
- Department of Computer Science, George Mason University, Fairfax 22030, Virginia, USA
| |
Collapse
|
2
|
Monti R, Ohler U. Toward Identification of Functional Sequences and Variants in Noncoding DNA. Annu Rev Biomed Data Sci 2023; 6:191-210. [PMID: 37262323 DOI: 10.1146/annurev-biodatasci-122120-110102] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
Understanding the noncoding part of the genome, which encodes gene regulation, is necessary to identify genetic mechanisms of disease and translate findings from genome-wide association studies into actionable results for treatments and personalized care. Here we provide an overview of the computational analysis of noncoding regions, starting from gene-regulatory mechanisms and their representation in data. Deep learning methods, when applied to these data, highlight important regulatory sequence elements and predict the functional effects of genetic variants. These and other algorithms are used to predict damaging sequence variants. Finally, we introduce rare-variant association tests that incorporate functional annotations and predictions in order to increase interpretability and statistical power.
Collapse
Affiliation(s)
- Remo Monti
- Max Delbrück Center for Molecular Medicine (MDC), Helmholtz Association of German Research Centers, Berlin Institute for Medical Systems Biology (BIMSB), Berlin, Germany;
- Digital Health-Machine Learning, Hasso Plattner Institute, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany
| | - Uwe Ohler
- Max Delbrück Center for Molecular Medicine (MDC), Helmholtz Association of German Research Centers, Berlin Institute for Medical Systems Biology (BIMSB), Berlin, Germany;
| |
Collapse
|
3
|
Gong J, Wang J, Zong X, Ma Z, Xu D. Prediction of protein stability changes upon single-point variant using 3D structure profile. Comput Struct Biotechnol J 2022; 21:354-364. [PMID: 36582438 PMCID: PMC9791599 DOI: 10.1016/j.csbj.2022.12.008] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2022] [Revised: 12/04/2022] [Accepted: 12/05/2022] [Indexed: 12/13/2022] Open
Abstract
Identifying protein thermodynamic stability changes upon single-point variants is crucial for studying mutation-induced alterations in protein biophysics, genomic variants, and mutation-related diseases. In the last decade, various computational methods have been developed to predict the effects of single-point variants, but the prediction accuracy is still far from satisfactory for practical applications. Herein, we review approaches and tools for predicting stability changes upon the single-point variant. Most of these methods require tertiary protein structure as input to achieve reliable predictions. However, the availability of protein structures limits the immediate application of these tools. To improve the performance of a computational prediction from a protein sequence without experimental structural information, we introduce a new computational framework: MU3DSP. This method assesses the effects of single-point variants on protein thermodynamic stability based on point mutated protein 3D structure profile. Given a protein sequence with a single variant as input, MU3DSP integrates both sequence-level features and averaged features of 3D structures obtained from sequence alignment to PDB to assess the change of thermodynamic stability induced by the substitution. MU3DSP outperforms existing methods on various benchmarks, making it a reliable tool to assess both somatic and germline substitution variants and assist in protein design. MU3DSP is available as an open-source tool at https://github.com/hurraygong/MU3DSP.
Collapse
Affiliation(s)
- Jianting Gong
- School of Information Science and Technology, and Institution of Computational Biology, Northeast Normal University, Changchun 130117, China
- Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, USA
| | - Juexin Wang
- Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, USA
- Department of BioHealth Informatics, School of Informatics and Computing, Indiana University Purdue University Indianapolis, Indianapolis, IN, USA
| | - Xizeng Zong
- School of Computer Science and Engineering, Changchun University of Technology, Changchun 130117, China
| | - Zhiqiang Ma
- School of Information Science and Technology, and Institution of Computational Biology, Northeast Normal University, Changchun 130117, China
- Department of Computer Science, College of Humanities & Sciences of Northeast Normal University, Changchun 130117, China
- Corresponding authors.
| | - Dong Xu
- Department of Electrical Engineering and Computer Science, and Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, USA
- Corresponding authors.
| |
Collapse
|
4
|
Li B, Jin B, Capra JA, Bush WS. Integration of Protein Structure and Population-Scale DNA Sequence Data for Disease Gene Discovery and Variant Interpretation. Annu Rev Biomed Data Sci 2022; 5:141-161. [PMID: 35508071 DOI: 10.1146/annurev-biodatasci-122220-112147] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
The experimental and computational techniques for capturing information about protein structures and genetic variation within the human genome have advanced dramatically in the past 20 years, generating extensive new data resources. In this review, we discuss these advances, along with new approaches for determining the impact a genetic variant has on protein function. We focus on the potential of new methods that integrate human genetic variation into protein structures to discover relationships to disease, including the discovery of mutational hotspots in cancer-related proteins, the localization of protein-altering variants within protein regions for common complex diseases, and the assessment of variants of unknown significance for Mendelian traits. We expect that approaches that integrate these data sources will play increasingly important roles in disease gene discovery and variant interpretation. Expected final online publication date for the Annual Review of Biomedical Data Science, Volume 5 is August 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.
Collapse
Affiliation(s)
- Bian Li
- Department of Biological Sciences and Center for Structural Biology, Vanderbilt University, Nashville, Tennessee, USA
| | - Bowen Jin
- Graduate Program in Systems Biology and Bioinformatics, Department of Nutrition, School of Medicine, Case Western Reserve University, Cleveland, Ohio, USA
| | - John A Capra
- Bakar Computational Health Sciences Institute and Department of Epidemiology and Biostatistics, University of California, San Francisco, California, USA;
| | - William S Bush
- Cleveland Institute for Computational Biology, Department of Population and Quantitative Health Sciences, Case Western Reserve University, Cleveland, Ohio, USA;
| |
Collapse
|
5
|
Zeng Z, Aptekmann AA, Bromberg Y. Decoding the effects of synonymous variants. Nucleic Acids Res 2021; 49:12673-12691. [PMID: 34850938 PMCID: PMC8682775 DOI: 10.1093/nar/gkab1159] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2021] [Revised: 11/02/2021] [Accepted: 11/08/2021] [Indexed: 12/12/2022] Open
Abstract
Synonymous single nucleotide variants (sSNVs) are common in the human genome but are often overlooked. However, sSNVs can have significant biological impact and may lead to disease. Existing computational methods for evaluating the effect of sSNVs suffer from the lack of gold-standard training/evaluation data and exhibit over-reliance on sequence conservation signals. We developed synVep (synonymous Variant effect predictor), a machine learning-based method that overcomes both of these limitations. Our training data was a combination of variants reported by gnomAD (observed) and those unreported, but possible in the human genome (generated). We used positive-unlabeled learning to purify the generated variant set of any likely unobservable variants. We then trained two sequential extreme gradient boosting models to identify subsets of the remaining variants putatively enriched and depleted in effect. Our method attained 90% precision/recall on a previously unseen set of variants. Furthermore, although synVep does not explicitly use conservation, its scores correlated with evolutionary distances between orthologs in cross-species variation analysis. synVep was also able to differentiate pathogenic vs. benign variants, as well as splice-site disrupting variants (SDV) vs. non-SDVs. Thus, synVep provides an important improvement in annotation of sSNVs, allowing users to focus on variants that most likely harbor effects.
Collapse
Affiliation(s)
- Zishuo Zeng
- Department of Biochemistry and Microbiology, Rutgers University, New Brunswick, NJ 08873, USA
| | - Ariel A Aptekmann
- Department of Biochemistry and Microbiology, Rutgers University, New Brunswick, NJ 08873, USA
| | - Yana Bromberg
- Department of Biochemistry and Microbiology, Rutgers University, New Brunswick, NJ 08873, USA
- Department of Genetics, Rutgers University, Piscataway, NJ 08854, USA
| |
Collapse
|