XGBMUT: Predicting the Functional Impact of Missense Mutations Using an Extreme Gradient Boost Classifier

Overview

Journal ACS Omega

Publisher American Chemical Society

Specialty Chemistry

Date 2025 Mar 10

PMID 40060867

Authors

Gabriel Rodrigues Coutinho Pereira

Loiane Mendonca Abrantes Da Conceicao

Barbara de Azevedo Abrahim-Vieira

Carlos Rangel Rodrigues

Lucio Mendes Cabral

Ricardo Limongi Franca Coelho

Joelma Freire De Mesquita

Affiliations

Soon will be listed here.

Abstract

Millions of new mutations have been discovered largely due to advancements in genome projects, but characterizing their effects through traditional wet-lab experiments remains labor-intensive and time-consuming. Functional prediction algorithms offer a solution by enabling the efficient screening of mutations, thereby saving time and resources. The objective of this study was to develop a competitive algorithm for predicting the functional impact of missense mutations. A unified database and substitution matrices containing predictor variables specifically for missense mutations were initially constructed. Subsequently, values for the predictor variables were collected from the training and test sets derived from the ClinVar and HumsaVar databases. A series of supervised machine learning classifiers were then trained, and their performance was evaluated using the test set. The best-performing model was additionally compared against ten currently available functional prediction algorithms. The proposed algorithm, XGBMut, demonstrates exceptional accuracy in classifying missense mutations while also exhibiting a competitive performance. Additionally, a user-friendly graphical interface was developed to enhance accessibility for professionals in various fields. Unlike most existing methods, XGBMut eliminates the need for a web server dependency and the installation of third-party software, making it a more versatile tool for users.

References

Gong T, Yang L, Shen F, Chen H, Pan Z, Zhang Q . Computational and Mass Spectrometry-Based Approach Identify Deleterious Non-Synonymous Single Nucleotide Polymorphisms (nsSNPs) in JMJD6. Molecules. 2021; 26(15). PMC: 8347302. DOI: 10.3390/molecules26154653. View

Jiang T, Fang L, Wang K . Deciphering "the language of nature": A transformer-based language model for deleterious mutations in proteins. Innovation (Camb). 2023; 4(5):100487. PMC: 10448337. DOI: 10.1016/j.xinn.2023.100487. View

Pejaver V, Urresti J, Lugo-Martinez J, Pagel K, Lin G, Nam H . Inferring the molecular and phenotypic impact of amino acid variants with MutPred2. Nat Commun. 2020; 11(1):5918. PMC: 7680112. DOI: 10.1038/s41467-020-19669-x. View

Da Conceicao L, Cabral L, Pereira G, De Mesquita J . An In Silico Analysis of Genetic Variants and Structural Modeling of the Human Frataxin Protein in Friedreich's Ataxia. Int J Mol Sci. 2024; 25(11). PMC: 11172458. DOI: 10.3390/ijms25115796. View

Richards S, Aziz N, Bale S, Bick D, Das S, Gastier-Foster J . Standards and guidelines for the interpretation of sequence variants: a joint consensus recommendation of the American College of Medical Genetics and Genomics and the Association for Molecular Pathology. Genet Med. 2015; 17(5):405-24. PMC: 4544753. DOI: 10.1038/gim.2015.30. View

Pereira G, de Azevedo Abrahim Vieira B, De Mesquita J . Comprehensive in silico analysis and molecular dynamics of the superoxide dismutase 1 (SOD1) variants related to amyotrophic lateral sclerosis. PLoS One. 2021; 16(2):e0247841. PMC: 7906464. DOI: 10.1371/journal.pone.0247841. View

Khan S, Khan M, Iqbal N, Dilshad N, Almufareh M, Alsubaie N . Enhancing Sumoylation Site Prediction: A Deep Neural Network with Discriminative Features. Life (Basel). 2023; 13(11). PMC: 10672286. DOI: 10.3390/life13112153. View

Vaser R, Adusumalli S, Leng S, Sikic M, Ng P . SIFT missense predictions for genomes. Nat Protoc. 2015; 11(1):1-9. DOI: 10.1038/nprot.2015.123. View

Kumar S U, Kumar D T, R S, C G, Zayed H . An extensive computational approach to analyze and characterize the functional mutations in the galactose-1-phosphate uridyl transferase (GALT) protein responsible for classical galactosemia. Comput Biol Med. 2020; 117:103583. DOI: 10.1016/j.compbiomed.2019.103583. View

10.

Bao W, Gu Y, Chen B, Yu H . Golgi_DF: Golgi proteins classification with deep forest. Front Neurosci. 2023; 17:1197824. PMC: 10213405. DOI: 10.3389/fnins.2023.1197824. View

11.

Kato G, Piel F, Reid C, Gaston M, Ohene-Frempong K, Krishnamurti L . Sickle cell disease. Nat Rev Dis Primers. 2018; 4:18010. DOI: 10.1038/nrdp.2018.10. View

12.

Bromberg Y, Yachdav G, Rost B . SNAP predicts effect of mutations on protein function. Bioinformatics. 2008; 24(20):2397-8. PMC: 2562009. DOI: 10.1093/bioinformatics/btn435. View

13.

Martelotto L, Ng C, De Filippo M, Zhang Y, Piscuoglio S, Lim R . Benchmarking mutation effect prediction algorithms using functionally validated cancer-related missense mutations. Genome Biol. 2014; 15(10):484. PMC: 4232638. DOI: 10.1186/s13059-014-0484-1. View

14.

AlJame M, Ahmad I, Imtiaz A, Mohammed A . Ensemble learning model for diagnosing COVID-19 from routine blood tests. Inform Med Unlocked. 2020; 21:100449. PMC: 7572278. DOI: 10.1016/j.imu.2020.100449. View

15.

Wang R, Luo W, Liu Z, Liu W, Liu C, Liu X . Integration of the Extreme Gradient Boosting model with electronic health records to enable the early diagnosis of multiple sclerosis. Mult Scler Relat Disord. 2020; 47:102632. DOI: 10.1016/j.msard.2020.102632. View

16.

Lu S, Wang J, Chitsaz F, Derbyshire M, Geer R, Gonzales N . CDD/SPARCLE: the conserved domain database in 2020. Nucleic Acids Res. 2019; 48(D1):D265-D268. PMC: 6943070. DOI: 10.1093/nar/gkz991. View

17.

Hornbeck P, Zhang B, Murray B, Kornhauser J, Latham V, Skrzypek E . PhosphoSitePlus, 2014: mutations, PTMs and recalibrations. Nucleic Acids Res. 2014; 43(Database issue):D512-20. PMC: 4383998. DOI: 10.1093/nar/gku1267. View

18.

Thusberg J, Olatubosun A, Vihinen M . Performance of mutation pathogenicity prediction methods on missense variants. Hum Mutat. 2011; 32(4):358-68. DOI: 10.1002/humu.21445. View

19.

Ray S, Pal J, Pal S . Computational approaches for identifying cancer miRNA expressions. Gene Expr. 2013; 15(5-6):243-53. PMC: 6043838. DOI: 10.3727/105221613x13571653093321. View

20.

Choi Y, Chan A . PROVEAN web server: a tool to predict the functional effect of amino acid substitutions and indels. Bioinformatics. 2015; 31(16):2745-7. PMC: 4528627. DOI: 10.1093/bioinformatics/btv195. View