Healthcare
Predicting Recurrent SARS-CoV-2 Mutations Using Machine Learning
- SARS-CoV-2 mutation prediction
- machine learning virology
- AI COVID-19 genomics
- recurrent mutation prediction
- neural networks genomics
- MLJAR AutoML research
- SHAP interpretability biology
- viral evolution modeling
- variant of concern prediction
- genome mutation forecasting
MLJAR tools were used in the following publication.
Prediction of Recurrent Mutations in SARS-CoV-2 Using Artificial Neural Networks
Bryan Saldivar-Espinoza, Guillem Macip, Pol Garcia-Segura, Júlia Mestres-Truyol, Pere Puigbò, Adrià Cereto-Massagué, Gerard Pujadas, Santiago Garcia-Vallve
Universitat Rovira i Virgili, Spain | University of Turku, Finland | EURECAT Technology Centre of Catalonia, Spain
This study published in the International Journal of Molecular Sciences presents a machine learning framework for predicting recurrent mutations in the SARS-CoV-2 genome. Using large-scale genomic data from GISAID (over 877,000 genomes for training and 4.6 million for evaluation), neural network models were developed to predict both recurrent mutation positions and specific nucleotide changes. The models achieved ROC-AUC up to 0.84 for mutation prediction and up to 0.81 for position prediction, with strong performance in M-pro protein (ROC-AUC 0.879). The study demonstrates that machine learning can successfully identify biologically meaningful mutation patterns and anticipate future recurrent mutations.
International Journal of Molecular Sciences • November 24, 2022
Research Domains
Explore peer-reviewed and applied machine learning studies across diverse domains, including healthcare analytics, financial modeling, manufacturing optimization, and structured data classification problems.
Why Researchers and ML Engineers Choose MLJAR Studio
A private, AI-powered Python notebook designed for reproducible machine learning experiments, structured benchmarking, and applied research workflows - fully under your control.
Reproducible Machine Learning Experiments
Design structured pipelines, save experiment runs, and compare results across iterations with full transparency. Every validation setup, hyperparameter configuration, and model benchmark is recorded - making your research repeatable and defensible.
Local-First Execution & Data Control
Run all workflows directly on your machine. Sensitive datasets remain private, with no mandatory cloud uploads or external AI services required. Maintain full control over runtime environments and compliance requirements.
Autonomous Model Benchmarking & Optimization
Automatically compare candidate models, perform cross-validation, and run hyperparameter optimization while retaining full visibility into generated Python code and evaluation metrics. Accelerate experimentation without sacrificing methodological rigor.
Build Research-Grade ML Workflows Locally
Run automated model benchmarking, hyperparameter optimization, and autonomous experiments while keeping full control over your data.