Artificial intelligence in variant calling: a review

Artificial intelligence (AI) has revolutionized numerous fields, including genomics, where it has significantly impacted variant calling, a crucial process in genomic analysis. Variant calling involves the detection of genetic variants such as single nucleotide polymorphisms (SNPs), insertions/delet...

Full description

Saved in:
Bibliographic Details
Main Authors: Omar Abdelwahab, Davoud Torkamaneh
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Bioinformatics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fbinf.2025.1574359/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850200958225612800
author Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
author_facet Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
author_sort Omar Abdelwahab
collection DOAJ
description Artificial intelligence (AI) has revolutionized numerous fields, including genomics, where it has significantly impacted variant calling, a crucial process in genomic analysis. Variant calling involves the detection of genetic variants such as single nucleotide polymorphisms (SNPs), insertions/deletions (InDels), and structural variants from high-throughput sequencing data. Traditionally, statistical approaches have dominated this task, but the advent of AI led to the development of sophisticated tools that promise higher accuracy, efficiency, and scalability. This review explores the state-of-the-art AI-based variant calling tools, including DeepVariant, DNAscope, DeepTrio, Clair, Clairvoyante, Medaka, and HELLO. We discuss their underlying methodologies, strengths, limitations, and performance metrics across different sequencing technologies, alongside their computational requirements, focusing primarily on SNP and InDel detection. By comparing these AI-driven techniques with conventional methods, we highlight the transformative advancements AI has introduced and its potential to further enhance genomic research.
format Article
id doaj-art-2112bef1c7cb42ea9d6f2c2c29a3e266
institution OA Journals
issn 2673-7647
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Bioinformatics
spelling doaj-art-2112bef1c7cb42ea9d6f2c2c29a3e2662025-08-20T02:12:10ZengFrontiers Media S.A.Frontiers in Bioinformatics2673-76472025-04-01510.3389/fbinf.2025.15743591574359Artificial intelligence in variant calling: a reviewOmar Abdelwahab0Omar Abdelwahab1Omar Abdelwahab2Omar Abdelwahab3Davoud Torkamaneh4Davoud Torkamaneh5Davoud Torkamaneh6Davoud Torkamaneh7Département de Phytologie, Université Laval, Québec City, QC, CanadaInstitut de Biologie Intégrative et des Systèmes (IBIS), Université Laval, Québec City, QC, CanadaCentre de recherche et d’innovation sur les végétaux (CRIV), Université Laval, Québec City, QC, CanadaInstitut intelligence et données (IID), Université Laval, Québec City, QC, CanadaDépartement de Phytologie, Université Laval, Québec City, QC, CanadaInstitut de Biologie Intégrative et des Systèmes (IBIS), Université Laval, Québec City, QC, CanadaCentre de recherche et d’innovation sur les végétaux (CRIV), Université Laval, Québec City, QC, CanadaInstitut intelligence et données (IID), Université Laval, Québec City, QC, CanadaArtificial intelligence (AI) has revolutionized numerous fields, including genomics, where it has significantly impacted variant calling, a crucial process in genomic analysis. Variant calling involves the detection of genetic variants such as single nucleotide polymorphisms (SNPs), insertions/deletions (InDels), and structural variants from high-throughput sequencing data. Traditionally, statistical approaches have dominated this task, but the advent of AI led to the development of sophisticated tools that promise higher accuracy, efficiency, and scalability. This review explores the state-of-the-art AI-based variant calling tools, including DeepVariant, DNAscope, DeepTrio, Clair, Clairvoyante, Medaka, and HELLO. We discuss their underlying methodologies, strengths, limitations, and performance metrics across different sequencing technologies, alongside their computational requirements, focusing primarily on SNP and InDel detection. By comparing these AI-driven techniques with conventional methods, we highlight the transformative advancements AI has introduced and its potential to further enhance genomic research.https://www.frontiersin.org/articles/10.3389/fbinf.2025.1574359/fullvariant callingartificial intelligencedeep learninggenomicsmachine learning (ML)
spellingShingle Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Omar Abdelwahab
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
Davoud Torkamaneh
Artificial intelligence in variant calling: a review
Frontiers in Bioinformatics
variant calling
artificial intelligence
deep learning
genomics
machine learning (ML)
title Artificial intelligence in variant calling: a review
title_full Artificial intelligence in variant calling: a review
title_fullStr Artificial intelligence in variant calling: a review
title_full_unstemmed Artificial intelligence in variant calling: a review
title_short Artificial intelligence in variant calling: a review
title_sort artificial intelligence in variant calling a review
topic variant calling
artificial intelligence
deep learning
genomics
machine learning (ML)
url https://www.frontiersin.org/articles/10.3389/fbinf.2025.1574359/full
work_keys_str_mv AT omarabdelwahab artificialintelligenceinvariantcallingareview
AT omarabdelwahab artificialintelligenceinvariantcallingareview
AT omarabdelwahab artificialintelligenceinvariantcallingareview
AT omarabdelwahab artificialintelligenceinvariantcallingareview
AT davoudtorkamaneh artificialintelligenceinvariantcallingareview
AT davoudtorkamaneh artificialintelligenceinvariantcallingareview
AT davoudtorkamaneh artificialintelligenceinvariantcallingareview
AT davoudtorkamaneh artificialintelligenceinvariantcallingareview