Scholarlink

The rapid evolution of high-throughput sequencing technologies has transformed genomicsGenomics into a data-intensive discipline, generating vast amounts of heterogeneous biological data. This chapter explores the transformative role of artificial intelligence (AIArtificial Intelligence (AI)) in addressing analytical challenges across the genomicGenomics pipeline. AIArtificial Intelligence (AI) methodologies, including machine learningMachine Learning (ML), deep learningDeep Learning (DL), probabilistic modeling, and graph-basedGraph-based modeling approaches, enable the integration of diverse data sources, capture nonlinear relationships, and scale to population-level datasets. Key applications discussed include AIArtificial Intelligence (AI)-assisted genome assemblyGenome assembly and base callingBase calling, variant callingVariant calling and prioritization, gene expression predictionGene expression prediction, epigenomicEpigenomics modeling, disease risk predictionDisease risk prediction, microbiome analysisMicrobiome analysis, and population genomicsPopulation genomics. Emphasis is placed on responsible AI deploymentResponsible AI deployment, transparent benchmarking, and biological interpretability. By complementing experimental and theoretical frameworks, AIArtificial Intelligence (AI) enhances hypothesis generation, accelerates discovery, and supports translational genomicsGenomics, shaping the future of precision medicinePrecision medicine and genomicGenomics science. ​

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Application of AI in Genomics

  • 章节

  • 发表日期：

    2026年

查看全文
  • Khalid Shaikh,
  • Rohit Thanki,
  • Sejal Shah

摘要

The rapid evolution of high-throughput sequencing technologies has transformed genomicsGenomics into a data-intensive discipline, generating vast amounts of heterogeneous biological data. This chapter explores the transformative role of artificial intelligence (AIArtificial Intelligence (AI)) in addressing analytical challenges across the genomicGenomics pipeline. AIArtificial Intelligence (AI) methodologies, including machine learningMachine Learning (ML), deep learningDeep Learning (DL), probabilistic modeling, and graph-basedGraph-based modeling approaches, enable the integration of diverse data sources, capture nonlinear relationships, and scale to population-level datasets. Key applications discussed include AIArtificial Intelligence (AI)-assisted genome assemblyGenome assembly and base callingBase calling, variant callingVariant calling and prioritization, gene expression predictionGene expression prediction, epigenomicEpigenomics modeling, disease risk predictionDisease risk prediction, microbiome analysisMicrobiome analysis, and population genomicsPopulation genomics. Emphasis is placed on responsible AI deploymentResponsible AI deployment, transparent benchmarking, and biological interpretability. By complementing experimental and theoretical frameworks, AIArtificial Intelligence (AI) enhances hypothesis generation, accelerates discovery, and supports translational genomicsGenomics, shaping the future of precision medicinePrecision medicine and genomicGenomics science. ​