AI for Phenomics: When Images Meet Molecules
Phenomics bridges the molecular and the visible—using high-throughput imaging, clinical phenotypes, and electronic health records to connect genotype to phenotype. AI is central to this effort.
term
Agentic AI
AI for Metagenomics: Decoding the Microbiome
How deep learning and transformer models are transforming metagenomics, from assembly and taxonomic classification to predicting microbiome-disease associations and antibiotic resistance.
AI for Metabolomics: The Chemical Fingerprint of Life
Metabolomics is the least 'language-model-ready' omics field, yet deep learning is transforming metabolite identification, pathway analysis, and biomarker discovery.
AI for Proteomics: From AlphaFold to Protein Design
Protein AI is the most mature omics AI field. But structure prediction was just the beginning—the frontier is now protein design, function prediction, and interaction modeling.
AI for Transcriptomics: Understanding Gene Expression at Scale
Exploring the rise of single-cell foundation models like scGPT and Geneformer, spatial transcriptomics, and how transformer architectures are deciphering the complex language of gene expression.
AI for Genomics: Reading the Book of Life with Transformers
DNA foundation models can now predict gene expression, identify regulatory elements, and classify variants from raw sequence alone. We review the major models—DNABERT-2, Nucleotide Transformer, Evo, and HyenaDNA—and what …
Benchmarks and Evaluation: How Do We Know If Omics AI Actually Works?
Claims of AI breakthroughs in biology are only as strong as their evaluation. This post critically examines benchmarks, metrics, and common pitfalls in evaluating biological AI models.
The Data Infrastructure Challenge: From Raw Reads to AI-Ready Datasets
The bottleneck for AI in omics is often not the model but the data. This post covers the infrastructure, standards, and preprocessing pipelines that make omics data AI-ready.
Foundation Models Meet Biology: The Transformer Revolution in Life Sciences
Why transformer-style foundation models work so well on biological data, where the analogy to language breaks down, and which genomics, proteomics, and single-cell models matter most in 2026.
The Omics Revolution: A Map of the Territory
Before diving into AI, we need a clear map of what 'omics' actually covers. Each discipline studies a different layer of biological information, and AI readiness varies dramatically across them.
