207: Semantic Design of de novo Genes with Evo

Semantic Design of de novo Genes with Evo Music:Enjoy the music based on this article at the end of the episode. DOI:10.1038/s41586-025-09749-7 License:This episode is based on an open-access article published under the Creative Commons Attribution 4.0 International License (CC BY 4.0) – https://creativecommons.org/licenses/by/4.0/ Support:Base by Base – Stripe donations: https://donate.stripe.com/7sY4gz71B2sN3RWac5gEg00 Official website https://basebybase.com On PaperCast Base by Base you’ll discover the latest in genomics, functional genomics, structural genomics, and proteomics. Episode link: https://basebybase.com/episodes/semantic-design-of-de-novo-genes-with-evo ️ Episode:207: Semantic Design of de novo Genes with Evo ️ Season:1 Article title:Semantic design of functional de novo genes from a genomic language model Journal:Nature QC:This episode was checked against the original article PDF and publication metadata for the episode release published on 2025-11-24. QC Scope:- article metadata and core scientific claims from the narration- excludes analogies, intro/outro, and music- transcript coverage: Audited transcript sections covering Evo 1.5 long-context genomic language modeling, in-context design with gene autocomplete, toxin–antitoxin (T2TA/T3TA) design and validation, anti-CRISPR (Acr) design, SynGenome database creation and analyses, and discussed limitations/future directions.- transcript topics: Evo 1.5 long-context genomic language model; In-context genomic design and autocomplete assessments; Amino acid sequence recovery and sequence diversity; Toxin–antitoxin (T2TA and T3TA) design and validation; Anti-CRISPR (Acr) design and validation; SynGenome database creation and analyses QC Summary:- factual score: 10/10- metadata score: 10/10- supported core claims: 6- claims flagged for review: 0- metadata checks passed: 4- metadata issues found: 0 Metadata Audited:- article_doi- article_title- article_journal- license Factual Items Audited:- Semantic design uses genomic context to enable function-guided design and generate de novo genes (Evo learns distributional semantics over prokaryotic genes).- Autocomplete test on conserved genes (e.g., rpoS) with Evo 1.5 achieved ~85% amino acid recovery at 30% input.- Evo-generated functional toxin–antitoxin (T2TA) systems with low sequence identity to known proteins, including multitoxin neutralization by EvoAT2 and EvoAT4.- Evo-design of type III toxin–antitoxin (T3TA) systems produced functional RNA antitoxins; EvoAT6 neutralized ToxN.- Anti-CRISPR (Acr) design yielded functional Acrs with a 17% experimental success rate in SpCas9 assays.- SynGenome: a database of over 120 billion base pairs of AI-generated genomic sequences; Pfam domain frequencies in SynGenome closely mirror natural genomes (Pearson r ≈ 0.78). QC result: Pass. Chapters (00:00:00) - A New Way to Design New Genomes(00:05:45) - Artificial Intelligence's challenge to protein design(00:11:08) - Uncovering the genome's hidden secrets(00:11:53) - The Secret Life of Genes