Base by Base24 Marras 2025

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 describing Evo 1.5 semantic design, contextual autocompletion, toxin–antitoxin designs (T2TA/T3TA), anti-CRISPR designs, and SynGenome, plus limitations and licensing statements.
- transcript topics: Semantic design and genomic context; In-context design and autoregression; Toxin–antitoxin (T2TA) design and validation; Toxin–antitoxin (T3TA) design and validation; Anti-CRISPR (Acr) design and validation; SynGenome database 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 of de novo genes (Evo 1.5).
- Autocomplete test: Evo 1.5 achieved 85% amino acid recovery for rpoS with 30% input.
- Toxin–antitoxin (T2TA) design yielded functional toxins and antitoxins; EvoRelE1 toxin; EvoAT1–4 antitoxins; EvoAT2 and EvoAT4 show multitoxin neutralization; EvoT3TA design produc
- Anti-CRISPR (Acr) designs produced functional Acrs; 17% of tested Acrs exhibited activity against SpCas9; EvoAcr1–5 validated.
- SynGenome database contains over 120 billion base pairs of AI-generated DNA; ~3.7 million predicted protein structures; Pfam-domain frequencies in SynGenome closely mirror natural
- Limitations include autoregressive generation risks (repetitive/hallucinated sequences) and reliance on genomic context; lab validation remains essential; applicability to human ge

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

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(441)

439: Coembedding Sequence and Structure: CLSS Maps the Protein Universe

Longo LM et al., PNAS - This episode summarizes a PNAS study introducing CLSS, a contrastive two-tower protein language model that coembeds domain sequences, structures, and subsequences into a shared...

11 Elo 23min

438: Mapping AIRE: a proactive atlas of 9,790 missense variants

Axakova A et al., The American Journal of Human Genetics - Axakova et al. generated a variant effect map for AIRE using an insulin‑promoter GFP reporter in HEK293 cells to measure the functional impac...

10 Elo 24min

437: Cell villages and Dirichlet modeling map human cell fitness genetics

Hanson C et al., The American Journal of Human Genetics - Hanson et al. combine pooled multi-donor human neural progenitor cell "villages" with Townlet, a hierarchical Dirichlet regression model, to e...

9 Elo 28min

436: KIAP4 and the ARND family: building the Leishmania adhesion plaque

Owino BO et al., PNAS - Using TurboID proximity proteomics and microscopy, researchers identify KIAP4 as the canonical member of a conserved Adhesion Related NTPase-like Domain (ARND) family that loca...

8 Elo 24min

435: E. coli TGT binds two tRNAs — cryo-EM reveals dual engagement

Ember M et al., PNAS - This episode examines a cryo-EM study of Escherichia coli tRNA-guanine transglycosylase (TGT) that solves the enzyme structure and its covalent intermediate with tRNATyr. Unexpe...

7 Elo 19min

434: High‑coverage genomes recast Japan's prehistoric demography

Ishiya K et al., PNAS - This episode examines a PNAS study that reports two high-coverage ancient human genomes from mainland Japan (an Initial Jomon >67× and a Middle Yayoi >46×). The genomes enable ...

6 Elo 27min

433: Lactate, HSP90α and the Mitochondrial Switch

Wu G et al., Proceedings of the National Academy of Sciences - This episode examines a PNAS study that identifies site-specific lactylation of HSP90α as a metabolic signal linking glycolysis to mitoch...

23 Heinä 23min

432: Echovirus 18: Capsid opening releases the genome

Mukhamedova L et al., Proceedings of the National Academy of Sciences - Using cryo-electron tomography and single-particle cryo-EM of infected Cos-7 cells, the authors show that echovirus 18 (E18) rel...

23 Heinä 18min