Personal Genomics Zone

Charla en español de Manuel Corpas en el III Webinar Latinoamericano en Análisis Bioinformático (DNA Institute, 14 de noviembre de 2026). Un agente de inteligencia artificial puede analizar un genoma sin que nadie escriba una línea de código, y puede equivocarse con un informe impecable sin que nadie lo note. Qué cuenta como agente, el fallo silencioso que parece correcto, el caso real del archivo vacío en ClawBio, la evidencia en farmacogenómica y tres niveles de validación. Grabación en directo con preguntas del público. Correcciones: las cifras de evidencia citadas proceden del preprint de bioRxiv de junio de 2026 y no del artículo aceptado, cuyo análisis actualizado no atribuye las diferencias entre cohortes a la ascendencia; ClawBio registra unas 3.400 clonaciones por semana, no 5.000. Vídeo y diapositivas en el enlace.

A snapshot of AI agents for biology at the end of 2026, drawn from a critical review of all 147 papers accepted to the NeurIPS 2026 workshop on Agentic AI for Biological Discovery. Five lessons: right answers for the wrong reasons, success measured at the wrong boundary, fragile AI judges, how rarely agents are compared with simpler methods, and a closed loop that is still mostly closed in silico. Plus a tour of what is being built in genomics, molecular design, the clinic and the literature, the eight oral papers, and what it all means for agents in science beyond biology. The review behind the episode was prepared with AI agents and checked by script; 28 papers were read in full and 119 from their abstracts. Narrated with a synthetic voice.

A revision episode from a morning of hands-on learning before a workshop on agents from local to production. Four lessons: the anatomy of an agent with Google ADK and local Gemma 4, watching the loop in the ADK web UI, moving tools into an MCP server, and swapping models with the same test. Includes the failures that taught the most: a lying docstring that passed, a stale tool server, and a codeine question that sat just past the edge of the tools. Narrated with a synthetic voice.

Manuel Corpas presentation recording, prepared for the MENA Microbiome Conference 2026. An unpublished Peru microbiome study asks what antimicrobial resistance annotations can establish across ancient gut, modern human and environmental microbiomes. The presentation examines why a historical comparison changed with the counting method, distinguishes resistance signals from demonstrated mobility or clinical risk, and sets out bounded implications for surveillance. Processing remains incompletely harmonised; the work does not establish a validated Qatar or MENA surveillance protocol. The supplied V9 audio is published unchanged. Duration: 20 minutes 16 seconds.

A 30-minute technical masterclass on agentic AI: tool-calling loops, agent harnesses, context engineering, inference-time computation, planning, multi-agent coordination, evaluation, security, and a reproducible frontier-lab experiment. AI-generated narration; prepared as an advanced learning resource, not a recording of Manuel Corpas speaking. Show notes and transcript: https://github.com/manuelcorpas/podcast/tree/main/episodes/2026-10-12-frontier-agents-01

My plenary keynote for the 2026 World Congress of Psychiatric Genetics in Glasgow, as a full recorded run-through from the day of the talk. How neglect compounds from biobanks to dosing rules to the AI models and agents that learn from them, what our pharmacogenomics benchmark shows when the answer key itself is wrong, and three things to do next: measure the silence, audit the answer key, and write the missing rules. Video with chapters: https://www.youtube.com/watch?v=Ua1cfKElPp8 . Slides: https://docs.clawbio.ai/presentations/wcpg-compounding-neglect-2026/ . Corrections: at 15:07 the 13 million are PubMed search results, not unique papers; at 25:35 97% is agreement with our reference, and the model spread narrowed from 21 to 6 points, not to zero; at 28:38 the Peruvian cohort is 736 people; at 30:11 the framing test used East African, not East Asian.

Manuel Corpas's Crick AI Club talk, recorded on Zoom on 14 September 2026.

Science after pipelines: what changes when scientists direct agents through objectives rather than manually connecting computational tools? This talk introduces ClawBio's inspectable scientific skills, the separation between reasoning, specification and execution, and the evidence needed to trust an agent's work.

Two figures from the pharmacogenomics study show the central result and its boundary: validated rules improve recommendations in a controlled task, while interpretation of genetic inputs still needs separate validation. The talk closes with composable scientific capabilities, executable methods and practical ways to get involved.

This is Manuel's recorded presentation, including the opening and closing remarks. It does not include a question-and-answer session or a live software demonstration. The pharmacogenomics evidence concerns tested components, not clinical validation of an end-to-end autonomous system.

Slides (PDF and PowerPoint): https://docs.clawbio.ai/presentations/crick-science-after-pipelines-2026/
YouTube: https://www.youtube.com/watch?v=k-oJZjFLWuU
Documentation: https://docs.clawbio.ai/
Events calendar: https://luma.com/clawbio
ClawBio Slack: https://app.slack.com/client/T0BP97N69KM/C0BP1FSGTHV
Event: https://luma.com/clawbio-7ibq
Benchmark data: https://doi.org/10.5281/zenodo.22141182

What changes when a scientist can direct an AI agent using scientific context rather than programming syntax? In this lecture from the INFLAMomx Training School in Salerno, Manuel Corpas demonstrates real RNA-seq and single-cell workflows, an invalid control that stops safely, and the role of skills, evals and equity in clinical-grade agentic genomics. PDF slides: https://docs.clawbio.ai/presentations/salerno-agentic-genomics-2026/Salerno-Agentic-Genomics-Slides.pdf

A practical starter for scientists and knowledge workers: requirements, five agentic prompts, a freshness test and a downloadable kit. Written by Manuel Corpas. Narrated with OpenAI Cedar, an AI-generated voice. Starter kit: https://manuelcorpas.github.io/podcast/resources/corpas-core-gbrain-starter.zip

I joined Arseniy Arsentyev on episode 16 of the Tomorrow's Medicine podcast to talk about agentic genomics: what it is, why I coined the term, and why the hard part is not intelligence but trust. We cover the road from a bioinformatics MSc in Manchester in 2000, to building DECIPHER at the Sanger Institute, to sequencing my own exome in 2010 and publishing my family's genomes. Then the last twelve months: Claude Code as the inflection point, ClawBio winning the Imperial College agentic AI hackathon, 43 contributors and around 5,000 clones a week, and why AI amplifies health inequity rather than solving it. Original show: https://www.youtube.com/@tommedpod