#GenBio
This week in #GenBioWeekly:

Malaria mosquito research in Burkina Faso, new vector surveillance findings from Angola, #OneHealth research, gene drives at #COP17, and a preview of Nairobi’s 2027 GenBio Congress.

Explore the latest edition: mailchi.mp/ce6e83675ec4...
The Genbio Weekly Newsletter
mailchi.mp
November 3, 2026 at 7:54 AM
This week in #GenBioWeekly:

Malaria mosquito research in Burkina Faso, new vector surveillance findings from Angola, #OneHealth research, gene drives at #COP17, and a preview of Nairobi’s 2027 GenBio Congress.

Explore the latest edition: mailchi.mp/ce6e83675ec4...
The Genbio Weekly Newsletter
mailchi.mp
November 3, 2026 at 8:06 AM
#Hantavirus Vaccine 💉Enabled by its High Resolution Structure of Glycoprotein Tetramer & its lattice organization possibly enabling an #mRNA Vaccine to do what was done with the COVID-19 #vaccine❗
genengnews.com/topics/infec... via
@GENbio
Hantavirus Vaccine Enabled by High Resolution Structure of Glycoprotein
High resolution structures of the hantavirus glycoprotein tetramer are poised to support vaccine development.
genengnews.com
October 20, 2026 at 10:13 AM
AI's Large Looting Models? The Emerging Generative Biology Stack as the Next Frontier of Biopiracy

#generativebiology (#GenBio) is the use of #generativeAI to redesign genomes, proteins, RNA and metabolic pathways. Promoted as a transformative solution for […]

[Original post on mastodon.social]
October 7, 2026 at 2:27 PM
GenBio AI, cofundada por el Nobel David Baker y Eric Xing (MBZUAI), presentó AIDO Cell, un "world model" que, según la empresa, simula una célula humana y su respuesta a fármacos, del ADN a la célula completa. Es una versión preliminar con métricas propias.
GenBio, cofundada por un Nobel, lanza una "célula virtual" con IA para simular fármacos
GenBio AI, una empresa de biotecnología con inteligencia artificial basada en Palo Alto (California) y con oficinas en Abu Dabi y París, presentó AIDO Cell, un sistema al que describe como el primer simulador de propósito general de la célula humana. Según la compañía, el modelo simula una célula y su respuesta a fármacos y otras intervenciones a lo largo de toda la jerarquía biológica, del ADN y el ARN a la célula completa. GenBio fue cofundada por el Nobel de Química 2024 David Baker y por Eric Xing, presidente de la Universidad de IA Mohamed bin Zayed (MBZUAI) de Abu Dabi; la embajada de los Emiratos Árabes Unidos en Washington destacó el desarrollo el 16 de septiembre. La promesa es acelerar el descubrimiento de medicamentos, aunque por ahora se trata de una versión preliminar. ## Qué hace AIDO Cell GenBio dice que AIDO Cell está construida sobre un "world model" (modelo del mundo), una arquitectura que mantiene un estado interno de la célula que el usuario puede perturbar, redirigir y leer en distintos momentos, en lugar de dar una sola predicción de golpe. Sobre ese motor, la empresa sumó una capa de control que sigue el estado de la célula a través de cada escala y traduce las órdenes del investigador en pasos ejecutables. Eso permite, según GenBio, encadenar perturbaciones sucesivas, por ejemplo una mutación de resistencia y dos tratamientos de seguimiento, y comparar los resultados como ramas de un mismo experimento. La versión 1.0 simula dos líneas celulares humanas muy estudiadas: K-562, de un paciente con leucemia, y Hep-G2, de un tumor de hígado. Como prueba de concepto, la empresa afirma que el sistema reprodujo el mecanismo conocido del imatinib, comercializado como Gleevec por Novartis, en células de leucemia K-562. AIDO Cell también funciona "hacia atrás": el usuario define un estado celular deseado y el sistema propone moléculas para alcanzarlo, algo que GenBio llama diseño molecular en contexto. David Baker, que compartió el Nobel de Química 2024, matizó que no han resuelto la biología celular, pero que por primera vez existe un sistema capaz de simular una célula en toda su jerarquía biológica, del ADN al comportamiento de la célula completa, en un mismo lugar. Eric Xing, científico jefe de la empresa, dijo que su objetivo es una biología "computable, predecible y, en última instancia, programable". Imagen ilustrativa de investigación en biología computacional; no muestra AIDO Cell. · Foto de Tima Miroshnichenko en Pexels ## El respaldo de los Emiratos y quién está detrás AIDO Cell salió de una colaboración en la que, además de GenBio, participaron investigadores de la MBZUAI de Abu Dabi, Harvard y Stanhope, según la embajada de los EAU en Washington, que difundió el trabajo. Eric Xing preside la MBZUAI y es cofundador y científico jefe de GenBio, que mantiene oficinas en Abu Dabi y París. La empresa dice que trabaja en un "banco de células virtuales" para que, con el tiempo, los investigadores descarguen células a medida y hagan experimentos abiertos, y que busca socios para lograrlo. Una difusión oficial demuestra qué afirma quien la emite, no que su versión sea concluyente. ## Por qué conviene leer la letra chica Los datos más llamativos vienen de la propia empresa. GenBio dice que AIDO Cell 1.0 alcanza el estado del arte en 24 de 31 métricas, pero esas métricas pertenecen a un banco de pruebas que creó ella misma, el Virtual Cell Benchmark 1.0, y no a una evaluación independiente. La compañía lo reconoce: compara la situación con la falta de un "CASP para la simulación celular", el tipo de prueba a ciegas y comunitaria que dio credibilidad a AlphaFold, y admite que ese estándar todavía no existe y que la validación en laboratorio de predicciones nuevas es "la prueba definitiva", con experimentos en marcha. Por ahora, AIDO Cell no es de acceso público: funciona para el equipo de GenBio y un grupo de colaboradores, con una lista de espera para investigadores, y no es un trabajo revisado por pares. Conviene tratar sus capacidades como lo que son: afirmaciones de la empresa pendientes de comprobación externa. La idea de una célula que se pueda programar, observar y depurar como un circuito es potente para una industria donde cada medicamento cuesta años y miles de millones de dólares. La distancia entre esa promesa y la práctica clínica la marcará la validación independiente que, por ahora, AIDO Cell no tiene. _Fuentes:_ 1, 2
fomoera.com
September 22, 2026 at 1:30 PM
📩 The latest GenBioWeekly Newsletter is here!

Stay informed with updates and insights on genetic biocontrol across Africa.

📷Subscribe for weekly updates:
eepurl.com/hG79X1

🔗Read the latest edition:
mailchi.mp/661abd12ffdb...

@genbio.bsky.social
#GenBioWeekly #Biotechnology #ScienceCommunication
The GenBio Weekly Newsletter
mailchi.mp
September 21, 2026 at 10:20 AM
In August 2026, GenBio AI and Arc Institute pushed biological AI from reading DNA to simulating a whole cell. The models are impressive; the data, the benchmarks and the GPU bill will decide who wins.
The Virtual Cell Race: AI Biology Moves From DNA to Whole-Cell Simulation
For three years, biology has been promised its ChatGPT moment. The sales pitch barely changes: a model that reads the language of life, writes sequences nature never got around to, and compresses a decade at the bench into an afternoon of inference. What landed in August 2026 is stranger and smaller than that pitch. On August 18, GenBio AI — a Palo Alto company co-founded by Nobel laureate David Baker and Eric Xing, president of the Mohamed bin Zayed University of Artificial Intelligence — introduced AIDO Cell. GenBio calls it the first world model of a human cell. The system walks the full biological hierarchy, from DNA and RNA through protein to the whole cell, and predicts how a drug or a switched-off gene ripples upward. Two days later, Arc Institute opened the 2026 Virtual Cell Challenge on the opposite principle: no training set, six cell lines no entrant has seen perturbed, and $100,000 for whoever predicts how each responds to a gene knockdown — switching one gene off. Both programs chase the same artifact. Both keep hitting the same wall. The binding constraint on simulated biology turned out to be compute, not biology. ## Three things the August milestones settled 🎯 **A virtual cell is now a scored benchmark.** Arc's challenge grades models zero-shot on cell lines they have never seen, so the leaderboard measures generalization rather than memorization. **The winning architecture is a stack.** A DNA foundation model, a perturbational dataset, and an agentic build harness sit underneath every credible cell simulator. **The compute vendors are inside the race.** NVIDIA's BioNeMo is the substrate GenBio builds on and a sponsor of Arc's challenge, which turns GPU capacity into a strategic input for biology labs. The two announcements matter less for what they shipped than for what they measured. A cell simulator became something a third party can grade. The build is assembling into layers. And the supplier of those layers now has a stake in the result. ## The stack underneath a cell Start with DNA as a language. Arc's Evo 2 is a genomic foundation model trained on more than 9.3 trillion nucleotides drawn from over 128,000 genomes, built as a 40-billion-parameter network with a one-million-token context window. It reads and writes DNA, RNA and protein sequences at single-nucleotide resolution — the level at which evolution actually operates. The work was published in Nature in March 2026, and the weights are open. The 40B model has passed six million API calls; the repository has cleared 88,000 downloads. Data is the second layer. Arc's Virtual Cell Atlas gathers more than 600 million cells, including Tahoe-100M — 100 million cells from roughly 60,000 drug-perturbation experiments, mapping 50 cancer models against more than 1,100 treatments. Tahoe built it on its Mosaic platform with Parse Biosciences' GigaLab and Ultima Genomics sequencing. Scale matters here because a cell simulator fails on the experiments it never saw. ## From sequence to simulation The third layer is the simulator. Arc shipped State, its first virtual cell model, in June 2025. GenBio's AIDO Cell, released in August 2026, tries the full hierarchy in one continuous system: perturb the cell at any level, from a single gene to a protein, then read out the whole response. Release 1.0 covers two human cell lines, K-562 and Hep-G2, and arrives with a Virtual Cell Benchmark. This is the direction we flagged in July, when AI protein-design platforms were already compressing the discovery loop. The virtual cell pushes that work up a level, from single molecules to an entire cell. TIMELINE: from DNA language to a simulated cell ───────────────────────────────────────────────────────────── 2024 2025 2025 2026 2026 🧬 🧬 🧪 🧪 ◉ NOW Evo 1 Evo 2 State AIDO Cell Virtual Cell 7B params preprint first whole-cell Challenge + BioNeMo virtual world model zero-shot cell model ───────────────────────────────────────────────────────────── Sources: Arc Institute, GenBio AI, Nature (2026) Evo 1 (Science, 2024), Evo 2 (Nature, March 2026), State (June 2025), AIDO Cell (August 2026), Virtual Cell Challenge 2026. Above all three layers sits the build harness. GenBio runs VCHarness, an agentic system that generates, tests and refines candidate cell components, wired into NVIDIA's BioNeMo, Megatron and NIM microservices. Biology's model factory is now an AI infrastructure project. 40B parameters #### Evo 2 genomic foundation model Trained on 9.3T nucleotides with a one-million-token context window. · _Nature, 2026_ 100M single cells #### Tahoe-100M perturbational dataset About 60,000 drug experiments across 50 cancer models; the Atlas holds 600M+ cells. · _Arc Virtual Cell Atlas, 2025_ > We are far from solving cell biology, but we have built a system that can be interrogated as though it were a cell.— Eric Xing, co-founder and chief scientist, GenBio AI ## Who is actually racing Arc Institute is the nonprofit anchor. Headquartered in Palo Alto, it builds the open stack — Evo, State, the Atlas — and runs the competition that sets the benchmark. It named Usman Muzaffar as chief technology officer in July 2026 to push the Virtual Cell Initiative. Its challenge is backed by NVIDIA, 10x Genomics and Ultima Genomics, and the final test set lands on October 22, 2026. GenBio AI is the commercial challenger. It assembles pre-trained models for DNA, RNA, protein and cell into one programmable system, and it is already selling the promise of downloadable cells for open-ended experiments. Its offices in Palo Alto, Abu Dhabi and Paris signal where it expects the buyers to be. Around them sit the incumbents of computational drug design. Isomorphic Labs, spun out of Alphabet's DeepMind, applies the AlphaFold lineage to molecular design. Insitro pairs lab-generated data with machine learning across metabolic and neurological disease. Recursion runs one of the largest automated wet-lab fleets in the industry. None of them owns a full-hierarchy cell simulator yet. That is the gap both August announcements claim to narrow. ## Where the promise breaks The Evo 2 team put a number on the distance still to travel. Fine-tuning the model on bacteriophage genomes produced 285 candidate designs; 16 of them propagated and inhibited the target bacteria without touching unrelated strains. That is a working rate near 6% — progress, and a long way from engineering. Cell biology adds its own friction. AIDO Cell 1.0 simulates two cell lines. Generalization across cell contexts — the exact capability Arc's 2026 challenge measures — is unsolved, and that is why the competition withholds a training set. Roughly one in 10,000 compounds that enter development reaches the clinic, the ratio the virtual cell is meant to improve. About a fifth of human proteins still have no known function, which limits what any simulator can be asked to predict. Biosafety is the quiet constraint. Arc excluded eukaryotic viruses from Evo 2's training on purpose, and its red-team reviews found that generated sequences for pathogenic viral proteins read as effectively random. The team has said plainly that future, more capable models will need stronger alignment work. ## What to watch next 📊 **Key signals to track** The Virtual Cell Challenge final test set releases on October 22, 2026 — the zero-shot scores will show whether generalization is real or leaderboard noise. Whether AIDO Cell expands past K-562 and Hep-G2 in its next release, or stays a two-cell demonstration. Whether a pharmaceutical company commits to replacing any part of a trial with an in-silico readout. Whether the Arc Atlas crosses one billion cells, and whether NVIDIA's biology stack becomes a paid line item for labs. The virtual cell is no longer a thought experiment. It has a benchmark, a dataset, a vendor stack and a scoreboard. What it does not yet have is proof that a simulation predicts a patient. The next twelve months of leaderboard results will say more about that than any launch. Compute decides how fast biology gets there. ## Sources Genome modelling and design across all domains of life with Evo 2 The peer-reviewed Evo 2 paper: 40B parameters, a one-million-token context and 9.3 trillion nucleotides of training data. Nature The primary source for the model layer of the stack — and for the 16-of-285 bacteriophage result. The 2026 Virtual Cell Challenge: zero-shot prediction across unseen cell lines Arc's benchmark sets the task: predict gene-knockdown responses in six cell lines the model has never been trained on, for a $100,000 prize. Arc Institute The benchmark design is the story: it measures generalization, which is the capability the field has not yet shown. AIDO Cell: A General-Purpose Simulator for Cell Biology GenBio AI's technical description of its whole-cell world model, covering the K-562 and Hep-G2 prototype and Virtual Cell Benchmark 1.0. GenBio AI The commercial counterweight to Arc's open stack — and the clearest statement yet of what a programmable cell is meant to sell.
nexi.fund
September 17, 2026 at 10:00 AM
📩 The latest GenBioWeekly Newsletter is here! Stay informed with updates and insights on genetic biocontrol across Africa.

📷Subscribe for weekly updates: eepurl.com/hG79X1

Read the latest edition: mailchi.mp/a3c67380dc69...

@genbio.bsky.social
#GenBioWeekly #Biotechnology #ScienceCommunication
The GenBio Weekly Newsletter
mailchi.mp
September 15, 2026 at 9:47 AM
[ainet] [AI가 세포를 기억하고 다시 조립한다? GenBio AIDO Cell, 가상 세포 시뮬레이션의 새 지평] DNA·RNA·단백질·세포 행동을 하나의 계산 환경에서 연결하고, 세포가 이전에 겪은 교란(perturbation)을 기억하는 상태 기반(state-based) 시뮬레이터
www.ainet.link/28430
[AI가 세포를 '기억'하고 다시 조립한다? GenBio AIDO Cell, 가상 세포 시뮬레이션의 새 지평] DNA·RNA·단백질·세포 행동을 하나의 계산 환경에서 연결하고, 세포가 이전에 겪은 교란(perturbation)을 기억하는 상태 기반(state-based) 시뮬레이터
AI가세포를'기억'하고다시조립한다?GenBioAIDOCell,가상세포시뮬레이션의새지평생물학은수세기동안분해(환원주의)를통해발전해왔다.유전자,단백질,신호
www.ainet.link
September 2, 2026 at 1:23 PM
🧬 Can we engineer life?

On BBC Radio 4, EIT's Prof Jason Chin explored one of biology’s biggest questions: how far can we go in understanding - and ultimately building - living systems?

🎧Listen on BBC Sounds: bbc.co.uk/sounds/play/m0030mc8

#GenBio #GenerativeBiology
August 27, 2026 at 1:11 PM
AIDO Cell simulates a whole human cell, DNA to structure, and remembers each step. Bold claim; wet-lab proof is still pending. Read the breakdown. #AIinBiology #VirtualCell #DrugDiscovery

artificialscience.org/2026/08/ai-v...
A Nobel Laureate's AI Just Tried to Simulate a Whole Human Cell — Artificial Science
GenBio AI's AIDO Cell is a 'world model' that simulates a human cell across scales, from DNA to shape. Here's what it does, why it matters, and what still needs proving.
artificialscience.org
August 25, 2026 at 5:53 AM
El objetivo es fortalecer la producción nacional frente a situaciones de riesgo y la economía del país. Laboratorios KENER invertirá 5 mil 180 mdp; GENBIO serán 4 mil mdp; ALPHARMA BioGenTec hará una inversión inicial de 800 mdp y NEOLSYM invertirá 500 mdp
Empresas farmaceúticas consolidan inversión en Querétaro
Como parte del Plan México, el Gobierno de México, a través de las secretarías de Economía y de Salud, anunció una inversión de 10 mil 480 millones de pesos (mdp) por parte de las empresas mexicanas KENER, que destinará 5 mil 180 mdp; GENBIO, 4 mil mdp, ALPHARMA BioGenTec, 800 mdp; y NEOLSYM, 500 mdp, con el objetivo de fortalecer la industria farmacéutica en el país.
amanecerqro.com
July 3, 2025 at 6:33 PM
Scientists successfully replace defective gene in mice to alleviate symptoms of Dravet syndrome—a rare form of epilepsy—without adverse side effects or death www.genengnews.com/topics/genom... via @GENbio
Gene Therapy Tested in Mice Offers New Hope for People with Dravet Syndrome
By replacing the defective gene associated with Dravet syndrome in mice, scientists successfully alleviated symptoms without side effects.
www.genengnews.com
March 21, 2025 at 12:33 PM
GEN | Insight & Intelligence™: Candidates’ Science Answers Raise More Questions http://www.genengnews.com/analysis-and-insight/candidates-science-answers-raise-more-questions/77899682/ via @genbio
Candidates’ Science Answers Raise More Questions
Presidental candidates’ responses to ScienceDebate.org qu...
www.genengnews.com
March 7, 2025 at 1:36 AM
MT @GENbio Dark World Awaits Women Ph.D.s: http://bit.ly/194L0oB Some helpful advice – Ellen Daniell on peer support http://bit.ly/18iBE9u
Dark World Awaits Women Ph.D.s
Wellcome Trust study “Do Babies Matter?” cites more caree...
bit.ly
March 6, 2025 at 11:42 PM
i wanna draw i don't want to study for my genbio test 😞😞
February 2, 2025 at 1:01 AM
This AI startup GenBio, which lists Nobel laureate David Baker among its co-founders, has announced a “world model” of a cell that can simulate both its natural state and responses to successive perturbations, potentially transforming biological research.

👉 Read more: https://ow.ly/y2Tr50ZB3jm
GenBio Launches a “Virtual Cell” AI Model | Lifespan Research Institute
This AI startup, which lists Nobel laureate David Baker among its co-founders, has announced a “world model” of a cell that can simulate both its natural state and responses to successive perturbations, potentially transforming biological research. Living in a simulation Simulating a living organism on a computer (in silico) has been a dream of both
ow.ly
August 19, 2026 at 6:01 PM
CRISPR used to edit brain epigenome to reset anxiety & excessive drinking in ratsvia @GENbio @UofIllinois

genengnews.com/topics/transla…
CRISPR Edits Brain Epigenome to Reset Anxiety and Excessive Drinking in Rats
Animal study shows gene editing reverses brain epigenetic reprogramming caused by adolescent binge drinking.
www.genengnews.com
December 1, 2024 at 4:19 AM
CRISPR Use Creates Malaria-Resistant Mosquitoesvia @genbio

genengnews.com/gen-news-highl…
CRISPR Use Creates Malaria-Resistant Mosquitoes
New study highlights the potential of mosquito gene modification to combat malaria
www.genengnews.com
December 1, 2024 at 4:01 AM
CRISPR used in a proof-of-concept study to improve the function of heart muscle in cells taken from muscular dystrophy patients. The technique could potentially correct a majority of thousands of DMD mutations.via @genbio

genengnews.com/gen-news-highl…
CRISPR Technique Could Correct Majority of Thousands of DMD Mutations
Eric Olson's team at the University of Texas (UT) Southwestern Medical Center reports on the use of a CRISPR/Cas9 gene-editing technique that could potentially correct most of the 3000 mutations that cause Duchenne muscular dystrophy
www.genengnews.com
December 1, 2024 at 4:00 AM
CRISPR Activation of Single Genes Turns Skin Cells to Stem Cellsvia @genbio

genengnews.com/gen-news-highl…
CRISPR Activation of Single Genes Turns Skin Cells to Stem Cells
Epigenetic remodeling of Oct4 or Sox2 via CRISPR activation generates authentic iPSCs
www.genengnews.com
December 1, 2024 at 4:00 AM