6 min read

NVIDIA arms agents for the lab bench

NVIDIA arms agents for the lab bench
Nº 01 · The Lede X Agents · Infrastructure

NVIDIA opens BioNeMo to agents

NVIDIA opens BioNeMo to agents
Fig. IX · Filed 24 Jun 2026.

NVIDIA launched BioNeMo Agent Toolkit, an open framework that exposes BioNeMo's protein, molecule, and genomics models as callable tools any LLM agent can invoke. The toolkit ships with adapters for MCP (Model Context Protocol, Anthropic's spec for letting agents talk to tools) and standard agent frameworks, meaning a Claude or GPT agent can now call AlphaFold-class structure prediction or molecular generation the same way it calls a calculator. NVIDIA is positioning BioNeMo as the default tool layer underneath whatever agent stack a lab picks.

Read the source

GPT-5 cracks a T-cell mystery
Fig. IIOpenAI · Filed 24 Jun 2026.
Nº 02 OpenAI Cell biology · Funding

GPT-5 cracks a T-cell mystery

GPT-5 Pro helped immunologist Derya Unutmaz resolve a three-year-old puzzle about T cell behavior, with OpenAI publishing the case as a worked example for cancer and autoimmune research. The write-up moves frontier reasoning models from "useful for literature search" to "co-author on a stuck mechanistic problem" — a capability threshold the field has been circling for two years.

Read more
Rare-disease reasoning model runs RCT
Fig. IIIarXiv · Filed 24 Jun 2026.
Nº 03 arXiv Field report

Rare-disease reasoning model runs RCT

A specialized reasoning LLM for rare-disease diagnosis cleared a randomized trial as a physician assistant, measuring time-to-diagnosis and accuracy against unassisted controls. Echoing the GPT-5 immunology result above, the gap between "AI helps an expert get unstuck" and "AI shortens diagnosis in a controlled trial" just narrowed — and now has trial-grade evidence behind it.

Read more
Also Filed · Five Briefs from the queue
Nº 04 bioRxiv Cell biology · Funding

CellOS learns a cell world model

CellOS trains a joint-embedding predictive model of cellular state, borrowing the JEPA architecture (joint embedding predictive architecture, the self-supervised approach LeCun has championed) from vision and applying it to single-cell data. Pushes virtual-cell modeling past transcriptome-only foundation models toward state-prediction as the benchmark target.

Read
Nº 05 bioRxiv Computational biology

biomeStat runs 1,000-genome epi pipeline

biomeStat chained agents through an end-to-end genomic epidemiology analysis of 1,000 Asian dengue genomes, from QC to phylogenetics to lineage assignment. Moves agentic pipelines from toy demos to outbreak-scale workloads — the kind public health labs actually run.

Read
Nº 06 arXiv Field report

DeepBD prioritizes birth-defect variants

DeepBD grounds variant prioritization for genetic birth defects in a structured agentic workflow, tying LLM reasoning to clinical-grade variant databases rather than free-form generation. Narrows the hallucination gap that has kept diagnostic LLMs out of clinical genetics review.

Read
Nº 07 X Field report

OpenAI on safety under pressure

OpenAI published research on getting safe model behavior to generalize into new domains and hold up under adversarial pressure as agents take on longer-horizon tasks. Relevant to biology deployments where agents touch patient data or order wet-lab reagents and the failure mode isn't a wrong answer but an unsafe action.

Read
Nº 08 Anthropic Field report

Anthropic: expertise still compounds

Anthropic argued that agentic coding rewards domain experts more, not less — the better the agent, the more leverage the expert prompt and review gets. Counters the "AI flattens skill" narrative with data from Claude Code usage.

Read

Reply with your discoveries. A human reads them. Forward freely.

Agentic Discovery  ·  Nº 42  ·  24 Jun 2026

Editor's Note

NVIDIA puts agentic tooling in biologists' hands the same day a rare-disease RCT and a cell world-model preprint land — a heavy Tuesday.

 

Nº 01 · The Lede  —  X  —  Agents · Infrastructure

NVIDIA opens BioNeMo to agents

NVIDIA opens BioNeMo to agents

Fig. I  X · Filed 24 Jun 2026.

NVIDIA launched BioNeMo Agent Toolkit, an open framework that exposes BioNeMo's protein, molecule, and genomics models as callable tools any LLM agent can invoke. The toolkit ships with adapters for MCP (Model Context Protocol, Anthropic's spec for letting agents talk to tools) and standard agent frameworks, meaning a Claude or GPT agent can now call AlphaFold-class structure prediction or molecular generation the same way it calls a calculator. NVIDIA is positioning BioNeMo as the default tool layer underneath whatever agent stack a lab picks.

Read the source →

Why it matters

Resets the reference tool layer for biology agents — the question stops being "can my agent call a protein model?" and starts being "which BioNeMo tool did it pick, and why?"

 

Nº 02  —  OpenAI  —  Cell biology · Funding

GPT-5 cracks a T-cell mystery

Fig. II  OpenAI · Filed 24 Jun 2026.

GPT-5 cracks a T-cell mystery

GPT-5 Pro helped immunologist Derya Unutmaz resolve a three-year-old puzzle about T cell behavior, with OpenAI publishing the case as a worked example for cancer and autoimmune research. The write-up moves frontier reasoning models from "useful for literature search" to "co-author on a stuck mechanistic problem" — a capability threshold the field has been circling for two years.

Read more →

 

Nº 03  —  arXiv  —  Field report

Rare-disease reasoning model runs RCT

Fig. III  arXiv · Filed 24 Jun 2026.

Rare-disease reasoning model runs RCT

A specialized reasoning LLM for rare-disease diagnosis cleared a randomized trial as a physician assistant, measuring time-to-diagnosis and accuracy against unassisted controls. Echoing the GPT-5 immunology result above, the gap between "AI helps an expert get unstuck" and "AI shortens diagnosis in a controlled trial" just narrowed — and now has trial-grade evidence behind it.

Read more →

 

Also Filed  ·  Five Briefs from the queue

Nº 04  —  bioRxiv  —  Cell biology · Funding

CellOS learns a cell world model

CellOS trains a joint-embedding predictive model of cellular state, borrowing the JEPA architecture (joint embedding predictive architecture, the self-supervised approach LeCun has championed) from vision and applying it to single-cell data. Pushes virtual-cell modeling past transcriptome-only foundation models toward state-prediction as the benchmark target.

Read →

Nº 05  —  bioRxiv  —  Computational biology

biomeStat runs 1,000-genome epi pipeline

biomeStat chained agents through an end-to-end genomic epidemiology analysis of 1,000 Asian dengue genomes, from QC to phylogenetics to lineage assignment. Moves agentic pipelines from toy demos to outbreak-scale workloads — the kind public health labs actually run.

Read →

Nº 06  —  arXiv  —  Field report

DeepBD prioritizes birth-defect variants

DeepBD grounds variant prioritization for genetic birth defects in a structured agentic workflow, tying LLM reasoning to clinical-grade variant databases rather than free-form generation. Narrows the hallucination gap that has kept diagnostic LLMs out of clinical genetics review.

Read →

Nº 07  —  X  —  Field report

OpenAI on safety under pressure

OpenAI published research on getting safe model behavior to generalize into new domains and hold up under adversarial pressure as agents take on longer-horizon tasks. Relevant to biology deployments where agents touch patient data or order wet-lab reagents and the failure mode isn't a wrong answer but an unsafe action.

Read →

Nº 08  —  Anthropic  —  Field report

Anthropic: expertise still compounds

Anthropic argued that agentic coding rewards domain experts more, not less — the better the agent, the more leverage the expert prompt and review gets. Counters the "AI flattens skill" narrative with data from Claude Code usage.

Read →

 

· · ·

Reply with your discoveries. A human reads them. Forward freely.