6 min read

Isomorphic goes beyond AlphaFold

Isomorphic goes beyond AlphaFold
Nº 01 · The Lede Hacker News Drug discovery · Computational

Isomorphic ships drug-design engine

Isomorphic ships drug-design engine
Fig. IHacker News · Filed 20 Jul 2026.

Isomorphic Labs unveiled its Drug Design Engine, positioning the platform as the step beyond AlphaFold — from predicting protein structures to generating candidate molecules against them. The engine couples structure prediction with generative chemistry and affinity ranking inside one loop, the piece Alphabet's drug-discovery spinout has been building toward since spinning out of DeepMind. Framed as a general-purpose design system rather than a target-specific tool, it lands as the most concrete answer yet to whether structure-prediction leaders can convert accuracy gains into real pipelines.

Read the source

Multimodal oncology lab funded at 1st percentile
Fig. IIX · Filed 20 Jul 2026.
Nº 02 X Clinical AI · Evaluation

Multimodal oncology lab funded at 1st percentile

Kevin Boehm's K99/R00 cleared NCI review at the 1st percentile to launch a 2027 lab fusing tumor histopathology with genomics for treatment-selection AI. Multimodal cancer models — image plus omics in one predictor — have been the field's most-promised, least-delivered category; a top-percentile NCI bet signals which architecture the agency thinks is closest to clinical utility.

Read more
BioReason-Pro pushes protein function prediction
Fig. IIIbioRxiv · Filed 20 Jul 2026.
Nº 03 bioRxiv Structural biology · Protein design

BioReason-Pro pushes protein function prediction

BioReason-Pro fuses sequence, structure, and text into a single reasoning model for protein function prediction, reporting gains on standard benchmarks over sequence-only baselines. Advances the multimodal-reasoning frontier for functional annotation — the workflow most affected by quarterly UniProt updates and where single-modality models have been the ceiling for two years.

Read more
Also Filed · Five Briefs from the queue
Nº 04 bioRxiv Field report

Perturbed flow matching for SBDD

PFM applies perturbed flow matching — a generative technique that learns molecular distributions by mapping noise to structure — to structure-based drug design, improving pocket-conditioned ligand generation. Sharpens the generative-chemistry toolkit that Isomorphic's engine above is productizing at scale.

Read
Nº 05 arXiv Benchmarks · Evaluation

Clinicians build medical-AI failure benchmark

MedFailBench probes where medical AI models cross safety boundaries — hallucinated dosing, missed red-flag symptoms, unsafe deferrals — using cases written by practicing clinicians. Anchors a reference benchmark for medical-AI safety claims; vendor pitches now have a clinician-authored floor to clear — a gap we've tracked since exam scores stopped predicting bedside performance.

Read
Nº 06 X Field report

Perturb-and-record assays as next frontier

Live-cell imaging plus time-resolved chemical composition — perturbing cells and recording exactly what changes — is the assay upgrade drug testing still mostly lacks. Names the capability gap between watching cell state and controlling it, the bottleneck most compound-screening pipelines still route around.

Read
Nº 07 arXiv Field report

AutoSynthesis automates meta-analysis

AutoSynthesis runs meta-analyses end-to-end — search, screening, extraction, synthesis — as an agentic pipeline, targeting the months-long human bottleneck in evidence synthesis. Moves systematic-review automation from demo to workflow-viable.

Read
Nº 08 OpenAI Field report

OpenAI's GPT-Red self-improves on safety

OpenAI released GPT-Red, an automated red-teaming system that uses self-play to harden models against jailbreaks and prompt injection. Raises the floor for what counts as adequate safety testing before a biomedical agent touches patient data.

Read

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

Agentic Discovery  ·  Nº 59  ·  20 Jul 2026

Editor's Note

Monday reset: Isomorphic pushes past structure prediction into design, and a K99 at the 1st percentile lands a multimodal oncology lab.

 

Nº 01 · The Lede  —  Hacker News  —  Drug discovery · Computational

Isomorphic ships drug-design engine

Isomorphic ships drug-design engine

Fig. I  Hacker News · Filed 20 Jul 2026.

Isomorphic Labs unveiled its Drug Design Engine, positioning the platform as the step beyond AlphaFold — from predicting protein structures to generating candidate molecules against them. The engine couples structure prediction with generative chemistry and affinity ranking inside one loop, the piece Alphabet's drug-discovery spinout has been building toward since spinning out of DeepMind. Framed as a general-purpose design system rather than a target-specific tool, it lands as the most concrete answer yet to whether structure-prediction leaders can convert accuracy gains into real pipelines.

Read the source →

Why it matters

Moves the AlphaFold lineage from prediction to design — resets the reference platform for AI-native drug discovery and forces every competitor to answer what their generation-plus-scoring loop actually delivers.

 

Nº 02  —  X  —  Clinical AI · Evaluation

Multimodal oncology lab funded at 1st percentile

Fig. II  X · Filed 20 Jul 2026.

Multimodal oncology lab funded at 1st percentile

Kevin Boehm's K99/R00 cleared NCI review at the 1st percentile to launch a 2027 lab fusing tumor histopathology with genomics for treatment-selection AI. Multimodal cancer models — image plus omics in one predictor — have been the field's most-promised, least-delivered category; a top-percentile NCI bet signals which architecture the agency thinks is closest to clinical utility.

Read more →

 

Nº 03  —  bioRxiv  —  Structural biology · Protein design

BioReason-Pro pushes protein function prediction

Fig. III  bioRxiv · Filed 20 Jul 2026.

BioReason-Pro pushes protein function prediction

BioReason-Pro fuses sequence, structure, and text into a single reasoning model for protein function prediction, reporting gains on standard benchmarks over sequence-only baselines. Advances the multimodal-reasoning frontier for functional annotation — the workflow most affected by quarterly UniProt updates and where single-modality models have been the ceiling for two years.

Read more →

 

Also Filed  ·  Five Briefs from the queue

Nº 04  —  bioRxiv  —  Field report

Perturbed flow matching for SBDD

PFM applies perturbed flow matching — a generative technique that learns molecular distributions by mapping noise to structure — to structure-based drug design, improving pocket-conditioned ligand generation. Sharpens the generative-chemistry toolkit that Isomorphic's engine above is productizing at scale.

Read →

Nº 05  —  arXiv  —  Benchmarks · Evaluation

Clinicians build medical-AI failure benchmark

MedFailBench probes where medical AI models cross safety boundaries — hallucinated dosing, missed red-flag symptoms, unsafe deferrals — using cases written by practicing clinicians. Anchors a reference benchmark for medical-AI safety claims; vendor pitches now have a clinician-authored floor to clear — a gap we've tracked since exam scores stopped predicting bedside performance.

Read →

Nº 06  —  X  —  Field report

Perturb-and-record assays as next frontier

Live-cell imaging plus time-resolved chemical composition — perturbing cells and recording exactly what changes — is the assay upgrade drug testing still mostly lacks. Names the capability gap between watching cell state and controlling it, the bottleneck most compound-screening pipelines still route around.

Read →

Nº 07  —  arXiv  —  Field report

AutoSynthesis automates meta-analysis

AutoSynthesis runs meta-analyses end-to-end — search, screening, extraction, synthesis — as an agentic pipeline, targeting the months-long human bottleneck in evidence synthesis. Moves systematic-review automation from demo to workflow-viable.

Read →

Nº 08  —  OpenAI  —  Field report

OpenAI's GPT-Red self-improves on safety

OpenAI released GPT-Red, an automated red-teaming system that uses self-play to harden models against jailbreaks and prompt injection. Raises the floor for what counts as adequate safety testing before a biomedical agent touches patient data.

Read →

 

· · ·

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