LatchBio
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
LatchBio acquires TwentyTwo to form Latch Biosecurity
Welcoming Harmon Bhasin, Evan Seeyave, and John Wang to the team.
19 hrs ago
•
Alfredo Andere
72
2
Benchmarking AI Agents on Long-Horizon Single-Cell Biology
A verifiable benchmark for recovering scientific conclusions from raw single-cell data
Jun 25
•
Kenny Workman
82
1
Benchmarking AI Agents on Small-Molecule Preclinical Pharmacology
A verifiable benchmark for practical decisions about potency, mechanism, exposure, safety, and efficacy
Jun 17
•
Kenny Workman
73
1
EpiBench: AI agents still struggle with epigenomics analysis
Benchmarking frontier models on practical CUT&Tag/CUT&RUN, ATAC-seq, ChIP-seq, and DNA methylation workflows
Jun 11
•
Kenny Workman
49
May 2026
Human Verification of SpatialBench
Two rounds of independent expert attempts define a verified subset of 115 spatial biology tasks and expose ambiguity in benchmark specification and…
May 29
•
Kenny Workman
82
Verifiable Benchmarking of Long-Horizon Spatial Biology
Evaluating whether AI agents can recover complex scientific conclusions from raw spatial biology data
May 27
•
Kenny Workman
99
scBench Updates: Opus 4.7, GPT 5.5, Gemini 3.1
Benchmarking frontier models on messy, real-world single cell data analysis
May 12
•
Kenny Workman
89
April 2026
Agentic biology is shaped like software
Biology will not jump straight to autonomous AI scientists. Like software, it will first accelerate where work is executable, feedback-rich, and…
Apr 30
•
Kenny Workman
121
5
New Frontier Models Are Faster, Not More Reliable, at Spatial Biology
Overall accuracy for GPT-5.5 and Opus 4.7 remains flat on SpatialBench. Scientist-reviewed trajectories reveal persistent gaps in assay-aware biological…
Apr 29
•
Kenny Workman
,
Hannah Le
,
Zhen Yang
, and
Harihara Muralidharan
13
3
February 2026
scBench: Can AI Agents Analyze Real-World Single-Cell Data?
394 verifiable problems across six sequencing platforms: 10X Chromium, BD Rhapsody, CSGenetics, Illumina, MissionBio, ParseBio
Feb 6
•
Kenny Workman
25
December 2025
SpatialBench: Can Agents Analyze Real-World Spatial Biology Data?
first contribution towards a broader family of benchmarks spanning major data types // 146 verifiable problems spanning 5 spatial platforms and 7 task…
Dec 26, 2025
•
Kenny Workman
31
1
2
agent.bio
A public, interactive agent sandbox for five major spatial kit/machine types: Takara Seeker, Vizgen MERFISH, AtlasXOmics DBiT-seq, 10X Xenium + 10X…
Dec 9, 2025
•
Kenny Workman
and
Hannah Le
40
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts