固定されたツイート
We just raised a $28 million Series A from Coatue and @Lux_Capital to build the AWS x GitHub for biocomputing.
1/N🔻
latchbio.substack.com/p/announcing-o…
English
LatchBio
638 posts
LatchBio
@LatchBio
Data Infrastructure for Biology
San Francisco, CA 参加日 Temmuz 2021
40 フォロー中4.3K フォロワー
LatchBio がリツイート
Talks at the intersection of systems engineering and computational biology
0:20 Why study systems x biology in "age of agents"
5:50 Forch: Building a utilitarian cloud container orchestrator (Max Smolin, LatchBio)
41:25 cyto: Ultra high-throughput processing of 10x Flex single-cell sequencing (Noam Teyssier, Arc Institute)
1:04:30 SLAF: A single-cell omics storage format for the virtual cell era (Pavan Ramkumar, SLAF Project)
1:33:30 Lessons in Perturbation Modeling: STATE, STACK, and Beyond (Dhruv Gautam, Arc Institute + UC Berkeley)
2:03:15 Leveraging Serverless Distributed Computing to Scale Computational Biology (Ben Shababo, Modal)
Topics span container orchestration, single-cell infra, perturbation modeling for biology at scale.
English
LatchBio がリツイート
Hosting another computing x biology reading group with Modal. Progress has really picked up the past 6 months + many interesting projects to highlight.
- Max Smolin (LatchBio): Building "Forch", a Utilitarian Cloud Container Orchestrator
- Noam Teyssier (Arc Institute): cyto: ultra high-throughput processing of 10x-flex single cell sequencing
- Pavan Ramkumar (SLAF Project): SLAF: A single-cell omics storage format for the virtual cell era
- Dhruv Gautam (Arc Institute): Lessons in Perturbation Modeling: STATE, STACK, and Beyond
- Ben Shabobo (Modal): Leveraging Serverless Distributed Computing to Scale Computational Biology
Come join us for pizza and good technical talks on March 4th in Mission Bay, SF. Design decisions, paper highlights + snippets of source code.
English
LatchBio がリツイート
How good are frontier models at analyzing single cell data?
scBench, 394 verifiable problems from real scRNA-seq workflows, shows the best model (Opus4.6) gets 53% accuracy. Better than spatial, but the best agents still fail roughly every other routine analysis task:
English
LatchBio がリツイート
Surprising how frontier models are still pretty weak at biology! It's been fun working with Kenny, Zhen, @Harihara_subrah to build this benchmark.
Below is a further breakdown of a model’s analysis journey, where it fails, plus insights that nearly 2X performance in our tests:
Kenny Workman@kenbwork
2026 will be the year of agents in biology. But we need better benchmarks. We worked with scientists to turn real world analysis into verifiable problems. SpatialBench stratifies frontier models, shows harnesses matter, and reveals distinct failure modes between model families:
English
LatchBio がリツイート
Made a website to easily visualize the results (which the team worked really hard on): benchmarks.bio
We believe that making LLMs better at biological data analysis is one of the best ways to make them more useful to scientists.
We will continue to expand to more types of platforms (including beyond spatial) and to more kinds of eval types.
Kenny Workman@kenbwork
2026 will be the year of agents in biology. But we need better benchmarks. We worked with scientists to turn real world analysis into verifiable problems. SpatialBench stratifies frontier models, shows harnesses matter, and reveals distinct failure modes between model families:
English
LatchBio がリツイート
2026 will be the year of agents in biology. But we need better benchmarks.
We worked with scientists to turn real world analysis into verifiable problems. SpatialBench stratifies frontier models, shows harnesses matter, and reveals distinct failure modes between model families:
English
LatchBio がリツイート
Launching a public agent sandbox for spatial biology. Five demo flows tailored to specific kits/machines
Try it now: agent.bio
This is a shippable intermediary towards reliable and widely deployed agentic systems used to make expensive scientific decisions.
English
LatchBio がリツイート
We don't know what most microbial genes do. Can genomic language models help?
there's only one way to find out! this is a 1 hour and 42 minute interview with an MIT professor (the famous @Micro_Yunha) chatting about these questions, her work in solving them at @tatta_bio, and more. zoomer captions are back too
Links in reply!
Timestamps:
00:00:00 - Clips + sponsor roll from the wonderful @LatchBio
00:02:07 – Introduction
00:02:23 – Why do microbial genomes matter
00:04:07 – Deep learning acceptance in metagenomics
00:05:25 – The case for genomic “context” over sequence matching
00:06:43 – OMG: the only ML-ready metagenomic dataset
00:09:27 – gLM2: A multimodal genomic language model
00:11:06 – What do you do with the output of genomic language models?
00:17:41 – How will OMG evolve?
00:20:26 – Why train on only microbial genomes, as opposed to all genomes?
00:22:58 – Do we need more sequences or more annotations?
00:23:54 – Is there a conserved microbial genome ‘language’?
00:28:11 – What non-obvious things can this genomic language model tell you?
00:33:08 – Semantic deduplication and evaluation
00:37:33 – How does benchmarking work for these types of models?
00:41:31 – Gaia: A genomic search engine
00:44:18 – Even ‘well-studied’ genomes are mostly unannotated
00:50:51 – Using agents on Gaia
00:54:53 – Will genomic language models reshape the tree of life?
00:59:18 – Current limitations of genomic language models
01:08:54 – Directed evolution as training data
01:12:35 – What is Tatta Bio?
01:19:02 – Building Google for genomic sequences (SeqHub)
01:25:46 – How to create communities around scientific OSS
01:29:06 – What’s the purpose in the centralization of the software?
01:35:37 – How will the way science is done change in 10 years?
English
LatchBio がリツイート
Agreed. When I first started working in genomics, I printed and read protocols for all common single-cell genomics assays— I learned a lot. #methodsmatter
Kenny Workman@kenbwork
If you work regularly with molecular data, but don't prep it yourself, highly recommend reading the user manual for a kit you interact with cover to cover. Every little step is there for a reason + will teach you interesting biology. Small deviations at the bench often perturb your chunk of data in subtle ways.
English
LatchBio がリツイート
It's often unclear how to how to *measure* biology agents and rigorously compare different systems.
Introducing SpatialBench, a suite of 98 dataset/eval packs with a focus on real world tasks.
Constructed in collaboration with spatial vendors and scientists on tasks like cell typing, cell segmentation and spatially aware differential expression.
Kenny Workman@kenbwork
Today, the frontier of biology research is tacit knowledge: distributed across thousands of labs in the minds of PIs/researchers. For any given disease or tissue, there are a handful of groups that know how to select, grow and identify the important molecular signatures from the models relevant to their work. A fraction of this information makes it into publication. The great task ahead of us is to formalize this knowledge into open eval banks to benchmark and improve agentic systems. If you work with spatial data and are interested in contributing to this project, please reach out.
English
LatchBio がリツイート
If you read this and thought, “awesome - but I’d do X/Y/Z to make the post stronger,” consider applying to our Growth Engineer role.
We focus our marketing on a handful of highly-technical prospects and reach them with value-add content: blog posts, market maps, in-person events, and product launches. The right person is able top own these end-to-end from idea → design → implementation → distribution.
We want someone who empathizes with scientists and knows what’s useful to them. My assumption is they'll need prior computational biology context to do this well (happy to be proven wrong though).
If this sounds like you or someone you know, reach out.
Kenny Workman@kenbwork
Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:
English
LatchBio がリツイート
I might be reading between the lines here but this feels like cursor for biological data 📈
Kenny Workman@kenbwork
Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:
English
LatchBio がリツイート
🤩 Glad to be part of this AI-driven spatial biology revolution at @AtlasXomics with @LatchBio and @10xGenomics, @vizgen_inc @TakaraBioUSA . In particular, spatial epigenomics & multi-omics reveals the mechanistic insights and empower therapeutic development 🤩
Kenny Workman@kenbwork
Agents are finally starting to work in biology. We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures. Our team believes this will soon be the standard way biologists interact with data. Spatial biology agents look a bit different from coding products: - tailored to the molecular details of each kit type - run in sandboxes on very large machines - orchestrate data infra, eg. bioinformatics workflows, with tool calls - build graphical analysis notebooks to communicate results Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:
English
LatchBio がリツイート
Agents are finally starting to work in biology.
We’ve partnered with Anthropic and major biotech vendors - Vizgen, AtlasXOmics, Takara, 10x Genomics - to build a tool that allows scientists to steer their own analysis with natural language. Raw spatial data to publication quality figures.
Our team believes this will soon be the standard way biologists interact with data.
Spatial biology agents look a bit different from coding products:
- tailored to the molecular details of each kit type
- run in sandboxes on very large machines
- orchestrate data infra, eg. bioinformatics workflows, with tool calls
- build graphical analysis notebooks to communicate results
Detailed breakdown of engineering decisions, product philosophy and concrete flows follows:
English
LatchBio がリツイート
Many are aware of the exponential growth of data in biology but the true scale of frontier assays is often abstract. Spatial epigenetics is finally approaching a size that breaks most systems: each slide is on the order of 100s of GB and a multi-slide cohort will quickly reach many TBs.
Unlike traditional downstream workflows in multi-omics, useful downstream scientific questions require biologists to manipulate this data in highly interactive and non-standard ways. This is a very hard problem.
AtlasXOmics was one of our early customers and have personally watched their molecular throughput compound over the years. The assay volume is a function of the size of capture spots on their chips, which has continued to drop every few months, and is still nowhere near saturating commodity semiconductor components.
AtlasXomics@AtlasXomics
Spatial FFPE ATAC-seq has arrived! AtlasXomics now brings single-cell chromatin accessibility mapping to FFPE tissue, unlocking spatial epigenomic insights from the world’s vast archives of clinical samples. Using our 5.5 × 5.5 mm chip at 10 µm resolution, we can now profile open chromatin directly in preserved tissue — maintaining spatial context. Check out our first FFPE kidney dataset on the interactive data portal, showcasing the robust performance and sensitivity of this new spatial assay. View more at: lnkd.in/e-8sTMnY #SpatialBiology #Epigenetics #CancerResearch
English
LatchBio がリツイート
Been working with Anthropic + handful of major sequencing providers to orchestrate our existing platform with the latest models. A window has opened up in the past few months as trends underpinning the explosive agentic software products - improving tool use, code reasoning, multi-turn workflows - now translate well to concrete tasks in biological data analysis with a good amount of engineering.
If you speak to biologists sitting on large molecular data, they are often able to produce a very clear description of what they want out of it - specific scientific questions, ability to reason about biological validity of outputs, details of the plots and figures - but often lack the procedural skill to get there.
Rather than general purpose analysis or literature distillation sandboxes, we believe precise and user-tested workflows adapted to the details of each specific machine/kit type will have a more immediate impact on industry. Spending years building stable data infra was very important. Looking forward to sharing details over the coming weeks.
Long skeptical of the practical application of LLMs to biology, have personally been surprised by early technical results and (importantly) the response from real scientists.
Anthropic@AnthropicAI
We’re building tools to support research in the life sciences, from early discovery through to commercialization. With Claude for Life Sciences, we’ve added connectors to scientific tools, Skills, and new partnerships to make Claude more useful for scientific work.
English
LatchBio がリツイート
Next week we’ll release a new interface to analyze multi-omics data. We've been patiently building bindings for the past two years. When we tested Sonnet 4.5, as we do routinely after every model release, we realized capabilities we thought were still 1-2 years away are now here.
Anthropic@AnthropicAI
We’re building tools to support research in the life sciences, from early discovery through to commercialization. With Claude for Life Sciences, we’ve added connectors to scientific tools, Skills, and new partnerships to make Claude more useful for scientific work.
English
LatchBio がリツイート
Large volumes of structured spatial data will help us discover new targets, mechanisms and drugs too difficult to reason about with unaided cognition.
Releasing:
(1) 25M curated cells - the largest open access spatial atlas to date - across 11 major vendors
(2) a tiled AnnData file format and visualization ecosystem to explore big matrix data in the browser without a server
English
LatchBio がリツイート
Computing x engineering biology is a playground for systems. Come join us for round three of the SF systems reading group with a focus on biotech.
- Noam Teyssier (Arc Institute): BINSEQ: A Family of High Performance Binary Formats for Nucleotide Sequences
- Aidan Abdullali (LatchBio): A Distributed Filesystem Built on Postgres and S3
- Abhinav Adduri (Arc Institute): Scaling Deep Learning to 1B+ Single Cells
Presentations on design decisions and paper highlights. We'll read snippets of source code, learn from each other and vibe. 5:30ish on 8/20
English
LatchBio がリツイート
Data is the oil of modern biotech. New tools allow us to model living systems too complex for unaided human cognition.
Latch is releasing a new capabilities in data curation + delivery:
- 30M observational cell atlas across 150 diseases, 200 tissues, 27 technologies
- a partnership with two expert labeling teams
- an agentic, human-in-the-loop framework for mass scRNA-seq curation
English