The ToolUniverse plugin for Claude Code is here: 2,000+ life-science tools and 120+ research skills, with a real source on every answer, installed with one prompt.
ToolUniverse already powers a range of AI agents. This plugin brings its full toolset and skill library into Claude Code. What it does:
β Claude Code automatically reaches for the right tools and skills to run a full life-science analysis end to end: variant interpretation, RNA-seq differential expression, drug and target lookups, rare-disease workups. Every claim comes back with a real source, instead of from memory.
β When accuracy is critical, dedicated commands add discipline:
β’ cross-validate a claim across 3+ independent sources
β’ literature-sweep, a graded review across 15+ indexes (PubMed, EuropePMC, OpenAlex, and more)
β’ compare, side-by-side tables for drugs, targets, diseases, or variants
β’ research, a step-by-step multi-source investigation
β’ translate-id, resolve an ID across every namespace
Install in one step. Paste this into Claude Code and it sets itself up:
Read https://t.co/Ja5m97nXx0 and install the ToolUniverse Claude Code plugin for me.
Blog post π
https://t.co/vPICA4vcrH
@marinkazitnik@ScientistTools@KempnerInst@HarvardDBMI
@tarkov Very thematic and well-designed map, though lack of other PMC's makes it more of a mechanical problem of clearing AI at which point you can loot without anxiety
With UMA playground, the crazy things Feynman could only ask us to imagine become something you can see. Heat, break, and build at https://t.co/bZFDORa9Mw
WOW! I've self-taught a lot of chemistry and always felt that there was a dissociation between textbook reaction descriptions and REALLY understanding what was going on at the atomic level.
As a visual learner, this is incredible.
Can I make a suggestion: Add a playground with a searchable list of common re-agents to facilitate specific reactions
For example, being able to quickly put together something like an Oppenauer Oxidation
@lauriewired Have you considered using one of the voice models to auto-dub your content across languages + do subtitle generation?
That's really cool to have such an international audience, love your content!
@eatonphil@julianhyde would be an interesting one
Apache Calcite author, worked on Looker at Google and also Apache Arrow/Drill.
Pretty unique perspectives on query engine implementations since Calcite supports arbitrary datasources as targets, lots of nuance in that
@Farooqi_Lab@ScienceMagazine@teichlab The atlas predicts that aromatase has the highest expression in the GI nervous system which would be a novel discovery as far as I've ever read
https://t.co/TWP6LgHUvk
@Farooqi_Lab@ScienceMagazine@teichlab Words cannot express how incredible this is. I could spend hours in the Hormone Cell Atlas app, so fascinating!
Thank you for sharing this
@biogerontology What is the best pipeline today for QSAR prediction?
Suppose I want to say "Identify candidates for receptor XYZ and generate QSAR/ADMET predictions"?
The event I am talking about is actually later today! But I made this really fun app for the event earlier using PromptQL. Shared context makes everything so much easier to do :)
I just sequenced a human genome to 30Γ coverage entirely at home.
As far as I know, this is the first time this has been done.
I didnβt step foot in a lab once. Every step - from saliva collection, to running the sequencer - took place in a single room with a dining table + kitchenette.
Six weeks ago, I had never done wet lab biology before.
I used an Oxford Nanopore P2 Solo - the only commercially available sequencing device portable enough to do 30x human genome sequencing at home.
Biggest takeaway - I could build something that combined software, hardware, and molecular biology far faster than I thought was possible.
I can name >100 specific instances where AI helped me solve a technical problem that would previously have blocked me because I lacked access to a domain expert.
For example: how do I save my sequencing run when my DNA extraction yield is 4x lower than I need it to be, and I have this limited set of reagents to hand?
To make this work, I had to navigate multiple disciplines:
- writing software to monitor sequencing runs and orchestrate remote GPU infra for basecalling
- learning + executing 5 hour long molecular biology protocols
- building a hardware device to quantify DNA concentration
Apologies for the hyperbole, but I feel super lucky to be living in 2026.
A few weeks ago I decided to sequence a human genome to 30x at home.
Then I actually did it. And I did it really quickly.
Recently moved to Seattle with my wife, and we're planning to stay.
We're both deeply into bodybuilding and strength training, but we've had a hard time finding a local lifting community. So we're helping build one!
I'm excited to announce a new meetup for lifters in the Seattle/Bellevue area. My gym has generously offered the event space, and I'll be catering the event.
If you're into BB'ing, PL'ing, Oly Lifting, Strongman, or strength training in general, come hang out, train, eat, and meet other lifters.
All levels welcome. Just show up and meet some good people!
π Tiger Gate Gym
ποΈ Sat, June 6
β° 11 AM - 2 PM
π Free catered food
ποΈ Open gym / all levels welcome
Accessible Clinical/Health AI is desperately needed.
Imagine an agent with access to your EHR, imaging, visit summaries, wearable biometrics data.
That would facilitate care and clinician-patient interaction to levels we can only dream of.
I'm sick of calling doctors and physically faxing + re-explaining things because the USA doesn't have integrated health records.