This is your cue to try Claude if you’ve been holding out still…
28.02.2026 01:11
👍 2
🔁 0
💬 0
📌 0
This is your cue to try Claude if you’ve been holding out still…
We're looking to sponsor applications to the new NSF PRFB who are interested in using AI to tackle microbiology's "Great Plate Count Anomaly"
Details below. Please share.
#microsky #postdoc #AI #microbiology
open.substack.com/pub/carinila...
CARB-X is opening a new funding round soon—sign up for their newsletter (link in replies) to get the announcement.
CARB-X is one of few organizations making meaningful progress ensuring access to new antimicrobial drugs and supporting preventatives/diagnostics.
Better, forbibden!
Looks interesting
Are you using the Claude agent SDK or a different platform? Any docs/guides you have found particularly helpful?
A stroller on top of a 5 foot tall mound of snow
My parking spot today
Really encourage folks who had bad impressions of earlier LLMs & hallucinations to take a look at domain-specific, agentic systems like Edison, Claude Code, etc.
Semantics aside--these things are just very useful now.
For the genomic analysis, Edison performed similarly, but "connected the dots" within the analysis in a way it is hard to imagine a PhD student doing on their own 5 years ago.
I knew what reasonable results should be and how long it would take a human.
For the NMR task, Edison performed similarly to a senior PhD student that manually reviewed the entire spectra, and correctly identified things like negative controls without instruction.
Tried Edison Analysis (not Kosmos) on two tasks and was blown away:
1. Uploaded 96 high-res NMR spectra of bacterial supernatants and asked for metabolite ID and quantification
2. Uploaded a bacterial genome and asked it to identify mobile genetic elements (more complex, but this is the gist)
Old news by now, but this is a fantastic short course—feels like Andrew Ng’s early coursera neural networks class. If you have not tried Claude Code, I recommend just skimming the videos to see what the chatter is about.
www.deeplearning.ai/short-course...
Yes, 2g fiber per serving too
Snoopy chocolate peppermint goldfish = toddler 🔥
Antimicrobial resistance (AMR) is one of the greatest threats to public health, with the potential to undo decades of medical progress.
This #WAAW2025, head to our LinkedIn to hear from world-leading experts on how we can tackle AMR and protect the future of medicine: t.ly/3Oxk1
Registration is now open for @keystonesymposia.bsky.social "Beyond #Antibiotics: Emerging Strategies Combating #BacterialInfection." Deadline for scholarships and abstract selected short talks is Jan 7! Join us this May for an amazing meeting! keysym.us/KSBeyondAntibiotics26 #KSBeyondAntibiotics26
Conference summary with organizers listed (also in post) and Keynote speaker, Diane Newman.
Thank you to @joeyzacks.bsky.social @kimingeneva.bsky.social @dariavantyne.bsky.social @maribyndloss.bsky.social for organizing!
I'll be speaking at Beyond Antibiotics: Emerging Strategies for Combating Bacterial Infection @keystonesymposia.bsky.social May 4-7, 2026. Abstract and scholarship submissions are open through Jan 7. Please encourage those in your network working on novel infection prevention/treatment to submit!
Is this actually the subskeet?
Incredibly powerful story from endocrinologist Dr. Caroline Fox candidly sharing her experience w an acute mental health crisis & her long, difficult, maddening, deeply inspiring journey towards recovery - & return to work as a senior biopharma R&D leader. www.youtube.com/watch?v=YVWS...
Largely agree with this—clinical validation of drugs is an extremely small N universe, and it’s not feasible to validate human- vs AI-generated hypothesis prob of success. AI is much better suited to solving the sub-problems in drug dev (which vanilla machine learning was already pretty good at).
What is their beef about needing to clear snow and ice off sidewalks?
Did this email have any tree-related content 🤔
Amazing resource—hope it gets used broadly and we see TnSeq datasets become more common for Bacteroidales.
Fully agreed—peptides don’t really overcome any of the policy, payment, or access issues that impede traditional anti-infective commercialization and utility. Cool to have in the armamentarium, but development $$ are mostly a zero sum game in the space…
Unfortunately there is a 1000% bollard tariff
No mere post can stop the F150s we so adore
Knowing the time without a watch
So many bollards lining the sidewalk
Things I love about London: BOLLARDS
🚨 Microbiologists! We are recruiting Assistant / Associate Professors in 3 collaborative areas of our U. Pittsburgh School of Medicine.
1) MMG (my dept): fundamental research in med micro
2) Peds ID / I4Kids institute
3) Center for Vaccine Research
🔗 to all 3 w/info: www.linkedin.com/posts/vaughn...
