Daniel Alvarez
@daninthenet.bsky.social
Senior Drug Designer | #AI Computational Medicinal Chemist | #medchem + #compchem | Also into #pottery and #oilpainting
Cool approach! More minds better results. www.nature.com/articles/s41...
Drugit: crowd-sourcing molecular design of non-peptidic VHL binders - Nature Communications
Citizen science taps the efforts of non-experts. Here, authors describe Drugit, an extension of the crowdsourcing game Foldit, and its use in designing a non-peptide binder of Von Hippel Lindau E3 lig...
nature.com
It turns out what I was trying to do with my side projects is called “vibe coding”! Basically, I try to build full apps using LLM prompting and ZERO coding. It’s rather impressive what can be achieved! Problem comes with large codebases due to limited LLM memory. But.. 1/2 #vibecoding #cursorai #llm
Big news: we are setting up a new non-profit organization to run bioRxiv and medRxiv. It's called openRxiv [no it's not a new preprint server; it's dedicated organization to oversee the servers] openrxiv.org 1/n
Homepage - openRxiv
openRxiv is an independent non-profit, the new organizational home for bioRxiv and medRxiv, enabling researchers to instantly share groundbreaking findings with the global scientific community.
openrxiv.org
Interesting new challenge similar in spirit to the well known CACHE!!
For all the gains AI affords in compound design and discovery, experimental validation still remains a bottleneck. But we're making that part easy for the cancer target TBXT with a suite of biophysical, in vitro and in vivo assay capabilities—plus prizes for potent binders: tbxtchallenge.org
For all the gains AI affords in compound design and discovery, experimental validation still remains a bottleneck. But we're making that part easy for the cancer target TBXT with a suite of biophysical, in vitro and in vivo assay capabilities—plus prizes for potent binders: tbxtchallenge.org
TBXT CHALLENGE – Make history in drug discovery
Make history in drug discovery
tbxtchallenge.org
Will AI revolutionise drug design and discovery? Not the parts that count, says @dereklowe.bsky.social. Biology doesn’t care whether a drug was designed by a human or an algorithm, and there is no AI yet that can competently predict clinical trial outcomes. www.chemistryworld.com/opinion/robo...
I am using GPT4o for patent data activity extraction and it works very well! Much better than Excel OCR. #gpt4o #medchem #patentextraction
And now o3-mini has also been released… and my first test is quite successful. I am prompting it to build a python interface for REINVENT4. So far o3-mini has performed best against deepseek and chat-gpt4. Best by far!
How do you imagine the new reasoning LLM models will impact drug design? I’m starting to realize how important Agents will be in near future. They might become the new interface for everything we do. It is overwhelming to imagine all the possibilities.
Hi there! I’m moving in. I need to rebuild the network I had on Twitter/X. I mainly use this to keep in touch with folks ans science in drug discovery in general. Structure based drug design in particular. Some support would be great! 🙌