💥 Drug discovery software is broken Customers pay big fees for tools that may not work 👉🏽 We started KlyneAI to build tailored tools for your challenges—not generic ones No sugar-coating. If it doesn’t work, we stop—you don’t waste money.Time for an honest, problem-driven approach to drug discovery
Akshat Nigam
@akshatai.bsky.social
PhD student @Stanford CS. drug discovery; protein modeling & machine learning. BioX Fellow. Founder @Stealth.
Hot take in drug discovery: The real value of molecular docking lies in ranking for (ultra-large) virtual screening. Structure co-folding models with ligands? Super cool! But unless they prove themselves in screening performance, conventional docking still wins 🤔
🚀 Big news from Klyne! We’re thrilled to be collaborating with @cgorgulla.bsky.social ky.social's lab to develop the next generation of tools for accelerating drug discovery. Stay tuned—some exciting papers are on the way from this collaboration!
More of this. Please. www.theguardian.com/global-devel...
‘Living proof that you can spend money on the poor’: Utopia comes to Mexico City
A visionary mayor has harnessed her imagination to promote health, wellbeing and culture in one of the Mexican capital’s most impoverished neighbourhoods
theguardian.com
🚀 Exciting News! 🚀 KlyneAI is thrilled to join JLABS! We’re pushing the boundaries of biotech innovation and developing cutting-edge tools for drug discovery. Want to collaborate on AI-driven drug discovery? → klyne@klyne.ai #Biotech #DrugDiscovery #AI #JLabs (Yes, the view’s amazing) 🤩
Registration for the 2025 Accelerate conference in Toronto (Aug 11–14) opens soon! Be the first to know: zr2z766pxls.typeform.com/accelerate25
In our recent publication, we describe a systematic framework leveraging the documentation of the quantum chemistry suite ORCA for developing large language models that are capable of providing input files based on user prompts with the help of prompt engineering, retrieval-augmented generation […]
Original post on mstdn.science
mstdn.science
Absolutely love working with @aspuru.bsky.social 😁
Happy to appear in #BNNBloomberg TV talking about our recent research paper in @naturebiotech.bsky.social about #ai and #quantum for KRAS binder discovery. With @akshatai.bsky.social @elonverse.bsky.social Igor Staglar @cgorgulla.bsky.social @ghazivakili.bsky.social and others #chemsky
Check out this great interview with the incredible @aspuru.bsky.social on BNNBloomberg, highlighting a recent publication co-authored by our CTO, @akshatai.bsky.social ! [Paper: rdcu.be/d68Fs] Exciting times ahead for Klyne—stay tuned for more! 🚀🔬 t.co/tkLsgjcSDb
https://www.bnnbloomberg.ca/video/shows/the-close/2025/02/05/how-researchers-are-using-quantum-computing-to-target-an-undruggable-cancer-protein/
t.co
Excited to share our latest work, published this morning in Nature Biotechnology! 🎉 We developed a hybrid quantum computing-enhanced generative model to design KRAS inhibitors. Check it out here: rdcu.be/d68Fs. Some fascinating insights along the way:
Thrilled to welcome @akshatai.bsky.social to Klyne! 🚀 Stay tuned for exciting science updates. Have biotech questions or needs? We're here to help: klyne@klyne.ai
Excited to share some news this New Year! I’ll be joining @klyneai.bsky.social as CTO soon. We co-founded Klyne to revolutionize biotech with cost-effective, no-licensing-fee software solutions. 🚀 If you're interested in screening, hit optimization, or FEP calculations, reach out: klyne@klyne.ai 😉
Excited to share some news this New Year! I’ll be joining @klyneai.bsky.social as CTO soon. We co-founded Klyne to revolutionize biotech with cost-effective, no-licensing-fee software solutions. 🚀 If you're interested in screening, hit optimization, or FEP calculations, reach out: klyne@klyne.ai 😉
#RobSelects paper of the week #ChemicalScience: Variational autoencoder for property-directed inverse design of organic copolymers. #aichem https://doi.org/10.1039/D4SC05900J
Inverse design of copolymers including stoichiometry and chain architecture
The demand for innovative synthetic polymers with improved properties is high, but their structural complexity and vast design space hinder rapid discovery. Machine learning-guided molecular design is a promising approach to accelerate polymer discovery. However, the scarcity of labeled polymer data and the
pubs.rsc.org
In biomolecular simulations, interesting phenomena often unfold slowly, with the viscosity of the surrounding water further hindering conformational sampling. But what if we could simulate water with lower viscosity while preserving the same thermodynamic properties? 👇
🎉 Thrilled to share that I’ve successfully defended my PhD @Stanford! My thesis, "Machine Learning Approaches for Predicting Biological Function and Molecular Design," explores the intersection of ML, biology, and chemistry. Some Highlights:
Thanks @anshulkundaje.bsky.social! Really appreciate all the support in my PhD from both my advisors 🙂
Congrats to DR. @akshatai.bsky.social for defending his PhD thesis with flying colors! 🎉🎉🎉🎉🎉 Akshat was co-advised by me and Mike Bassik. He has done brilliant work on developing ML models of protein (repressor) function and small molecules. Check it out scholar.google.com/citations?hl... 1/
Surprised by how much of the scientific community has moved here—seeing so much more scientific content and a big boost in post quality here! Looking forward to posting more here! 😉