🚨 We are currently recruiting 2 PhD students to join our team at Chalmers, which you can learn more about on our team website: ailab.bio/join-us

Details in thread below! (1/5)

Work done with Víctor Sabanza, Zlatko Joncěv, Jeremy Luterbacher, @pschwllr.bsky.social

Thank you to NSERC and NCCR Catalysis for the support!

(4/4)

In the pre-print, check out how 𝘨𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘷𝘦 design can loosely mimic virtual screening of ultra-large make-on-demand libraries - docking only 15,000 molecules identified promising candidates in a 142 billion space (amounting to 0.00001%)!

(3/4)

Reaction constraints can be “mix-and-matched” - all molecules have a synthesis route and allowing to:

1. Enforce the presence of 𝘴𝘱𝘦𝘤𝘪𝘧𝘪𝘤 reactions

2. Enforce 𝘰𝘯𝘭𝘺 specific reactions are used

3. Avoid specific reactions

4. Minimize synthesis route length

(2/4)

Generate property-optimized small molecules with 𝘴𝘵𝘦𝘦𝘳𝘢𝘣𝘭𝘦 𝘢𝘯𝘥 𝘨𝘳𝘢𝘯𝘶𝘭𝘢𝘳 synthesizability control - allowing complete user-flexibility to impose various reaction constraints!

Pre-print: arxiv.org/abs/2505.08774
Code: github.com/schwallergro...

(1/4)

My colleague Michaela Wenzel at Chalmers is recruiting 2 PhD students in AI-assisted antibiotic discovery. Very interesting projects with a great supervisor! You can learn more about the positions (and apply by May 5th) here: www.chalmers.se/en/about-cha...

Industry PhD opportunity: together with AstraZeneca, we’re recruiting an industial PhD student in data-driven life sciences to join us here in Gothenburg, SE! Deadline to apply April 24. More info in ad: www.scilifelab.se/career/indus...

(2) Synthesizability heuristics can be a noisy proxy for synthesizability but have out-of-distribution limitations

(3) This approach *generalizes* across molecule classes (drug and materials design)

Thanks to my PI @pschwllr.bsky.social!

(2/2)

Check out our paper published in @chemicalscience.rsc.org - pubs.rsc.org/en/content/a...

(1) *General-purpose* generative model + retrosynthesis model = design molecules with optimized properties with an *explicit* predicted synthesis pathway

(1/2)