Zhengkai Tu

PhD student @MIT

[Songtao Liu @SongtaoLiu]

#ICML2023 I'm excited to share that my paper "FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning" has been accepted by ICML 2023.

code: https://t.co/eKre4l7cet

arXiv: https://t.co/bs3Oa6AiLt

[MIT Jameel Clinic for AI & Health @AIHealthMIT]

The authors of MolScribe, which uses AI for molecular structure recognition, now present RxnScribe, a model which goes a step further by extracting reaction diagrams & predicting reactions in new diagrams.
Paper: https://t.co/7dSP3u6ttI
Code: https://t.co/MUZpTQBVlu

[Lucky Pattanaik @lucky_pattanaik]

Another one 🔥🥳🎉 Big year for the Chem+ML group here @MITChemE. Our work describing how to use QM descriptors calculated on-the-fly to predict substitution regioselectivity of is up @ChemicalScience! Led by Yanfei Guan, with @cwcoley and @thomasstruble
https://t.co/eUDAPpHQ3w

[Connor W. Coley @cwcoley]

"Defining and Exploring Chemical Spaces" | A mini-review I wrote over the summer is out in @TrendsChemistry. Could be a nice starting point for researchers interested in algorithmic molecular optimization. Open access until Feb 4 via https://t.co/CQOgEB8qLP #compchem

[Connor W. Coley @cwcoley]

1/ I'm excited to announce David Graff's (@HarvardCCB) first preprint with our group, "Accelerating high-throughput virtual screening with molecular pool-based active learning" at https://t.co/HABVTwCImE & https://t.co/1YCAqhgfEf #compchem

[Connor W. Coley @cwcoley]

Still have multiple openings for new postdocs @MITChemE -- get in touch by email ([email protected]) if you're interested in ML for reaction informatics, synthesis planning, and laboratory automation!

[Wenhao Gao @WenhaoGao1]

Proud of being part of this fantastic team! Our vision is build a platform for both domain scientists and ML community. Domain scientists can post tasks (and/or data) need to be solved and ML researchers can benchmark their models with real world data. Calling for contribution!