RXN for Chemistry
@forrxn
Account for news and general info on the freely available AI platform made by #compchem chemists for #organic chemists. Try it today. π©βπ¬π¨βπ¬βοΈπ§ͺ
ID: 1065899150921908224
http://rxn.res.ibm.com 23-11-2018 09:25:35
334 Tweet
984 Followers
7 Following
On 08.24 at 08:25 CDT, Amol Thakkar (Amol Thakkar) will present "Augmented disconnection aware retrosynthesis to facilitate user interaction". Don't miss this talk, if you are curious to see the latest performance improvements in retrosynthesis in RXN for Chemistry. 5/8
On 08.24 at 09:40 CDT, Jannis Born (Jannis Born) will present "Guiding multistep retrosynthesis planning with continuous pathway representations". Federico Zipoli and Jannis did a THING: a string method for chemical reactions to create human grade retrosynthesis. Bar rises. 6/8
On 08.24 at 10:20, our own Alain Vaucher (Alain Vaucher) will present "Combining high-quality, humanly curated data with language models: the dawn of on-demand machine learning models for digital chemistry" in collaboration with Chemistry at Thieme @SOSChem 7/8
And congrats to the IBM Research team for winning the Sandmeyer prize Swiss Chemical Society Philippe Schwaller (he/him) Teodoro Laino Alain Vaucher Daniel Probst @[email protected] and colleagues. You rock! RXN for Chemistry
The Swiss Chemical Society Science Night was stunning. IBM Research was awarded with the Sandmeyer Prize for the multi-years efforts in digitalizing chemistry. It took sweat, determination and hard work: kudos to all of you friends. I am privileged to work with you. Whoβs who ? 1/2
This week we released "Unbiasing Retrosynthesis Language Models with Disconnection Prompts" pre-print: chemrxiv.org/engage/chemrxi⦠code: github.com/rxn4chemistry/⦠Let's dive in! Thread 𧡠#compchem #MachineLearning #Chemistry #chemtwitter RXN for Chemistry
Our preprint on retrosynthesis models with boosted diversity is out! preprint: openreview.net/forum?id=Bmk_Gβ¦ Check out the code at: github.com/rxn4chemistry/β¦ . Open-source models are also available! π Alain Vaucher Philippe Schwaller (he/him) Teodoro Laino #compchem #MachineLearning #Chemistry RXN for Chemistry
The talks will be presented by myself, Yves Gaetan, Matteo Manica, Anuv, Miruna Cretu, Amol Thakkar, Federico Zipoli, and Alek Sobczyk (2/3).
We published "Unbiasing Retrosynthesis Language Models with Disconnection Prompts" in ACS Central Science paper: pubs.acs.org/doi/10.1021/ac⦠code: github.com/rxn4chemistry/⦠Let's dive in! #compchem #MachineLearning #Chemistry #chemtwitter RXN for Chemistry
Our latest work in ACS Central Science on steering retrosynthesis predictions using #NLP has been highlighted by Organic Process Research & Development We empower chemists by enabling them to select disconections, leading to more diverse outputs. Try the automated retrosynthesis functionπ rxn.res.ibm.com