Philippe Schwaller (he/him) Profile picture
Dec 28, 2019 9 tweets 6 min read Read on X
Looking for a weekend/holiday read?
Happy to share this major update of our #NeurIPS2019 #ML4PS workshop paper on chemical reaction classificaction (but not only.. 🧪⚗️🌍). @IBMResearch @unibern #compchem #RealTimeChem

Summary thread ⬇️:
We compared different RXN classification methods. 📍Using a BERT model borrowed from NLP, we matched the ground truth (Pistachio, @nmsoftware) with an accuracy of 98.2%. Image
We did not only visualize what was important for the class predictions by looking at the different attention weights... Image
... but also mapped the chemical reaction space using the embeddings of our RXN BERT classifier (RXN fingerprint): Image
We investigated different combinations of RXN fingerprints: a) unsupervised, b) hand-crafted, c) supervised, d) a + b merged, and e) b + c merged. Image
And showed that our BERT RXN fingerprint can be used for efficient nearest neighbor searches in the reaction space without knowing the reaction center or distinguishing between reactants and reagents. Examples: Image
The similar precursors, products and reaction centers can be recognized even by non-experts. Image
For more examples and info read our manuscript. Made with love by @pschwllr, @skepteis, @acvaucher, Vishnu, @teodorolaino and @jrjrjlr.
Throughout this project we used (among others) the following tools and libraries: @PyTorch, @TensorFlow, @huggingface transformers, OpenNMT, @RDKit_org, @the_cdk and TMAP. Many thanks!

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Philippe Schwaller (he/him)

Philippe Schwaller (he/him) Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @pschwllr

Jul 4, 2022
I had planned to add all my #LINO22 highlights chronologically to my thread but there are just too many. So, I will just cherry-pick a few here.

Starting with the inspirational talk by @ben_list on the importance of catalysis for a more sustainable future.
Related to that the "Catalysis and Green Chemistry" panel discussion with Richard Schrock, Dave MacMillan (@dmac68), Liang Feng (@LiangFeng_chem), Jiangnan Li, Carla Casadevall (@CasadevallCarla) - well done!
Dave MacMillan’s (@dmac68) excellent advice for young group leaders/scientists:
- Be passionate and work on things you are truly excited about
- Be as generous as you can be and treat people with respect
Read 9 tweets
Mar 4, 2022
It was a great pleasure to present at M2D2. Tons of interesting questions and some remained unanswered. I will address them in this thread 🧵
@one_know_wonho: For yield prediction, how are the data labels distributed? Does the dataset also include reactant sets where no reaction happens between them (thus zero yield)?
Yes, the yields are distributed between 0 and 100%. For the Buchwald-Hartwig reactions (science.org/doi/abs/10.112…), the dataset contains more low- than high-yielding reactions. You can find more information in iopscience.iop.org/article/10.108….
Read 14 tweets
Jul 1, 2021
1/ What makes this @ChemicalScience front cover so special is how it was made.

It is probably the first-ever journal cover designed using a VQGAN + CLIP and the unreal engine trick!
#VQGAN #CLIP #GenerativeArt

More information in the thread ⬇️ Image
2/ The AI model (VQGAN + CLIP) generated most of the image using “enzymatic chemical reactions. green chemistry. advanced unreal engine” as input.
It’s interesting that you can recognise the lab with the blackboards, the floor and the “reactions”.
3/ I’ve added an enzymatic reaction from our publication (pubs.rsc.org/en/content/art…) on top of the image.

Before (AI generated) | after (final cover) ImageImage
Read 8 tweets
Sep 28, 2020
Taking chemical reaction prediction models one step further in a great collaboration with Giorgio (@Giorgio_P_), a brilliant organic chemist!

A thread ⬇️1/N
A major limitation of current deep learning reaction prediction models is stereochemistry. It is not taken into account by graph-neural networks and a weakness of text-based prediction models, like the Molecular Transformer (doi.org/10.1021/acscen…).
How can we improve? 2/N
In this work, we take carbohydrate reactions as an example. Compared to the reactions in patents (avg. 0.4 stereocentres in product), carbohydrate contain multiple stereocentres (avg. >6 in our test set), which make reactivity predictions challenging even for human experts. 3/N
Read 14 tweets
Mar 5, 2020
Awesome! All the video recordings of #AMLD2020 are now available on youtube. Check out the ones from the fantastic speakers we had in the #AIMolecularWorld track⬇️

@appliedmldays @befcorreia @pgainza @FreyrSverrisson Image
ML-based Design of Proteins and Small Molecules - Jennifer Listgarten (@jlistgarten)
Conditional Generation of Molecules from Disentangled Representations - Amina Mollaysa
Read 9 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(