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”.
4/ Adding “unreal engine” or “advanced unreal engine” to the text input prompt is important as it substantially increases the quality of the output image.
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
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⬇️
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%.
We did not only visualize what was important for the class predictions by looking at the different attention weights...