Advancing chemical reaction prediction in data-scarce drug discovery with active and geometric deep learning.
The success of generative molecular design depends on the synthetic accessibility of the molecules it creates. While computational models can help predict chemical reactions, their current effectiveness is limited by a lack of reference data and the difficulty of accurately predicting reaction regioselectivity. Here, t...
Mason Minot, Yannick Stenzhorn, Jens Wolfard et al.
· Nature Computational Science · 0 citations