Fig. 6From: Improving chemical reaction yield prediction using pre-trained graph neural networksDistribution of reaction-wise error decreases by MolDescPred, compared to From-Scratch and MolCLR: (a) Buchwald-Hartwig (Random Split), (b) Suzuki-Miyaura (Random Split), (c) Buchwald-Hartwig (Out-Of-Sample Split)Back to article page