Structured Multi-task Learning for Molecular Property Prediction, AISTATS'22 (https://proceedings.mlr.press/v151/liu22e.html)

I predicted the pCHEMBL values, AlogP values, Molecular Weight and nunmber of Lipinski's Rule of 5 Violations of a biomolecule by end to end training multiple pretrained Language models, on Dopamine D2 active compounds sourced from the CHeMBL database.