AI | Jannik P. Roth

Developing a fragment-level framework for the calculation of exact Shapley Values.

Chemically Interpretable Explanations for Molecular Property Prediction via Fragment-Level Shapley Values

This work introduces a fragment-level Shapley value framework that enables the exact computation of feature contributions at the level of chemically meaningful fragments for molecular property predictions without relying on sampling or feature imputation.

Learning characteristics of transformer models are studied using control calculations and dataset maniputlation.

Unraveling learning characteristics of transformer models for molecular design

The learning characteristics of transformer based models for generative compound designs are studied using control calculations and careful manipulation of datasets.