Towards a more inductive world - AI4D3@Neurips

We are thrilled to announce that after several months (actually more than a year) working on this manuscript, it got accepted as an oral communication at the AI4D3 Workshop of Neurips 2023 🥳. Check it here.

This paper consists of a thorough evaluation of state-of-the-art models for predicting drug-target interaction (DTI) and a toolbox for easing the future model design.

In this work, we first perform an in-depth evaluation of current DTI datasets and prediction models through a robust benchmarking process and show that DTI prediction methods based on transductive models lack generalization and lead to inflated performance when evaluated as previously done in the literature, hence not being suited for drug repurposing approaches. We then propose a novel biologically-driven strategy for negative edge subsampling and show through in vitro validation that newly discovered interactions are true. We envision this work as the underpinning for future fair benchmarking and robust model design. All generated resources and tools are publicly available as a Python package.

We are currently in the process of submitting this work for publication in a journal.

Will keep you posted! 👩‍💻