Search for: All records

We compute the monodromy of the mirabolic $\mathcal{D}$-module for all values of the parameters $(\vartheta ,c)$ in rank 1 and outside an explicit codimension 2 set of values in ranks 2 and higher. This shows in particular that the Finkelberg–Ginzburg conjecture, which is known to hold for generic values of $(\vartheta ,c)$, fails at special values even in rank 1. Our main tools are Opdam’s shift operators and intertwiners for the extended affine Weyl group, which allow for the resolution of resonances outside the codimension two set.

 

Identifying novel drug-target interactions is a critical and rate-limiting step in drug discovery. While deep learning models have been proposed to accelerate the identification process, here we show that state-of-the-art models fail to generalize to novel (i.e., never-before-seen) structures. We unveil the mechanisms responsible for this shortcoming, demonstrating how models rely on shortcuts that leverage the topology of the protein-ligand bipartite network, rather than learning the node features. Here we introduce AI-Bind, a pipeline that combines network-based sampling strategies with unsupervised pre-training to improve binding predictions for novel proteins and ligands. We validate AI-Bind predictions via docking simulations and comparison with recent experimental evidence, and step up the process of interpreting machine learning prediction of protein-ligand binding by identifying potential active binding sites on the amino acid sequence. AI-Bind is a high-throughput approach to identify drug-target combinations with the potential of becoming a powerful tool in drug discovery.