Artificial Intelligence-Based Computational Screening and Functional Assays Identify Candidate Small Molecule Antagonists of PTPmu-Dependent Adhesion

Abstract

PTPmu (PTPµ) is a member of the receptor protein tyrosine phosphatase IIb family that participates in cell-cell adhesion and signaling. PTPmu is proteolytically downregulated in glioblastoma (glioma), and the resulting extracellular and intracellular fragments are believed to stimulate cancer cell growth and/or migration. Therefore, drugs targeting these fragments may have therapeutic potential. Here, we used the AtomNet® platform, the first deep learning neural network for drug design and discovery, to screen a molecular library of several million compounds and identified 76 candidates predicted to interact with a groove between the MAM and Ig extracellular domains required for PTPmu-mediated cell adhesion. These candidates were screened in two cell-based assays: PTPmu-dependent aggregation of Sf9 cells and a tumor growth assay where glioma cells grow in three-dimensional spheres. Four compounds inhibited PTPmu-mediated aggregation of Sf9 cells, six compounds inhibited glioma sphere formation/growth, while two priority compounds were effective in both assays. The stronger of these two compounds inhibited PTPmu aggregation in Sf9 cells and inhibited glioma sphere formation down to 25 micromolar. Additionally, this compound was able to inhibit the aggregation of beads coated with an extracellular fragment of PTPmu, directly demonstrating an interaction. This compound presents an interesting starting point for the development of PTPmu-targeting agents for treating cancer including glioblastoma.