Performance and robustness of small molecule retention time prediction with molecular graph neural networks in industrial drug discovery campaigns.

This study explores how machine-learning can be used to predict chromatographic retention times (RT) for the analysis of small molecules, with the objective of identifying a machine-learning framework with the robustness required to support a chemical synthesis production platform. We used internally generated data from high-throughput parallel synthesis in context of pharmaceutical drug discovery projects. We tested machine-learning models from the following frameworks: XGBoost, ChemProp, and DeepChem, using a dataset of 7552 small molecules. Our findings show that two specific models, AttentiveFP and ChemProp, performed better than XGBoost and a regular neural network in predicting RT accurately. We also assessed how well these models performed over time and found that molecular graph neural networks consistently gave accurate predictions for new chemical series. In addition, when we applied ChemProp on the publicly available METLIN SMRT dataset, it performed impressively with an average error of 38.70 s. These results highlight the efficacy of molecular graph neural networks, especially ChemProp, in diverse RT prediction scenarios, thereby enhancing the efficiency of chromatographic analysis.

Discovery of NSD2-Degraders from Novel and Selective DEL Hits.

NSD2 is a histone methyltransferase predominantly catalyzing di-methylation of histone H3 on lysine K36. Increased NSD2 activity due to mutations or fusion-events affecting the gene encoding NSD2 is considered an oncogenic event and a driver in various cancers, including multiple myelomas carrying t(4;14) chromosomal translocations and acute lymphoblastic leukemia's expressing the hyperactive NSD2 mutant E1099 K. Using DNA-encoded libraries, we have identified small molecule ligands that selectively and potently bind to the PWWP1 domain of NSD2, inhibit NSD2 binding to H3K36me2-bearing nucleosomes, but do not inhibit the methyltransferase activity. The ligands were subsequently converted to selective VHL1-recruiting NSD2 degraders and by using one of the most efficacious degraders in cell lines, we show that it leads to NSD2 degradation, decrease in K3 K36me2 levels and inhibition of cell proliferation.