Screening for novel antibacterial compounds in small molecule libraries has a low success rate. We applied machine learning (ML)-based virtual screening for antibacterial activity and evaluated its predictive power by experimental validation. We first binarized 29,537 compounds according to their growth inhibitory activity (hit rate 0.87%) against the antibiotic-resistant bacterium Burkholderia cenocepacia and described their molecular features with a directed-message passing neural network (D-MPNN). Then, we used the data to train an ML model that achieved a receiver operating characteristic (ROC) score of 0.823 on the test set. Finally, we predicted antibacterial activity in virtual libraries corresponding to 1,614 compounds from the Food and Drug Administration (FDA)-approved list and 224,205 natural products. Hit rates of 26% and 12%, respectively, were obtained when we tested the top-ranked predicted compounds for growth inhibitory activity against B. cenocepacia, which represents at least a 14-fold increase from the previous hit rate. In addition, more than 51% of the predicted antibacterial natural compounds inhibited ESKAPE pathogens showing that predictions expand beyond the organism-specific dataset to a broad range of bacteria. Overall, the developed ML approach can be used for compound prioritization before screening, increasing the typical hit rate of drug discovery.

To streamline the elucidation of antibacterial compounds’ mechanism of action, comprehensive high-throughput assays interrogating multiple putative targets are necessary. However, current chemogenomic approaches for antibiotic target identification have not fully utilized the multiplexing potential of next-generation sequencing.

The CD24 cell surface receptor promotes apoptosis in developing B cells, and we recently found that it induces B cells to release plasma membrane-derived, CD24-bearing microvesicles (MVs). Here we have performed a systematic characterization of B cell MVs released from WEHI-231 B lymphoma cells in response to CD24 stimulation. We found that B cells constitutively release MVs of approximately 120 nm, and that CD24 induces an increase in phosphatidylserine-positive MV release. RNA cargo is predominantly comprised of 5S rRNA, regardless of stimulation; however, CD24 causes a decrease in the incorporation of protein coding transcripts. The MV proteome is enriched with mitochondrial and metabolism-related proteins after CD24 stimulation; however, these changes were variable and could not be fully validated by Western blotting. CD24-bearing MVs carry Siglec-2, CD63, IgM, and, unexpectedly, Ter119, but not Siglec-G or MHC-II despite their presence on the cell surface. CD24 stimulation also induces changes in CD63 and IgM expression on MVs that is not mirrored by the changes in cell surface expression. Overall, the composition of these MVs suggests that they may be involved in releasing mitochondrial components in response to pro-apoptotic stress with changes to the surface receptors potentially altering the cell type(s) that interact with the MVs.