Estimating protein-ligand interactions with geometric deep learning and mixture density models.

Understanding the interactions between a ligand and its molecular target is crucial in guiding the optimization of molecules for any drug design workflow. Multiple experimental and computational methods have been developed to better understand these intermolecular interactions. With the availability of a large number of structural datasets, there is a need for developing statistical frameworks that improve upon existing physicsbased solutions.

Investigating the interaction pattern of FDA approved compounds with GidB to understand their potential as antibiotics.

() drug resistance is a major challenge in eradicating its infection globally. is continuously evolving to overcome the anti-TB drug stress and retain its survival inside the host cells. This continuous evolution of can only be tackled by the continuous search for novel drug targets as well as developing new therapeutics.

Enhanced depletion of MLL-fusion proteins in acute leukemia: potential for improved therapeutic outcomes.

Rearrangements of the MLL (KMT2A) locus are associated with aggressive leukaemia of both myeloid and lymphoid lineages, that present profound therapeutic challenges in pediatric and adult patient populations. MLL-fusion genes resulting from these rearrangements function as driving oncogenes and have been the focus of research aimed at understanding mechanisms underlying their leukemogenic activity and revealing novel therapeutic opportunities. Inspired by the paradigm of depleting the PML-RARA fusion protein in acute promyelocytic leukemia using all-trans retinoic acid and arsenic trioxide, we conducted a screen to identify FDA-approved drugs capable of depleting MLL-fusion protein expression in leukemia cells.