Computational methods to assist in the discovery of pharmacological chaperones for rare diseases

Improvement of Mutant Galactose-1-Phosphate Uridylyltransferase (GALT) Activity by FDA-Approved Pharmacochaperones: A Preliminary Study

Classic galactosemia is a rare disease with long-term consequences that seriously affect the quality of life of patients. To date, various therapeutic approaches are being developed, but treatments that target the molecular defects in the mutant galactose-1-phosphate uridylyltransferase (GALT) gene are lacking. We conducted a computational search for putative pharmacochaperones by applying a drug repurposing strategy, and we found that one compound, already active as a pharmacochaperone in another pathology, doubled the enzymatic activity of the purified mutant enzyme in an in vitro test. Furthermore, an extensive computational search in a database of known active molecules found another compound able in its turn to improve in vitro enzymatic activity. Both compounds are predicted to interact with a cavity at the enzyme interface previously supposed to be an allosteric site for the GALT enzyme. In vitro tests confirmed also the reduced accumulation of galactose-1-phosphate (G1P) in fibroblasts of patients. Although these results must be considered preliminary, our findings pave the way for future research lines focused on the search for promising pharmacochaperones that can directly rescue the activity of the enzyme.

Computational model for drug research

This special issue focuses on computational model for drug research regarding drug bioactivity prediction, drug-related interaction prediction, modelling for immunotherapy and modelling for treatment of a specific disease, as conveyed by the following six research and four review articles. Notably, these 10 papers described a wide variety of in-depth drug research from the computational perspective and may represent a snapshot of the wide research landscape.

Applications of machine learning in computer-aided drug discovery

Machine learning (ML) has revolutionised the field of structure-based drug design (SBDD) in recent years. During the training stage, ML techniques typically analyse large amounts of experimentally determined data to create predictive models in order to inform the drug discovery process. Deep learning (DL) is a subfield of ML, that relies on multiple layers of a neural network to extract significantly more complex patterns from experimental data, and has recently become a popular choice in SBDD. This review provides a thorough summary of the recent DL trends in SBDD with a particular focus on de novo drug design, binding site prediction, and binding affinity prediction of small molecules.