ABSTRACT
Artificial intelligence and machine learning have demonstrated their potential role in predictive chemistry and synthetic planning of small molecules; there are at least a few reports of companies employing in silico synthetic planning into their overall approach to accessing target molecules. A data-driven synthesis planning program is one component being developed and evaluated by the Machine Learning for Pharmaceutical Discovery and Synthesis (MLPDS) consortium, comprising MIT and 13 chemical and pharmaceutical company members. Together, we wrote this perspective to share how we think predictive models can be integrated into medicinal chemistry synthesis workflows, how they are currently used within MLPDS member companies, and the outlook for this field.
Subject(s)
Chemistry Techniques, Synthetic/methods , Chemistry, Pharmaceutical/methods , Machine Learning , Chemical Industry/methods , Drug Discovery/methods , Models, Chemical , Pharmaceutical Research/methodsABSTRACT
Janus kinase (JAK) inhibitors are emerging as novel and efficacious drugs for treating psoriasis and other inflammatory skin disorders, but their full potential is hampered by systemic side effects. To overcome this limitation, we set out to discover soft drug JAK inhibitors for topical use. A fragment screen yielded an indazole hit that was elaborated into a potent JAK inhibitor using structure-based design. Growing the fragment by installing a phenol moiety in the 6-position afforded a greatly improved potency. Fine-tuning the substituents on the phenol and sulfonamide moieties afforded a set of compounds with lead-like properties, but they were found to be phototoxic and unstable in the presence of light.
