With the advent of the Human Genome Project came the industrialisation of the drug discovery process and a belief that combinatorial chemistry and high throughput screening would deliver molecules with increased potency, against a single target of interest. Yet the attrition rate is still at the 90% mark and there remain many human diseases for which no effective treatment exists. As Swinney et al have shown , there is compelling evidence that first-in-class drugs are more likely to be found by assays that measure a clinically meaningful phenotype in a physiologically relevant system rather than a single target based screening approach in an artificial setting.
One perceived issue with phenotypic screening is the lack of mechanistic knowledge. Whilst understanding mechanism of action (MOA) is not a prerequisite for FDA approval, it can guide a medicinal chemistry effort, predict potential toxicities and help define patient populations for clinical trials and ultimately the market place. There are a number of in vitro approaches to target deconvolution. However, these tend to be of lower throughput and better placed later in a screening cascade. So there is a real need for in silico based approaches that can be deployed early on in a drug discovery programme to identify potential MOAs.
Using publicly available data on the Published Kinase Inhibitor Set (PKIS) [2,3], we describe the application of Formal Concept Analysis (FCA), an association mining technique with roots in set theory, to the problem of deconvoluting a phenotypic screen. We describe each compound in the PKIS by the set of kinases it inhibits. We then construct a Galois Lattice, whose nodes correspond to a set of compounds inhibiting a common set of kinases and where two nodes are connected if the compound set of the child node is a subset of the compound set of the parent node. Lattice nodes enriched with compounds that promote neurite outgrowth in rat inform on which kinases should be targeted when seeking small molecules that encourage CNS axon repair following injury. The targets we identify using this unsupervised and interpretable approach, are in line with those identified in  where here the authors use a combination of support vector machines, considered a black box method, and mutual information, then confirm in siRNA studies.
- Swinney DC, Anthony J. How were new medicines discovered? Nat Rev Drug Discov. 2011;10:507–19.
- Drewry DH, Willson TM, Zuercher WJ. Seeding collaborations to advance kinase science with the GSK Published Kinase Inhibitor Set (PKIS). Curr Top Med Chem 2014;14:340–2.
- Al-Ali H, Lee DH, Danzi MC, Nassif H, Gautam P, Wennerberg K, Zuercher WJ, Drewry DH, Lee JK, Lemmon VP, Bixby JL. Rational polypharmacology: systematically identifying and engaging multiple drug targets to promote axon growth. ACS Chem Biol 2015;10:1939–51.