ILP-assisted de novo drug design

Abstract

De novo design of drugs uses the three-dimensional structure of a target protein (often called the receptor) to design molecules (or ligands) that could bind to the receptor and hence inhibit its functioning. Thus, unlike a ligand-based approach, this form of drug design does not require prior knowledge of inhibitors. In this paper, the three-dimensional structure of a receptor is used indirectly, in the form of molecular interaction fields of the receptor and small molecules (or probes). In addition, we also use domain-specific constraints encoding basic geometric and pharmacological requirements imposed by the target. Interaction energies of one or more targets with a set of probes are used to identify threedimensional constraints that occur in many-preferably all-targets. In a graph-theoretic sense, the constraints are (small, fixed-size) cliques in graphs with labelled vertices representing probe-specific points of high interaction energy, and edges between a pair of vertices are labelled by the three-dimensional distance between the corresponding points of interaction. Our interest is in the discovery of frequent cliques that satisfy domain-specific constraints. In the paper, the discovery of such patterns is done using an Inductive Logic Programming (ILP) engine. The case for the use of ILP stems primarily from the explicit ways of incorporating domain-constraints, but any other technique capable of discovering frequent cliques from data can be used with some additional effort. The frequent cliques discovered are used to hypothesize pharmacophore-like structures on potential ligands. We test the utility of this approach by conducting a case study on the discovery of anti-malarials. Specifically, we test the approach on proteins belonging to the class of aspartic proteases. We are particularly interested in plasmepsin II, which is an enzyme in the haemoglobin degradation pathway of Plasmodium falciparum. We assess the pharmacophore-like constraints using: (a) a database of known inhibitors and non-inhibitors of aspartic proteases; and (b) a database of decoys that are physico-chemically similar to the aspartic proteases. Our results suggest that the

Using Domain-Knowledge to Assist Lead Discovery in Early-Stage Drug Design

“…This may presage a move to a probabilistic logic representation of the domainknowledge. On discriminators, BotGNNs continue to be a good choice for inclusion of symbolic knowledge into deep networks, although, as we have pointed out, the BotGNN model could be improved by inclusion as part of domain-knowledge, results from models constructed by programs like like Chemprop (the extensive use of fingerprints by such programs is essentially a form of relational information), and also the possibility of inclusion of 3-dimensional constraints (see for example, [38]). Looking beyond the goal of novel molecule generation, a promis-ing line of research concerns the development of schedules for synthesis of new molecules.…”

Inductive logic programming at 30

“…Perhaps the most prominent application of ILP is in scientific discovery. ILP has, for instance, been used to identify and predict ligands (substructures responsible for medical activity) (Kaalia et al, 2016) and infer missing pathways in protein signalling networks (Inoue et al, 2013). There has been much recent work on applying ILP in ecology (Bohan et al, 2011(Bohan et al, , 2017Tamaddoni-Nezhad et al, 2014).…”

Inductive logic programming at 30

“…Perhaps the most prominent application of ILP is in scinefitic discovery. ILP has, for instance, been used to identify and predict ligands (substructures re-sponsible for medical activity) [52] and infer missing pathways in protein signalling networks [50]. There has been much recent work on applying ILP in ecology [10,105,11].…”