Generative artificial intelligence models present a fresh approach to chemogenomics and de novo drug design, as they provide researchers with the ability to narrow down their search of the chemical space and focus on regions of interest. We present a method for molecular de novo design that utilizes generative recurrent neural networks (RNN) containing long short‐term memory (LSTM) cells. This computational model captured the syntax of molecular representation in terms of SMILES strings with close to perfect accuracy. The learned pattern probabilities can be used for de novo SMILES generation. This molecular design concept eliminates the need for virtual compound library enumeration. By employing transfer learning, we fine‐tuned the RNN′s predictions for specific molecular targets. This approach enables virtual compound design without requiring secondary or external activity prediction, which could introduce error or unwanted bias. The results obtained advocate this generative RNN‐LSTM system for high‐impact use cases, such as low‐data drug discovery, fragment based molecular design, and hit‐to‐lead optimization for diverse drug targets.

Automating the molecular design-make-test-analyze cycle accelerates hit and lead finding for drug discovery. Using deep learning for molecular design and a microfluidics platform for on-chip chemical synthesis, liver X receptor (LXR) agonists were generated from scratch. The computational pipeline was tuned to explore the chemical space of known LXRα agonists and generate novel molecular candidates. To ensure compatibility with automated on-chip synthesis, the chemical space was confined to the virtual products obtainable from 17 one-step reactions. Twenty-five de novo designs were successfully synthesized in flow. In vitro screening of the crude reaction products revealed 17 (68%) hits, with up to 60-fold LXR activation. The batch resynthesis, purification, and retesting of 14 of these compounds confirmed that 12 of them were potent LXR agonists. These results support the suitability of the proposed design-make-test-analyze framework as a blueprint for automated drug design with artificial intelligence and miniaturized bench-top synthesis.

The sodium ion site is an allosteric site conserved among many G protein-coupled receptors (GPCRs). Amiloride 1 and 5-(N,N-hexamethylene)amiloride 2 (HMA) supposedly bind in this sodium ion site and can influence orthosteric ligand binding. The availability of a high-resolution X-ray crystal structure of the human adenosine A2A receptor (hA2AAR), in which the allosteric sodium ion site was elucidated, makes it an appropriate model receptor for investigating the allosteric site. In this study, we report the synthesis and evaluation of novel 5'-substituted amiloride derivatives as hA2AAR allosteric antagonists. The potency of the amiloride derivatives was assessed by their ability to displace orthosteric radioligand [(3)H]4-(2-((7-amino-2-(furan-2-yl)-[1,2,4]triazolo[1,5-a]-[1,3,5]triazin-5-yl)amino)ethyl)phenol ([(3)H]ZM-241,385) from both the wild-type and sodium ion site W246A mutant hA2AAR. 4-Ethoxyphenethyl-substituted amiloride 12l was found to be more potent than both amiloride and HMA, and the shift in potency between the wild-type and mutated receptor confirmed its likely binding to the sodium ion site.

The sentence "The dataset was then pre-processed to remove duplicates, salts and stereochemical information." in Section 2.1 of the article should read "The dataset was then pre-processed to remove salts and stereochemical information." Erratum

No abstract