De Novo Design of Bioactive Small Molecules by Artificial Intelligence

Abstract

Generative artificial intelligence offers a fresh view on molecular design. We present the first-time prospective application of a deep learning model for designing new druglike compounds with desired activities. For this purpose, we trained a recurrent neural network to capture the constitution of a large set of known bioactive compounds represented as SMILES strings. By transfer learning, this general model was fine-tuned on recognizing retinoid X and peroxisome proliferator-activated receptor agonists. We synthesized five top-ranking compounds designed by the generative model. Four of the compounds revealed nanomolar to low-micromolar receptor modulatory activity in cell-based assays. Apparently, the computational model intrinsically captured relevant chemical and biological knowledge without the need for explicit rules. The results of this study advocate generative artificial intelligence for prospective de novo molecular design, and demonstrate the potential of these methods for future medicinal chemistry.

Keywords: Automation; drug discovery; machine learning; medicinal chemistry; nuclear receptor.

Figure 1

Concept of generative artificial intelligence (AI). A model of the training data (e. g., molecular structures) is obtained that can be used to emit new instances (new chemical entities) within the training domain by sampling.

Figure 2

Chemical space analysis by multi‐dimensional scaling. Compounds were represented by Morgan substructure fingerprints (radius=0–4 bonds, length=1024 bit), and similarity was defined by the Jaccard‐Tanimoto index. Colored dots represent the training data (light grey), fine‐tuning set (green), known RXR (orange) and PPAR (blue) agonists, sampled molecules (dark grey), and the selected de novo designs 1–5 (red). Compounds 1, 2, 3 and 5 populate the same area as the known RXR and PPAR agonists, while 4 is similar to PPAR agonist but remote from known RXR actives.

Scheme 1

Synthesis of designs 1–5. Reagents & conditions: (a) H₂N−C₆H₄−COOH (7), EDC, 4‐DMAP, THF, reflux, 4 h; (b) C₆H₅−B(OH)₂ (9), Pd(PPh₃)₄, Cs₂CO₃, dioxane, 100 °C, 16 h; (c) KOH, MeOH/THF/H₂O, μw, 70 °C, 30 min; (d) HO‐C₆H₃F−B(OH)₂ (12), Pd(PPh₃)₄, Cs₂CO₃, toluene/EtOH, 100 °C, 20 h; (e) F‐C₆H₄‐CH₂‐Br (15), K₂CO₃, DMF, μw, 100 °C, 120 min; (f) MeOH, H₂SO₄cc, reflux, 4 h; (g) C₅H₉Br (18), K₂CO₃, DMF, μw, 100 °C, 6 h; (h) HO‐C₆H₄‐B(OH)₂ (20), Pd(PPh₃)₄, Cs₂CO₃, toluene/EtOH, 100 °C, 16 h; (i) C₆H₄Cl‐C₆H₄‐COOH (24), EDC, 4‐DMAP, CHCl₃, relux, 12 h; (j) C₆H₃Br(OH)₂ (27), Pd(PPh₃)₄, Cs₂CO₃, dioxane/DMF, reflux, 4 h; (k) malonic acid, pyridine/piperidine, μw, 100 °C, 30 min.