7 January 2023 in Nature Communications
Generative chemical language models (CLMs) can be used for de novo molecular structure generation by learning from a textual representation of molecules. Here, we show that hybrid CLMs can additionally leverage the bioactivity information available for the training compounds. To computationally design ligands of phosphoinositide 3-kinase gamma (PI3Kγ), a collection of virtual molecules was created with a generative CLM. This virtual compound library was refined using a CLM-based classifier for bioactivity prediction. This second hybrid CLM was pretrained with patented molecular structures and fine-tuned with known PI3Kγ ligands. Several of the computer-generated molecular designs were commercially available, enabling fast prescreening and preliminary experimental validation. A new PI3Kγ ligand with sub-micromolar activity was identified, highlighting the method’s scaffold-hopping potential. Chemical synthesis and biochemical testing of two of the top-ranked de novo designed molecules and their derivatives corroborated the model’s ability to generate PI3Kγ ligands with medium to low nanomolar activity for hit-to-lead expansion. The most potent compounds led to pronounced inhibition of PI3K-dependent Akt phosphorylation in a medulloblastoma cell model, demonstrating efficacy of PI3Kγ ligands in PI3K/Akt pathway repression in human tumor cells. The results positively advocate hybrid CLMs for virtual compound screening and activity-focused molecular design.
19 November 2024 in RSC Advances
Semi-empirical quantum chemistry methods estimate the binding free energies of de novo generated ligand–protein complexes.
20 October 2022 in Future Medicinal Chemistry
Among neurodegenerative pathologies affecting the older population, Alzheimer’s disease is the most common type of dementia and leads to neurocognitive and behavioral disorders. It is a complex and... Graphical abstract
6 June 2025 in Nucleic Acids Research
Polyribonucleotide nucleotidyl-transferases (PNPases) play a critical role in the degradation of mRNA. The mycobacterial PNPase, guanosine penta-phosphate synthase I (GpsI), is an essential enzyme in Mycobacterium tuberculosis (Mtb), collaborating with endoribonucleases and helicases to process RNA. In this study, we identify GpsI as a novel and underexplored drug target. The inhibitor 1-(4′-(2-phenyl-5-(trifluoromethyl) oxazole-4-carboxamido)-[1,1′-biphenyl]-4-caroxamido) cyclopentane-1-carboxylic acid (X1), discovered through a whole-cell screening, specifically inhibits GpsI activity in biochemical assays. Biochemical and physiological analyses of engineered GpsI variants and recombinant Mycobacterium smegmatis pinpoint amino acids 328 and 527 as critical residues for the selective activity of X1 against Mtb complex. High-resolution cryo-electron microscopy analysis of the ternary GpsI–X1–poly(A) complex elucidates the drug-binding pocket, providing insight into its mechanism of action. This study introduces a potent inhibitor targeting the underexplored Mtb-GpsI and offers a molecular explanation for its selective specificity.
21 August 2026 in ChemRxiv
Developing safe and potent analgesics remains a critical global public health priority. Here, we show that generative de novo design can rapidly deliver novel opioid receptor agonists with high synthetic accessibility and desirable pharmacology. Inspired by the natural product mitragynine pseudoindoxyl, a complex metabolite found in traditional medicinal Kratom leaves, we leveraged its µ-opioid receptor binding characteristics to guide our generative computational framework. This deep learning approach successfully translated the partial agonism of the natural product and its G protein signaling bias into novel, structurally distinct chemotypes. One-third of the synthesized compounds exhibited potent receptor activation. Without requiring optimization, lead designs showed favorable pharmacokinetics, minimal off-target activity, and no β-arrestin recruitment. Cryogenic electron microscopy confirmed orthosteric receptor engagement, revealing that sub-pocket interactions alone do not account for their signaling behavior. By shifting away from stochastic high-throughput screening, this nature-inspired, artificial intelligence-driven workflow compresses discovery timelines while maximizing hit rates and molecular quality to deliver next-generation therapeutics.