Artificial intelligence-guided discovery of a lead compound with antifolate-like activity against bacterial and human
Yi-Lin Chen1, Yi-Min Chen2, Yan Zou1
1Department of Medical Oncology, Quzhou People's Hospital, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou, China.
Abstract:
Thymidylate synthase (TYMS) is an established colorectal cancer (CRC) target. We evaluated whether conserved active-site architecture between human TYMS and the bacterial homolog TYSY KLEP7 could support early cross-species TYMS-axis lead discovery within the antifolate landscape. AlphaFold3, Chai-1 complex modeling, crystal-structure cross-validation, docking, ligand strain energy, MM-GBSA rescoring, and explicit-solvent MD were integrated to compare pocket states and prioritize antifolate-like Compound 8. Modeling indicated that Compound 8 preserves an acidic folate-groove anchoring motif while tolerating species- and ligand-induced pocket variation. Phenotypic assays showed dose-dependent inhibition of CRC cell viability with preliminary NCM460 selectivity, whereas antibacterial activity against K. pneumoniae was modest, with a MIC of 96 µM and bactericidal activity only at 4× MIC after 24 h. Target-axis assays supported TYMS/thyA engagement: siTYMS and AS-thyA reduced transcript levels, and Compound 8 inhibited crude-lysate TS activity with apparent AC50 values of 7.8 µM in HCT116 and 13.2 µM in K. pneumoniae. Overall, this work establishes an AI-enabled structure-to-phenotype framework and positions Compound 8 as an early antifolate-like TYMS-axis lead requiring purified-enzyme, ADME, safety, and antibacterial optimization studies.
Insights
This study explores Compound 8 as a potential antifolate drug targeting thymidylate synthase (TYMS) in colorectal cancer (CRC) and bacteria. AI-driven modeling and assays show its promise as an early lead, though further optimization is needed.
Area of Science:
- Biochemistry
- Computational Biology
- Drug Discovery
Background:
- Thymidylate synthase (TYMS) is a validated target for colorectal cancer (CRC) therapy.
- Conserved active-site architecture between human TYMS and bacterial homologs offers potential for cross-species drug discovery.
- Antifolates are a key class of drugs targeting the TYMS pathway.
Purpose of the Study:
- To evaluate the conserved active-site architecture of human TYMS and bacterial TYSY KLEP7 for early lead discovery.
- To investigate Compound 8 as an antifolate-like lead targeting the TYMS-axis.
- To establish an AI-enabled structure-to-phenotype framework for drug discovery.
Main Methods:
- Integrated computational methods including AlphaFold3, molecular modeling, docking, and molecular dynamics (MD).
- Cross-validation using crystal structures and biochemical assays.
- Phenotypic assays for cell viability and antibacterial activity.
- Target-axis engagement assays using siRNAs and antisense oligonucleotides.
Main Results:
- Compound 8 demonstrated dose-dependent inhibition of CRC cell viability with preliminary selectivity.
- Antibacterial activity against *K. pneumoniae* was modest, requiring higher concentrations for bactericidal effects.
- Compound 8 engaged both human TYMS and bacterial *thyA* (the gene encoding TYSY), inhibiting enzyme activity.
- AI-driven modeling predicted Compound 8's ability to maintain key interactions within the folate-binding groove.
Conclusions:
- An AI-enabled structure-to-phenotype framework was established for TYMS-axis drug discovery.
- Compound 8 represents an early-stage antifolate-like lead for TYMS-axis targeting.
- Further studies are required for purified-enzyme validation, ADME profiling, safety assessment, and antibacterial optimization.
Related Concept Videos
Drug Discovery: Overview
Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase
Antiprotozoal Agents


