Skip to content

Core Technology

DTIGN — drug-target graphs, at industrial scale.

A graph-based deep learning stack that turns a 2B+ compound library into actionable, ranked candidates for our preclinical programs.

Key metrics

Compound library
2B+

Virtually screenable molecules accessible through our AI pipeline.

Molecules generated
10M+

Novel candidates produced by our generative discovery models.

Hit-rate uplift
64x

Measured improvement over conventional high-throughput screening.

Predictive accuracy
44.83%

Top-line model performance reported in our IEEE DTIGN paper.

Generative chemistry

10M+ novel candidates generated, filtered through pharma-grade ADME/Tox screens before in vitro validation.

Drug-target graph network (DTIGN)

Our IEEE-published model encodes drug-target topology to predict binding, achieving 44.83% accuracy on benchmark assays.

Closed-loop validation

Wet-lab assays feed back into the model weekly, compounding hit-rate improvements (currently 64x over HTS).

Publications

Research Briefs

Subscribe to NYB Research Briefs

Monthly digest of our AI drug discovery progress, publications, and longevity science.

By submitting this form, you consent to Nanyang Biologics processing your personal data in accordance with our Privacy Policy and Singapore's Personal Data Protection Act (PDPA).