Open-source software, web servers, and datasets developed by the AIDDPM Lab.
An AI-powered immunotherapy response prediction tool. COMPASS integrates multi-modal clinical and genomic features to predict cancer patients' response to immune checkpoint blockade therapy. Validated across multiple clinical cohorts.
Transforms molecular descriptors and fingerprints into structured 2D feature maps, enabling convolutional neural networks to learn rich spatial patterns for drug property prediction. Integrated into ZairaChem's fully automated drug discovery pipeline.
A multi-omics data structurization and visualization tool. AggMap automatically organizes high-dimensional omics features into interpretable 2D maps using unsupervised manifold learning, enabling downstream deep learning analysis.
An automated drug design platform enabling a closed-loop of design–synthesis–testing–analysis for small molecule lead compounds, developed in collaboration with the NUS synthetic chemistry laboratory.
All tools developed by AIDDPM Lab are released as open-source software under permissive licenses. We believe in reproducibility and the democratization of AI methods in drug discovery. All code, pre-trained models, and benchmark datasets are made publicly available upon publication.