Saved in:
Bibliographic Details
Main Authors: Strømme, Magnus H., de Sá, Alex G. C., Ascher, David B.
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.26114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914533172314112
author Strømme, Magnus H.
de Sá, Alex G. C.
Ascher, David B.
author_facet Strømme, Magnus H.
de Sá, Alex G. C.
Ascher, David B.
contents DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule anti-cancer activity across the NCI-60 panel, trained and evaluated under a strict chemistry-aware data-partitioning scheme. On the hold-out test set, the classifier achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.87 (95% CI [0.86, 0.88]) and Area Under the Precision-Recall Curve (AUPRC) of 0.73 (95% CI [0.70, 0.76]); per-cell-line regression models for 73 cell lines produced a median Pearson's Correlation Coefficient (Pearson's R) of 0.64 and median Root Mean Squared Error (RMSE) of 0.67 for pGI50-value prediction. Benchmarks against pdCSM-Cancer, MLASM, and ACLPred under matched data conditions yielded consistently higher Matthew's Correlation Coefficient (MCC) scores, an occlusion-based attribution analysis confirmed that model explanations were quantitatively faithful to classifier decisions, and an applicability-domain analysis characterised reliability as a function of chemical distance. To facilitate widespread adoption, DPD-Cancer is available as a free, user-friendly web server for unrestricted use at https://biosig.lab.uq.edu.au/dpd_cancer/.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26114
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DPD-Cancer: Explainable Graph-Based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
Strømme, Magnus H.
de Sá, Alex G. C.
Ascher, David B.
Machine Learning
Artificial Intelligence
DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule DPD-Cancer is a graph-attention deep learning framework for predicting small-molecule anti-cancer activity across the NCI-60 panel, trained and evaluated under a strict chemistry-aware data-partitioning scheme. On the hold-out test set, the classifier achieved an Area Under the Receiver Operating Characteristic Curve (AUROC) of 0.87 (95% CI [0.86, 0.88]) and Area Under the Precision-Recall Curve (AUPRC) of 0.73 (95% CI [0.70, 0.76]); per-cell-line regression models for 73 cell lines produced a median Pearson's Correlation Coefficient (Pearson's R) of 0.64 and median Root Mean Squared Error (RMSE) of 0.67 for pGI50-value prediction. Benchmarks against pdCSM-Cancer, MLASM, and ACLPred under matched data conditions yielded consistently higher Matthew's Correlation Coefficient (MCC) scores, an occlusion-based attribution analysis confirmed that model explanations were quantitatively faithful to classifier decisions, and an applicability-domain analysis characterised reliability as a function of chemical distance. To facilitate widespread adoption, DPD-Cancer is available as a free, user-friendly web server for unrestricted use at https://biosig.lab.uq.edu.au/dpd_cancer/.
title DPD-Cancer: Explainable Graph-Based Deep Learning for Small Molecule Anti-Cancer Activity Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.26114