Document Type


Publication Date




JAX Source

Bioinform Adv. 2023;3(1):vbad051.







Research reported in this publication was supported in part by The Jackson Laboratory Director Innovation Fund (DIF) and the National Cancer Institute (NCI) of the National Institutes of Health (NIH) under award number R01CA089713. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.


Motivation: Drug synergy prediction is approached with machine learning techniques using molecular and pharmacological data. The published Cancer Drug Atlas (CDA) predicts a synergy outcome in cell-line models from drug target information, gene mutations and the models’ monotherapy drug sensitivity. We observed low performance of the CDA, 0.339, measured by Pearson correlation of predicted versus measured sensitivity on DrugComb datasets.

Results: We augmented the approach CDA by applying a random forest regression and optimization via cross-validation hyper-parameter tuning and named it Augmented CDA (ACDA). We benchmarked the ACDA’s performance, which is 68% higher than that of the CDA when trained and validated on the same dataset spanning 10 tissues. We compared the performance of ACDA to one of the winning methods of the DREAM Drug Combination Prediction Challenge, the performance of which was lower than ACDA in 16 out of 19 cases. We further trained the ACDA on Novartis Institutes for BioMedical Research PDX encyclopedia data and generated sensitivity predictions for PDX models. Finally, we developed a novel approach to visualize synergy-prediction data.

Availability and implementation: The source code is available at and the software package at PyPI.

Contact: or

Supplementary information: Supplementary data are available at Bioinformatics Advances online.


This is an Open Access article distributed under the terms of the Creative Commons Attribution License (, which permits unre- stricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.