Multifactorial drug response modeling based on cancer organoid data.

e13544 Background: Prediction of drug response based on cancer molecular profiles is of paramount importance for precision oncology. Most existing drug response prediction models are built using drug screening data of immortalized cancer cell lines, which usually have altered genomic profiles compared with patient tumors. Recently, patient-derived organoids (PDOs) are emerging as a promising platform better representing patient tumors. We build computational drug response prediction models based on PDO drug screening data, which is the first study of its type to our knowledge. Methods: We successfully developed 27 PDO lines of colorectal cancer and 20 PDO lines of head and neck (H&N) cancer. Transcriptomics, copy number variation (CNV), and targeted DNA mutation data were generated for the PDO lines. The PDO lines were screened with 36 drugs of diversified mechanisms. The area under the dose response curve was taken as the response measurement. We used the LightGBM algorithm to build response prediction models based on cancer molecular data and drug chemical descriptors/fingerprints. To investigate the influence of different factors on the prediction performance, including different cancer types, cancer molecular features, drug features, data preprocessing methods, and others, we applied a multifactorial analysis scenario to build and evaluate 3,384 prediction models constructed with all possible combinations of the factors. For example, we built prediction models for H&N and colorectal PDOs separately and jointly. Results: A prediction model built for H&N PDOs achieved the highest prediction performance among all prediction models, which was R2 of 0.790 in 10-fold cross-validation. The model was built using drug descriptors, CNVs, and expressions of “landmark” genes well-representing cellular transcriptomic changes identified in the LINCS project. The table below includes all the factorial differences that caused an average R2 change larger than 1%. All R2 changes are statistically significant (p-values < 1×10–50), evaluated by pair-wise t-tests comparing models built with the status of the factor changed. The prediction performance increased, from colorectal cancer to two cancer types combined, and to H&N cancer. Gene expression data, either whole-transcriptome or the subset of LINCS genes, boosted the prediction performance. Between the two different dyes used to stain dead cells, TO-PRO-3 provided a higher prediction performance than Caspase-3/7. Conclusions: The highest drug response prediction performance achieved is R2 of 0.790. Cancer type, dye, and whether gene expressions are used in modeling are the factors most influential on prediction performance.[Table: see text]