A systematic assessment of deep learning methods for drug response prediction: from in vitro to clinical applications.

Drug response prediction is an important problem in personalized cancer therapy. Among various newly developed models, significant improvement in prediction performance has been reported using deep learning methods. However, systematic comparisons of deep learning methods, especially of the transferability from preclinical models to clinical cohorts, are currently lacking. To provide a more rigorous assessment, the performance of six representative deep learning methods for drug response prediction using nine evaluation metrics, including the overall prediction accuracy, predictability of each drug, potential associated factors and transferability to clinical cohorts, in multiple application scenarios was benchmarked. Most methods show promising prediction within cell line datasets, and TGSA, with its lower time cost and better performance, is recommended. Although the performance metrics decrease when applying models trained on cell lines to patients, a certain amount of power to distinguish clinical response on some drugs can be maintained using CRDNN and TGSA. With these assessments, we provide a guidance for researchers to choose appropriate methods, as well as insights into future directions for the development of more effective methods in clinical scenarios.

Dual-view jointly learning improves personalized drug synergy prediction.

MOTIVATION: Accurate and robust estimation of the synergistic drug combination is important for medicine precision. Although some computational methods have been developed, some predictions are still unreliable especially for the cross-dataset predictions, due to the complex mechanism of drug combinations and heterogeneity of cancer samples. RESULTS: We have proposed JointSyn that utilizes dual-view jointly learning to predict sample-specific effects of drug combination from drug and cell features. JointSyn outperforms existing state-of-the-art methods in predictive accuracy and robustness across various benchmarks. Each view of JointSyn captures drug synergy-related characteristics and make complementary contributes to the final prediction of drug combination. Moreover, JointSyn with fine-tuning improves its generalization ability to predict a novel drug combination or cancer sample using a small number of experimental measurements. We also used JointSyn to generate an estimated atlas of drug synergy for pan-cancer and explored the differential pattern among cancers. These results demonstrate the potential of JointSyn to predict drug synergy, supporting the development of personalized combinatorial therapies. AVAILABILITY: Source code and data are available at https://github.com/LiHongCSBLab/JointSyn. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Applying machine learning for multi-individual Raman spectroscopic data to identify different stages of proliferating human hepatocytes.

Cell therapy using proliferating human hepatocytes (ProliHHs) is an effective treatment approach for advanced liver diseases. However, rapid and accurate identification of high-quality ProliHHs from different donors is challenging due to individual heterogeneity. Here, we developed a machine learning framework to integrate single-cell Raman spectroscopy from multiple donors and identify different stages of ProliHHs. A repository of more than 14,000 Raman spectra, consisting of primary human hepatocytes (PHHs) and different passages of ProliHHs from six donors, was generated. Using a sliding window algorithm, potential biomarkers distinguishing the different cell stages were identified through differential analysis. Leveraging machine learning models, accurate classification of cell stages was achieved in both within-donor and cross-donor prediction tasks. Furthermore, the study assessed the relationship between donor and cell numbers and its impact on prediction accuracy, facilitating improved quality control design. A similar workflow can also be extended to encompass other cell types.

Large-scale pharmacogenomic studies and drug response prediction for personalized cancer medicine.

The response rate of most anti-cancer drugs is limited because of the high heterogeneity of cancer and the complex mechanism of drug action. Personalized treatment that stratifies patients into subgroups using molecular biomarkers is promising to improve clinical benefit. With the accumulation of preclinical models and advances in computational approaches of drug response prediction, pharmacogenomics has made great success over the last 20 years and is increasingly used in the clinical practice of personalized cancer medicine. In this article, we first summarize FDA-approved pharmacogenomic biomarkers and large-scale pharmacogenomic studies of preclinical cancer models such as patient-derived cell lines, organoids, and xenografts. Furthermore, we comprehensively review the recent developments of computational methods in drug response prediction, covering network, machine learning, and deep learning technologies and strategies to evaluate immunotherapy response. In the end, we discuss challenges and propose possible solutions for further improvement.