Abstract Accurate and robust prediction of patient-specific responses to a new compound is critical to personalized drug discovery and development. However, patient data are often too scarce to train a generalized machine learning model. Although many methods have been developed to utilize cell-line screens for predicting clinical responses, their performances are unreliable owing to data heterogeneity and distribution shift. Here we have developed a novel context-aware deconfounding autoencoder (CODE-AE) that can extract intrinsic biological signals masked by context-specific patterns and confounding factors. Extensive comparative studies demonstrated that CODE-AE effectively alleviated the out-of-distribution problem for the model generalization and significantly improved accuracy and robustness over state-of-the-art methods in predicting patient-specific clinical drug responses purely from cell-line compound screens. Using CODE-AE, we screened 59 drugs for 9,808 patients with cancer. Our results are consistent with existing clinical observations, suggesting the potential of CODE-AE in developing personalized therapies and drug response biomarkers. 

/pdf/a-context-aware-deconfounding-autoencoder-for-robust-2mzidhyj.pdf

A context-aware deconfounding autoencoder for robust prediction of personalized clinical drug response from cell-line compound screening

Data discrepancy between preclinical and clinical datasets poses a major challenge for accurate drug response prediction based on gene expression data. Different methods of transfer learning have been proposed to address such data discrepancy in drug response prediction for different cancers. These methods generally use cell lines as source domains, and patients, patient-derived xenografts or other cell lines as target domains; however, it is assumed that the methods have access to the target domain during training or fine-tuning, and they can only take labelled source domains as input. The former is a strong assumption that is not satisfied during deployment of these models in the clinic, whereas the latter means these methods rely on labelled source domains that are of limited size. To avoid these assumptions, we formulate drug response prediction in cancer as an out-of-distribution generalization problem, which does not assume that the target domain is accessible during training. Moreover, to exploit unlabelled source domain data—which tends to be much more plentiful than labelled data—we adopt a semi-supervised approach. We propose Velodrome, a semi-supervised method of out-of-distribution generalization that takes labelled and unlabelled data from different resources as input and makes generalizable predictions. Velodrome achieves this goal by introducing an objective function that combines a supervised loss for accurate prediction, an alignment loss for generalization and a consistency loss to incorporate unlabelled samples. Our experimental results demonstrate that Velodrome outperforms state-of-the-art pharmacogenomics and transfer learning baselines on cell lines, patient-derived xenografts and patients. Finally, we showed that Velodrome models generalize to different tissue types that were well-represented, under-represented or completely absent in the training data. Overall, our results suggest that Velodrome may guide precision oncology more accurately. Providing patient specific predictions for drug responses is challenging as preclinical data across a large population is hard to collect. Sharifi-Noghabi and colleagues present a semi-supervised method to predict drug response from limited data that can generalize successfully to different tissue types.

Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction

Cancer claims millions of lives yearly worldwide. While many therapies have been made available in recent years, by in large cancer remains unsolved. Exploiting computational predictive models to study and treat cancer holds great promise in improving drug development and personalized design of treatment plans, ultimately suppressing tumors, alleviating suffering, and prolonging lives of patients. A wave of recent papers demonstrates promising results in predicting cancer response to drug treatments while utilizing deep learning methods. These papers investigate diverse data representations, neural network architectures, learning methodologies, and evaluations schemes. However, deciphering promising predominant and emerging trends is difficult due to the variety of explored methods and lack of standardized framework for comparing drug response prediction models. To obtain a comprehensive landscape of deep learning methods, we conducted an extensive search and analysis of deep learning models that predict the response to single drug treatments. A total of 61 deep learning-based models have been curated, and summary plots were generated. Based on the analysis, observable patterns and prevalence of methods have been revealed. This review allows to better understand the current state of the field and identify major challenges and promising solution paths.

https://www.frontiersin.org/articles/10.3389/fmed.2023.1086097/pdf

Deep learning methods for drug response prediction in cancer: Predominant and emerging trends

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.

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

Machine learning algorithms have become ubiquitous in a number of applications (e.g. image classification). However, due to the insufficient measurement of traditional metrics (e.g. the coarse-grained Accuracy of each classifier), substantial gaps are usually observed between the real-world performance of these algorithms and their scores in standardized evaluations. In this paper, inspired by the psychometric theories from human measurement, we propose a task-agnostic evaluation framework Camilla, where a multi-dimensional diagnostic metric Ability is defined for collaboratively measuring the multifaceted strength of each machine learning algorithm. Specifically, given the response logs from different algorithms to data samples, we leverage cognitive diagnosis assumptions and neural networks to learn the complex interactions among algorithms, samples and the skills (explicitly or implicitly pre-defined) of each sample. In this way, both the abilities of each algorithm on multiple skills and some of the sample factors (e.g. sample difficulty) can be simultaneously quantified. We conduct extensive experiments with hundreds of machine learning algorithms on four public datasets, and our experimental results demonstrate that Camilla not only can capture the pros and cons of each algorithm more precisely, but also outperforms state-of-the-art baselines on the metric reliability, rank consistency and rank stability.

Multi-Dimensional Ability Diagnosis for Machine Learning Algorithms

Data discrepancy between preclinical and clinical datasets poses a major challenge for accurate drug response prediction based on gene expression data. Different methods of transfer learning have been proposed to address this data discrepancy. These methods generally use cell lines as source domains and patients, patient-derived xenografts, or other cell lines as target domains. However, they assume that they have access to the target domain during training or fine-tuning and they can only take labeled source domains as input. The former is a strong assumption that is not satisfied during deployment of these models in the clinic. The latter means these methods rely on labeled source domains which are of limited size. To avoid these assumptions, we formulate drug response prediction as an out-of-distribution generalization problem which does not assume that the target domain is accessible during training. Moreover, to exploit unlabeled source domain data, which tends to be much more plentiful than labeled data, we adopt a semi-supervised approach. We propose Velodrome, a semi-supervised method of out-of-distribution generalization that takes labeled and unlabeled data from different resources as input and makes generalizable predictions. Velodrome achieves this goal by introducing an objective function that combines a supervised loss for accurate prediction, an alignment loss for generalization, and a consistency loss to incorporate unlabeled samples. Our experimental results demonstrate that Velodrome outperforms state-of-the-art pharmacogenomics and transfer learning baselines on cell lines, patient-derived xenografts, and patients. Finally, we showed that Velodrome models generalize to different tissue types that were well-represented, under-represented, or completely absent in the training data. Overall, our results suggest that Velodrome may guide precision oncology more accurately.

/pdf/velodrome-out-of-distribution-generalization-from-labeled-3jpmsyx2ra.pdf

Parsa Alamzadeh Harjandi

Papers

Velodrome: Out-of-Distribution Generalization from Labeled and Unlabeled Gene Expression Data for Drug Response Prediction

Out-of-distribution generalization from labelled and unlabelled gene expression data for drug response prediction