BDKANN - Biological Domain Knowledge-based Artificial Neural Network for drug response prediction

Snow, Oliver; Noghabi, Hossein Sharifi; Lu, Jianying; Zolotareva, Olga; Lee, Mark; Ester, Martin

doi:10.1101/840553

Cited by 8 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data-rich nature of preclinical pharmacogenomics datasets has paved the way for the development of machine learning approaches to predict drug sensitivity in vitro and in vivo [25][26][27]. These computational approaches range from simple linear regression models [28,29] Lasso [30], and Elastic Net [31] to Random Forest [32], kernel-based models [33][34][35][36], highly non-linear models based on Deep Neural Networks [37][38][39][40][41][42][43][44], and most recently, reinforcement learning [45], few-shot learning [46], and multi-task learning [47]. These methods often take gene expression as input and predict the area above/under the dose-response curve (AAC/AUC) or half-maximal inhibitory concentration (IC50), the concentration of the drug that reduces the viability by 50%.…”

Section: Introductionmentioning

confidence: 99%

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models

Sharifi-Noghabi

Jahangiri

Смирнов

et al. 2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

The goal of precision oncology is to tailor treatment for patients individually using the genomic profile of their tumors. Pharmacogenomics datasets such as cancer cell lines are among the most valuable resources for drug sensitivity prediction, a crucial task of precision oncology. Machine learning methods have been employed to predict drug sensitivity based on the multiple omics data available for large panels of cancer cell lines. However, there are no comprehensive guidelines on how to properly train and validate such machine learning models for drug sensitivity prediction. In this paper, we introduce a set of guidelines for different aspects of training gene expression-based predictors using cell line datasets. These guidelines provide extensive analysis of the generalization of drug sensitivity predictors and challenge many current practices in the community including the choice of training dataset and measure of drug sensitivity. The application of these guidelines in future studies will enable the development of more robust preclinical biomarkers.

show abstract

Section: Introductionmentioning

confidence: 99%

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models

Sharifi-Noghabi

Jahangiri

Смирнов

et al. 2021

Briefings in Bioinformatics

View full text Add to dashboard Cite

show abstract

“…Another possible future direction is to incorporate domain-expert knowledge into the structure of the model. A recent study has shown that such a structure improves the drug response prediction performance on cell line datasets and, more importantly, provides an explainable model as well ( Snow et al , 2019 ).…”

Section: Resultsmentioning

confidence: 99%

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

et al. 2020

Self Cite

View full text Add to dashboard Cite

Motivation The goal of pharmacogenomics is to predict drug response in patients using their single- or multi-omics data. A major challenge is that clinical data (i.e. patients) with drug response outcome is very limited, creating a need for transfer learning to bridge the gap between large pre-clinical pharmacogenomics datasets (e.g. cancer cell lines), as a source domain, and clinical datasets as a target domain. Two major discrepancies exist between pre-clinical and clinical datasets: (i) in the input space, the gene expression data due to difference in the basic biology, and (ii) in the output space, the different measures of the drug response. Therefore, training a computational model on cell lines and testing it on patients violates the i.i.d assumption that train and test data are from the same distribution. Results We propose Adversarial Inductive Transfer Learning (AITL), a deep neural network method for addressing discrepancies in input and output space between the pre-clinical and clinical datasets. AITL takes gene expression of patients and cell lines as the input, employs adversarial domain adaptation and multi-task learning to address these discrepancies, and predicts the drug response as the output. To the best of our knowledge, AITL is the first adversarial inductive transfer learning method to address both input and output discrepancies. Experimental results indicate that AITL outperforms state-of-the-art pharmacogenomics and transfer learning baselines and may guide precision oncology more accurately. Availability and implementation https://github.com/hosseinshn/AITL. Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

“…Velodrome can also be extended to incorporate additional information about the drug, such as the chemical representation, to improve the performance (Jiang et al 2020). Finally, we did not discuss the explainability of the Velodrome model, but we note that the feature extractor of Velodrome can be replaced by a knowledge-based network (Snow et al 2020) to offer explainability and transparency (Yu et al 2018). A major limitation of our work is the output space discrepancy between cell lines, PDX samples, and patients, because on cell lines the drug response is measured based on the concentration of the drug but on PDX samples and patients the response is measured based on the change in the tumor volume after treatment.…”

Section: Discussionmentioning

confidence: 99%

“…Various methods of transfer learning have been proposed in the context of drug response prediction. These methods either address these discrepancies implicitly (Sharifi- Noghabi et al 2019;Snow et al 2020;Kuenzi et al 2020), or explicitly which means they assume that the model has access to the desired labeled or unlabeled target domain during training (Sharifi-Noghabi et al 2020;Mourragui et al 2019Mourragui et al , 2020Ma et al 2021;Zhu et al 2020;Warren et al 2020;Peres da Silva, Suphavilai, and Nagarajan 2021).…”

Section: Introductionmentioning

confidence: 99%

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

Sharifi-Noghabi

Harjandi

Zolotareva

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 this assumption, 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 and therefore, may guide precision oncology more accurately.

show abstract

BDKANN - Biological Domain Knowledge-based Artificial Neural Network for drug response prediction

Cited by 8 publications

References 33 publications

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models

Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics

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

Contact Info

Product

Resources

About