Modular within and between score for drug response prediction in cancer cell lines

Abstract Predicting the sensitivity of tumors to specific anti-cancer treatments is a challenge of paramount importance for precision medicine. Machine learning(ML) algorithms can be trained on high-throughput screening data to develop models that are able to predict the response of cancer cell lines and patients to novel drugs or drug combinations. Deep learning (DL) refers to a distinct class of ML algorithms that have achieved top-level performance in a variety of fields, including drug discovery. These types of models have unique characteristics that may make them more suitable for the complex task of modeling drug response based on both biological and chemical data, but the application of DL to drug response prediction has been unexplored until very recently. The few studies that have been published have shown promising results, and the use of DL for drug response prediction is beginning to attract greater interest from researchers in the field. In this article, we critically review recently published studies that have employed DL methods to predict drug response in cancer cell lines. We also provide a brief description of DL and the main types of architectures that have been used in these studies. Additionally, we present a selection of publicly available drug screening data resources that can be used to develop drug response prediction models. Finally, we also address the limitations of these approaches and provide a discussion on possible paths for further improvement. Contact:[email protected]

Download Full-text

A novel heterogeneous network-based method for drug response prediction in cancer cell lines

Scientific Reports ◽

10.1038/s41598-018-21622-4 ◽

2018 ◽

Vol 8 (1) ◽

Cited By ~ 30

Author(s):

Fei Zhang ◽

Minghui Wang ◽

Jianing Xi ◽

Jianghong Yang ◽

Ao Li

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Heterogeneous Network ◽

Drug Response ◽

Response Prediction ◽

Cancer Cell Lines

Download Full-text

A novel approach for drug response prediction in cancer cell lines via network representation learning

Bioinformatics ◽

10.1093/bioinformatics/bty848 ◽

2018 ◽

Vol 35 (9) ◽

pp. 1527-1535 ◽

Cited By ~ 17

Author(s):

Jianghong Yang ◽

Ao Li ◽

Yongqiang Li ◽

Xiangqian Guo ◽

Minghui Wang

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Response ◽

Response Prediction ◽

Representation Learning ◽

Cancer Cell Lines ◽

Network Representation ◽

Novel Approach

Download Full-text

Cancer cell lines as patient avatars for drug response prediction

Nature Genetics ◽

10.1038/s41588-018-0245-2 ◽

2018 ◽

Vol 50 (10) ◽

pp. 1350-1351 ◽

Cited By ~ 3

Author(s):

Ultan McDermott

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Response ◽

Response Prediction ◽

Cancer Cell Lines

Download Full-text

kESVR: An Ensemble Model for Drug Response Prediction in Precision Medicine Using Cancer Cell Lines Gene Expression

Genes ◽

10.3390/genes12060844 ◽

2021 ◽

Vol 12 (6) ◽

pp. 844

Author(s):

Abhishek Majumdar ◽

Yueze Liu ◽

Yaoqin Lu ◽

Shaofeng Wu ◽

Lijun Cheng

Keyword(s):

Gene Expression ◽

Support Vector Regression ◽

Cell Line ◽

Cell Lines ◽

Cancer Cell ◽

Drug Response ◽

Prediction Models ◽

Response Prediction ◽

Cancer Cell Lines ◽

Support Vector

Background: Cancer cell lines are frequently used in research as in-vitro tumor models. Genomic data and large-scale drug screening have accelerated the right drug selection for cancer patients. Accuracy in drug response prediction is crucial for success. Due to data-type diversity and big data volume, few methods can integrative and efficiently find the principal low-dimensional manifold of the high-dimensional cancer multi-omics data to predict drug response in precision medicine. Method: A novelty k-means Ensemble Support Vector Regression (kESVR) is developed to predict each drug response values for single patient based on cell-line gene expression data. The kESVR is a blend of supervised and unsupervised learning methods and is entirely data driven. It utilizes embedded clustering (Principal Component Analysis and k-means clustering) and local regression (Support Vector Regression) to predict drug response and obtain the global pattern while overcoming missing data and outliers’ noise. Results: We compared the efficiency and accuracy of kESVR to 4 standard machine learning regression models: (1) simple linear regression, (2) support vector regression (3) random forest (quantile regression forest) and (4) back propagation neural network. Our results, which based on drug response across 610 cancer cells from Cancer Cell Line Encyclopedia (CCLE) and Cancer Therapeutics Response Portal (CTRP v2), proved to have the highest accuracy (smallest mean squared error (MSE) measure). We next compared kESVR with existing 17 drug response prediction models based a varied range of methods such as regression, Bayesian inference, matrix factorization and deep learning. After ranking the 18 models based on their accuracy of prediction, kESVR ranks first (best performing) in majority (74%) of the time. As for the remaining (26%) cases, kESVR still ranked in the top five performing models. Conclusion: In this paper we introduce a novel model (kESVR) for drug response prediction using high dimensional cell-line gene expression data. This model outperforms current existing prediction models in terms of prediction accuracy and speed and overcomes overfitting. This can be used in future to develop a robust drug response prediction system for cancer patients using the cancer cell-lines guidance and multi-omics data.

Download Full-text

Network Propagation Reveals Novel Features Predicting Drug Response of Cancer Cell Lines

Current Bioinformatics ◽

10.2174/1574893611666160125222144 ◽

2016 ◽

Vol 11 (2) ◽

pp. 203-210 ◽

Cited By ~ 3

Author(s):

Jiguang Wang ◽

Judith Kribelbauer ◽

Raul Rabadan

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Response ◽

Cancer Cell Lines ◽

Network Propagation

Download Full-text

Saudi anti-human cancer plants database (SACPD): A collection of plants with anti-human cancer activities

Oncology Reviews ◽

10.4081/oncol.2018.349 ◽

2018 ◽

Cited By ~ 1

Author(s):

Ateeq Ahmed Al-Zahrani

Keyword(s):

Saudi Arabia ◽

Cell Lines ◽

Anticancer Drugs ◽

Plant Species ◽

Cancer Cell ◽

Human Cancer ◽

Cancer Cell Lines ◽

Anticancer Activities ◽

Excellent Starting Point ◽

Starting Point

Several anticancer drugs have been developed from natural products such as plants. Successful experiments in inhibiting the growth of human cancer cell lines using Saudi plants were published over the last three decades. Up to date, there is no Saudi anticancer plants database as a comprehensive source for the interesting data generated from these experiments. Therefore, there was a need for creating a database to collect, organize, search and retrieve such data. As a result, the current paper describes the generation of the Saudi anti-human cancer plants database (SACPD). The database contains most of the reported information about the naturally growing Saudi anticancer plants. SACPD comprises the scientific and local names of 91 plant species that grow naturally in Saudi Arabia. These species belong to 38 different taxonomic families. In Addition, 18 species that represent16 family of medicinal plants and are intensively sold in the local markets in Saudi Arabia were added to the database. The website provides interesting details, including plant part containing the anticancer bioactive compounds, plants locations and cancer/cell type against which they exhibit their anticancer activity. Our survey revealed that breast, liver and leukemia were the most studied cancer cell lines in Saudi Arabia with percentages of 27%, 19% and 15%, respectively. The current SACPD represents a nucleus around which more development efforts can expand to accommodate all future submissions about new Saudi plant species with anticancer activities. SACPD will provide an excellent starting point for researchers and pharmaceutical companies who are interested in developing new anticancer drugs. SACPD is available online at https://teeqrani1.wixsite.com/sapd

Download Full-text

Nonlinear mixed-effects models for modeling in vitro drug response data to determine problematic cancer cell lines

Scientific Reports ◽

10.1038/s41598-019-50936-0 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 1

Author(s):

Farnoosh Abbas-Aghababazadeh ◽

Pengcheng Lu ◽

Brooke L. Fridley

Keyword(s):

Cell Lines ◽

Cancer Cell ◽

Drug Response ◽

Functional Form ◽

Cancer Cell Lines ◽

Mixed Effects ◽

Nonlinear Mixed Effects ◽

Nonlinear Mixed Effects Models ◽

Modeling Framework ◽

Response Data

Abstract Cancer cell lines (CCLs) have been widely used to study of cancer. Recent studies have called into question the reliability of data collected on CCLs. Hence, we set out to determine CCLs that tend to be overly sensitive or resistant to a majority of drugs utilizing a nonlinear mixed-effects (NLME) modeling framework. Using drug response data collected in the Cancer Cell Line Encyclopedia (CCLE) and the Genomics of Drug Sensitivity in Cancer (GDSC), we determined the optimal functional form for each drug. Then, a NLME model was fit to the drug response data, with the estimated random effects used to determine sensitive or resistant CCLs. Out of the roughly 500 CCLs studies from the CCLE, we found 17 cell lines to be overly sensitive or resistant to the studied drugs. In the GDSC, we found 15 out of the 990 CCLs to be excessively sensitive or resistant. These results can inform researchers in the selection of CCLs to include in drug studies. Additionally, this study illustrates the need for assessing the dose-response functional form and the use of NLME models to achieve more stable estimates of drug response parameters.

Download Full-text