Dataset Information

Methodological challenges in translational drug response modeling in cancer: A systematic analysis with FORESEE.

ABSTRACT: Translational models directly relating drug response specific processes that can be observed in vitro to their in vivo role in cancer patients constitute a crucial part of the development of personalized medication. Unfortunately, current studies often focus on the optimization of isolated model characteristics instead of examining the overall modeling workflow and the interplay of the individual model components. Moreover, they are often limited to specific data sets only. Therefore, they are often confined by the irreproducibility of the results and the non-transferability of the approaches into other contexts. In this study, we present a thorough investigation of translational models and their ability to predict the drug responses of cancer patients originating from diverse data sets using the R-package FORESEE. By systematically scanning the modeling space for optimal combinations of different model settings, we can determine models of extremely high predictivity and work out a few modeling guidelines that promote simplicity. Yet, we identify noise within the data, sample size effects, and drug unspecificity as factors that deteriorate the models' robustness. Moreover, we show that cell line models of high accuracy do not necessarily excel in predicting drug response processes in patients. We therefore hope to motivate future research to consider in vivo aspects more carefully to ultimately generate deeper insights into applicable precision medicine.

SUBMITTER: Schatzle LK

PROVIDER: S-EPMC7192505 | biostudies-literature | 2020 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Methodological challenges in translational drug response modeling in cancer: A systematic analysis with FORESEE.

Schätzle Lisa-Katrin LK Hadizadeh Esfahani Ali A Schuppert Andreas A

PLoS computational biology 20200420 4

Translational models directly relating drug response specific processes that can be observed in vitro to their in vivo role in cancer patients constitute a crucial part of the development of personalized medication. Unfortunately, current studies often focus on the optimization of isolated model characteristics instead of examining the overall modeling workflow and the interplay of the individual model components. Moreover, they are often limited to specific data sets only. Therefore, they are o ...[more]

PMID: 32310964

Similar Datasets

Project description:Gene Expression Profiling of Breast Cancer Patients with Brain Metastases Brain metastases confer the worst prognosis of breast cancer as no therapy exists that prevents or eliminates the cancer from spreading to the brain. We developed a new computational modeling method to derive specific downstream signaling pathways that reveal unknown target-disease connections and new mechanisms for specific cancer subtypes. The model enables us to reposition drugs based on available gene expression data of patients. We applied this model to repurpose known or shelved drugs for brain, lung, and bone metastases of breast cancer with the hypothesis that cancer subtypes have their own specific signaling mechanisms. To test the hypothesis, we addressed the specific CSBs for each metastasis that satisfy that (1) CSB proteins are activated by the maximal number of enriched signaling pathways specific to this metastasis, and (2) CSB proteins involve in the most differential expressed coding-genes specific to the specific breast cancer metastasis. The identified signaling networks for the three types of metastases contain 31, 15, and 18 proteins, respectively, and are used to reposition 15, 9, and 2 drug candidates for the brain, lung, and bone metastases of breast cancer. We performed in vitro and in vivo preclinical experiments as well as analysis on patient tumor specimens to evaluate the targets and repositioned drugs. Two known drugs, Sunitinib (FDA approved for renal cell carcinoma and imatinib-resistant gastrointestinal stromal tumor) and Dasatinib (FDA approved for chronic myelogenous leukemia (CML) after imatinib treatment and Philadelphia chromosome-positive acute lymphoblastic leukemia), were shown to prohibit the metastatic colonization in brain. The TMH-52 cohort includes 11 patients who were examined with brain metastasis at the time of breast cancer diagnosis. The other 41 patients were examined with other organ metastasis at the time of breast cancer diagnosis.

Project description:BackgroundThe availability and generation of large amounts of genomic data has led to the development of a new paradigm in cancer treatment emphasizing a precision approach at the molecular and genomic level. Statistical modeling techniques aimed at leveraging broad scale in vitro, in vivo, and clinical data for precision drug treatment has become an active area of research. As a rapidly developing discipline at the crossroads of medicine, computer science, and mathematics, techniques ranging from accepted to those on the cutting edge of artificial intelligence have been utilized. Given the diversity and complexity of these techniques a systematic understanding of fundamental modeling principles is essential to contextualize influential factors to better understand results and develop new approaches.MethodsUsing data available from the Genomics of Drug Sensitivity in Cancer (GDSC) and the NCI60 we explore principle components regression, linear and non-linear support vector regression, and artificial neural networks in combination with different implementations of correlation based feature selection (CBF) on the prediction of drug response for several cytotoxic chemotherapeutic agents.ResultsOur results indicate that the regression method and features used have marginal effects on Spearman correlation between the predicted and measured values as well as prediction error. Detailed analysis of these results reveal that the bulk relationship between tissue of origin and drug response is a major driving factor in model performance.ConclusionThese results display one of the challenges in building predictive models for drug response in pan-cancer models. Mainly, that bulk genotypic traits where the signal to noise ratio is high is the dominant behavior captured in these models. This suggests that improved techniques of feature selection that can discriminate individual cell response from histotype response will yield more successful pan-cancer models.

Project description:The utility of tumor-derived cell lines is dependent on their ability to recapitulate underlying genomic aberrations and primary tumor biology. Here, we sequenced the exomes of 25 bladder cancer (BCa) cell lines and compared mutations, copy number alterations (CNAs), gene expression and drug response to BCa patient profiles in The Cancer Genome Atlas (TCGA). We observed a mutation pattern associated with altered CpGs and APOBEC-family cytosine deaminases similar to mutation signatures derived from somatic alterations in muscle-invasive (MI) primary tumors, highlighting a major mechanism(s) contributing to cancer-associated alterations in the BCa cell line exomes. Non-silent sequence alterations were confirmed in 76 cancer-associated genes, including mutations that likely activate oncogenes TERT and PIK3CA, and alter chromatin-associated proteins (MLL3, ARID1A, CHD6 and KDM6A) and established BCa genes (TP53, RB1, CDKN2A and TSC1). We identified alterations in signaling pathways and proteins with related functions, including the PI3K/mTOR pathway, altered in 60% of lines; BRCA DNA repair, 44%; and SYNE1-SYNE2, 60%. Homozygous deletions of chromosome 9p21 are known to target the cell cycle regulators CDKN2A and CDKN2B. This loci was commonly lost in BCa cell lines and we show the deletions extended to the polyamine enzyme methylthioadenosine (MTA) phosphorylase (MTAP) in 36% of lines, transcription factor DMRTA1 (27%) and antiviral interferon epsilon (IFNE, 19%). Overall, the BCa cell line genomic aberrations were concordant with those found in BCa patient tumors. We used gene expression and copy number data to infer pathway activities for cell lines, then used the inferred pathway activities to build a predictive model of cisplatin response. When applied to platinum-treated patients gathered from TCGA, the model predicted treatment-specific response. Together, these data and analysis represent a valuable community resource to model basic tumor biology and to study the pharmacogenomics of BCa.

Dataset Information

Methodological challenges in translational drug response modeling in cancer: A systematic analysis with FORESEE.

Publications

Methodological challenges in translational drug response modeling in cancer: A systematic analysis with FORESEE.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure