scholarly journals Predicting drug sensitivity of cancer cells based on DNA methylation levels

2020 ◽  
Author(s):  
Sofia P. Miranda ◽  
Fernanda A. Baião ◽  
Paula M. Maçaira ◽  
Julia L. Fleck ◽  
Stephen R. Piccolo
Keyword(s):  
Dna Methylation ◽  
Drug Development ◽  
Cell Line ◽  
Cell Lines ◽  
Drug Sensitivity ◽  
Machine Learning Algorithms ◽  
The Cancer Genome Atlas ◽  
Molecular Features ◽  
Regression Algorithms ◽  
Treatment Responses

AbstractCancer cell lines, which are cell cultures developed from tumor samples, represent one of the least expensive and most studied preclinical models for drug development. Accurately predicting drug response for a given cell line based on molecular features may help to optimize drug-development pipelines and explain mechanisms behind treatment responses. In this study, we focus on DNA methylation profiles as one type of molecular feature that is known to drive tumorigenesis and modulate treatment responses. Using genome-wide, DNA methylation profiles from 987 cell lines from the Genomics of Drug Sensitivity in Cancer database, we applied machine-learning algorithms to evaluate the potential to predict cytotoxic responses for eight anti-cancer drugs. We compared the performance of five classification algorithms and four regression algorithms that use diverse methodologies, including tree-, probability-, kernel-, ensemble-, and distance-based approaches. For both types of algorithm, we artificially subsampled the data to varying degrees, aiming to understand whether training models based on relatively extreme outcomes would yield improved performance. We also performed an information-gain analysis to examine which genes were most predictive of drug responses. Finally, we used tumor data from The Cancer Genome Atlas to evaluate the feasibility of predicting clinical responses in humans based on models derived from cell lines. When using classification or regression algorithms to predict discrete or continuous responses, respectively, we consistently observed excellent predictive performance when the training and test sets both consisted of cell-line data. However, classification models derived from cell-line data failed to generalize effectively for tumors.

scholarly journals Predicting drug sensitivity of cancer cells based on DNA methylation levels

PLoS ONE ◽  
2021 ◽  
Vol 16 (9) ◽  
pp. e0238757
Author(s):  
Sofia P. Miranda ◽  
Fernanda A. Baião ◽  
Julia L. Fleck ◽  
Stephen R. Piccolo
Keyword(s):  
Dna Methylation ◽  
Drug Development ◽  
Cell Line ◽  
Cell Lines ◽  
Drug Response ◽  
Drug Sensitivity ◽  
Classification Algorithms ◽  
Low Grade ◽  
Regression Algorithms ◽  
Treatment Responses

Cancer cell lines, which are cell cultures derived from tumor samples, represent one of the least expensive and most studied preclinical models for drug development. Accurately predicting drug responses for a given cell line based on molecular features may help to optimize drug-development pipelines and explain mechanisms behind treatment responses. In this study, we focus on DNA methylation profiles as one type of molecular feature that is known to drive tumorigenesis and modulate treatment responses. Using genome-wide, DNA methylation profiles from 987 cell lines in the Genomics of Drug Sensitivity in Cancer database, we used machine-learning algorithms to evaluate the potential to predict cytotoxic responses for eight anti-cancer drugs. We compared the performance of five classification algorithms and four regression algorithms representing diverse methodologies, including tree-, probability-, kernel-, ensemble-, and distance-based approaches. We artificially subsampled the data to varying degrees, aiming to understand whether training based on relatively extreme outcomes would yield improved performance. When using classification or regression algorithms to predict discrete or continuous responses, respectively, we consistently observed excellent predictive performance when the training and test sets consisted of cell-line data. Classification algorithms performed best when we trained the models using cell lines with relatively extreme drug-response values, attaining area-under-the-receiver-operating-characteristic-curve values as high as 0.97. The regression algorithms performed best when we trained the models using the full range of drug-response values, although this depended on the performance metrics we used. Finally, we used patient data from The Cancer Genome Atlas to evaluate the feasibility of classifying clinical responses for human tumors based on models derived from cell lines. Generally, the algorithms were unable to identify patterns that predicted patient responses reliably; however, predictions by the Random Forests algorithm were significantly correlated with Temozolomide responses for low-grade gliomas.

scholarly journals Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Krzysztof Koras ◽  
Ewa Kizling ◽  
Dilafruz Juraeva ◽  
Eike Staub ◽  
Ewa Szczurek
Keyword(s):  
Neural Network ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Recommender System ◽  
Computational Models ◽  
Drug Sensitivity ◽  
Kinase Inhibitor ◽  
Cancer Cell Lines ◽  
Molecular Features

AbstractComputational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Importantly, multi-task models require a tailored approach to model interpretability. In this work, we develop DEERS, a neural network recommender system for kinase inhibitor sensitivity prediction. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel interpretability approach, which in addition to the set of modeled features considers also the genes and processes outside of this set. Our approach outperforms simpler matrix factorization models, achieving R $$=$$ =  0.82 correlation between true and predicted response for the unseen cell lines. The interpretability analysis identifies 67 biological processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib.

scholarly journals Association of expression of epigenetic molecular factors with DNA methylation and sensitivity to chemotherapeutic agents in cancer cell lines

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Suleyman Vural ◽  
Alida Palmisano ◽  
William C. Reinhold ◽  
Yves Pommier ◽  
Beverly A. Teicher ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Cell Line ◽  
Cell Lines ◽  
Cancer Cell ◽  
Antitumor Agents ◽  
Cancer Cell Lines ◽  
Chemotherapeutic Agents ◽  
Epigenetic Factors ◽  
Expression Of Genes ◽  
Genes Encoding

Abstract Background Altered DNA methylation patterns play important roles in cancer development and progression. We examined whether expression levels of genes directly or indirectly involved in DNA methylation and demethylation may be associated with response of cancer cell lines to chemotherapy treatment with a variety of antitumor agents. Results We analyzed 72 genes encoding epigenetic factors directly or indirectly involved in DNA methylation and demethylation processes. We examined association of their pretreatment expression levels with methylation beta-values of individual DNA methylation probes, DNA methylation averaged within gene regions, and average epigenome-wide methylation levels. We analyzed data from 645 cancer cell lines and 23 cancer types from the Cancer Cell Line Encyclopedia and Genomics of Drug Sensitivity in Cancer datasets. We observed numerous correlations between expression of genes encoding epigenetic factors and response to chemotherapeutic agents. Expression of genes encoding a variety of epigenetic factors, including KDM2B, DNMT1, EHMT2, SETDB1, EZH2, APOBEC3G, and other genes, was correlated with response to multiple agents. DNA methylation of numerous target probes and gene regions was associated with expression of multiple genes encoding epigenetic factors, underscoring complex regulation of epigenome methylation by multiple intersecting molecular pathways. The genes whose expression was associated with methylation of multiple epigenome targets encode DNA methyltransferases, TET DNA methylcytosine dioxygenases, the methylated DNA-binding protein ZBTB38, KDM2B, SETDB1, and other molecular factors which are involved in diverse epigenetic processes affecting DNA methylation. While baseline DNA methylation of numerous epigenome targets was correlated with cell line response to antitumor agents, the complex relationships between the overlapping effects of each epigenetic factor on methylation of specific targets and the importance of such influences in tumor response to individual agents require further investigation. Conclusions Expression of multiple genes encoding epigenetic factors is associated with drug response and with DNA methylation of numerous epigenome targets that may affect response to therapeutic agents. Our findings suggest complex and interconnected pathways regulating DNA methylation in the epigenome, which may both directly and indirectly affect response to chemotherapy.

scholarly journals Predicting tumor response to drugs based on gene-expression biomarkers of sensitivity learned from cancer cell lines

BMC Genomics ◽  
2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Yuanyuan Li ◽  
David M. Umbach ◽  
Juno M. Krahn ◽  
Igor Shats ◽  
Xiaoling Li ◽  
...  
Keyword(s):  
Gene Expression ◽  
Cell Lines ◽  
Cancer Cell ◽  
Predictive Models ◽  
Drug Sensitivity ◽  
Human Cancer ◽  
Cancer Cell Lines ◽  
The Cancer Genome Atlas ◽  
Differential Sensitivity ◽  
Tumor Type

Abstract Background Human cancer cell line profiling and drug sensitivity studies provide valuable information about the therapeutic potential of drugs and their possible mechanisms of action. The goal of those studies is to translate the findings from in vitro studies of cancer cell lines into in vivo therapeutic relevance and, eventually, patients’ care. Tremendous progress has been made. Results In this work, we built predictive models for 453 drugs using data on gene expression and drug sensitivity (IC50) from cancer cell lines. We identified many known drug-gene interactions and uncovered several potentially novel drug-gene associations. Importantly, we further applied these predictive models to ~ 17,000 bulk RNA-seq samples from The Cancer Genome Atlas (TCGA) and the Genotype-Tissue Expression (GTEx) database to predict drug sensitivity for both normal and tumor tissues. We created a web site for users to visualize and download our predicted data (https://manticore.niehs.nih.gov/cancerRxTissue). Using trametinib as an example, we showed that our approach can faithfully recapitulate the known tumor specificity of the drug. Conclusions We demonstrated that our approach can predict drugs that 1) are tumor-type specific; 2) elicit higher sensitivity from tumor compared to corresponding normal tissue; 3) elicit differential sensitivity across breast cancer subtypes. If validated, our prediction could have relevance for preclinical drug testing and in phase I clinical design.

scholarly journals Identification of synthetic chemosensitivity genes paired with BRAF for BRAF/MAPK inhibitors

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Kye Hwa Lee ◽  
Jinmin Goh ◽  
Yi-Jun Kim ◽  
Kwangsoo Kim
Keyword(s):  
Cell Lines ◽  
Drug Sensitivity ◽  
Synthetic Lethality ◽  
Synergistic Effects ◽  
Personalised Medicine ◽  
The Cancer Genome Atlas ◽  
Gene Pairs ◽  
Tissue Interactions ◽  
Cancer Genome Atlas ◽  
Mapk Inhibitors

AbstractMolecular-targeted approaches are important for personalised cancer treatment, which requires knowledge regarding drug target specificity. Here, we used the synthetic lethality concept to identify candidate gene pairs with synergistic effects on drug responses. A synergistic chemo-sensitivity response was identified if a drug had a significantly lower half-maximal inhibitory concentration (IC50) in cell lines with a pair of mutated genes compared with those in other cell lines (wild-type or one mutated gene). Among significantly damaging mutations in the Genomics of Drug Sensitivity in Cancer database, we found 580 candidate synergistic chemo-sensitivity interaction sets for 456 genes and 54 commercial drugs. Clustering analyses according to drug/gene and drug/tissue interactions showed that BRAF/MAPK inhibitors clustered together; 11 partner genes for BRAF were identified. The combined effects of these partners on IC50 values were significant for both drug-specific and drug-combined comparisons. Survival analysis using The Cancer Genome Atlas data showed that patients who had mutated gene pairs in synergistic interaction sets had longer overall survival compared with that in patients with other mutation profiles. Overall, this analysis demonstrated that synergistic drug-responsive gene pairs could be successfully used as predictive markers of drug sensitivity and patient survival, offering new targets for personalised medicine.

Connecting gene expression subtypes of colorectal cancer (CRC) with cell lines and drug resistance.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. e14544-e14544
Author(s):  
Eva Budinska ◽  
Jenny Wilding ◽  
Vlad Calin Popovici ◽  
Edoardo Missiaglia ◽  
Arnaud Roth ◽  
...  
Keyword(s):  
Gene Expression ◽  
Cell Line ◽  
Clinical Significance ◽  
Cell Lines ◽  
Drug Response ◽  
Drug Sensitivity ◽  
Expression Profiles ◽  
Enrichment Analysis ◽  
Gene Set Enrichment Analysis

e14544 Background: We identified CRC gene expression subtypes (ASCO 2012, #3511), which associate with established parameters of outcome as well as relevant biological motifs. We now substantiate their biological and potentially clinical significance by linking them with cell line data and drug sensitivity, primarily attempting to identify models for the poor prognosis subtypes Mesenchymal and CIMP-H like (characterized by EMT/stroma and immune-associated gene modules, respectively). Methods: We analyzed gene expression profiles of 35 publicly available cell lines with sensitivity data for 82 drug compounds, and our 94 cell lines with data on sensitivity for 7 compounds and colony morphology. As in vitro, stromal and immune-associated genes loose their relevance, we trained a new classifier based on genes expressed in both systems, which identifies the subtypes in both tissue and cell cultures. Cell line subtypes were validated by comparing their enrichment for molecular markers with that of our CRC subtypes. Drug sensitivity was assessed by linking original subtypes with 92 drug response signatures (MsigDB) via gene set enrichment analysis, and by screening drug sensitivity of cell line panels against our subtypes (Kruskal-Wallis test). Results: Of the cell lines 70% could be assigned to a subtype with a probability as high as 0.95. The cell line subtypes were significantly associated with their KRAS, BRAF and MSI status and corresponded to our CRC subtypes. Interestingly, the cell lines which in matrigel created a network of undifferentiated cells were assigned to the Mesenchymal subtype. Drug response studies revealed potential sensitivity of subtypes to multiple compounds, in addition to what could be predicted based on their mutational profile (e.g. sensitivity of the CIMP-H subtype to Dasatinib, p<0.01). Conclusions: Our data support the biological and potentially clinical significance of the CRC subtypes in their association with cell line models, including results of drug sensitivity analysis. Our subtypes might not only have prognostic value but might also be predictive for response to drugs. Subtyping cell lines further substantiates their significance as relevant model for functional studies.

scholarly journals Epigenetic Age Acceleration of Stomach Adenocarcinoma Associated With Tumor Stemness Features, Immunoactivation, and Favorable Prognosis

2021 ◽  
Vol 12 ◽  
Author(s):  
Chunhong Hong ◽  
Shaohua Yang ◽  
Qiaojin Wang ◽  
Shiqiang Zhang ◽  
Wenhui Wu ◽  
...  
Keyword(s):  
Dna Methylation ◽  
Correlation Analysis ◽  
Gene Expression Omnibus ◽  
The Cancer Genome Atlas ◽  
Chronological Age ◽  
Favorable Prognosis ◽  
Molecular Features ◽  
Epigenetic Age ◽  
Epigenetic Age Acceleration ◽  
Stomach Adenocarcinoma

Background: Abnormal DNA methylation (DNAm) age has been assumed to be an indicator for canceration and all-cause mortality. However, associations between DNAm age and molecular features of stomach adenocarcinoma (STAD), and its prognosis have not been systematically studied.Method: We calculated the DNAm age of 591 STAD samples and 115 normal stomach samples from The Cancer Genome Atlas (TCGA) and gene expression omnibus (GEO) database using the Horvath’s clock model. Meanwhile, we utilized survival analysis to evaluate the prognostic value of DNAm age and epigenetic age acceleration shift. In addition, we performed weighted gene co-expression network analysis (WGCNA) to identify DNAm age-associated gene modules and pathways. Finally, the association between DNAm age and molecular features was performed by correlation analysis.Results: DNA methylation age was significantly correlated with chronological age in normal gastric tissues (r = 0.85, p &lt; 0.0001), but it was not associated with chronological age in STAD samples (r = 0.060, p = 0.2369). Compared with tumor adjacent normal tissue, the DNAm age of STAD tissues was significantly decreased. Meanwhile, chronological age in STAD samples was higher than its DNAm age. Both DNAm age and epigenetic acceleration shift were associated with the prognosis of STAD patients. By using correlation analysis, we also found that DNAm age was associated with immunoactivation and stemness in STAD samples.Conclusion: In summary, epigenetic age acceleration of STAD was associated with tumor stemness, immunoactivation, and favorable prognosis.

scholarly journals Matching cell lines with cancer type and subtype of origin via mutational, epigenomic and transcriptomic patterns

2019 ◽  
Author(s):  
Marina Salvadores ◽  
Francisco Fuster-Tormo ◽  
Fran Supek
Keyword(s):  
Cell Line ◽  
Cell Lines ◽  
Experimental Work ◽  
Drug Sensitivity ◽  
Tissue Cell ◽  
Cancer Type ◽  
Tumor Type ◽  
Cell Type ◽  
Cancer Subtypes ◽  
The One

AbstractCell lines are commonly used as cancer models. Because the tissue and/or cell type of origin provide important context for understanding mechanisms of cancer, we systematically examined whether cell lines exhibit features matching the cancer type that supposedly originated them. To this end, we aligned the mRNA expression and DNA methylation data between ∼9,000 solid tumors and ∼600 cell lines to remove the global differences stemming from growth in cell culture. Next, we created classification models for cancer type and subtype using tumor data, and applied them to cell line data. Overall, the transcriptomic and epigenomic classifiers consistently identified 35 cell lines which better matched a different tissue or cell type than the one the cell line was originally annotated with; we recommend caution in using these cell lines in experimental work. Six cell lines were identified as originating from the skin, of which five were further corroborated by the presence of a UV-like mutational signature in their genome, strongly suggesting mislabelling. Overall, genomic evidence additionally supports that 22 (3.6% of all considered) cell lines may be mislabelled because we predict they originate from a different tissue/cell type. Finally, we cataloged 366 cell lines in which both transcriptomic and epigenomic profiles strongly resemble the tumor type of origin, designating them as ‘golden set’ cell lines. We suggest these cell lines are better suited for experimental work that depends on tissue identity and propose tentative assignments to cancer subtypes. Finally, we show that accounting for the uncertain tissue-of-origin labels can change the interpretation of drug sensitivity and CRISPR genetic screening data. In particular, in brain, lung and pancreatic cancer cell lines, many novel determinants of drug sensitivity or resistance emerged by focussing on the cell lines that are best matched to the cancer type of interest.

scholarly journals Epigenetic Modifier Mutations in the LL-100 Panel

Blood ◽  
2018 ◽  
Vol 132 (Supplement 1) ◽  
pp. 5271-5271
Author(s):  
Hilmar Quentmeier ◽  
Claudia Pommerenke ◽  
Hans G. Drexler
Keyword(s):  
Amino Acid ◽  
Drug Development ◽  
Cell Line ◽  
Cell Lines ◽  
Human Cell ◽  
Conflicts Of Interest ◽  
Human Cancer ◽  
Human Cell Line ◽  
Dominant Negative ◽  
Epigenetic Modifier

Abstract The NCI-60 human cell line panel, developed for use in drug development comprises sixty human cancer cell lines derived from nine different tissues. Only six cell lines of the NCI-60 were derived from blood cancers. Therefore, most forms and subtypes of leukemia and lymphoma are not represented in the NCI-60 panel. To respond to this apparent gap, we suggest the novel LL-100 panel, 100 leukemia and lymphoma cell lines representing the major leukemia/lymphoma entities, for basic research and drug development. Whole exome sequencing and RNA sequencing were performed to identify mutations in 100 cell lines. Here we list the 100 cell lines, ordered by subtype and show mutations in epigenetic modifier genes. We found cell lines with mutations in ASXL1, EZH2, IDH1, TET2 and in DNMT3A. Hitherto, cell line OCI-AML3 was the only human cell line described with a DNMT3A mutation. Twenty-two percent of patients with acute myeloid leukemia contain DNMT3A mutations and the median overall survival with DNMT3A mutations is shorter than without. Most DNMT3A mutations are heterozygous and alter amino acid R882, R882H being the most common DNMT3A mutation in AML. Exogenously mutant murine R878H (equivalent to human R882H) inhibits DNMT3A activity in a dominant negative manner. We describe here that the AML cell line SET-2 carries a heterozygous G to A transition at chr2_25234373 (hg38) which leads to the DNMT3A R882H amino acid substitution. Chip-based methylation analysis revealed that the described DNMT3A targets IRF8, KLF2, HOXA11 and HOXB2 are hypomethylated in cell lines OCI-AML3 (DNMT3A R882C) and in SET-2 (DNMT3A R882H). These data suggest that SET-2 is a novel model cell line for functional analysis of the DNMT3A R882 mutation and a first gain in knowledge through data mining the LL-100 panel. Disclosures No relevant conflicts of interest to declare.

scholarly journals A Non-Negative Matrix Tri-Factorization based Method for Predicting Antitumor Drug Sensitivity

2021 ◽  
Author(s):  
Sara Pidò ◽  
Carolina Testa ◽  
Pietro Pinoli
Keyword(s):  
Cell Line ◽  
Cell Lines ◽  
Drug Response ◽  
Missing Values ◽  
Drug Sensitivity ◽  
Factorization Method ◽  
Data Types ◽  
Drug Profile ◽  
The Matrix ◽  
Ic50 Values

AbstractLarge annotated cell line collections have been proven to enable the prediction of drug response in the preclinical setting. We present an enhancement of Non-Negative Matrix Tri-Factorization method, which allows the integration of different data types for the prediction of missing associations. To test our method we retrieved a dataset from CCLE, containing the connections among cell lines and drugs by means of their IC50 values. We performed two different kind of experiments: a) prediction of missing values in the matrix, b) prediction of the complete drug profile of a new cell line, demonstrating the validity of the method in both scenarios.

Sign in / Sign up

Export Citation Format

Share Document