Profiling Of Cancer Cell Lines Research Articles

Comparison of multiple modalities for drug response prediction with learning curves using neural networks and XGBoost.

Anti-cancer drug response prediction is a central problem within stratified medicine. Transcriptomic profiles of cancer cell lines are typically used for drug response prediction, but we hypothesize that proteomics or phosphoproteomics might be more suitable as they give a more direct insight into cellular processes. However, there has not yet been a systematic comparison between all three of these datatypes using consistent evaluation criteria. Due to the limited number of cell lines with phosphoproteomics profiles we use learning curves, a plot of predictive performance as a function of dataset size, to compare the current performance and predict the future performance of the three omics datasets with more data. We use neural networks and XGBoost and compare them against a simple rule-based benchmark. We show that phosphoproteomics slightly outperforms RNA-seq and proteomics using the 38 cell lines with profiles of all three omics data types. Furthermore, using the 877 cell lines with proteomics and RNA-seq profiles, we show that RNA-seq slightly outperforms proteomics. With the learning curves we predict that the mean squared error using the phosphoproteomics dataset would decrease by if a dataset of the same size as the proteomics/transcriptomics was collected. For the cell lines with proteomics and RNA-seq profiles the learning curves reveal that for smaller dataset sizes neural networks outperform XGBoost and vice versa for larger datasets. Furthermore, the trajectory of the XGBoost curve suggests that it will improve faster than the neural networks as more data are collected. See https://github.com/Nik-BB/Learning-curves-for-DRP for the code used.

Genetic Profiling and Genome-Scale Dropout Screening to Identify Therapeutic Targets in Mouse Models of Malignant Peripheral Nerve Sheath Tumor.

Malignant Peripheral Nerve Sheath Tumors (MPNSTs) are derived from Schwann cells or their precursors. In patients with the tumor susceptibility syndrome neurofibromatosis type 1 (NF1), MPNSTs are the most common malignancy and the leading cause of death. These rare and aggressive soft-tissue sarcomas offer a stark future, with 5-year disease-free survival rates of 34-60%. Treatment options for individuals with MPNSTs are disappointingly limited, with disfiguring surgery being the foremost treatment option. Many once-promising therapies such as tipifarnib, an inhibitor of Ras signaling, have failed clinically. Likewise, phase II clinical trials with erlotinib, which targets the epidermal growth factor (EFGR), and sorafenib, which targets the vascular endothelial growth factor receptor (VEGF), platelet-derived growth factor receptor (PDGF), and Raf, in combination with standard chemotherapy, have also failed to produce a response in patients. In recent years, functional genomic screening methods combined with genetic profiling of cancer cell lines have proven useful for identifying essential cytoplasmic signaling pathways and the development of target-specific therapies. In the case of rare tumor types, a variation of this approach known as cross-species comparative oncogenomics is increasingly being used to identify novel therapeutic targets. In cross-species comparative oncogenomics, genetic profiling and functional genomics are performed in genetically engineered mouse (GEM) models and the results are then validated in the rare human specimens and cell lines that are available. This paper describes how to identify candidate driver gene mutations in human and mouse MPNST cells using whole exome sequencing (WES). We then describe how to perform genome-scale shRNA screens to identify and compare critical signaling pathways in mouse and human MPNST cells and identify druggable targets in these pathways. These methodologies provide an effective approach to identifying new therapeutic targets in a variety of human cancer types.

A performance evaluation of drug response prediction models for individual drugs.

Drug response prediction is important to establish personalized medicine for cancer therapy. Model construction for predicting drug response (i.e., cell viability half-maximal inhibitory concentration [IC50]) of an individual drug by inputting pharmacogenomics in disease models remains critical. Machine learning (ML) has been predominantly applied for prediction, despite the advent of deep learning (DL). Moreover, whether DL or traditional ML models are superior for predicting cell viability IC50s has to be established. Herein, we constructed ML and DL drug response prediction models for 24 individual drugs and compared the performance of the models by employing gene expression and mutation profiles of cancer cell lines as input. We observed no significant difference in drug response prediction performance between DL and ML models for 24 drugs [root mean squared error (RMSE) ranging from 0.284 to 3.563 for DL and from 0.274 to 2.697 for ML; R2 ranging from -7.405 to 0.331 for DL and from -8.113 to 0.470 for ML]. Among the 24 individual drugs, the ridge model of panobinostat exhibited the best performance (R2 0.470 and RMSE 0.623). Thus, we selected the ridge model of panobinostat for further application of explainable artificial intelligence (XAI). Using XAI, we further identified important genomic features for panobinostat response prediction in the ridge model, suggesting the genomic features of 22 genes. Based on our findings, results for an individual drug employing both DL and ML models were comparable. Our study confirms the applicability of drug response prediction models for individual drugs.

Passage number of cancer cell lines: Importance, intricacies, and way-forward.

Cancer cell lines play a crucial role as invaluable models in cancer research, facilitating the examination of cancer progression as well as the advancement of diagnostics and treatments. While they may not perfectly replicate the original tumor, they generally exhibit similar characteristics. Low-passage cancer cell lines are generally preferred due to their closer resemblance to the original tumor, as long-term culturing can alter the genetic and molecular profiles of a cell line thereby highlighting the importance of monitoring the passage number (PN). Variations in proliferation, migration, gene expression, and drug sensitivity can be linked to PN differences. PN can also influence DNA methylation levels, metabolic profiles, and the expression of genes/or proteins in cancer cell lines. When conducting research on cancer cell lines, it is crucial for researchers to carefully select the appropriate PN to maintain consistency and reliability of results. Moreover, to ensure dependability and replicability, scientists ought to actively track the growth, migration, and gene/or protein profiles of cancer cell lines at specific PNs. This approach enables the identification of the most suitable range of PNs for experiments, guaranteeing consistent and precise results. Additionally, such efforts serve to minimize disparities and uphold the integrity of research. In this review, we have laid out recommendations for laboratories to overcome these PN discrepancies when working with cancer cell lines.

The impact of violating the independence assumption in meta-analysis on biomarker discovery.

With rapid advancements in high-throughput sequencing technologies, massive amounts of "-omics" data are now available in almost every biomedical field. Due to variance in biological models and analytic methods, findings from clinical and biological studies are often not generalizable when tested in independent cohorts. Meta-analysis, a set of statistical tools to integrate independent studies addressing similar research questions, has been proposed to improve the accuracy and robustness of new biological insights. However, it is common practice among biomarker discovery studies using preclinical pharmacogenomic data to borrow molecular profiles of cancer cell lines from one study to another, creating dependence across studies. The impact of violating the independence assumption in meta-analyses is largely unknown. In this study, we review and compare different meta-analyses to estimate variations across studies along with biomarker discoveries using preclinical pharmacogenomics data. We further evaluate the performance of conventional meta-analysis where the dependence of the effects was ignored via simulation studies. Results show that, as the number of non-independent effects increased, relative mean squared error and lower coverage probability increased. Additionally, we also assess potential bias in the estimation of effects for established meta-analysis approaches when data are duplicated and the assumption of independence is violated. Using pharmacogenomics biomarker discovery, we find that treating dependent studies as independent can substantially increase the bias of meta-analyses. Importantly, we show that violating the independence assumption decreases the generalizability of the biomarker discovery process and increases false positive results, a key challenge in precision oncology.

Deep learning-based multi-drug synergy prediction model for individually tailored anti-cancer therapies.

While synergistic drug combinations are more effective at fighting tumors with complex pathophysiology, preference compensating mechanisms, and drug resistance, the identification of novel synergistic drug combinations, especially complex higher-order combinations, remains challenging due to the size of combination space. Even though certain computational methods have been used to identify synergistic drug combinations in lieu of traditional in vitro and in vivo screening tests, the majority of previously published work has focused on predicting synergistic drug pairs for specific types of cancer and paid little attention to the sophisticated high-order combinations. The main objective of this study is to develop a deep learning-based approach that integrated multi-omics data to predict novel synergistic multi-drug combinations (DeepMDS) in a given cell line. To develop this approach, we firstly created a dataset comprising of gene expression profiles of cancer cell lines, target information of anti-cancer drugs, and drug response against a large variety of cancer cell lines. Based on the principle of a fully connected feed forward Deep Neural Network, the proposed model was constructed using this dataset, which achieved a high performance with a Mean Square Error (MSE) of 2.50 and a Root Mean Squared Error (RMSE) of 1.58 in the regression task, and gave the best classification accuracy of 0.94, an area under the Receiver Operating Characteristic curve (AUC) of 0.97, a sensitivity of 0.95, and a specificity of 0.93. Furthermore, we utilized three breast cancer cell subtypes (MCF-7, MDA-MD-468 and MDA-MB-231) and one lung cancer cell line A549 to validate the predicted results of our model, showing that the predicted top-ranked multi-drug combinations had superior anti-cancer effects to other combinations, particularly those that were widely used in clinical treatment. Our model has the potential to increase the practicality of expanding the drug combinational space and to leverage its capacity to prioritize the most effective multi-drug combinational therapy for precision oncology applications.

Ceramide Kinase (CERK) Emerges as a Common Therapeutic Target for Triple Positive and Triple Negative Breast Cancer Cells.

Simple SummaryExisting chemotherapy treatments for breast cancer patients are high on toxicity. There are very limited options available for triple-positive breast cancer (TPBC) patients, and there have not been any major breakthrough for targeted therapy for triple-negative breast cancer (TNBC) patients. Therefore, there is a need to identify common therapeutic targets for breast cancer patients. In this manuscript, we compared the sphingolipid profiles of cancer cell lines representing TPBC and TNBC, and correlated these profiles with the proliferation and migration properties the of cell types. We then associated the sphingolipid profiles for each subtype specific cell line with transcriptional and translational expression of corresponding metabolizing enzymes. Our results suggested that ceramide kinase (CERK) that catalyzes the synthesis of ceramide-1-phosphates from ceramides is dysregulated in both cell types. We also showed that the targeting of CERK at transcriptional level by siRNA therapeutics or inhibiting the CERK activity by hydrogel-mediated delivery of chemical inhibitors can be an effective strategy to slow down the tumor progression. Therefore, CERK emerges as a potential therapeutic target that can be explored further for cancer therapy.Sphingolipids are key signaling biomolecules that play a distinct role in cell proliferation, migration, invasion, drug resistance, metastasis, and apoptosis. Triple-negative (ER−PR−HER2−) and triple-positive (ER+PR+HER2+) breast cancer (called TNBC and TPBC, respectively) subtypes reveal distinct phenotypic characteristics and responses to therapy. Here, we present the sphingolipid profiles of BT-474 and MDA-MB-231 breast cancer cell lines representing the TPBC and TNBC subtypes. We correlated the level of different classes of sphingolipids and the expression of their corresponding metabolizing enzymes with the cell proliferation and cell migration properties of BT-474 and MDA-MB-231 cells. Our results showed that each cell type exhibits a unique sphingolipid profile, and common enzymes such as ceramide kinase (CERK, responsible for the synthesis of ceramide-1-phosphates) are deregulated in these cell types. We showed that siRNA/small molecule-mediated inhibition of CERK can alleviate cell proliferation in BT-474 and MDA-MB-231 cells, and cell migration in MDA-MB-231 cells. We further demonstrated that nanoparticle-mediated delivery of CERK siRNA and hydrogel-mediated sustained delivery of CERK inhibitor to the tumor site can inhibit tumor progression in BT-474 and MDA-MB-231 tumor models. In summary, distinct sphingolipid profiles of TPBC and TNBC representing cell lines provide potential therapeutic targets such as CERK, and nanoparticle/hydrogel mediated pharmacological manipulations of such targets can be explored for future cancer therapeutics.

Abstract 1196: Elucidating compound mechanism of action and polypharmacology with a large-scale perturbational profile compendium

Abstract Traditional approaches to elucidate small molecule mechanism of action (MoA) are usually based on affinity binding assays. These often fail to detect lower affinity binding targets and secondary effectors that are usually highly tissue context-dependent. As such, these can vary dramatically across different cancer types. To address this challenge and facilitate more quantitative approaches to targeted cancer therapy, a more comprehensive picture of drug MoA, including poly-pharmacology and toxicity effects mediated by the full range of its high-affinity (primary), as well as its context-specific lower-affinity (secondary) and downstream effector (tertiary) targets. For this purpose, we generated transcriptional genome-wide RNA-Seq profiles of cancer cell lines, following compounds perturbation with FDA approved and late-stage experimental oncology drugs using a fully automated and highly efficient PLATE-Seq technology1. Compared to prior approaches, this provides (a) genome-wide readouts, rather than readouts limited to a small set of landmark genes, (b) in cell lines that were specifically selected as the highest-fidelity models for published human cancer cohorts, using the OncoMatch algorithm2, and (c) for a drug repertoire that is clinically relevant. In addition, to avoid confounding effects from drug stress/death response pathway activation—a common issue in previous studies—drugs were titrated at their maximum sub-lethal concentration (48-hr IC20) using 10-point dose response curves in each cell line. The ~20,000 molecular profiles generated by these assays were analyzed using the VIPER algorithm3 to reproducibly assess the effect of each drug on the activity of ~6,500 regulatory and signaling proteins compared to vehicle control. The resulting PanACEA (Pancancer Activity-based Compound Efficacy Analysis), a database comprising drug perturbation profiles for 23 different cancer cell lines and > 700 oncology drugs, representing the largest resources of functionally annotated, genome-wide perturbational profiles for clinically relevant drugs. Systematic analysis identified critical drug mechanism of action and drugs capable of reproducibly targeting undruggable proteins, such as MYC or KRAS. We also leveraged graph theory-based network approach to generate a conserved drug functional network and drug functional networks in different cancer contexts, which pinpoint critical novel poly-pharmacology effects. Citation Format: Lucas Zhongming Hu, Eugene Douglass, Ron Realubit, Charles Karan, Mariano Alvarez, Andrea Califano. Elucidating compound mechanism of action and polypharmacology with a large-scale perturbational profile compendium [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1196.

Predicting patient treatment response and resistance via single-cell transcriptomics of their tumors.

e20540 Background: Tailoring the best treatments to cancer patients is an important open challenge. Here, we build a precision oncology data science and software framework for PERsonalized single-Cell Expression-based Planning for Treatments In Oncology (PERCEPTION). Methods: Our approach capitalizes on recently published matched bulk and single-cell transcriptome profiles of large-scale cell-line drug screens to build treatment response models from patients’ single-cell (SC) tumor transcriptomics. Our approach is a two-step process: first, the prediction models are trained on large-scale bulk-expression profiles of cancer cell lines and then, in a second step, the models’ performance is further optimized by training on SC-expression profiles of cancer cell lines. Results: First, we show that PERCEPTION successfully predicts the response to monotherapy and combination treatments in screens performed in cancer and patient-tumor-derived primary cells based on SC-expression profiles. Second, it successfully stratifies responders to combination therapy based on the patients’ tumor’s SC-expression in two very recent multiple myeloma and breast cancer clinical trials. Thirdly, it captures the development of clinical resistance to five standard tyrosine kinase inhibitors using tumor SC-expression profiles obtained during treatment in a lung cancer patients’ cohort. Notably, PERCEPTION outperforms state-of-the-art bulk expression-based predictors in all three clinical cohorts. Conclusions: In sum, this study provides a first-of-its-kind conceptual and computational method that is predictive of response to therapy in patients, based on the clonal SC gene expression of their tumors.

Glycome Profiling of Cancer Cell Lines Cultivated in Physiological and Commercial Media.

A complex physiological culture medium (Plasmax) was introduced recently, composed of nutrients and metabolites at concentrations normally found in human plasma to mimic the in vivo environment for cell line cultivation. As glycosylation has been proved to be involved in cancer development, it is necessary to investigate the glycan expression changes in media with different nutrients. In this study, a breast cancer cell line, MDA-MB-231BR, and a brain cancer cell line, CRL-1620, were cultivated in Plasmax and commercial media to reveal cell line glycosylation discrepancies prompted by nutritional environments. Glycomics analyses of cell lines were performed using LC-MS/MS. The expressions of multiple fucosylated N-glycans, such as HexNAc4Hex3DeoxyHex1 and HexNAc5Hex3DeoxyHex1, derived from both cell lines exhibited a significant increase in Plasmax. Among the O-glycans, significant differences were also observed. Both cell lines cultivated in EMEM had the lowest amounts of O-glycans expressed. The original work described the development of Plasmax, which improves colony formation, and resulted in transcriptomic and metabolomic alterations of cancer cell lines, while our results indicate that Plasmax can significantly impact protein glycosylation. This study also provides information to guide the selection of media for in vitro cancer cell glycomics studies.

Identification of Pan-Cancer Biomarkers Based on the Gene Expression Profiles of Cancer Cell Lines.

There are many types of cancers. Although they share some hallmarks, such as proliferation and metastasis, they are still very different from many perspectives. They grow on different organ or tissues. Does each cancer have a unique gene expression pattern that makes it different from other cancer types? After the Cancer Genome Atlas (TCGA) project, there are more and more pan-cancer studies. Researchers want to get robust gene expression signature from pan-cancer patients. But there is large variance in cancer patients due to heterogeneity. To get robust results, the sample size will be too large to recruit. In this study, we tried another approach to get robust pan-cancer biomarkers by using the cell line data to reduce the variance. We applied several advanced computational methods to analyze the Cancer Cell Line Encyclopedia (CCLE) gene expression profiles which included 988 cell lines from 20 cancer types. Two feature selection methods, including Boruta, and max-relevance and min-redundancy methods, were applied to the cell line gene expression data one by one, generating a feature list. Such list was fed into incremental feature selection method, incorporating one classification algorithm, to extract biomarkers, construct optimal classifiers and decision rules. The optimal classifiers provided good performance, which can be useful tools to identify cell lines from different cancer types, whereas the biomarkers (e.g. NCKAP1, TNFRSF12A, LAMB2, FKBP9, PFN2, TOM1L1) and rules identified in this work may provide a meaningful and precise reference for differentiating multiple types of cancer and contribute to the personalized treatment of tumors.

Metabolism, HDACs, and HDAC Inhibitors: A Systems Biology Perspective.

Histone deacetylases (HDACs) are epigenetic enzymes that play a central role in gene regulation and are sensitive to the metabolic state of the cell. The cross talk between metabolism and histone acetylation impacts numerous biological processes including development and immune function. HDAC inhibitors are being explored for treating cancers, viral infections, inflammation, neurodegenerative diseases, and metabolic disorders. However, how HDAC inhibitors impact cellular metabolism and how metabolism influences their potency is unclear. Discussed herein are recent applications and future potential of systems biology methods such as high throughput drug screens, cancer cell line profiling, single cell sequencing, proteomics, metabolomics, and computational modeling to uncover the interplay between metabolism, HDACs, and HDAC inhibitors. The synthesis of new systems technologies can ultimately help identify epigenomic and metabolic biomarkers for patient stratification and the design of effective therapeutics.

GraphCDR: a graph neural network method with contrastive learning for cancer drug response prediction.

Predicting the response of a cancer cell line to a therapeutic drug is an important topic in modern oncology that can help personalized treatment for cancers. Although numerous machine learning methods have been developed for cancer drug response (CDR) prediction, integrating diverse information about cancer cell lines, drugs and their known responses still remains a great challenge. In this paper, we propose a graph neural network method with contrastive learning for CDR prediction. GraphCDR constructs a graph neural network based on multi-omics profiles of cancer cell lines, the chemical structure of drugs and known cancer cell line-drug responses for CDR prediction, while a contrastive learning task is presented as a regularizer within a multi-task learning paradigm to enhance the generalization ability. In the computational experiments, GraphCDR outperforms state-of-the-art methods under different experimental configurations, and the ablation study reveals the key components of GraphCDR: biological features, known cancer cell line-drug responses and contrastive learning are important for the high-accuracy CDR prediction. The experimental analyses imply the predictive power of GraphCDR and its potential value in guiding anti-cancer drug selection.

Drug Repositioning Based on the Reversal of Gene Expression Signatures Identifies TOP2A as a Therapeutic Target for Rectal Cancer.

Simple SummaryRectal cancer is the 8th most common cancer globally. Most patients with locally advanced rectal cancer receive neoadjuvant therapy based on 5-fluorouracil and radiotherapy showing variable responses. About 70–90% of patients present partial response, while 20% show treatment resistance. Repositioning drugs approved by regulatory agencies or drugs currently in clinical trials is a strategy to accelerate the development of drug-based cancer therapies. We compared rectal cancer gene expression signatures with reverse drug-induced gene-expression profiles of cancer cell lines to identify potential drugs for repositioning. Our analyses revealed that approved topoisomerase II inhibitors are candidate drugs for rectal cancer treatment. We also verified TOP2A copy number gains and increased expression in rectal tumors. These TOP2A alterations were independent predictive markers of topoisomerase inhibitor efficacy in colorectal cancer cells that closely represent rectal cancer signatures. Topoisomerase inhibitors are potentially helpful to treat rectal cancer patients with TOP2A imbalances.Rectal cancer is a common disease with high mortality rates and limited therapeutic options. Here we combined the gene expression signatures of rectal cancer patients with the reverse drug-induced gene-expression profiles to identify drug repositioning candidates for cancer therapy. Among the predicted repurposable drugs, topoisomerase II inhibitors (doxorubicin, teniposide, idarubicin, mitoxantrone, and epirubicin) presented a high potential to reverse rectal cancer gene expression signatures. We showed that these drugs effectively reduced the growth of colorectal cancer cell lines closely representing rectal cancer signatures. We also found a clear correlation between topoisomerase 2A (TOP2A) gene copy number or expression levels with the sensitivity to topoisomerase II inhibitors. Furthermore, CRISPR-Cas9 and shRNA screenings confirmed that loss-of-function of the TOP2A has the highest efficacy in reducing cellular proliferation. Finally, we observed significant TOP2A copy number gains and increased expression in independent cohorts of rectal cancer patients. These findings can be translated into clinical practice to evaluate TOP2A status for targeted and personalized therapies based on topoisomerase II inhibitors in rectal cancer patients.

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

Computational 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.

LncGSEA: a versatile tool to infer lncRNA associated pathways from large-scale cancer transcriptome sequencing data

BackgroundLong non-coding RNAs (lncRNAs) are a growing focus in cancer research. Deciphering pathways influenced by lncRNAs is important to understand their role in cancer. Although knock-down or overexpression of lncRNAs followed by gene expression profiling in cancer cell lines are established approaches to address this problem, these experimental data are not available for a majority of the annotated lncRNAs.ResultsAs a surrogate, we present lncGSEA, a convenient tool to predict the lncRNA associated pathways through Gene Set Enrichment Analysis of gene expression profiles from large-scale cancer patient samples. We demonstrate that lncGSEA is able to recapitulate lncRNA associated pathways supported by literature and experimental validations in multiple cancer types.ConclusionsLncGSEA allows researchers to infer lncRNA regulatory pathways directly from clinical samples in oncology. LncGSEA is written in R, and is freely accessible at https://github.com/ylab-hi/lncGSEA.

Converting tabular data into images for deep learning with convolutional neural networks

Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.

Assessing Various Control Samples for Microarray Gene Expression Profiling of Laryngeal Squamous Cell Carcinoma.

Selection of optimal control samples is crucial in expression profiling tumor samples. To address this issue, we performed microarray expression profiling of control samples routinely used in head and neck squamous cell carcinoma studies: human bronchial and tracheal epithelial cells, squamous cells obtained by laser uvulopalatoplasty and tumor surgical margins. We compared the results using multidimensional scaling and hierarchical clustering versus tumor samples and laryngeal squamous cell carcinoma cell lines. A general observation from our study is that the analyzed cohorts separated according to two dominant factors: “malignancy”, which separated controls from malignant samples and “cell culture-microenvironment” which reflected the differences between cultured and non-cultured samples. In conclusion, we advocate the use of cultured epithelial cells as controls for gene expression profiling of cancer cell lines. In contrast, comparisons of gene expression profiles of cancer cell lines versus surgical margin controls should be treated with caution, whereas fresh frozen surgical margins seem to be appropriate for gene expression profiling of tumor samples.

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

BackgroundHuman 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.ResultsIn 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.ConclusionsWe 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.

Multi‐modal meta‐analysis of cancer cell line omics profiles identifies ECHDC1 as a novel breast tumor suppressor

Molecular and functional profiling of cancer cell lines is subject to laboratory‐specific experimental practices and data analysis protocols. The current challenge therefore is how to make an integrated use of the omics profiles of cancer cell lines for reliable biological discoveries. Here, we carried out a systematic analysis of nine types of data modalities using meta‐analysis of 53 omics studies across 12 research laboratories for 2,018 cell lines. To account for a relatively low consistency observed for certain data modalities, we developed a robust data integration approach that identifies reproducible signals shared among multiple data modalities and studies. We demonstrated the power of the integrative analyses by identifying a novel driver gene, ECHDC1, with tumor suppressive role validated both in breast cancer cells and patient tumors. The multi‐modal meta‐analysis approach also identified synthetic lethal partners of cancer drivers, including a co‐dependency of PTEN deficient endometrial cancer cells on RNA helicases.