Clinical responses to cancer treatment are strongly influenced by the patient's genomic landscape, pushing modern therapeutics toward a more personalized approach (1). To this end, despite their inability to reflect many aspects of a drug's behavior in the human body, cancer cell lines have been the most widely used models to explore the molecular basis of drug activity. Indeed, since the NCI-60 project, several major screenings of unite genetic profiling and drug testing have been created to investigate how genomic portraits can shape cancer response to therapy. These efforts required the definition of integrated frameworks that, leveraging on high-throughput technologies and computational methods, addressed the identification of genomic factors of cancer vulnerability associated with drug sensitivity. The NCI-60 project (https://dtp.cancer.gov/discovery_development/nci-60/) has been the first extensive screening of a massive number of chemical compounds (>50,000) on a well-defined set of cancer cell lines (60 across nine different tumoral tissues) (2, 3). Building on the NCI-60 approach, several other projects investigated the interplay between genomic backgrounds and responses to drug treatment in cancer cell lines (Figure 1A). All cancer cell line screenings basically adopt two approaches. In the first strategy, the molecular profiles of untreated cells and their response to various compounds are investigated in parallel to assess or predict how the molecular portraits determine intrinsic cell sensitivity and resistance to drugs or potential drugs. In the second, cell lines are profiled both before and after treatment to assess how their expression profiles respond to perturbation by the various agents tested. In particular, the Cancer Cell Line Encyclopedia (CCLE, https://portals.broadinstitute.org/ccle) project fully characterized the molecular profiles of more than 1,000 untreated cancer cell lines along with their response to a panel of 24 Food and Drug Administration (FDA)-approved drugs (4–6). Similarly, the Genomics of Drug Sensitivity in Cancer (GDSC, https://www.cancerrxgene.org) and the Cancer Therapeutics Response Portal (CTRP, http://portals.broadinstitute.org/ctrp/) linked genomic features of more than 800 cancer cell lines to their sensitivity to hundreds of chemical compounds comprising FDA-approved drugs, clinical candidates, and small molecules (7–11). Conversely, the Connectivity Map (CMap) and its recent development, L1000 (CLUE, https://clue.io), profiled cancer cell lines before and after the treatment with several chemical compounds and genomic perturbagens, retrieving gene signatures directly associated to their administration (12–14). Although these screenings share a similar experimental pipeline, most of the produced data are heterogeneous and lack concordance in terms of investigated cell lines, tested compounds, and genomic information. In this review, we will describe some computational tools for the integrative analysis of data from different pharmacogenomics resources.

Inspired by the NCI-60 project, several collaborative efforts scaled up the number of cancer cell lines investigated in pharmacogenomics studies from the original 60 to more than 1,400, planning to reach over 10,000 publicly available cancer models in the near future (15). The massive amount of genomic and drug response data generated by these screenings are commonly collected in databases that, through dedicated web portals, provide direct insights into potential interactions between the analyzed cancer cell lines and the tested drugs. These databases are commonly equipped with computational resources specifically designed for the navigation and the analysis of the pharmacogenomics data, as for instance GDSCTools (16), CellMiner (17), Enrichr (18), L1000 Viewer (19), PharmacoGx, and PharmacoDB (20, 21), and the recently deployed RING (22). However, most of these tools are database specific and have limited capabilities in integrating data obtained from different screenings. This limitation is mostly due to the heterogeneity of data provided by the various studies, with drug tests not standardized across projects and genomic profiling not always available for the entire panel of cell lines. In addition, data are often unbalanced, with experiments comprising a high number of cell lines screened on few drugs (e.g., CCLE and GDSC) and, vice versa, screenings of large pools of chemical compounds performed on small cohorts of cancer cell lines (as in the NCI-60). Finally, while genomic data are rather homogeneous and can be easily integrated across studies after removing batch effects, pharmacological data derived from distinct experimental designs must be kept separate as they are profoundly different in terms of analytical assays, tested drug concentration, and retrieved inhibitory potential (23, 24). Despite these intrinsic limitations, several approaches have been proposed for the integrative analysis of genomics and pharmacological data collected from different screenings (Figure 1B). In particular, CellMinerCDB combines genomic profiles from NCI-60, CCLE, GDSC, and CTRP with the pharmacological data provided by the NCI-60 screening (25); the Genomics and Drugs integrated Analysis portal (GDA) integrates pharmacological data derived from the NCI-60 with the genomic information of NCI-60 and CCLE (26); and the CMap enables the investigation of the L1000 data through the correlation of gene lists and transcriptional signatures modulated by the drug treatment (12, 14, 27).

Efforts to decipher the molecular mechanisms of cancer stimulated scientists to explore the interconnection between the genomic landscape of cancer models and their response to drug treatments. This resulted in large pharmacogenomics screenings that, with the advent of high-throughput technologies, generated large amounts of genomics and pharmacological data. However, the integration of these precious information is still challenging due to the variable type and number of drugs and cancer cell lines that have been screened by the various projects and the heterogeneous assays used for drug testing in the different studies (23, 24, 33–35). Despite these intrinsic difficulties, several computational approaches have been developed for the integrative analysis of genomics and pharmacological data. Their application allowed to discover several new connections between drug sensitivity and genomic backgrounds, enabling the potential repurposing of commercially available drugs to cancer treatment (36–38). However, these computational resources, although proven effective, still suffer the limitations of the original studies as the sparsity of the drug and cell interaction matrices, the effective impossibility to merge drug response data across different screenings, and the criticalities of cancer cell lines as a reliable cancer model (39–41). To this end, the project for a Patient-Derived Model Database (PDMB) launched in 2012 by the NCI might represent a potential breakthrough as genomic and drug response data directly collected from patients and patient-derived xenografts (PDXs) will reproduce more accurately the cancer disease and its environment than any cell line model (42). Furthermore, while novel experimental models are generating more accurate data, advanced computational methods are under development to enhance the analytical potential of existing algorithms. As recently discussed (43–45), artificial intelligence approaches as network-based models, deep-learning frameworks, and machine-learning techniques are increasingly applied to investigate pharmacogenomics connections and drug repositioning. These methods can be effective not only for data integration but also to predict new interactions and applications of already approved drugs (46–48). In summary, computational approaches for the integration of genomic and pharmacological data have the potential to become crucial for the systematic identification of new biomarkers of drug sensitivity and the discovery of novel anticancer drugs on the basis of specific genetic abnormalities, as long as reliable cellular models and highly curated data become available.

JC and SB conceived the project. JC, MD, and SB wrote and revised the manuscript.