FORESEE: a tool for the systematic comparison of translational drug response modeling pipelines

Abstract

Summary Translational models that utilize omics data generated in in vitro studies to predict the drug efficacy of anti-cancer compounds in patients are highly distinct, which complicates the benchmarking process for new computational approaches. In reaction to this, we introduce the uniFied translatiOnal dRug rESponsE prEdiction platform FORESEE, an open-source R-package. FORESEE not only provides a uniform data format for public cell line and patient datasets, but also establishes a standardized environment for drug response prediction pipelines, incorporating various state-of-the-art pre-processing methods, model training algorithms and validation techniques. The modular implementation of individual elements of the pipeline facilitates a straightforward development of combinatorial models, which can be used to re-evaluate and improve already existing pipelines as well as to develop new ones. Availability and implementation FORESEE is licensed under GNU General Public License v3.0 and available at https://github.com/JRC-COMBINE/FORESEE and https://doi.org/10.17605/OSF.IO/RF6QK, and provides vignettes for documentation and application both online and in the Supplementary Files 2 and 3. Supplementary information Supplementary data are available at Bioinformatics online.

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

“…For the testing of the translational models in this study, information of patients with breast cancer (GSE6434 [20] and GSE18864 [24]), lung cancer (GSE33072 [28]), ovarian cancer (GSE51373 [29]) and multiple myeloma (the Bortezomib arms of GSE9782 [30]) was organized into ForeseePatient objects including gene expression data and one measure of in vivo drug efficacy, which is summarized in Table 2. Details about the preparation of the data sets can also be found in the Supplementary File 2 of the FORESEE package [19].…”

“…For the systematic comparison of different translational drug response modeling pipelines, the R-package FORESEE [19] was used. FORESEE, which is short for uniFied translatiOnal dRug rESponsE prEdcition platform, partitions the general modeling pipeline into defined functional elements in order to enable the user to thoroughly investigate the impact of each of them on the model performance.…”

“…Accordingly, in this study, we intend to systematically investigate the workflow of translational models of such kind, using our R-package FORESEE [19] to explore all relevant model components and their interplay. By including publicly available approaches and running the different modeling pipelines automatically, we reduce the bias introduced by the users' heterogeneous experiences in those methods.…”

“…Gene labeling. Within the context of collecting the different data sets and enforcing them into the same ForeseeObject formats for the FORESEE R package [19], the biomaRt package [22,23] was applied to convert all gene labels into Entrez IDs.…”

Two-step multi-omics modelling of drug sensitivity in cancer cell lines to identify driving mechanisms

“…Expanding on this concept of systematically identifying optimal choices in distinct steps of the modelling pipeline and applying it to translative modelling, Turnhoff et al have published an R package that can be used to perform even more intricate analyses in the context of predicting clinical responses while training on cell line data [10,11].…”