Objectives

In this paper, we discuss leveraging cloud-based platforms to collect, visualize, analyze, and share data in the context of a clinical trial. Our cloud-based infrastructure, Patient Repository of Biomolecular Entities (PRoBE), has given us the opportunity for uniform data structure, more efficient analysis of valuable data, and increased collaboration between researchers.

Materials and methods

We utilize a multi-cloud platform to manage and analyze data generated from the clinical Investigation of Serial Studies to Predict Your Therapeutic Response with Imaging And moLecular Analysis 2 (I-SPY 2 TRIAL). A collaboration with the Institute for Systems Biology Cancer Gateway in the Cloud has additionally given us access to public genomic databases. Applications to I-SPY 2 data have been built using R Shiny, while leveraging Google's BigQuery tables and SQL commands for data mining.

Results

We highlight the implementation of PRoBE in several unique case studies including prediction of biomarkers associated with clinical response, access to the Pan-Cancer Atlas, and integrating pathology images within the cloud. Our data integration pipelines, documentation, and all codebase will be placed in a Github repository.

Discussion and conclusion

We are hoping to develop risk stratification diagnostics by integrating additional molecular, magnetic resonance imaging, and pathology markers into PRoBE to better predict drug response. A robust cloud infrastructure and tool set can help integrate these large datasets to make valuable predictions of response to multiple agents. For that reason, we are continuously improving PRoBE to advance the way data is stored, accessed, and analyzed in the I-SPY 2 clinical trial.

Molecular subtyping of breast cancer is based mostly on HR/HER2 and gene expression-based immune, DNA repair deficiency, and luminal signatures. We extend this description via functional protein pathway activation mapping using pre-treatment, quantitative expression data from 139 proteins/phosphoproteins from 736 patients across 8 treatment arms of the I-SPY 2 Trial (ClinicalTrials.gov: NCT01042379). We identify predictive fit-for-purpose, mechanism-of-action-based signatures and individual predictive protein biomarker candidates by evaluating associations with pathologic complete response. Elevated levels of cyclin D1, estrogen receptor alpha, and androgen receptor S650 associate with non-response and are biomarkers for global resistance. We uncover protein/phosphoprotein-based signatures that can be utilized both for molecularly rationalized therapeutic selection and for response prediction. We introduce a dichotomous HER2 activation response predictive signature for stratifying triple-negative breast cancer patients to either HER2 or immune checkpoint therapy response as a model for how protein activation signatures provide a different lens to view the molecular landscape of breast cancer and synergize with transcriptomic-defined signatures.

Using pre-treatment gene expression, protein/phosphoprotein, and clinical data from the I-SPY2 neoadjuvant platform trial (NCT01042379), we create alternative breast cancer subtypes incorporating tumor biology beyond clinical hormone receptor (HR) and human epidermal growth factor receptor-2 (HER2) status to better predict drug responses. We assess the predictive performance of mechanism-of-action biomarkers from ∼990 patients treated with 10 regimens targeting diverse biology. We explore >11 subtyping schemas and identify treatment-subtype pairs maximizing the pathologic complete response (pCR) rate over the population. The best performing schemas incorporate Immune, DNA repair, and HER2/Luminal phenotypes. Subsequent treatment allocation increases the overall pCR rate to 63% from 51% using HR/HER2-based treatment selection. pCR gains from reclassification and improved patient selection are highest in HR⁺ subsets (>15%). As new treatments are introduced, the subtyping schema determines the minimum response needed to show efficacy. This data platform provides an unprecedented resource and supports the usage of response-based subtypes to guide future treatment prioritization.