Diagnostic potential for a serum miRNA neural network for detection of ovarian cancer
- Brigham and Women's Hospital, United States
- Harvard Medical School, United States
- Medical University of Lodz, Poland
Abstract
Recent studies posit a role for non-coding RNAs in epithelial ovarian cancer (EOC). Combining small RNA sequencing from 179 human serum samples with a neural network analysis produced a miRNA algorithm for diagnosis of EOC (AUC 0.90; 95% CI: 0.81-0.99). The model significantly outperformed CA125 and functioned well regardless of patient age, histology, or stage. Among 454 patients with various diagnoses, the miRNA neural network had 100% specificity for ovarian cancer. After using 325 samples to adapt the neural network to qPCR measurements, the model was validated using 51 independent clinical samples, with a positive predictive value of 91.3% (95% CI: 73.3% - 97.6%) and negative predictive value of 78.6% (95% CI: 64.2% - 88.2%). Finally, biologic relevance was tested using in situ hybridization on 30 pre-metastatic lesions, showing intratumoral concentration of relevant miRNAs. These data suggest circulating miRNAs have potential to develop a non-invasive diagnostic test for ovarian cancer.
Data availability
Article and author information
Author details
Dipanjan Chowdhury
Funding
Robert and Deborah First Family Fund
- Kevin M Elias
- Ross S Berkowitz
- Dipanjan Chowdhury
U.S. Department of Defense (OC093426)
- Panagiotis Konstantinopoulos
Honorable Tina Brozman Foundation
- Kevin M Elias
- Dipanjan Chowdhury
U.S. Department of Defense (OC140632)
- Panagiotis Konstantinopoulos
National Institutes of Health (K12HD13015)
- Kevin M Elias
Ruth N White Research Fellowship in Gynecologic Oncology
- Kevin M Elias
- Stephen J Fiascone
Saltonstall Research Fund
- Kevin M Elias
- Stephen J Fiascone
- Ross S Berkowitz
Potter Research Fund
- Kevin M Elias
- Stephen J Fiascone
- Ross S Berkowitz
Sperling Family Fund Fellowship
- Kevin M Elias
- Stephen J Fiascone
- Ross S Berkowitz
Bach Underwood Fund
- Kevin M Elias
- Stephen J Fiascone
- Ross S Berkowitz
First TEAM grant of the foundation for Polish Science and the Smart Growth Operational Programme of the European Union
- Wojciech Fendler
National Institutes of Health (P50CA105009)
- Allison F Vitonis
- Daniel W Cramer
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Charles L Sawyers, Memorial Sloan-Kettering Cancer Center, United States
Ethics
Human subjects: All samples were collected after signed informed consent according to locally-approved Institutional Review Board protocols. These studies were approved by the Dana-Farber Cancer Institute Institutional Review Board Protocol 05-060 (NECC study), Brigham and Women's Hospital Institutional Review Board Protocol 2000-P-001678 (Pelvic Mass Protocol), and Dana-Farber/Harvard Cancer Center Institutional Review Board Protocol 12-532 (ERASMOS).
Version history
- Received: May 23, 2017
- Accepted: October 11, 2017
- Accepted Manuscript published: October 31, 2017 (version 1)
- Version of Record published: November 3, 2017 (version 2)
Copyright
© 2017, Elias et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 8,159
- views
-
- 1,138
- downloads
-
- 111
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Diagnostic potential for a serum miRNA neural network for detection of ovarian cancer
eLife 6:e28932.
https://doi.org/10.7554/eLife.28932
Further reading
-
- Cancer Biology
BRAFV600E mutation is a driver mutation in the serrated pathway to colorectal cancers. BRAFV600E drives tumorigenesis through constitutive downstream extracellular signal-regulated kinase (ERK) activation, but high-intensity ERK activation can also trigger tumor suppression. Whether and how oncogenic ERK signaling can be intrinsically adjusted to a ‘just-right’ level optimal for tumorigenesis remains undetermined. In this study, we found that FAK (Focal adhesion kinase) expression was reduced in BRAFV600E-mutant adenomas/polyps in mice and patients. In Vil1-Cre;BRAFLSL-V600E/+;Ptk2fl/fl mice, Fak deletion maximized BRAFV600E’s oncogenic activity and increased cecal tumor incidence to 100%. Mechanistically, our results showed that Fak loss, without jeopardizing BRAFV600E-induced ERK pathway transcriptional output, reduced EGFR (epidermal growth factor receptor)-dependent ERK phosphorylation. Reduction in ERK phosphorylation increased the level of Lgr4, promoting intestinal stemness and cecal tumor formation. Our findings show that a ‘just-right’ ERK signaling optimal for BRAFV600E-induced cecal tumor formation can be achieved via Fak loss-mediated downregulation of ERK phosphorylation.
-
- Cancer Biology
- Computational and Systems Biology
Untargeted metabolomic profiling through liquid chromatography-mass spectrometry (LC-MS) measures a vast array of metabolites within biospecimens, advancing drug development, disease diagnosis, and risk prediction. However, the low throughput of LC-MS poses a major challenge for biomarker discovery, annotation, and experimental comparison, necessitating the merging of multiple datasets. Current data pooling methods encounter practical limitations due to their vulnerability to data variations and hyperparameter dependence. Here, we introduce GromovMatcher, a flexible and user-friendly algorithm that automatically combines LC-MS datasets using optimal transport. By capitalizing on feature intensity correlation structures, GromovMatcher delivers superior alignment accuracy and robustness compared to existing approaches. This algorithm scales to thousands of features requiring minimal hyperparameter tuning. Manually curated datasets for validating alignment algorithms are limited in the field of untargeted metabolomics, and hence we develop a dataset split procedure to generate pairs of validation datasets to test the alignments produced by GromovMatcher and other methods. Applying our method to experimental patient studies of liver and pancreatic cancer, we discover shared metabolic features related to patient alcohol intake, demonstrating how GromovMatcher facilitates the search for biomarkers associated with lifestyle risk factors linked to several cancer types.
