Journal article
Developing a predictive model for metastatic potential in pancreatic neuroendocrine tumor
The journal of clinical endocrinology and metabolism, Vol.110(1), pp.263-274
12/18/2024
DOI: 10.1210/clinem/dgae380
PMCID: PMC11651689
PMID: 38817124
Abstract
Pancreatic neuroendocrine tumors (PNETs) exhibit a wide range of behavior from localized disease to aggressive metastasis. A comprehensive transcriptomic profile capable of differentiating between these phenotypes remains elusive.
Use machine learning to develop predictive models of PNET metastatic potential dependent upon transcriptomic signature.
RNA-sequencing data were analyzed from 95 surgically-resected primary PNETs in an international cohort. Two cohorts were generated with equally balanced metastatic PNET composition. Machine learning was used to create predictive models distinguishing between localized and metastatic tumors. Models were validated on an independent cohort of 29 formalin-fixed, paraffin-embedded samples using NanoString nCounter®, a clinically-available mRNA quantification platform.
Gene expression analysis identified concordant differentially expressed genes between the two cohorts. Gene set enrichment analysis identified additional genes that contributed to enriched biologic pathways in metastatic PNETs. Expression values for these genes were combined with an additional 7 genes known to contribute to PNET oncogenesis and prognosis, including ARX and PDX1. Eight specific genes (AURKA, CDCA8, CPB2, MYT1L, NDC80, PAPPA2, SFMBT1, ZPLD1) were identified as sufficient to classify the metastatic status with high sensitivity (87.5% - 93.8%) and specificity (78.1% - 96.9%). These models remained predictive of the metastatic phenotype using NanoString nCounter® on the independent validation cohort, achieving a median AUROC of 0.886.
We identified and validated an eight-gene panel predictive of the metastatic phenotype in PNETs, which can be detected using the clinically-available NanoString nCounter® system. This panel should be studied prospectively to determine its utility in guiding operative versus non-operative management.
Details
- Title: Subtitle
- Developing a predictive model for metastatic potential in pancreatic neuroendocrine tumor
- Creators
- Jacques A Greenberg - Cornell UniversityYajas Shah - Lander InstituteNikolay A Ivanov - Weill Cornell MedicineTeagan Marshall - Cornell UniversityScott Kulm - Lander InstituteJelani Williams - University of ChicagoCatherine Tran - University of IowaTheresa Scognamiglio - Weill Cornell MedicineJonas J Heymann - Weill Cornell MedicineYeon Joo Lee-Saxton - Cornell UniversityCaitlin Egan - Cornell UniversitySonali Majumdar - The Wistar InstituteIrene M Min - Cornell UniversityRasa Zarnegar - Cornell UniversityJames Howe - University of IowaXavier M Keutgen - University of ChicagoThomas J Fahey Iii - Weill Cornell MedicineOlivier Elemento - Cornell UniversityBrendan M Finnerty - Cornell University
- Resource Type
- Journal article
- Publication Details
- The journal of clinical endocrinology and metabolism, Vol.110(1), pp.263-274
- DOI
- 10.1210/clinem/dgae380
- PMID
- 38817124
- PMCID
- PMC11651689
- NLM abbreviation
- J Clin Endocrinol Metab
- eISSN
- 1945-7197
- Language
- English
- Electronic publication date
- 05/31/2024
- Date published
- 12/18/2024
- Academic Unit
- Surgery
- Record Identifier
- 9984634258002771
Metrics
9 Record Views