CUP-AI-Dx: A tool for inferring cancer tissue of origin and molecular subtype using RNA gene-expression data and artificial intelligence
Yue Zhao,
Ziwei Pan,
Sandeep Namburi,
Andrew Pattison,
Atara Posner,
Shiva Balachander,
Carolyn A. Paisie,
Honey V Reddi,
Jens Rueter,
Anthony J Gill,
Stephen Fox,
Kanwal P.S. Raghav,
William F Flynn,
Richard W. Tothill,
Sheng Li,
R. Krishna Murthy Karuturi,
Joshy George
Affiliations
Yue Zhao
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
Ziwei Pan
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA
Sandeep Namburi
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
Andrew Pattison
Department of Clinical Pathology and Centre for Cancer Research, University of Melbourne, Parkville, Melbourne, Australia
Atara Posner
Department of Clinical Pathology and Centre for Cancer Research, University of Melbourne, Parkville, Melbourne, Australia
Shiva Balachander
Department of Clinical Pathology and Centre for Cancer Research, University of Melbourne, Parkville, Melbourne, Australia
Carolyn A. Paisie
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
Honey V Reddi
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA; The Jackson Laboratory Cancer Center, Bar Harbor, ME, USA
Jens Rueter
The Jackson Laboratory Cancer Center, Bar Harbor, ME, USA
Anthony J Gill
Cancer Diagnosis and Pathology Group, Kolling Institute of Medical Research, Royal North Shore Hospital, St Leonards, New South Wales 2065 Australia; NSW Health Pathology, Department of Anatomical Pathology, Royal North Shore Hospital, Sydney, New South Wales 2065 Australia; Department of Anatomical Pathology, Douglass Hanly Moir Pathology, Macquarie Park, New South Wales 2113 Australia; University of Sydney, Sydney, New South Wales 2006 Australia
Stephen Fox
Peter MacCallum Cancer Centre, Department of Pathology, University of Melbourne, Victoria, Australia
Kanwal P.S. Raghav
Department of Gastrointestinal Medical Oncology, Division of Cancer Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
William F Flynn
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA
Richard W. Tothill
Department of Clinical Pathology and Centre for Cancer Research, University of Melbourne, Parkville, Melbourne, Australia; Peter MacCallum Cancer Centre, Parkville, Melbourne, Australia; Corresponding author at: The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA.
Sheng Li
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA; The Jackson Laboratory Cancer Center, Bar Harbor, ME, USA; Department of Genetics and Genome Sciences, University of Connecticut Health Center, Farmington, CT, USA; Department of Computer Science and Engineering, University of Connecticut, Storrs, CT, USA; Corresponding author at: The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA.
R. Krishna Murthy Karuturi
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA; The Jackson Laboratory Cancer Center, Bar Harbor, ME, USA; Department of Computer Science and Engineering, University of Connecticut, Storrs, CT, USA; Corresponding author at: The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA.
Joshy George
The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA; The Jackson Laboratory Cancer Center, Bar Harbor, ME, USA; Corresponding author at: The Jackson Laboratory for Genomic Medicine, 10 Discovery Drive, Farmington, CT, USA.
Background: Cancer of unknown primary (CUP), representing approximately 3-5% of all malignancies, is defined as metastatic cancer where a primary site of origin cannot be found despite a standard diagnostic workup. Because knowledge of a patient's primary cancer remains fundamental to their treatment, CUP patients are significantly disadvantaged and most have a poor survival outcome. Developing robust and accessible diagnostic methods for resolving cancer tissue of origin, therefore, has significant value for CUP patients. Methods: We developed an RNA-based classifier called CUP-AI-Dx that utilizes a 1D Inception convolutional neural network (1D-Inception) model to infer a tumor's primary tissue of origin. CUP-AI-Dx was trained using the transcriptional profiles of 18,217 primary tumours representing 32 cancer types from The Cancer Genome Atlas project (TCGA) and International Cancer Genome Consortium (ICGC). Gene expression data was ordered by gene chromosomal coordinates as input to the 1D-CNN model, and the model utilizes multiple convolutional kernels with different configurations simultaneously to improve generality. The model was optimized through extensive hyperparameter tuning, including different max-pooling layers and dropout settings. For 11 tumour types, we also developed a random forest model that can classify the tumour's molecular subtype according to prior TCGA studies. The optimised CUP-AI-Dx tissue of origin classifier was tested on 394 metastatic samples from 11 tumour types from TCGA and 92 formalin-fixed paraffin-embedded (FFPE) samples representing 18 cancer types from two clinical laboratories. The CUP-AI-Dx molecular subtype was also independently tested on independent ovarian and breast cancer microarray datasets Findings: CUP-AI-Dx identifies the primary site with an overall top-1-accuracy of 98.54% in cross-validation and 96.70% on a test dataset. When applied to two independent clinical-grade RNA-seq datasets generated from two different institutes from the US and Australia, our model predicted the primary site with a top-1-accuracy of 86.96% and 72.46% respectively. Interpretation: The CUP-AI-Dx predicts tumour primary site and molecular subtype with high accuracy and therefore can be used to assist the diagnostic work-up of cancers of unknown primary or uncertain origin using a common and accessible genomics platform. Funding: NIH R35 GM133562, NCI P30 CA034196, Victorian Cancer Agency Australia.
