Association of Omics Features with Histopathology Patterns in Lung Adenocarcinoma.
Kun-Hsing Yu, Gerald J Berry, Daniel L Rubin, Christopher Ré, Russ B Altman, Michael Snyder
Author Information
Kun-Hsing Yu: Biomedical Informatics Program, Stanford University, Stanford, CA 94305-5479, USA; Department of Genetics, Stanford University, Stanford, CA 94305-5120, USA; Department of Biomedical Informatics, Harvard Medical School, Boston, MA 02115, USA.
Gerald J Berry: Department of Pathology, Stanford University, Stanford, CA 94305, USA.
Daniel L Rubin: Biomedical Informatics Program, Stanford University, Stanford, CA 94305-5479, USA; Department of Biomedical Data Science, Stanford University, Stanford, CA 94305, USA; Department of Radiology, Stanford University, Stanford, CA 94305-5105, USA; Department of Medicine (Biomedical Informatics Research), Stanford University, Stanford, CA 94305-5479, USA.
Christopher Ré: Department of Computer Science, Stanford University, Stanford, CA 94305-9025, USA.
Russ B Altman: Biomedical Informatics Program, Stanford University, Stanford, CA 94305-5479, USA; Department of Genetics, Stanford University, Stanford, CA 94305-5120, USA; Department of Computer Science, Stanford University, Stanford, CA 94305-9025, USA; Department of Bioengineering, Stanford University, Stanford, CA 94305-4125, USA.
Michael Snyder: Department of Genetics, Stanford University, Stanford, CA 94305-5120, USA. Electronic address: mpsnyder@stanford.edu.
Adenocarcinoma accounts for more than 40% of lung malignancy, and microscopic pathology evaluation is indispensable for its diagnosis. However, how histopathology findings relate to molecular abnormalities remains largely unknown. Here, we obtained H&E-stained whole-slide histopathology images, pathology reports, RNA sequencing, and proteomics data of 538 lung adenocarcinoma patients from The Cancer Genome Atlas and used these to identify molecular pathways associated with histopathology patterns. We report cell-cycle regulation and nucleotide binding pathways underpinning tumor cell dedifferentiation, and we predicted histology grade using transcriptomics and proteomics signatures (area under curve >0.80). We built an integrative histopathology-transcriptomics model to generate better prognostic predictions for stage I patients (p = 0.0182 ± 0.0021) compared with gene expression or histopathology studies alone, and the results were replicated in an independent cohort (p = 0.0220 ± 0.0070). These results motivate the integration of histopathology and omics data to investigate molecular mechanisms of pathology findings and enhance clinical prognostic prediction.
