Cargando…

Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning

Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained his...

Descripción completa

Detalles Bibliográficos
Autores principales: Azuaje, Francisco, Kim, Sang-Yoon, Perez Hernandez, Daniel, Dittmar, Gunnar
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832975/
https://www.ncbi.nlm.nih.gov/pubmed/31557788
http://dx.doi.org/10.3390/jcm8101535
_version_ 1783466270090330112
author Azuaje, Francisco
Kim, Sang-Yoon
Perez Hernandez, Daniel
Dittmar, Gunnar
author_facet Azuaje, Francisco
Kim, Sang-Yoon
Perez Hernandez, Daniel
Dittmar, Gunnar
author_sort Azuaje, Francisco
collection PubMed
description Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained histopathology images remains largely uncharacterized. Here we investigate such associations through the application of machine learning, including deep neural networks, to proteomics and histology imaging datasets generated by the Clinical Proteomic Tumor Analysis Consortium (CPTAC) from clear cell renal cell carcinoma patients. We report robust correlations between a set of diagnostic proteins and predictions generated by an imaging-based classification model. Proteins significantly correlated with the histology-based predictions are significantly implicated in immune responses, extracellular matrix reorganization, and metabolism. Moreover, we showed that the genes encoding these proteins also reliably recapitulate the biological associations with imaging-derived predictions based on strong gene–protein expression correlations. Our findings offer novel insights into the integrative modeling of histology and omics data through machine learning, as well as the methodological basis for new research opportunities in this and other cancer types.
format Online
Article
Text
id pubmed-6832975
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-68329752019-11-25 Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning Azuaje, Francisco Kim, Sang-Yoon Perez Hernandez, Daniel Dittmar, Gunnar J Clin Med Article Proteomics data encode molecular features of diagnostic value and accurately reflect key underlying biological mechanisms in cancers. Histopathology imaging is a well-established clinical approach to cancer diagnosis. The predictive relationship between large-scale proteomics and H&E-stained histopathology images remains largely uncharacterized. Here we investigate such associations through the application of machine learning, including deep neural networks, to proteomics and histology imaging datasets generated by the Clinical Proteomic Tumor Analysis Consortium (CPTAC) from clear cell renal cell carcinoma patients. We report robust correlations between a set of diagnostic proteins and predictions generated by an imaging-based classification model. Proteins significantly correlated with the histology-based predictions are significantly implicated in immune responses, extracellular matrix reorganization, and metabolism. Moreover, we showed that the genes encoding these proteins also reliably recapitulate the biological associations with imaging-derived predictions based on strong gene–protein expression correlations. Our findings offer novel insights into the integrative modeling of histology and omics data through machine learning, as well as the methodological basis for new research opportunities in this and other cancer types. MDPI 2019-09-25 /pmc/articles/PMC6832975/ /pubmed/31557788 http://dx.doi.org/10.3390/jcm8101535 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Azuaje, Francisco
Kim, Sang-Yoon
Perez Hernandez, Daniel
Dittmar, Gunnar
Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title_full Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title_fullStr Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title_full_unstemmed Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title_short Connecting Histopathology Imaging and Proteomics in Kidney Cancer through Machine Learning
title_sort connecting histopathology imaging and proteomics in kidney cancer through machine learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6832975/
https://www.ncbi.nlm.nih.gov/pubmed/31557788
http://dx.doi.org/10.3390/jcm8101535
work_keys_str_mv AT azuajefrancisco connectinghistopathologyimagingandproteomicsinkidneycancerthroughmachinelearning
AT kimsangyoon connectinghistopathologyimagingandproteomicsinkidneycancerthroughmachinelearning
AT perezhernandezdaniel connectinghistopathologyimagingandproteomicsinkidneycancerthroughmachinelearning
AT dittmargunnar connectinghistopathologyimagingandproteomicsinkidneycancerthroughmachinelearning