Deep learning integrates histopathology and proteogenomics at a pan-cancer level

Clinical Proteomic Tumor Analysis Consortium; Joshua M. Wang; Runyu Hong; Elizabeth G. Demicco; Jimin Tan; Rossana Lazcano; Andre L. Moreira; Yize Li; Anna Calinawan; Narges Razavian; Tobias Schraink; Michael A. Gillette; Gilbert S. Omenn; Eunkyung An; Henry Rodriguez; Aristotelis Tsirigos; Kelly V. Ruggles; Li Ding; Ana I. Robles; D. R. Mani; Karin D. Rodland; Alexander J. Lazar; Wenke Liu; David Fenyö; François Aguet; Yo Akiyama; Shankara Anand; Meenakshi Anurag; Özgün Babur; Jasmin Bavarva; Chet Birger; Michael J. Birrer; Lewis C. Cantley; Song Cao; Steven A. Carr; Michele Ceccarelli; Daniel W. Chan; Arul M. Chinnaiyan; Hanbyul Cho; Shrabanti Chowdhury; Marcin P. Cieslik; Karl R. Clauser; Antonio Colaprico; Daniel Cui Zhou; Felipe da Veiga Leprevost; Corbin Day; Saravana M. Dhanasekaran; Marcin J. Domagalski; Yongchao Dou; Brian J. Druker; Nathan Edwards; Matthew J. Ellis; Myvizhi Esai Selvan; Steven M. Foltz; Alicia Francis; Yifat Geffen; Gad Getz; Tania J. Gonzalez Robles; Sara J.C. Gosline; Zeynep H. Gümüş; David I. Heiman; Tara Hiltke; Galen Hostetter; Yingwei Hu; Chen Huang; Emily Huntsman; Antonio Iavarone; Eric J. Jaehnig; Scott D. Jewell; Jiayi Ji; Wen Jiang; Jared L. Johnson; Lizabeth Katsnelson; Karen A. Ketchum; Iga Kolodziejczak; Karsten Krug; Chandan Kumar-Sinha; Jonathan T. Lei; Wen Wei Liang; Yuxing Liao; Caleb M. Lindgren; Tao Liu; Weiping Ma; Fernanda Martins Rodrigues; Wilson McKerrow; Mehdi Mesri; Alexey I. Nesvizhskii; Chelsea J. Newton; Robert Oldroyd; Amanda G. Paulovich; Samuel H. Payne; Francesca Petralia; Pietro Pugliese; Boris Reva; Dmitry Rykunov; Shankha Satpathy; Sara R. Savage; Eric E. Schadt; Michael Schnaubelt; Stephan Schürer; Zhiao Shi; Richard D. Smith; Xiaoyu Song; Yizhe Song; Vasileios Stathias; Erik P. Storrs; Nadezhda V. Terekhanova; Ratna R. Thangudu; Mathangi Thiagarajan; Nicole Tignor; Liang Bo Wang; Pei Wang; Ying Wang; Bo Wen; Maciej Wiznerowicz; Yige Wu; Matthew A. Wyczalkowski; Lijun Yao; Tomer M. Yaron; Xinpei Yi; Bing Zhang; Hui Zhang; Qing Zhang; Xu Zhang; Zhen Zhang

doi:10.1016/j.xcrm.2023.101173

Deep learning integrates histopathology and proteogenomics at a pan-cancer level

Clinical Proteomic Tumor Analysis Consortium, Joshua M. Wang, Runyu Hong, Elizabeth G. Demicco, Jimin Tan, Rossana Lazcano, Andre L. Moreira, Yize Li, Anna Calinawan, Narges Razavian, Tobias Schraink, Michael A. Gillette, Gilbert S. Omenn, Eunkyung An, Henry Rodriguez, Aristotelis Tsirigos, Kelly V. Ruggles, Li Ding, Ana I. Robles, D. R. ManiKarin D. Rodland, Alexander J. Lazar, Wenke Liu, David Fenyö, François Aguet, Yo Akiyama, Shankara Anand, Meenakshi Anurag, Özgün Babur, Jasmin Bavarva, Chet Birger, Michael J. Birrer, Lewis C. Cantley, Song Cao, Steven A. Carr, Michele Ceccarelli, Daniel W. Chan, Arul M. Chinnaiyan, Hanbyul Cho, Shrabanti Chowdhury, Marcin P. Cieslik, Karl R. Clauser, Antonio Colaprico, Daniel Cui Zhou, Felipe da Veiga Leprevost, Corbin Day, Saravana M. Dhanasekaran, Marcin J. Domagalski, Yongchao Dou, Brian J. Druker, Nathan Edwards, Matthew J. Ellis, Myvizhi Esai Selvan, Steven M. Foltz, Alicia Francis, Yifat Geffen, Gad Getz, Tania J. Gonzalez Robles, Sara J.C. Gosline, Zeynep H. Gümüş, David I. Heiman, Tara Hiltke, Galen Hostetter, Yingwei Hu, Chen Huang, Emily Huntsman, Antonio Iavarone, Eric J. Jaehnig, Scott D. Jewell, Jiayi Ji, Wen Jiang, Jared L. Johnson, Lizabeth Katsnelson, Karen A. Ketchum, Iga Kolodziejczak, Karsten Krug, Chandan Kumar-Sinha, Jonathan T. Lei, Wen Wei Liang, Yuxing Liao, Caleb M. Lindgren, Tao Liu, Weiping Ma, Fernanda Martins Rodrigues, Wilson McKerrow, Mehdi Mesri, Alexey I. Nesvizhskii, Chelsea J. Newton, Robert Oldroyd, Amanda G. Paulovich, Samuel H. Payne, Francesca Petralia, Pietro Pugliese, Boris Reva, Dmitry Rykunov, Shankha Satpathy, Sara R. Savage, Eric E. Schadt, Michael Schnaubelt, Stephan Schürer, Zhiao Shi, Richard D. Smith, Xiaoyu Song, Yizhe Song, Vasileios Stathias, Erik P. Storrs, Nadezhda V. Terekhanova, Ratna R. Thangudu, Mathangi Thiagarajan, Nicole Tignor, Liang Bo Wang, Pei Wang, Ying Wang, Bo Wen, Maciej Wiznerowicz, Yige Wu, Matthew A. Wyczalkowski, Lijun Yao, Tomer M. Yaron, Xinpei Yi, Bing Zhang, Hui Zhang, Qing Zhang, Xu Zhang, Zhen Zhang

Research output: Contribution to journal › Article › peer-review

8 Scopus citations

Abstract

We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

Original language	English
Article number	101173
Journal	Cell Reports Medicine
Volume	4
Issue number	9
DOIs	https://doi.org/10.1016/j.xcrm.2023.101173
State	Published - Sep 19 2023

Keywords

CPTAC
cancer imaging
cancer proteogenomics
computational pathology
molecular diagnostics

Access to Document

10.1016/j.xcrm.2023.101173

Cite this

Clinical Proteomic Tumor Analysis Consortium, Wang, J. M., Hong, R., Demicco, E. G., Tan, J., Lazcano, R., Moreira, A. L., Li, Y., Calinawan, A., Razavian, N., Schraink, T., Gillette, M. A., Omenn, G. S., An, E., Rodriguez, H., Tsirigos, A., Ruggles, K. V., Ding, L., Robles, A. I., ... Zhang, Z. (2023). Deep learning integrates histopathology and proteogenomics at a pan-cancer level. Cell Reports Medicine, 4(9), Article 101173. https://doi.org/10.1016/j.xcrm.2023.101173

@article{fec54aa439044211861e9ef46ccf4f0a,

title = "Deep learning integrates histopathology and proteogenomics at a pan-cancer level",

abstract = "We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.",

keywords = "CPTAC, cancer imaging, cancer proteogenomics, computational pathology, molecular diagnostics",

author = "{Clinical Proteomic Tumor Analysis Consortium} and Wang, {Joshua M.} and Runyu Hong and Demicco, {Elizabeth G.} and Jimin Tan and Rossana Lazcano and Moreira, {Andre L.} and Yize Li and Anna Calinawan and Narges Razavian and Tobias Schraink and Gillette, {Michael A.} and Omenn, {Gilbert S.} and Eunkyung An and Henry Rodriguez and Aristotelis Tsirigos and Ruggles, {Kelly V.} and Li Ding and Robles, {Ana I.} and Mani, {D. R.} and Rodland, {Karin D.} and Lazar, {Alexander J.} and Wenke Liu and David Feny{\"o} and Fran{\c c}ois Aguet and Yo Akiyama and Shankara Anand and Meenakshi Anurag and {\"O}zg{\"u}n Babur and Jasmin Bavarva and Chet Birger and Birrer, {Michael J.} and Cantley, {Lewis C.} and Song Cao and Carr, {Steven A.} and Michele Ceccarelli and Chan, {Daniel W.} and Chinnaiyan, {Arul M.} and Hanbyul Cho and Shrabanti Chowdhury and Cieslik, {Marcin P.} and Clauser, {Karl R.} and Antonio Colaprico and Zhou, {Daniel Cui} and {da Veiga Leprevost}, Felipe and Corbin Day and Dhanasekaran, {Saravana M.} and Domagalski, {Marcin J.} and Yongchao Dou and Druker, {Brian J.} and Nathan Edwards and Ellis, {Matthew J.} and Selvan, {Myvizhi Esai} and Foltz, {Steven M.} and Alicia Francis and Yifat Geffen and Gad Getz and {Gonzalez Robles}, {Tania J.} and Gosline, {Sara J.C.} and G{\"u}m{\"u}{\c s}, {Zeynep H.} and Heiman, {David I.} and Tara Hiltke and Galen Hostetter and Yingwei Hu and Chen Huang and Emily Huntsman and Antonio Iavarone and Jaehnig, {Eric J.} and Jewell, {Scott D.} and Jiayi Ji and Wen Jiang and Johnson, {Jared L.} and Lizabeth Katsnelson and Ketchum, {Karen A.} and Iga Kolodziejczak and Karsten Krug and Chandan Kumar-Sinha and Lei, {Jonathan T.} and Liang, {Wen Wei} and Yuxing Liao and Lindgren, {Caleb M.} and Tao Liu and Weiping Ma and Rodrigues, {Fernanda Martins} and Wilson McKerrow and Mehdi Mesri and Nesvizhskii, {Alexey I.} and Newton, {Chelsea J.} and Robert Oldroyd and Paulovich, {Amanda G.} and Payne, {Samuel H.} and Francesca Petralia and Pietro Pugliese and Boris Reva and Dmitry Rykunov and Shankha Satpathy and Savage, {Sara R.} and Schadt, {Eric E.} and Michael Schnaubelt and Stephan Sch{\"u}rer and Zhiao Shi and Smith, {Richard D.} and Xiaoyu Song and Yizhe Song and Vasileios Stathias and Storrs, {Erik P.} and Terekhanova, {Nadezhda V.} and Thangudu, {Ratna R.} and Mathangi Thiagarajan and Nicole Tignor and Wang, {Liang Bo} and Pei Wang and Ying Wang and Bo Wen and Maciej Wiznerowicz and Yige Wu and Wyczalkowski, {Matthew A.} and Lijun Yao and Yaron, {Tomer M.} and Xinpei Yi and Bing Zhang and Hui Zhang and Qing Zhang and Xu Zhang and Zhen Zhang",

note = "Publisher Copyright: {\textcopyright} 2023 The Author(s)",

year = "2023",

month = sep,

day = "19",

doi = "10.1016/j.xcrm.2023.101173",

language = "English",

volume = "4",

journal = "Cell Reports Medicine",

issn = "2666-3791",

number = "9",

}

Clinical Proteomic Tumor Analysis Consortium, Wang, JM, Hong, R, Demicco, EG, Tan, J, Lazcano, R, Moreira, AL, Li, Y, Calinawan, A, Razavian, N, Schraink, T, Gillette, MA, Omenn, GS, An, E, Rodriguez, H, Tsirigos, A, Ruggles, KV, Ding, L, Robles, AI, Mani, DR, Rodland, KD, Lazar, AJ, Liu, W, Fenyö, D, Aguet, F, Akiyama, Y, Anand, S, Anurag, M, Babur, Ö, Bavarva, J, Birger, C, Birrer, MJ, Cantley, LC, Cao, S, Carr, SA, Ceccarelli, M, Chan, DW, Chinnaiyan, AM, Cho, H, Chowdhury, S, Cieslik, MP, Clauser, KR, Colaprico, A, Zhou, DC, da Veiga Leprevost, F, Day, C, Dhanasekaran, SM, Domagalski, MJ, Dou, Y, Druker, BJ, Edwards, N, Ellis, MJ, Selvan, ME, Foltz, SM, Francis, A, Geffen, Y, Getz, G, Gonzalez Robles, TJ, Gosline, SJC, Gümüş, ZH, Heiman, DI, Hiltke, T, Hostetter, G, Hu, Y, Huang, C, Huntsman, E, Iavarone, A, Jaehnig, EJ, Jewell, SD, Ji, J, Jiang, W, Johnson, JL, Katsnelson, L, Ketchum, KA, Kolodziejczak, I, Krug, K, Kumar-Sinha, C, Lei, JT, Liang, WW, Liao, Y, Lindgren, CM, Liu, T, Ma, W, Rodrigues, FM, McKerrow, W, Mesri, M, Nesvizhskii, AI, Newton, CJ, Oldroyd, R, Paulovich, AG, Payne, SH, Petralia, F, Pugliese, P, Reva, B, Rykunov, D, Satpathy, S, Savage, SR, Schadt, EE, Schnaubelt, M, Schürer, S, Shi, Z, Smith, RD, Song, X, Song, Y, Stathias, V, Storrs, EP, Terekhanova, NV, Thangudu, RR, Thiagarajan, M, Tignor, N, Wang, LB, Wang, P, Wang, Y, Wen, B, Wiznerowicz, M, Wu, Y, Wyczalkowski, MA, Yao, L, Yaron, TM, Yi, X, Zhang, B, Zhang, H, Zhang, Q, Zhang, X & Zhang, Z 2023, 'Deep learning integrates histopathology and proteogenomics at a pan-cancer level', Cell Reports Medicine, vol. 4, no. 9, 101173. https://doi.org/10.1016/j.xcrm.2023.101173

TY - JOUR

T1 - Deep learning integrates histopathology and proteogenomics at a pan-cancer level

AU - Clinical Proteomic Tumor Analysis Consortium

AU - Wang, Joshua M.

AU - Hong, Runyu

AU - Demicco, Elizabeth G.

AU - Tan, Jimin

AU - Lazcano, Rossana

AU - Moreira, Andre L.

AU - Li, Yize

AU - Calinawan, Anna

AU - Razavian, Narges

AU - Schraink, Tobias

AU - Gillette, Michael A.

AU - Omenn, Gilbert S.

AU - An, Eunkyung

AU - Rodriguez, Henry

AU - Tsirigos, Aristotelis

AU - Ruggles, Kelly V.

AU - Ding, Li

AU - Robles, Ana I.

AU - Mani, D. R.

AU - Rodland, Karin D.

AU - Lazar, Alexander J.

AU - Liu, Wenke

AU - Fenyö, David

AU - Aguet, François

AU - Akiyama, Yo

AU - Anand, Shankara

AU - Anurag, Meenakshi

AU - Babur, Özgün

AU - Bavarva, Jasmin

AU - Birger, Chet

AU - Birrer, Michael J.

AU - Cantley, Lewis C.

AU - Cao, Song

AU - Carr, Steven A.

AU - Ceccarelli, Michele

AU - Chan, Daniel W.

AU - Chinnaiyan, Arul M.

AU - Cho, Hanbyul

AU - Chowdhury, Shrabanti

AU - Cieslik, Marcin P.

AU - Clauser, Karl R.

AU - Colaprico, Antonio

AU - Zhou, Daniel Cui

AU - da Veiga Leprevost, Felipe

AU - Day, Corbin

AU - Dhanasekaran, Saravana M.

AU - Domagalski, Marcin J.

AU - Dou, Yongchao

AU - Druker, Brian J.

AU - Edwards, Nathan

AU - Ellis, Matthew J.

AU - Selvan, Myvizhi Esai

AU - Foltz, Steven M.

AU - Francis, Alicia

AU - Geffen, Yifat

AU - Getz, Gad

AU - Gonzalez Robles, Tania J.

AU - Gosline, Sara J.C.

AU - Gümüş, Zeynep H.

AU - Heiman, David I.

AU - Hiltke, Tara

AU - Hostetter, Galen

AU - Hu, Yingwei

AU - Huang, Chen

AU - Huntsman, Emily

AU - Iavarone, Antonio

AU - Jaehnig, Eric J.

AU - Jewell, Scott D.

AU - Ji, Jiayi

AU - Jiang, Wen

AU - Johnson, Jared L.

AU - Katsnelson, Lizabeth

AU - Ketchum, Karen A.

AU - Kolodziejczak, Iga

AU - Krug, Karsten

AU - Kumar-Sinha, Chandan

AU - Lei, Jonathan T.

AU - Liang, Wen Wei

AU - Liao, Yuxing

AU - Lindgren, Caleb M.

AU - Liu, Tao

AU - Ma, Weiping

AU - Rodrigues, Fernanda Martins

AU - McKerrow, Wilson

AU - Mesri, Mehdi

AU - Nesvizhskii, Alexey I.

AU - Newton, Chelsea J.

AU - Oldroyd, Robert

AU - Paulovich, Amanda G.

AU - Payne, Samuel H.

AU - Petralia, Francesca

AU - Pugliese, Pietro

AU - Reva, Boris

AU - Rykunov, Dmitry

AU - Satpathy, Shankha

AU - Savage, Sara R.

AU - Schadt, Eric E.

AU - Schnaubelt, Michael

AU - Schürer, Stephan

AU - Shi, Zhiao

AU - Smith, Richard D.

AU - Song, Xiaoyu

AU - Song, Yizhe

AU - Stathias, Vasileios

AU - Storrs, Erik P.

AU - Terekhanova, Nadezhda V.

AU - Thangudu, Ratna R.

AU - Thiagarajan, Mathangi

AU - Tignor, Nicole

AU - Wang, Liang Bo

AU - Wang, Pei

AU - Wang, Ying

AU - Wen, Bo

AU - Wiznerowicz, Maciej

AU - Wu, Yige

AU - Wyczalkowski, Matthew A.

AU - Yao, Lijun

AU - Yaron, Tomer M.

AU - Yi, Xinpei

AU - Zhang, Bing

AU - Zhang, Hui

AU - Zhang, Qing

AU - Zhang, Xu

AU - Zhang, Zhen

PY - 2023/9/19

Y1 - 2023/9/19

N2 - We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

AB - We introduce a pioneering approach that integrates pathology imaging with transcriptomics and proteomics to identify predictive histology features associated with critical clinical outcomes in cancer. We utilize 2,755 H&E-stained histopathological slides from 657 patients across 6 cancer types from CPTAC. Our models effectively recapitulate distinctions readily made by human pathologists: tumor vs. normal (AUROC = 0.995) and tissue-of-origin (AUROC = 0.979). We further investigate predictive power on tasks not normally performed from H&E alone, including TP53 prediction and pathologic stage. Importantly, we describe predictive morphologies not previously utilized in a clinical setting. The incorporation of transcriptomics and proteomics identifies pathway-level signatures and cellular processes driving predictive histology features. Model generalizability and interpretability is confirmed using TCGA. We propose a classification system for these tasks, and suggest potential clinical applications for this integrated human and machine learning approach. A publicly available web-based platform implements these models.

KW - CPTAC

KW - cancer imaging

KW - cancer proteogenomics

KW - computational pathology

KW - molecular diagnostics

UR - http://www.scopus.com/inward/record.url?scp=85171478742&partnerID=8YFLogxK

U2 - 10.1016/j.xcrm.2023.101173

DO - 10.1016/j.xcrm.2023.101173

M3 - Article

C2 - 37582371

AN - SCOPUS:85171478742

SN - 2666-3791

VL - 4

JO - Cell Reports Medicine

JF - Cell Reports Medicine

IS - 9

M1 - 101173

ER -

Deep learning integrates histopathology and proteogenomics at a pan-cancer level

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this