1
|
Lucarelli N, Yun D, Han D, Ginley B, Moon KC, Rosenberg AZ, Tomaszewski JE, Zee J, Jen KY, Han SS, Sarder P. Discovery of Novel Digital Biomarkers for Type 2 Diabetic Nephropathy Classification via Integration of Urinary Proteomics and Pathology. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.04.28.23289272. [PMID: 37205413 PMCID: PMC10187347 DOI: 10.1101/2023.04.28.23289272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/21/2023]
Abstract
Background The heterogeneous phenotype of diabetic nephropathy (DN) from type 2 diabetes complicates appropriate treatment approaches and outcome prediction. Kidney histology helps diagnose DN and predict its outcomes, and an artificial intelligence (AI)-based approach will maximize clinical utility of histopathological evaluation. Herein, we addressed whether AI-based integration of urine proteomics and image features improves DN classification and its outcome prediction, altogether augmenting and advancing pathology practice. Methods We studied whole slide images (WSIs) of periodic acid-Schiff-stained kidney biopsies from 56 DN patients with associated urinary proteomics data. We identified urinary proteins differentially expressed in patients who developed end-stage kidney disease (ESKD) within two years of biopsy. Extending our previously published human-AI-loop pipeline, six renal sub-compartments were computationally segmented from each WSI. Hand-engineered image features for glomeruli and tubules, and urinary protein measurements, were used as inputs to deep-learning frameworks to predict ESKD outcome. Differential expression was correlated with digital image features using the Spearman rank sum coefficient. Results A total of 45 urinary proteins were differentially detected in progressors, which was most predictive of ESKD (AUC=0.95), while tubular and glomerular features were less predictive (AUC=0.71 and AUC=0.63, respectively). Accordingly, a correlation map between canonical cell-type proteins, such as epidermal growth factor and secreted phosphoprotein 1, and AI-based image features was obtained, which supports previous pathobiological results. Conclusions Computational method-based integration of urinary and image biomarkers may improve the pathophysiological understanding of DN progression as well as carry clinical implications in histopathological evaluation.
Collapse
Affiliation(s)
- Nicholas Lucarelli
- J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, Gainesville, FL, USA
| | - Donghwan Yun
- Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Dohyun Han
- Proteomics Core Facility, Biomedical Research Institute, Seoul National University Hospital, Seoul, Republic of Korea
| | - Brandon Ginley
- The Janssen Pharmaceutical Companies of Johnson & Johnson, Raritan NJ, USA
| | - Kyung Chul Moon
- Department of Pathology, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Avi Z. Rosenberg
- Department of Pathology, Johns Hopkins University, Baltimore, MD, USA
| | - John E. Tomaszewski
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York
| | - Jarcy Zee
- Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania and Children’s Hospital of Philadelphia, PA, USA
| | - Kuang-Yu Jen
- Department of Pathology and Laboratory Medicine, University of California, Davis Medical Center, CA, USA
| | - Seung Seok Han
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea
| | - Pinaki Sarder
- Department of Medicine-Quantitative Health, University of Florida College of Medicine, Gainesville, FL, USA
- Department of Electrical and Computer Engineering, University of Florida College of Engineering, Gainesville, FL, USA
| |
Collapse
|
2
|
Lucarelli N, Yun D, Han D, Ginley B, Moon KC, Rosenberg A, Tomaszewski J, Han SS, Sarder P. Computational Integration of Renal Histology and Urinary Proteomics using Neural Networks. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2022; 12039:120390U. [PMID: 37817878 PMCID: PMC10563119 DOI: 10.1117/12.2613500] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/12/2023]
Abstract
Histological image data and molecular profiles provide context into renal condition. Often, a biopsy is drawn to diagnose or monitor a suspected kidney problem. However, molecular profiles can go beyond a pathologist's ability to see and diagnose. Using AI, we computationally incorporated urinary proteomic profiles with microstructural morphology from renal biopsy to investigate new and existing molecular links to image phenotypes. We studied whole slide images of periodic acid-Schiff stained renal biopsies from 56 DN patients matched with 2,038 proteins measured from each patient's urine. Using Seurat, we identified differentially expressed proteins in patients that developed end-stage renal disease within 2 years of biopsy. Glomeruli, globally sclerotic glomeruli, and tubules were segmented from WSI using our previously published HAIL pipeline. For each glomerulus, 315 handcrafted digital image features were measured, and for tubules, 207 features. We trained fully connected networks to predict urinary protein measurements that were differentially expressed between patients who did/ did not progress to ESRD within 2 years of biopsy. The input to this network was either glomerular or tubular histomorphological features in biopsy. Trained network weights were used as a proxy to rank which morphological features correlated most highly with specific urinary proteins. We identified significant image feature-protein pairs by ranking network weights by magnitude. We also looked at which features on average were most significant in predicting proteins. For both glomeruli and tubules, RGB color values and variance in PAS+ areas (specifically basement membrane for tubules) were, on average, more predictive of molecular profiles than other features. There is a strong connection between molecular profile and image phenotype, which can be elucidated through computational methods. These discovered links can provide insight to disease pathways, and discover new factors contributing to incidence and progression.
Collapse
Affiliation(s)
- Nicholas Lucarelli
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York, Buffalo, New York
| | - Donghwan Yun
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Dohyun Han
- Proteomics Core Facility, Biomedical Research Institute, Seoul National University Hospital, Seoul, Korea
| | - Brandon Ginley
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York, Buffalo, New York
| | - Kyung Chul Moon
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Avi Rosenberg
- Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland
| | - John Tomaszewski
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York, Buffalo, New York
| | - Seung Seok Han
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul, Korea
| | - Pinaki Sarder
- Department of Pathology and Anatomical Sciences, University at Buffalo – The State University of New York, Buffalo, New York
| |
Collapse
|
3
|
Chen W, Chen L, Tian R. An integrated strategy for highly sensitive phosphoproteome analysis from low micrograms of protein samples. Analyst 2018; 143:3693-3701. [DOI: 10.1039/c8an00792f] [Citation(s) in RCA: 16] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Phospho-SISPROT achieves highly sensitive phosphoproteome analysis from lower than 20 μg of cell lysates.
Collapse
Affiliation(s)
- Wendong Chen
- Department of Chemistry
- Southern University of Science and Technology
- Shenzhen 518055
- China
- SUSTech Academy for Advanced Interdisciplinary Studies
| | - Lan Chen
- Department of Chemistry
- Southern University of Science and Technology
- Shenzhen 518055
- China
| | - Ruijun Tian
- Department of Chemistry
- Southern University of Science and Technology
- Shenzhen 518055
- China
- Guangdong Provincial Key Laboratory of Cell Microenvironment and Disease Research
| |
Collapse
|
4
|
Sanchez-Lucas R, Mehta A, Valledor L, Cabello-Hurtado F, Romero-Rodrıguez MC, Simova-Stoilova L, Demir S, Rodriguez-de-Francisco LE, Maldonado-Alconada AM, Jorrin-Prieto AL, Jorrín-Novo JV. A year (2014-2015) of plants in Proteomics journal. Progress in wet and dry methodologies, moving from protein catalogs, and the view of classic plant biochemists. Proteomics 2016; 16:866-76. [PMID: 26621614 DOI: 10.1002/pmic.201500351] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/27/2015] [Revised: 10/26/2015] [Accepted: 11/04/2015] [Indexed: 12/23/2022]
Abstract
The present review is an update of the previous one published in Proteomics 2015 Reviews special issue [Jorrin-Novo, J. V. et al., Proteomics 2015, 15, 1089-1112] covering the July 2014-2015 period. It has been written on the bases of the publications that appeared in Proteomics journal during that period and the most relevant ones that have been published in other high-impact journals. Methodological advances and the contribution of the field to the knowledge of plant biology processes and its translation to agroforestry and environmental sectors will be discussed. This review has been organized in four blocks, with a starting general introduction (literature survey) followed by sections focusing on the methodology (in vitro, in vivo, wet, and dry), proteomics integration with other approaches (systems biology and proteogenomics), biological information, and knowledge (cell communication, receptors, and signaling), ending with a brief mention of some other biological and translational topics to which proteomics has made some contribution.
Collapse
Affiliation(s)
- Rosa Sanchez-Lucas
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain
| | - Angela Mehta
- Embrapa Recursos Genéticos e Biotecnologia (CENARGEN), Brasília, DF, Brazil
| | - Luis Valledor
- Department of Biology of Organisms and Systems (BOS), University of Oviedo, Oviedo, Spain
| | | | - M Cristina Romero-Rodrıguez
- Centro Multidisciplinario de Investigaciones Tecnológicas, and Departamento de Fitoquímica, Facultad de Ciencias Químicas, Universidad Nacional de Asunción, San Lorenzo, Paraguay
| | - Lyudmila Simova-Stoilova
- Plant Molecular Biology Department, Institute of Plant Physiology and Genetics, Bulgarian Academy of Sciences, Sofia, Bulgaria
| | - Sekvan Demir
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain
| | - Luis E Rodriguez-de-Francisco
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain.,INTEC-Sto. Domingo, Santo Domingo, República Dominicana
| | - Ana M Maldonado-Alconada
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain
| | - Ana L Jorrin-Prieto
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain
| | - Jesus V Jorrín-Novo
- Agroforestry and Plant Biochemistry and Proteomics Research Group, Department of Biochemistry and Molecular Biology, University of Córdoba-CeiA3, Córdoba, Spain
| |
Collapse
|
5
|
Affiliation(s)
- Nicholas M. Riley
- Genome Center of Wisconsin, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States
- Department of Chemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States
| | - Joshua J. Coon
- Genome Center of Wisconsin, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States
- Department of Chemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States
- Department of Biomolecular Chemistry, University of Wisconsin-Madison, Madison, Wisconsin 53706, United States
| |
Collapse
|
6
|
Mukherjee G, Claudia Röwer C, Koy C, Protzel C, Lorenz P, Thiesen HJ, Hakenberg OW, Glocker MO. Ultraviolet matrix-assisted laser desorption/ionization time-of-flight mass spectrometry for phosphopeptide analysis with a solidified ionic liquid matrix. EUROPEAN JOURNAL OF MASS SPECTROMETRY (CHICHESTER, ENGLAND) 2015; 21:65-77. [PMID: 26181280 DOI: 10.1255/ejms.1362] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/04/2023]
Abstract
A solidified ionic liquid matrix (SILM) consisting of 3-aminoquinoline, α-cyano-4- hydroxycinnamic acid and ammonium dihydrogen phosphate combines the benefits of liquid and solid MALDI matrices and proves to be well suitable for phosphopeptide analysis using MALDI-MS in the low femtomole range. Desalting and buffer exchange that typically follow after phosphopeptide elution from metal oxide affinity chromatography (MOAC) materials can be omitted. Shifting the pH from acidic to basic during target preparation causes slow matrix crystallization and homogeneous embedding of the analyte molecules, forming a uniform preparation from which (phospho)peptides can be ionized in high yields over long periods of time. The novel combination of MOAC-based phosphopeptide enrichment with SILM preparation has been developed with commercially available standard phosphopeptides and with α-casein as phosphorylated standard protein. The applicability of the streamlined phosphopeptide analysis procedure to cell biological and clinical samples has been tested (i) using affinity-enriched endogenous TRIM28 from cell cultures and (ii) by analysis of a two-dimensional gel-separated protein spot from a bladder cancer sample.
Collapse
Affiliation(s)
| | | | - Cornelia Koy
- Proteome Center Rostock, University of Rostock, Germany..
| | - Chris Protzel
- Urology Clinic and Polyclinic, University Medicine Rostock, Germany..
| | - Peter Lorenz
- Institute of Immunology, University Medicine Rostock, Germany..
| | | | - Oliver W Hakenberg
- Urology Clinic and Polyclinic, University Medicine Rostock, Germany. - rostock.de
| | | |
Collapse
|