Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis
Primary sclerosing cholangitis (PSC) is a rare, progressive disease, characterized by inflammation and fibrosis of the bile ducts, lacking reliable prognostic biomarkers for disease activity. Machine learning applied to broad proteomic profiling of sera allowed for the discovery of markers of diseas...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
MDPI
2024
|
| _version_ | 1811139664342417408 |
|---|---|
| author | Snir, T Greenman, R Aricha, R Frankel, M Lawler, J Saffioti, F Pinzani, M Thorburn, D Mor, A Vaknin, I |
| author_facet | Snir, T Greenman, R Aricha, R Frankel, M Lawler, J Saffioti, F Pinzani, M Thorburn, D Mor, A Vaknin, I |
| author_sort | Snir, T |
| collection | OXFORD |
| description | Primary sclerosing cholangitis (PSC) is a rare, progressive disease, characterized by inflammation and fibrosis of the bile ducts, lacking reliable prognostic biomarkers for disease activity. Machine learning applied to broad proteomic profiling of sera allowed for the discovery of markers of disease presence, severity, and cirrhosis and the exploration of the involvement of CCL24, a chemokine with fibro-inflammatory activity. Sera from 30 healthy controls and 45 PSC patients were profiled with proximity extension assay, quantifying the expression of 2870 proteins, and used to train an elastic net model. Proteins that contributed most to the model were tested for correlation to enhanced liver fibrosis (ELF) score and used to perform pathway analysis. Statistical modeling for the presence of cirrhosis was performed with principal component analysis (PCA), and receiver operating characteristics (ROC) curves were used to assess the useability of potential biomarkers. The model successfully predicted the presence of PSC, where the top-ranked proteins were associated with cell adhesion, immune response, and inflammation, and each had an area under receiver operator characteristic (AUROC) curve greater than 0.9 for disease presence and greater than 0.8 for ELF score. Pathway analysis showed enrichment for functions associated with PSC, overlapping with pathways enriched in patients with high levels of CCL24. Patients with cirrhosis showed higher levels of CCL24. This data-driven approach to characterize PSC and its severity highlights potential serum protein biomarkers and the importance of CCL24 in the disease, implying its therapeutic potential in PSC. |
| first_indexed | 2024-09-25T04:09:41Z |
| format | Journal article |
| id | oxford-uuid:e4f581ff-b1df-42a3-bef7-61ac0a0f0bbc |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-09-25T04:09:41Z |
| publishDate | 2024 |
| publisher | MDPI |
| record_format | dspace |
| spelling | oxford-uuid:e4f581ff-b1df-42a3-bef7-61ac0a0f0bbc2024-06-07T20:08:13ZMachine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to CirrhosisJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:e4f581ff-b1df-42a3-bef7-61ac0a0f0bbcEnglishJisc Publications RouterMDPI2024Snir, TGreenman, RAricha, RFrankel, MLawler, JSaffioti, FPinzani, MThorburn, DMor, AVaknin, IPrimary sclerosing cholangitis (PSC) is a rare, progressive disease, characterized by inflammation and fibrosis of the bile ducts, lacking reliable prognostic biomarkers for disease activity. Machine learning applied to broad proteomic profiling of sera allowed for the discovery of markers of disease presence, severity, and cirrhosis and the exploration of the involvement of CCL24, a chemokine with fibro-inflammatory activity. Sera from 30 healthy controls and 45 PSC patients were profiled with proximity extension assay, quantifying the expression of 2870 proteins, and used to train an elastic net model. Proteins that contributed most to the model were tested for correlation to enhanced liver fibrosis (ELF) score and used to perform pathway analysis. Statistical modeling for the presence of cirrhosis was performed with principal component analysis (PCA), and receiver operating characteristics (ROC) curves were used to assess the useability of potential biomarkers. The model successfully predicted the presence of PSC, where the top-ranked proteins were associated with cell adhesion, immune response, and inflammation, and each had an area under receiver operator characteristic (AUROC) curve greater than 0.9 for disease presence and greater than 0.8 for ELF score. Pathway analysis showed enrichment for functions associated with PSC, overlapping with pathways enriched in patients with high levels of CCL24. Patients with cirrhosis showed higher levels of CCL24. This data-driven approach to characterize PSC and its severity highlights potential serum protein biomarkers and the importance of CCL24 in the disease, implying its therapeutic potential in PSC. |
| spellingShingle | Snir, T Greenman, R Aricha, R Frankel, M Lawler, J Saffioti, F Pinzani, M Thorburn, D Mor, A Vaknin, I Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title | Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title_full | Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title_fullStr | Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title_full_unstemmed | Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title_short | Machine Learning Identifies Key Proteins in Primary Sclerosing Cholangitis Progression and Links High CCL24 to Cirrhosis |
| title_sort | machine learning identifies key proteins in primary sclerosing cholangitis progression and links high ccl24 to cirrhosis |
| work_keys_str_mv | AT snirt machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT greenmanr machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT arichar machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT frankelm machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT lawlerj machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT saffiotif machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT pinzanim machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT thorburnd machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT mora machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis AT vaknini machinelearningidentifieskeyproteinsinprimarysclerosingcholangitisprogressionandlinkshighccl24tocirrhosis |