Presenter(s)
Thomas Pelowitz
Abstract
Retroperitoneal fibrosis (RPF) is a rare inflammatory disease characterized by the formation of scar-like tissue in the retroperitoneum, which can lead to life-threatening obstructive nephropathy. RPF is typically a secondary disease, arising from various underlying conditions. Currently, no objective and highly accurate diagnostic methods exist. Identifying blood protein biomarkers specific to RPF could facilitate the development of objective minimally invasive diagnostic tests.
In this study, blood plasma samples were collected from 45 participants spanning 5 different primary causes of RPF, including idiopathic cases where no underlying condition was identified. Six participants without significant diseases at the time of sample collection served as healthy controls. From these plasma samples, the abundances of 7,293 proteins were measured.
A total of 176 proteins were found to be significantly differentially abundant in individuals with RPF compared to healthy controls. Additional comparisons identified distinct differentially expressed proteins associated with specific primary causes. Proteins shared across multiple comparisons offer insights into the common pathogenesis of RPF, while those unique to a single primary cause suggest mechanistic links between the underlying disease and RPF development.
Further analysis compared the blood proteomes of individuals with idiopathic RPF to individuals with a known related primary cause, assessing whether idiopathic cases are biologically distinct. A similar analysis examined whether RPF secondary to IgG4-related disease results in a significantly different plasma proteome than idiopathic RPF.
Finally, a machine learning approach was applied to classify individuals with RPF versus healthy controls. A machine learning pipeline was developed that trained a random forest classifier on 100 differentially expressed proteins, which achieved an average ROC-AUC of 0.809 (out of 1.000) across 100 bootstrapped trials. The pipeline was also used to test the potential of classifying various other comparisons that are of clinical interest. The success of this pipeline demonstrates the potential for blood-based classification of RPF for clinical use.
These findings highlight key proteomic differences associated with RPF and its primary causes, providing a foundation for improved diagnostic strategies and a deeper understanding of disease mechanisms.
College
College of Science & Engineering
Department
Computer Science
Campus
Winona
First Advisor/Mentor
Collin J. Engstrom
Start Date
4-24-2025 10:00 AM
End Date
4-24-2025 11:00 AM
Presentation Type
Poster Session
Format of Presentation or Performance
In-Person
Session
1b=10am-11am
Poster Number
54
Included in
Plasma Profiling Reveals Proteins Specific to Primary Disease Origin of Retroperitoneal Fibrosis
Retroperitoneal fibrosis (RPF) is a rare inflammatory disease characterized by the formation of scar-like tissue in the retroperitoneum, which can lead to life-threatening obstructive nephropathy. RPF is typically a secondary disease, arising from various underlying conditions. Currently, no objective and highly accurate diagnostic methods exist. Identifying blood protein biomarkers specific to RPF could facilitate the development of objective minimally invasive diagnostic tests.
In this study, blood plasma samples were collected from 45 participants spanning 5 different primary causes of RPF, including idiopathic cases where no underlying condition was identified. Six participants without significant diseases at the time of sample collection served as healthy controls. From these plasma samples, the abundances of 7,293 proteins were measured.
A total of 176 proteins were found to be significantly differentially abundant in individuals with RPF compared to healthy controls. Additional comparisons identified distinct differentially expressed proteins associated with specific primary causes. Proteins shared across multiple comparisons offer insights into the common pathogenesis of RPF, while those unique to a single primary cause suggest mechanistic links between the underlying disease and RPF development.
Further analysis compared the blood proteomes of individuals with idiopathic RPF to individuals with a known related primary cause, assessing whether idiopathic cases are biologically distinct. A similar analysis examined whether RPF secondary to IgG4-related disease results in a significantly different plasma proteome than idiopathic RPF.
Finally, a machine learning approach was applied to classify individuals with RPF versus healthy controls. A machine learning pipeline was developed that trained a random forest classifier on 100 differentially expressed proteins, which achieved an average ROC-AUC of 0.809 (out of 1.000) across 100 bootstrapped trials. The pipeline was also used to test the potential of classifying various other comparisons that are of clinical interest. The success of this pipeline demonstrates the potential for blood-based classification of RPF for clinical use.
These findings highlight key proteomic differences associated with RPF and its primary causes, providing a foundation for improved diagnostic strategies and a deeper understanding of disease mechanisms.