SYSTEMIC LUPUS ERYTHEMATOSUS DISEASE COURSE CLASSIFICATION FROM IMMUNOGLOBULIN-G-DERIVED N-GLYCANS ANALYZED VIA THE GLYCOTYPER™ LIQUID BIOPSY PLATFORM
Bibliographic record
Abstract
PT010 / #726 Topic: AS04 - Biomarkers POSTER TOUR 02: RECENT INSIGHTS ON THE PATHOGENESIS OF LUPUS NEPHRITIS 23-05-2025 10:00 AM - 10:40 AM Background/Purpose Systemic lupus erythematosus (SLE) is a chronic autoimmune condition characterized by autoantibody-driven immune-complex formation. Lupus nephritis (LN), a kidney disease caused by SLE, develops due to immune-complex deposition in the glomeruli. The immune activation caused by these glomerular aggregates leads to inflammation, tissue damage, and potentially kidney failure. Early diagnosis and treatment of LN with immunosuppressants are of critical importance to prevent end-stage renal disease. While renal biopsy is the current standard of care for LN diagnosis, alternative liquid-biopsy-based approaches are urgently needed to avoid biopsy-associated complications. Methods In order to characterize changes in immunoglobulin N-glycan expression as a function of lupus disease course, we applied the GlycoTyper™ platform, a MALDI-MS-based method for N-glycan analysis, to urine samples from 114 healthy controls (HC), 116 SLE patients, and 210 LN patients. In this study, anti-IgG antibody arrays were printed on amine-reactive slides; multi-well modules were then applied to enable the analysis of 16 patient samples per slide. N-glycans were released from captured IgG using PNGase F before being embedded in a chemical matrix for analysis by MALDI-MS (Bruker timsTOF fleX). A quality strategy consisting of preacquisition system suitability tests and on-slide QC arrays was employed to ensure the robustness of the platform Results Using N-glycan profiles and 2 demographic characteristics (age and sex), a multiclass random forest classifier was generated with an area under the receiver operating characteristic curve of 0.87 for differentiating LN patients from HCs and SLE patients without kidney disease. This model demonstrated a sensitivity of 0.9 and specificity of 0.88 on a validation data set in a 1-vs-all classification scheme with LN treated as the positive case. For model generation, N-glycan intensities were normalized and transformed to centered log ratios (CLRs). While the classifier performed well in differentiating patients with LN from HC or SLE using IgG-derived N-glycans from urine samples, N-glycan profiles from HC and SLE patient samples showed no statistically significant differences. A subsequent longitudinal analysis of LN patients randomly sorted into 3 immunosuppressant treatment groups identified 4 N-glycans whose abundances were associated at statistically significant levels with an improved urine protein-to-creatinine ratio (UPCR), a key marker of LN treatment response. Conclusions We conclude that glycoproteomic characterization of IgG provides a novel and powerful analytical tool to differentiate SLE with and without renal involvement, potentially predict likelihood of progression from SLE to lupus nephritis, and may allow prediction of treatment response in lupus nephritis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".