Novel DNA methylome biomarkers associated with adalimumab response in rheumatoid arthritis patients
Bibliographic record
Abstract
Background and aims: Rheumatoid arthritis (RA) patients are currently treated with biological agents mostly aimed at cytokine blockade, such as tumor necrosis factor-alpha (TNFα). Currently, there are no biomarkers to predict therapy response to these agents. Here, we aimed to predict response to adalimumab (ADA) treatment in RA patients using DNA methylation in peripheral blood (PBL). Methods: DNA methylation profiling on whole peripheral blood from 92 RA patients before the start of ADA treatment was determined using Illumina HumanMethylationEPIC BeadChip array. After 6 months, treatment response was assessed according to the European Alliance of Associations for Rheumatology (EULAR) criteria for disease activity. Patients were classified as responders (Disease Activity Score in 28 Joints (DAS28) < 3.2 or decrease of 1.2 points) or as non-responders (DAS28 > 5.1 or decrease of less than 0.6 points). Machine learning models were built through stability-selected gradient boosting to predict response prior to ADA treatment with predictor DNA methylation markers. Results: Of the 94 RA patients, we classified 49 and 43 patients as responders and non-responders, respectively. We were capable of differentiating responders from non-responders with a high performance (area under the curve (AUC) 0.76) using a panel of 27 CpGs. These classifier CpGs are annotated to genes involved in immunological and pathophysiological pathways related to RA such as T-cell signaling, B-cell pathology, and angiogenesis. Conclusion: Our findings indicate that the DNA methylome of PBL provides discriminative capabilities in discerning responders and non-responders to ADA treatment and may therefore serve as a tool for therapy prediction.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".