Dataset Information

Multiomics and Machine Learning Accurately Predict Clinical Response to Adalimumab and Etanercept Therapy in Patients With Rheumatoid Arthritis.

ABSTRACT:

Objective

To predict response to anti-tumor necrosis factor (anti-TNF) prior to treatment in patients with rheumatoid arthritis (RA), and to comprehensively understand the mechanism of how different RA patients respond differently to anti-TNF treatment.

Methods

Gene expression and/or DNA methylation profiling on peripheral blood mononuclear cells (PBMCs), monocytes, and CD4+ T cells obtained from 80 RA patients before they began either adalimumab (ADA) or etanercept (ETN) therapy was studied. After 6 months, treatment response was evaluated according to the European League Against Rheumatism criteria for disease response. Differential expression and methylation analyses were performed to identify the response-associated transcription and epigenetic signatures. Using these signatures, machine learning models were built by random forest algorithm to predict response prior to anti-TNF treatment, and were further validated by a follow-up study.

Results

Transcription signatures in ADA and ETN responders were divergent in PBMCs, and this phenomenon was reproduced in monocytes and CD4+ T cells. The genes up-regulated in CD4+ T cells from ADA responders were enriched in the TNF signaling pathway, while very few pathways were differential in monocytes. Differentially methylated positions (DMPs) were strongly hypermethylated in responders to ETN but not to ADA. The machine learning models for the prediction of response to ADA and ETN using differential genes reached an overall accuracy of 85.9% and 79%, respectively. The models using DMPs reached an overall accuracy of 84.7% and 88% for ADA and ETN, respectively. A follow-up study validated the high performance of these models.

Conclusion

Our findings indicate that machine learning models based on molecular signatures accurately predict response before ADA and ETN treatment, paving the path toward personalized anti-TNF treatment.

SUBMITTER: Tao W

PROVIDER: S-EPMC7898388 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multiomics and Machine Learning Accurately Predict Clinical Response to Adalimumab and Etanercept Therapy in Patients With Rheumatoid Arthritis.

Tao Weiyang W Concepcion Arno N AN Vianen Marieke M Marijnissen Anne C A ACA Lafeber Floris P G J FPGJ Radstake Timothy R D J TRDJ Pandit Aridaman A

Arthritis & rheumatology (Hoboken, N.J.) 20201226 2

<h4>Objective</h4>To predict response to anti-tumor necrosis factor (anti-TNF) prior to treatment in patients with rheumatoid arthritis (RA), and to comprehensively understand the mechanism of how different RA patients respond differently to anti-TNF treatment.<h4>Methods</h4>Gene expression and/or DNA methylation profiling on peripheral blood mononuclear cells (PBMCs), monocytes, and CD4+ T cells obtained from 80 RA patients before they began either adalimumab (ADA) or etanercept (ETN) therapy ...[more]

PMID: 32909363

Similar Datasets

Project description:BACKGROUND:Patient perceptions of treatment success, including satisfaction/preference, may complement clinical efficacy assessments. OBJECTIVE:Our objective was to evaluate satisfaction with subcutaneous golimumab and its auto-injector in patients with rheumatoid arthritis (RA) and an inadequate adalimumab/etanercept response. METHODS:In the multicenter, assessor-blinded GO-SAVE study, 433 patients with active RA (28-joint Disease Activity Score incorporating erythrocyte sedimentation rate [DAS28-ESR] ? 3.6 and six or more swollen and six or more tender joints) despite methotrexate and past adalimumab/etanercept treatment received open-label subcutaneous golimumab 50 mg every 4 weeks (q4w) through week 12. Week 16 responders (DAS28-ESR improvement from baseline > 1.2 and score ? 3.2) continued therapy through week 52; nonresponders were randomized (1:2) to double-blind subcutaneous golimumab 50 mg q4w or intravenous golimumab 2 mg/kg [weeks 16, 20, every 8 weeks (q8w)]. Patients rated satisfaction with their injection experience on a 5-point scale (1 = very dissatisfied; 5 = very satisfied) at screening, week 8 (all enrolled patients), and week 44 (for patients continuing open-label subcutaneous golimumab 50 mg q4w). Discomfort, pain, stinging, burning, and redness related to injection were assessed (none, mild, moderate, severe). RESULTS:Similar proportions of patients (N = 433) had most recently received adalimumab (50.3%) or etanercept (49.7%) prior to golimumab. Overall satisfaction (somewhat/very) with the golimumab injection experience was reported by 84.4% of patients at week 8 versus 63.4% of patients who were satisfied with prior adalimumab/etanercept. Patients receiving open-label subcutaneous golimumab through week 44 (N = 75) reported much less discomfort (60.9%), redness (60.9%), pain (59.4%), stinging (67.2%), and burning (65.6%) with the golimumab injection than with their previous tumor necrosis factor antagonist medication injection. CONCLUSION:Most patients with RA receiving golimumab following adalimumab/etanercept inadequate response were satisfied with their overall golimumab experience, including its auto-injector versus their previous injection device. CLINICAL TRIALS.GOV: NCT01004432; EudraCT 2009-010582-23.

Dataset Information

Multiomics and Machine Learning Accurately Predict Clinical Response to Adalimumab and Etanercept Therapy in Patients With Rheumatoid Arthritis.

Objective

Methods

Results

Conclusion

Publications

Multiomics and Machine Learning Accurately Predict Clinical Response to Adalimumab and Etanercept Therapy in Patients With Rheumatoid Arthritis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets