Dataset Information

Development of a Machine Learning Model to Predict Non-Durable Response to Anti-TNF Therapy in Crohn's Disease Using Transcriptome Imputed from Genotypes.

ABSTRACT: Almost half of patients show no primary or secondary response to monoclonal anti-tumor necrosis factor α (anti-TNF) antibody treatment for inflammatory bowel disease (IBD). Thus, the exact mechanisms of a non-durable response (NDR) remain inadequately defined. We used our genome-wide genotype data to impute expression values as features in training machine learning models to predict a NDR. Blood samples from various IBD cohorts were used for genotyping with the Korea Biobank Array. A total of 234 patients with Crohn's disease (CD) who received their first anti-TNF therapy were enrolled. The expression profiles of 6294 genes in whole-blood tissue imputed from the genotype data were combined with clinical parameters to train a logistic model to predict the NDR. The top two and three most significant features were genetic features (DPY19L3, GSTT1, and NUCB1), not clinical features. The logistic regression of the NDR vs. DR status in our cohort by the imputed expression levels showed that the β coefficients were positive for DPY19L3 and GSTT1, and negative for NUCB1, concordant with the known eQTL information. Machine learning models using imputed gene expression features effectively predicted NDR to anti-TNF agents in patients with CD.

SUBMITTER: Park SK

PROVIDER: S-EPMC9224874 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of a Machine Learning Model to Predict Non-Durable Response to Anti-TNF Therapy in Crohn's Disease Using Transcriptome Imputed from Genotypes.

Park Soo Kyung SK Kim Yea Bean YB Kim Sangsoo S Lee Chil Woo CW Choi Chang Hwan CH Kang Sang-Bum SB Kim Tae Oh TO Bang Ki Bae KB Chun Jaeyoung J Cha Jae Myung JM Im Jong Pil JP Kim Min Suk MS Ahn Kwang Sung KS Kim Seon-Young SY Park Dong Il DI

Journal of personalized medicine 20220609 6

Almost half of patients show no primary or secondary response to monoclonal anti-tumor necrosis factor α (anti-TNF) antibody treatment for inflammatory bowel disease (IBD). Thus, the exact mechanisms of a non-durable response (NDR) remain inadequately defined. We used our genome-wide genotype data to impute expression values as features in training machine learning models to predict a NDR. Blood samples from various IBD cohorts were used for genotyping with the Korea Biobank Array. A total of 23 ...[more]

PMID: 35743732

Similar Datasets

Project description:BackgroundUstekinumab and vedolizumab are both effective for treating Crohn's disease (CD). However, no head-to-head trials have been conducted thus far. We aimed to compare the effectiveness of ustekinumab and vedolizumab in CD patients either naïve or exposed to tumor necrosis factor-alpha inhibitors (TNFi).MethodsPatients treated with vedolizumab or ustekinumab for luminal CD were included from six centers in China from May 2020 to July 2023. Steroid-free remission, clinical remission, objective response, and remission at Weeks 26 and 52 were evaluated in a retrospective multicenter propensity score-weighted cohort.FindingsA total of 536 patients were included (386 ustekinumab, and 150 vedolizumab). After adjustment, ustekinumab showed higher rates of clinical remission (56.4% vs. 47.8%, P = 0.005), steroid-free remission (55.4% vs. 46.1%, P = 0.003), and objective response (67.8% vs. 42.7%, P < 0.001) than vedolizumab at Week 26. At Week 52, ustekinumab exhibited significantly higher rates of clinical remission (65.8% vs. 37.5%, P < 0.001), steroid-free remission (65.8% vs. 37.5%, P < 0.001), objective response (66.7% vs. 23.8%, P < 0.001), and objective remission (31.4% vs. 12.7%, P < 0.001). Subgroup analyses revealed that ustekinumab had higher rates of clinical remission, steroid-free remission, and objective response at Weeks 26 and 52, and objective remission at Week 52 in TNFi-exposed patients, while ustekinumab showed higher rates of objective response at Weeks 26 and 52 and clinical remission, steroid-free remission and objective remission at Week 52 in TNFi-naïve patients. Adverse event rates were similar between the groups (4.9% ustekinumab vs. 6.7% vedolizumab, P = 0.423).InterpretationUstekinumab showed superior clinical and objective outcomes compared to vedolizumab, with comparable safety outcomes. The therapeutic superiority was observed in both short-term and long-term phases in TNFi-exposed patients, and the long-term phase in TNFi-naïve patients.FundingNational Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Key Research Projects of the Sixth Affiliated Hospital, Sun Yat-sen University, the program of Guangdong Provincial Clinical Research Center for Digestive Diseases, and National Key Clinical Discipline.

Dataset Information

Development of a Machine Learning Model to Predict Non-Durable Response to Anti-TNF Therapy in Crohn's Disease Using Transcriptome Imputed from Genotypes.

Publications

Development of a Machine Learning Model to Predict Non-Durable Response to Anti-TNF Therapy in Crohn's Disease Using Transcriptome Imputed from Genotypes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets