Dataset Information

Supervised machine learning and logistic regression identifies novel epistatic risk factors with PTPN22 for rheumatoid arthritis.

ABSTRACT: Investigating genetic interactions (epistasis) has proven difficult despite the recent advances of both laboratory methods and statistical developments. With no 'best' statistical approach available, combining several analytical methods may be optimal for detecting epistatic interactions. Using a multi-stage analysis that incorporated supervised machine learning and methods of association testing, we investigated epistatic interactions with a well-established genetic factor (PTPN22 1858T) in a complex autoimmune disease (rheumatoid arthritis (RA)). Our analysis consisted of four principal stages: Stage I (data reduction)-identifying candidate chromosomal regions in 292 affected sibling pairs, by predicting PTPN22 concordance using multipoint identity-by-descent probabilities and a supervised machine learning algorithm (Random Forests); Stage II (extension analysis)-testing detailed genetic data within candidate chromosomal regions for epistasis with PTPN22 1858T in 677 cases and 750 controls using logistic regression; Stage III (replication analysis)-confirmation of epistatic interactions in 947 cases and 1756 controls; Stage IV (combined analysis)-a pooled analysis including all 1624 RA cases and 2506 control subjects for final estimates of effect size. A total of seven replicating epistatic interactions were identified. SNP variants within CDH13, MYO3A, CEP72 and near WFDC1 showed significant evidence for interaction with PTPN22, affecting susceptibility to RA.

SUBMITTER: Briggs FB

PROVIDER: S-EPMC3118040 | biostudies-literature | 2010 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Supervised machine learning and logistic regression identifies novel epistatic risk factors with PTPN22 for rheumatoid arthritis.

Briggs F B S FB Ramsay P P PP Madden E E Norris J M JM Holers V M VM Mikuls T R TR Sokka T T Seldin M F MF Gregersen P K PK Criswell L A LA Barcellos L F LF

Genes and immunity 20100121 3

Investigating genetic interactions (epistasis) has proven difficult despite the recent advances of both laboratory methods and statistical developments. With no 'best' statistical approach available, combining several analytical methods may be optimal for detecting epistatic interactions. Using a multi-stage analysis that incorporated supervised machine learning and methods of association testing, we investigated epistatic interactions with a well-established genetic factor (PTPN22 1858T) in a c ...[more]

PMID: 20090771

Similar Datasets

Project description:The goals of this study were to examine whether machine-learning algorithms outperform multivariable logistic regression in the prediction of insufficient response to methotrexate (MTX); secondly, to examine which features are essential for correct prediction; and finally, to investigate whether the best performing model specifically identifies insufficient responders to MTX (combination) therapy. The prediction of insufficient response (3-month Disease Activity Score 28-Erythrocyte-sedimentation rate (DAS28-ESR) > 3.2) was assessed using logistic regression, least absolute shrinkage and selection operator (LASSO), random forest, and extreme gradient boosting (XGBoost). The baseline features of 355 rheumatoid arthritis (RA) patients from the "treatment in the Rotterdam Early Arthritis CoHort" (tREACH) and the U-Act-Early trial were combined for analyses. The model performances were compared using area under the curve (AUC) of receiver operating characteristic (ROC) curves, 95% confidence intervals (95% CI), and sensitivity and specificity. Finally, the best performing model following feature selection was tested on 101 RA patients starting tocilizumab (TCZ)-monotherapy. Logistic regression (AUC = 0.77 95% CI: 0.68-0.86) performed as well as LASSO (AUC = 0.76, 95% CI: 0.67-0.85), random forest (AUC = 0.71, 95% CI: 0.61 = 0.81), and XGBoost (AUC = 0.70, 95% CI: 0.61-0.81), yet logistic regression reached the highest sensitivity (81%). The most important features were baseline DAS28 (components). For all algorithms, models with six features performed similarly to those with 16. When applied to the TCZ-monotherapy group, logistic regression's sensitivity significantly dropped from 83% to 69% (p = 0.03). In the current dataset, logistic regression performed equally well compared to machine-learning algorithms in the prediction of insufficient response to MTX. Models could be reduced to six features, which are more conducive for clinical implementation. Interestingly, the prediction model was specific to MTX (combination) therapy response.

Project description:Tumor progression includes the obtainment of progenitor and stem cell-like features and the gradual loss of a differentiated phenotype. Stemness was defined as the potential for differentiation and self-renewal from the cell of origin. Previous studies have confirmed the effective application of stemness in a number of malignancies. However, the mechanisms underlying the growth and maintenance of multiple myeloma (MM) stem cells remain unclear. We calculated the stemness index for samples of MM by utilizing a novel one-class logistic regression (OCLR) machine learning algorithm and found that mRNA expression-based stemness index (mRNAsi) was an independent prognostic factor of MM. Based on the same cutoff value, mRNAsi could stratify MM patients into low and high groups with different outcomes. We identified 127 stemness-related signatures using weighted gene co-expression network analysis (WGCNA) and differential expression analysis. Functional annotation and pathway enrichment analysis indicated that these genes were mainly involved in the cell cycle, cell differentiation, and DNA replication and repair. Using the molecular complex detection (MCODE) algorithm, we identified 34 pivotal signatures. Meanwhile, we conducted unsupervised clustering and classified the MM cohorts into three MM stemness (MMS) clusters with distinct prognoses. Samples in MMS-cluster3 possessed the highest stemness fractions and the worst prognosis. Additionally, we applied the ESTIMATE algorithm to infer differential immune infiltration among the three MMS clusters. The immune core and stromal score were significantly lower in MMS-cluster3 than in the other clusters, supporting the negative relation between stemness and anticancer immunity. Finally, we proposed a prognostic nomogram that allows for individualized assessment of the 3- and 5-year overall survival (OS) probabilities among patients with MM. Our study comprehensively assessed the MM stemness index based on large cohorts and built a 34-gene based classifier for predicting prognosis and potential strategies for stemness treatment.

Project description:Most human cancers develop from stem and progenitor cell populations through the sequential accumulation of various genetic and epigenetic alterations. Cancer stem cells have been identified from medulloblastoma (MB), but a comprehensive understanding of MB stemness, including the interactions between the tumor immune microenvironment and MB stemness, is lacking. Here, we employed a trained stemness index model based on an existent one-class logistic regression (OCLR) machine-learning method to score MB samples; we then obtained two stemness indices, a gene expression-based stemness index (mRNAsi) and a DNA methylation-based stemness index (mDNAsi), to perform an integrated analysis of MB stemness in a cohort of primary cancer samples (n = 763). We observed an inverse trend between mRNAsi and mDNAsi for MB subgroup and metastatic status. By applying the univariable Cox regression analysis, we found that mRNAsi significantly correlated with overall survival (OS) for all MB patients, whereas mDNAsi had no significant association with OS for all MB patients. In addition, by combining the Lasso-penalized Cox regression machine-learning approach with univariate and multivariate Cox regression analyses, we identified a stemness-related gene expression signature that accurately predicted survival in patients with Sonic hedgehog (SHH) MB. Furthermore, positive correlations between mRNAsi and prognostic copy number aberrations in SHH MB, including MYCN amplifications and GLI2 amplifications, were detected. Analyses of the immune microenvironment revealed unanticipated correlations of MB stemness with infiltrating immune cells. Lastly, using the Connectivity Map, we identified potential drugs targeting the MB stemness signature. Our findings based on stemness indices might advance the development of objective diagnostic tools for quantitating MB stemness and lead to novel biomarkers that predict the survival of patients with MB or the efficacy of strategies targeting MB stem cells.

Project description:ObjectiveTo predict preterm birth in nulliparous women using logistic regression and machine learning.DesignPopulation-based retrospective cohort.ParticipantsNulliparous women (N = 112,963) with a singleton gestation who gave birth between 20-42 weeks gestation in Ontario hospitals from April 1, 2012 to March 31, 2014.MethodsWe used data during the first and second trimesters to build logistic regression and machine learning models in a "training" sample to predict overall and spontaneous preterm birth. We assessed model performance using various measures of accuracy including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) in an independent "validation" sample.ResultsDuring the first trimester, logistic regression identified 13 variables associated with preterm birth, of which the strongest predictors were diabetes (Type I: adjusted odds ratio (AOR): 4.21; 95% confidence interval (CI): 3.23-5.42; Type II: AOR: 2.68; 95% CI: 2.05-3.46) and abnormal pregnancy-associated plasma protein A concentration (AOR: 2.04; 95% CI: 1.80-2.30). During the first trimester, the maximum AUC was 60% (95% CI: 58-62%) with artificial neural networks in the validation sample. During the second trimester, 17 variables were significantly associated with preterm birth, among which complications during pregnancy had the highest AOR (13.03; 95% CI: 12.21-13.90). During the second trimester, the AUC increased to 65% (95% CI: 63-66%) with artificial neural networks in the validation sample. Including complications during the pregnancy yielded an AUC of 80% (95% CI: 79-81%) with artificial neural networks. All models yielded 94-97% negative predictive values for spontaneous PTB during the first and second trimesters.ConclusionAlthough artificial neural networks provided slightly higher AUC than logistic regression, prediction of preterm birth in the first trimester remained elusive. However, including data from the second trimester improved prediction to a moderate level by both logistic regression and machine learning approaches.

Dataset Information

Supervised machine learning and logistic regression identifies novel epistatic risk factors with PTPN22 for rheumatoid arthritis.

Publications

Supervised machine learning and logistic regression identifies novel epistatic risk factors with PTPN22 for rheumatoid arthritis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets