Dataset Information

Feature selection using a one dimensional naive Bayes' classifier increases the accuracy of support vector machine classification of CDR3 repertoires.

ABSTRACT:

Motivation

Somatic DNA recombination, the hallmark of vertebrate adaptive immunity, has the potential to generate a vast diversity of antigen receptor sequences. How this diversity captures antigen specificity remains incompletely understood. In this study we use high throughput sequencing to compare the global changes in T cell receptor ? chain complementarity determining region 3 (CDR3?) sequences following immunization with ovalbumin administered with complete Freund's adjuvant (CFA) or CFA alone.

Results

The CDR3? sequences were deconstructed into short stretches of overlapping contiguous amino acids. The motifs were ranked according to a one-dimensional Bayesian classifier score comparing their frequency in the repertoires of the two immunization classes. The top ranking motifs were selected and used to create feature vectors which were used to train a support vector machine. The support vector machine achieved high classification scores in a leave-one-out validation test reaching >90% in some cases.

Summary

The study describes a novel two-stage classification strategy combining a one-dimensional Bayesian classifier with a support vector machine. Using this approach we demonstrate that the frequency of a small number of linear motifs three amino acids in length can accurately identify a CD4 T cell response to ovalbumin against a background response to the complex mixture of antigens which characterize Complete Freund's Adjuvant.

Availability and implementation

The sequence data is available at www.ncbi.nlm.nih.gov/sra/?term¼SRP075893 . The Decombinator package is available at github.com/innate2adaptive/Decombinator . The R package e1071 is available at the CRAN repository https://cran.r-project.org/web/packages/e1071/index.html .

Contact

b.chain@ucl.ac.uk.

Supplementary information

Supplementary data are available at Bioinformatics online.

SUBMITTER: Cinelli M

PROVIDER: S-EPMC5860388 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Feature selection using a one dimensional naïve Bayes' classifier increases the accuracy of support vector machine classification of CDR3 repertoires.

Cinelli Mattia M Sun Yuxin Y Best Katharine K Heather James M JM Reich-Zeliger Shlomit S Shifrut Eric E Friedman Nir N Shawe-Taylor John J Chain Benny B

Bioinformatics (Oxford, England) 20170401 7

<h4>Motivation</h4>Somatic DNA recombination, the hallmark of vertebrate adaptive immunity, has the potential to generate a vast diversity of antigen receptor sequences. How this diversity captures antigen specificity remains incompletely understood. In this study we use high throughput sequencing to compare the global changes in T cell receptor β chain complementarity determining region 3 (CDR3β) sequences following immunization with ovalbumin administered with complete Freund's adjuvant (CFA) ...[more]

PMID: 28073756

Similar Datasets

Project description:Verbal autopsy (VA) deals with post-mortem surveys about deaths, mostly in low and middle income countries, where the majority of deaths occur at home rather than a hospital, for retrospective assignment of causes of death (COD) and subsequently evidence-based health system strengthening. Automated algorithms for VA COD assignment have been developed and their performance has been assessed against physician and clinical diagnoses. Since the performance of automated classification methods remains low, we aimed to enhance the Naïve Bayes Classifier (NBC) algorithm to produce better ranked COD classifications on 26,766 deaths from four globally diverse VA datasets compared to some of the leading VA classification methods, namely Tariff, InterVA-4, InSilicoVA and NBC. We used a different strategy, by training multiple NBC algorithms using the one-against-all approach (OAA-NBC). To compare performance, we computed the cumulative cause-specific mortality fraction (CSMF) accuracies for population-level agreement from rank one to five COD classifications. To assess individual-level COD assignments, cumulative partially-chance corrected concordance (PCCC) and sensitivity was measured for up to five ranked classifications. Overall results show that OAA-NBC consistently assigns CODs that are the most alike physician and clinical COD assignments compared to some of the leading algorithms based on the cumulative CSMF accuracy, PCCC and sensitivity scores. The results demonstrate that our approach improves the performance of classification (sensitivity) by between 6% and 8% compared with other VA algorithms. Population-level agreements for OAA-NBC and NBC were found to be similar or higher than the other algorithms used in the experiments. Although OAA-NBC still requires improvement for individual-level COD assignment, the one-against-all approach improved its ability to assign CODs that more closely resemble physician or clinical COD classifications compared to some of the other leading VA classifiers.

Project description:BackgroundOntology has attracted substantial attention from both academia and industry. Handling uncertainty reasoning is important in researching ontology. For example, when a patient is suffering from cirrhosis, the appearance of abdominal vein varices is four times more likely than the presence of bitter taste. Such medical knowledge is crucial for decision-making in various medical applications but is missing from existing medical ontologies. In this paper, we aim to discover medical knowledge probabilities from electronic medical record (EMR) texts to enrich ontologies. First, we build an ontology by identifying meaningful entity mentions from EMRs. Then, we propose a symptom-dependency-aware naïve Bayes classifier (SDNB) that is based on the assumption that there is a level of dependency among symptoms. To ensure the accuracy of the diagnostic classification, we incorporate the probability of a disease into the ontology via innovative approaches.ResultsWe conduct a series of experiments to evaluate whether the proposed method can discover meaningful and accurate probabilities for medical knowledge. Based on over 30,000 deidentified medical records, we explore 336 abdominal diseases and 81 related symptoms. Among these 336 gastrointestinal diseases, the probabilities of 31 diseases are obtained via our method. These 31 probabilities of diseases and 189 conditional probabilities between diseases and the symptoms are added into the generated ontology.ConclusionIn this paper, we propose a medical knowledge probability discovery method that is based on the analysis and extraction of EMR text data for enriching a medical ontology with probability information. The experimental results demonstrate that the proposed method can effectively identify accurate medical knowledge probability information from EMR data. In addition, the proposed method can efficiently and accurately calculate the probability of a patient suffering from a specified disease, thereby demonstrating the advantage of combining an ontology and a symptom-dependency-aware naïve Bayes classifier.

Project description:The present study aimed to identify the feature genes associated with smoking in lung adenocarcinoma (LAC) samples and explore the underlying mechanism. Three gene expression datasets of LAC samples were downloaded from the Gene Expression Omnibus database through pre?set criteria and the expression data were processed using meta?analysis. Differentially expressed genes (DEGs) between LAC samples of smokers and non?smokers were identified using limma package in R. The classification accuracy of selected DEGs were visualized using hierarchical clustering analysis in R language. A protein?protein interaction (PPI) network was constructed using gene interaction data from the Human Protein Reference Database for the DEGs. Betweenness centrality was calculated for each node in the network and genes with the greatest BC values were utilized for the construction of the support vector machine (SVM) classifier. The dataset GSE43458 was used as the training dataset for the construction and the other datasets (GSE12667 and GSE10072) were used as the validation datasets. The classification accuracy of the classifier was tested using sensitivity, specificity, positive predictive value, negative predictive value and area under curve parameters with the pROC package in R language. The feature genes in the SVM classifier were subjected to pathway enrichment analysis using Fisher's exact test. A total of 347 genes were identified to be differentially expressed between samples of smokers and non?smokers. The PPI network of DEGs were comprised of 202 nodes and 300 edges. An SVM classifier comprised of 26 feature genes was constructed to distinguish between different LAC samples, with prediction accuracies for the GSE43458, GSE12667 and GSE10072 datasets of 100, 100 and 94.83%, respectively. Furthermore, the 26 feature genes that were significantly enriched in 9 overrepresented biological pathways, including extracellular matrix?receptor interaction, proteoglycans in cancer, cell adhesion molecules, p53 signaling pathway, microRNAs in cancer and apoptosis, were identified to be smoking?related genes in LAC. In conclusion, an SVM classifier with a high prediction accuracy for smoking and non?smoking samples was obtained. The genes in the classifier may likely be the potential feature genes associated with the development of patients with LAC who smoke.