Comparative study of classification algorithms for immunosignaturing data

Abstract

BackgroundHigh-throughput technologies such as DNA, RNA, protein, antibody and peptide microarrays are often used to examine differences across drug treatments, diseases, transgenic animals, and others. Typically one trains a classification system by gathering large amounts of probe-level data, selecting informative features, and classifies test samples using a small number of features. As new microarrays are invented, classification systems that worked well for other array types may not be ideal. Expression microarrays, arguably one of the most prevalent array types, have been used for years to help develop classification algorithms. Many biological assumptions are built into classifiers that were designed for these types of data. One of the more problematic is the assumption of independence, both at the probe level and again at the biological level. Probes for RNA transcripts are designed to bind single transcripts. At the biological level, many genes have dependencies across transcriptional pathways where co-regulation of transcriptional units may make many genes appear as being completely dependent. Thus, algorithms that perform well for gene expression data may not be suitable when other technologies with different binding characteristics exist. The immunosignaturing microarray is based on complex mixtures of antibodies binding to arrays of random sequence peptides. It relies on many-to-many binding of antibodies to the random sequence peptides. Each peptide can bind multiple antibodies and each antibody can bind multiple peptides. This technology has been shown to be highly reproducible and appears promising for diagnosing a variety of disease states. However, it is not clear what is the optimal classification algorithm for analyzing this new type of data.ResultsWe characterized several classification algorithms to analyze immunosignaturing data. We selected several datasets that range from easy to difficult to classify, from simple monoclonal binding to complex binding patterns in asthma patients. We then classified the biological samples using 17 different classification algorithms. Using a wide variety of assessment criteria, we found ‘Naïve Bayes’ far more useful than other widely used methods due to its simplicity, robustness, speed and accuracy.Conclusions‘Naïve Bayes’ algorithm appears to accommodate the complex patterns hidden within multilayered immunosignaturing microarray data due to its fundamental mathematical properties.

Scalable high-density peptide arrays for comprehensive health monitoring

“…Previous studies indicated information content should peak between 20 and 100 features per disease 16 and the performance of linear classifiers tends to suffer as the total number of features increases 29 . The top 50 informative peptides and important sequence motifs are listed in Supplementary Tables 1 and 2.…”

General Assessment of Humoral Activity in Healthy Humans

“…By using data from many features, immunosignatures can accommodate variations in the nondisease population, which may include an endemic population having substantial subclinical pathogen exposures. Analysis can be very basic, with statistical methods used to select features and probabilistic classifiers for class prediction (14).…”

Beta process based adaptive learning for immunosignature microarray feature identification

“…Such methods include t-tests [5], ANaYA [6], princi pal component analysis (PC A) [7]- [9], clustering [10]- [13], singular value decomposition (SYM) [14], and Naive Bayes approach [3]. In [9], sequence morphologies were used to determine latent relationships between various peptides and disease states.…”