SVM-Based Classification of Class C GPCRs from Alignment-Free Physicochemical Transformations of Their Sequences

König

et al. 2015

Genomics Comput Biol

Self Cite

G-protein-coupled receptors are cell membrane proteins of great interest in biology and pharmacology. Previous analysis of Class C of these receptors has revealed the existence of an upper boundary on the accuracy that can be achieved in the classification of their standard subtypes from the unaligned transformation of their primary sequences. To further investigate this apparent boundary, the focus of the analysis in this paper is placed on receptor sequences that were previously misclassified using supervised learning methods. In our experiments, these sequences are visualized using a nonlinear dimensionality reduction technique and phylogenetic trees. They are subsequently characterized against the rest of the data and, particularly, against the rest of cases of their own subtype. This exploratory visualization should help us to discriminate between different types of misclassification and to build hypotheses about database quality problems and the extent to which GPCR sequence transformations limit subtype discriminability. The reported experiments provide a proof of concept for the proposed method.

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Visual Characterization of Misclassified Class C GPCRs through Manifold-based Machine Learning Methods

Cárdenas

König

et al. 2015

Genomics Comput Biol

Self Cite

“…The amino acid sequences of varying lengths were first transformed into fixed-size feature representations. For this, we used in previous work transformations based on the physicochemical properties of the sequences [8]. Instead, in this work we use short protein subsequences in the form of n-gram features.…”

Section: Methodsmentioning

confidence: 99%

“…This paper specifically focuses on the class C subset of a publicly available GPCR database. These data were analyzed in a previous study [8] using a supervised, multi-class classification approach that yielded relatively high accuracies in the discrimination of the seven constituting subtypes of the class. This previous work used several transformations based on the physicochemical properties of the sequence amino acids.…”

Section: Introductionmentioning

confidence: 99%

Finding Class C GPCR Subtype-Discriminating N-grams through Feature Selection

König

Alquézar

8th International Conference on Practical Applications of Computational Biology &Amp; Bioinformatics (PACBB 2014)

et al. 2014

Self Cite

Abstract. G protein-coupled receptors (GPCRs) are a large and heterogeneous superfamily of receptors that are key cell players for their role as extracellular signal transmitters. Class C GPCRs, in particular, are of great interest in pharmacology. The lack of knowledge about their full 3-D structure prompts the use of their primary amino acid sequences for the construction of robust classifiers, capable of discriminating their different subtypes. In this paper, we describe the use of feature selection techniques to build Support Vector Machine (SVM)-based classification models from selected receptor subsequences described as n-grams. We show that this approach to classification is useful for finding class C GPCR subtype-specific motifs.

“…The data in the following experiments were extracted from GPCRDB Previous research [20] investigated the supervised classification of these data sequences, from several of their alignment-free transformations, including AAC, digram, and ACC, among others. Here, we use K-Means and FCM to investigate to what extent the natural clustering structure of the data fits the subfamilies (classes) description.…”

Section: Materials and Experimental Settingmentioning

confidence: 99%

A Weighted Cramér’s V Index for the Assessment of Stability in the Fuzzy Clustering of Class C G Protein-Coupled Receptors

Bioinformatics and Biomedical Engineering

Halka

Nebot

2015

Self Cite

Abstract. After decades of intensive use, K-Means is still a common choice for crisp data clustering in real-world applications, particularly in biomedicine and bioinformatics. It is well-known that different initializations of the algorithm can lead to different solutions, precluding replicability. It has also been reported that even solutions with very similar errors may widely differ. A criterion for the choice of clustering solutions according to a combination of error and stability measures has recently been suggested. It is based on the use of Cramér's V index, calculated from contingency tables, which is valid only for crisp clustering. Here, this criterion is extended to fuzzy and probabilistic clustering by first defining weighted contingency tables and a corresponding weighted Cramér's V index. The proposed method is illustrated using Fuzzy C-Means in a proteomics problem.