RESUMO
(1) Background: The data from independent gene expression sources may be integrated for the purpose of molecular diagnostics of cancer. So far, multiple approaches were described. Here, we investigated the impacts of different data fusion strategies on classification accuracy and feature selection stability, which allow the costs of diagnostic tests to be reduced. (2) Methods: We used molecular features (gene expression) combined with a feature extracted from the independent clinical data describing a patient's sample. We considered the dependencies between selected features in two data fusion strategies (early fusion and late fusion) compared to classification models based on molecular features only. We compared the best accuracy classification models in terms of the number of features, which is connected to the potential cost reduction of the diagnostic classifier. (3) Results: We show that for thyroid cancer, the extracted clinical feature is correlated with (but not redundant to) the molecular data. The usage of data fusion allows a model to be obtained with similar or even higher classification quality (with a statistically significant accuracy improvement, a p-value below 0.05) and with a reduction in molecular dimensionality of the feature space from 15 to 3-8 (depending on the feature selection method). (4) Conclusions: Both strategies give comparable quality results, but the early fusion method provides better feature selection stability.
Assuntos
Neoplasias da Glândula Tireoide , Algoritmos , Humanos , Neoplasias da Glândula Tireoide/diagnóstico , Neoplasias da Glândula Tireoide/genéticaRESUMO
BACKGROUND: Here, we present an R package for entropy/variability analysis that facilitates prompt and convenient data extraction, manipulation and visualization of protein features from multiple sequence alignments. BALCONY can work with residues dispersed across a protein sequence and map them on the corresponding alignment of homologous protein sequences. Additionally, it provides several entropy and variability scores that indicate the conservation of each residue. RESULTS: Our package allows the user to visualize evolutionary variability by locating the positions most likely to vary and to assess mutation candidates in protein engineering. CONCLUSION: In comparison to other R packages BALCONY allows conservation/variability analysis in context of protein structure with linkage of the appropriate metrics with physicochemical features of user choice. AVAILABILITY: CRAN project page: https://cran.r-project.org/package=BALCONY and our website: http://www.tunnelinggroup.pl/software/ for major platforms: Linux/Unix, Windows and Mac OS X.
Assuntos
Proteínas/química , Alinhamento de Sequência/métodos , Software , Sequência de Aminoácidos , Entropia , Evolução Molecular , HumanosRESUMO
MOTIVATION: The identification and tracking of molecules which enter active site cavity requires screening the positions of thousands of single molecules along several thousand molecular dynamic steps. To fill the existing gap between tools searching for tunnels and pathways and advanced tools employed for accelerated water flux investigations, we have developed AQUA-DUCT. RESULTS: AQUA-DUCT is an easy-to-use tool that facilitates analysis of the behaviour of molecules that penetrate any selected region in a protein. It can be used for any type of molecules, e.g. water, oxygen, carbon dioxide, organic solvents, ions. AVAILABILITY AND IMPLEMENTATION: Linux, Windows, macOS, OpenBSD, http://www.aquaduct.pl . CONTACT: a.gora@tunnelinggroup.pl or info@aquaduct.pl. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.