Filters








15 Hits in 7.3 sec

Feature Selection on High Throughput SELDI-TOF Mass-Spectrometry Data for Identifying Biomarker Candidates in Ovarian and Prostate Cancer

Claudia Plant, Melanie Osl, Bernhard Tilg, Christian Baumgartner
2006 Sixth IEEE International Conference on Data Mining - Workshops (ICDMW'06)  
In this paper, we present a 3-step feature selection framework combining the advantages of efficient filter and effective wrapper techniques.  ...  We demonstrate the performance of our framework on two SELDI-TOF-MS data sets for identifying biomarker candidates in ovarian and prostate cancer.  ...  Conclusions In this paper, we presented a framework for feature selection on high-throughput mass spectrometry data. We evaluated our method on two SELDI-TOF-MS data sets on cancer identification.  ... 
doi:10.1109/icdmw.2006.80 dblp:conf/icdm/PlantOTB06 fatcat:qdd5syc7mrawdafgwhhrxf72le

Feature Selection for Microarray Gene Expression Data Using Simulated Annealing Guided by the Multivariate Joint Entropy

Felix F. Gonzalez-Navarro, Lluís A. Belanche-Muñoz
2014 Journal of Computacion y Sistemas  
The proposed algorithm combines a simulated annealing schedule specially designed for feature subset selection with the incrementally computed joint entropy, reusing previous values to compute current  ...  In this context, feature subset selection techniques can be very useful to reduce the representation space to one that is manageable by classification techniques.  ...  CGL2004-04702-C02-02, CONACyT and UABC for supporting this research from its beginning.  ... 
doi:10.13053/cys-18-2-2014-032 fatcat:xde4vbjfjbemlby2yad3keoftq

Feature Selection for Microarray Gene Expression Data using Simulated Annealing guided by the Multivariate Joint Entropy [article]

Fernando González, Lluís A. Belanche
2013 arXiv   pre-print
The mu-TAFS algorithm --named as such to differentiate it from previous TAFS algorithms-- implements a simulated annealing technique specially designed for feature subset selection.  ...  This measure is the basis for a fast information-theoretic based evaluation of gene relevance in a Microarray Gene Expression data context.  ...  A few contributions using the classical SA algorithm for FSS are found in prostate protein mass spectrometry data [6] , marketing applications [7] , or parameter optimization in clustering gene expression  ... 
arXiv:1302.1733v1 fatcat:c3hm6lbthzfz3kyu3vxidduahe

Feature Selection for Microarray Gene Expression Data Using Simulated Annealing Guided by the Multivariate Joint Entropy

Felix F. Gonzalez-Navarro, Lluís A. Belanche-Muñoz
2014 Journal of Computacion y Sistemas  
The µ-TAFS algorithm -named as such to differentiate it from previous TAFS algorithms-implements a simulated annealing technique specially designed for feature subset selection.  ...  This measure is the basis for a fast information-theoretic based evaluation of gene relevance in a Microarray Gene Expression data context.  ...  A few contributions using the classical SA algorithm for FSS are found in prostate protein mass spectrometry data [6] , marketing applications [7] , or parameter optimization in clustering gene expression  ... 
doi:10.13053/cys-18-1-2014-032 fatcat:bkqqcn7v6bdnjhz7hps6ijjivm

DWFS: A Wrapper Feature Selection Tool Based on a Parallel Genetic Algorithm

Othman Soufan, Dimitrios Kleftogiannis, Panos Kalnis, Vladimir B. Bajic, Dinesh Gupta
2015 PLoS ONE  
A well-studied variant of the wrapper model is the randomized one, which relies on search strategies such as, for example, genetic algorithms (GA), hill climbing and simulated annealing.  ...  DWFS follows the wrapper paradigm and applies a search strategy based on Genetic Algorithms (GAs).  ...  Introduction In the last decade, the leading high-throughput experimental techniques in biology, such as next generation sequencing, mass spectrometry, array-based methods and others, let to the massively  ... 
doi:10.1371/journal.pone.0117988 pmid:25719748 pmcid:PMC4342225 fatcat:fixiz6uhjzegzemm7c4x7o7iua

SVM-RFE With MRMR Filter for Gene Selection

P.A. Mundra, J.C. Rajapakse
2010 IEEE Transactions on Nanobioscience  
The method provides a framework for combining filter methods and wrapper methods of gene selection, as illustrated with MRMR and SVM-RFE methods.  ...  We enhance the support vector machine recursive feature elimination (SVM-RFE) method for gene selection by incorporating a minimum-redundancy maximum-relevancy (MRMR) filter.  ...  Duan for his inputs in the early part of this research.  ... 
doi:10.1109/tnb.2009.2035284 pmid:19884101 fatcat:o5fbhw5pazb5hkgta2ui4j3q4e

Applications of Support Vector Machines in Chemistry [chapter]

Ovidiu Ivanciuc
2007 Reviews in computational chemistry  
Zomer et al. used pyrolysisgas chromatography-mass-spectrometry coupled with SVM classification to discriminate between the two tablet production methods. 161 Mass spectra data were submitted to a PCA  ...  In one test, both feature selection algorithms produced comparable results, whereas in all other cases, SVM-based feature selection had better predictions.  ... 
doi:10.1002/9780470116449.ch6 fatcat:aumcn53nvfhhhocxvav32rhwzm

Specific and Selective Targeting Human Cancer Cells, Tissues and Tumors with Seaborgium Nanoparticles as Carriers and Nano–Enhanced Drug Delivery and Therapeutic in Cancer Treatment and Beyond under Synchrotron Radiation

Alireza Heidari, Katrina Schmitt, Maria Henderson, Elizabeth Besana
2020 Zenodo  
Calculations of nanorods showed that due to ability for shifting surface Plasmon frequency toward longer wavelength as well as more increase in temperature, this nanostructure is more appropriate for medical  ...  The performances of this method are evaluated on the popular data set which the experimental results show that since QGA-SVM is used as one of wrapper methods, as a result, its overall performance is better  ...  However, in the suggested algorithm, SVM classifier performance and the dimension of the selected feature vector are dependent on heuristic information for QGA [270] [271] [272] [273] [274] [275] [276  ... 
doi:10.5281/zenodo.3880506 fatcat:dkurkcw2pngaheodgit3x5kkmq

Novel Data Mining Methods for Virtual Screening of Biological Active Chemical Compounds

Othman Soufan
2016
In order to achieve an efficient virtual screening using data mining, I start by addressing the problem of feature selection and provide analysis of best ways to describe a chemical compound for an enhanced  ...  Part of this sophisticated process is based on preliminary investigations to suggest a set of chemical compounds as candidate drugs for the treatment.  ...  A well-studied variant of the wrapper model is the randomized one, which relies on search strategies such as, for example, genetic algorithms (GA), hill climbing and simulated annealing.  ... 
doi:10.25781/kaust-uy8y6 fatcat:lohjttpqzzcqdpjka3wucxi7xu

New statistical algorithms for the analysis of mass spectrometry time-of- flight mass data with applications in clinical diagnostics [article]

Tim Conrad, Universitätsbibliothek Der FU Berlin, Universitätsbibliothek Der FU Berlin
2008
Mass spectrometry (MS) based techniques have emerged as a standard for large- scale protein analysis.  ...  In this thesis we have developed new algorithms for automatic extraction of disease specific fingerprints from mass spectrometry data.  ...  Identification of ATM/ATR candidates in DNA-damage Response Pathways An excellent example how quantative mass spectrometry-based methods can used for mapping protein phosphorylation sites in proteomes  ... 
doi:10.17169/refubium-14645 fatcat:rdto5m4wg5ffjgadfn2fho3tju

Bioinformatic analyses for T helper cell subtypes discrimination and gene regulatory network reconstruction

Stefan Kröger, Humboldt-Universität Zu Berlin, Humboldt-Universität Zu Berlin
2017
In this thesis, we build a large gene expression data set based on publicly available studies for further research on T cell subtype discrimination and the reconstruction of T cell specific gene regulatory  ...  This data set is applied to a machine learning based strategy of extracting surface protein markers to enable Treg cell subtype discrimination.  ...  Wrapper methods Wrapper methods combine two components into one algorithm, namely a model hypothesis search within the feature subset search.  ... 
doi:10.18452/18122 fatcat:hkjexp6kprg23nfln5bpjcao4a

Statistical analysis of microarray based DNA methylation data [article]

Fabian Model, Technische Universität Berlin, Technische Universität Berlin, Ulrich Kockelkorn
2007
A methodology for microarray quality and process control is introduced that estimates the quality of individual microarrays based solely on the distribution of the actual measurements without requiring  ...  In this thesis novel statistical methods for the analysis of DNA methylation microarray data are developed.  ...  I thank Professor Ulrich Kockelkorn for critically reading this manuscript and supervising this thesis.  ... 
doi:10.14279/depositonce-1647 fatcat:jrj6tfp5czcobbyq5p5mmewiim

Characterizing the granzyme-perforin pathway and its utility as a cell-to-cell delivery system for cellular therapeutics

Daniel Woodsworth
2017
A computational biophysical model of this process was developed and implemented using a spatial stochastic simulation algorithm, which indicated that hindered diffusion in the immune synapse is critical  ...  Alongside small molecules and biologics, cell-based therapies are emerging as a third class of medical therapy.  ...  Based on this data I think it would be worth considering re-engineering the fusion protein.  ... 
doi:10.14288/1.0348382 fatcat:mcfps6gyungwtmgxx523lucfhm

Reinforcement Learning (Dagstuhl Seminar 13321) The Critical Internet Infrastructure (Dagstuhl Seminar 13322) Coding Theory (Dagstuhl Seminar 13351) Interaction with Information for Visual Reasoning (Dagstuhl Seminar 13352)

Peter Auer, Marcus Hutter, Laurent, Georg Carle, Jochen Schiller, Steve Uhlig, Walter Willinger, Matthias Wählisch, Thore Husfeldt, Ramamohan Paturi, Gregory Sorkin, Ryan Williams (+14 others)
unpublished
Alex: Flow Cytometry data analysis is a real case of Big-Data robots producing much larger data than can be processed at the moment.  ...  Is there a lesson for biology? Anja: We are working in this area. Yet, already agreeing on terminology is difficult. Marc: Sensors are underrated, ON and OFF rates need to be studied.  ...  MINT: A mutual-information based software for transductive feature selection based on genetic trait prediction, considering interaction between markers (2 markers together may boost a trait).  ... 
fatcat:iz3co5xisfejfbnx2t6ptrorfm

Study of The Adverse Effects of Environmental Contaminants on Gene Expression in Fish [article]

Ava Zare, University Of Calgary, University Of Calgary, Hamid R Habibi
2017
The presence of contaminants with hormone-like activity and their potential harmful effects on the aquatic ecosystems has been a major concern for over three decades.  ...  The primary goal of this thesis was to investigate the in vivo effects of BPA, NP, and DEHP at environmentally relevant concentrations, individually and in a mixture, on gene expression patterns in goldfish  ...  Hamid Habibi, for his supervision, support, and advice during my time as a graduate student.  ... 
doi:10.11575/prism/27921 fatcat:enpxtapaj5hcpokheqmpa6pf4y