114 Hits in 4.6 sec

Discriminating Transmembrane Proteins From Signal Peptides Using SVM-Fisher Approach

R.Y. Kahsay, G.R. Gao, Li Liao
Fourth International Conference on Machine Learning and Applications (ICMLA'05)  
Here, we present a new approach that combines the SVM-Fisher discrimination method and TMMOD -a hidden Markov model based predictor for transmembrane proteins.  ...  Because signal peptides also contain hydrophobic segments, these computational prediction methods often misidentify signal peptides as transmembrane proteins.  ...  Acknowledgments This publication was made possible by NIH Grant Number P20 RR-15588 from the COBRE Program of the National Center for Research Resources, and by a DuPont Science and Engineering grant.  ... 
doi:10.1109/icmla.2005.24 dblp:conf/icmla/LiaoKG05 fatcat:5gpey6tf5zf3xdwh27ebucpob4

Signal peptide discrimination and cleavage site identification using SVM and NN

H.B. Kazemian, S.A. Yusuf, K. White
2014 Computers in Biology and Medicine  
The proposed method utilises a dual phase classification approach using SVM as a primary classifier to discriminate SP sequences from Non-SP.  ...  a genome contain a signal peptide (SP) sequence, at the N-terminus, that targets the protein to intracellular secretory pathways.  ...  from globular proteins using SVM; The prediction of signal peptide cleavage site using NNs.  ... 
doi:10.1016/j.compbiomed.2013.11.017 pmid:24480169 fatcat:xhi6foxnancxziruaysmml7cdy

Differential Protein Expression Profiles Between Plasmodium falciparum Parasites Isolated From Subjects Presenting With Pregnancy-Associated Malaria and Uncomplicated Malaria in Benin

Gwladys I. Bertin, Audrey Sabbagh, François Guillonneau, Sayeh Jafari-Guemouri, Sem Ezinmegnon, Christian Federici, Benjamin Hounkpatin, Nadine Fievet, Philippe Deloron
2013 Journal of Infectious Diseases  
Using filter-based feature-selection methods combined with supervised data analysis, we identified a subset of 53 proteins that distinguished PAM and UM samples.  ...  VAR2CSA is identified and associated with PAM, validating our experimental approach. Other PAM-predictive proteins included PFI1785w, PF14_0018, PFB0115w, PFF0325c, and PFA_0410w.  ...  Also, we thank Benoît Hareng and Fatma Mounsi for the preparation and extraction of protein samples. Financial support. This work was supported by IRD and Labex GR-Ex.  ... 
doi:10.1093/infdis/jit377 pmid:23901091 fatcat:6vt5muoatnbcrioldzfgiyiixm

A Novel Method for Classifying Subfamilies and Sub-subfamilies of G-Protein Coupled Receptors [chapter]

Majid Beigi, Andreas Zell
2006 Lecture Notes in Computer Science  
G-protein coupled receptors (GPCRs) are a large superfamily of integral membrane proteins that transduce signals across the cell membrane.  ...  The results shows that Our oversampling technique can be used for other applications of protein classification with the problem of imbalanced data.  ...  Our study shows again that a discriminative approach for protein classification of GPCRs is more accurate than a generative approach.  ... 
doi:10.1007/11946465_3 fatcat:hdvtcgly5zbgbhvwftbue42sty

Mapping the stabilome: a novel computational method for classifying metabolic protein stability

Ralph Patrick, Kim-Anh Cao, Melissa Davis, Bostjan Kobe, Mikael Bodén
2012 BMC Systems Biology  
We also investigate the impact of N-terminal protein tagging as used to generate the data set, in particular the impact it may have on the measurements for secreted and transmembrane proteins; we train  ...  New experimental techniques coupled with powerful data integration methods now enable us to not only investigate what features govern protein stability in general, but also to build models that identify  ...  Sequence SVM: Set according to the continuous score of the SVM (which is trained to discriminate between stable and unstable protein sequences -see Section "Classifying stability from sequence: SVM").  ... 
doi:10.1186/1752-0509-6-60 pmid:22682214 pmcid:PMC3439251 fatcat:yu24rkudtjgdzgavrei4glokzi

Classifying G-protein coupled receptors with support vector machines

R. Karchin, K. Karplus, D. Haussler
2002 Bioinformatics  
(SVMs), that transform protein sequences into fixed-length feature vectors.  ...  The methods described in this paper use only primary sequence information to make their predictions.  ...  Our work with the transformation from protein sequence into Fisher Score Vector (FSV) space (described in Appendix A) introduced the possibility of an alternate approach to nearest-neighbor classification  ... 
doi:10.1093/bioinformatics/18.1.147 pmid:11836223 fatcat:atr3aktehrd7ldwxv7chyohg7y

Urinary Signatures of Renal Cell Carcinoma Investigated by Peptidomic Approaches

Clizia Chinello, Marta Cazzaniga, Gabriele De Sio, Andrew James Smith, Erica Gianazza, Angelica Grasso, Francesco Rocco, Stefano Signorini, Marco Grasso, Silvano Bosari, Italo Zoppis, Mohammed Dakna (+4 others)
2014 PLoS ONE  
Most of the peptide signals used in the two models were observed at higher abundance in patient urines and could be identified as fragments of proteins involved in tumour pathogenesis and progression.  ...  Two different peptide signatures were obtained by a MALDI-TOF profiling approach based on urine pre-purification by C8 magnetic beads.  ...  Hereby we describe two patterns of twelve urinary peptides with a high discrimination power obtained by an SVM-based statistical approach. Seven of these signals were most likely identified.  ... 
doi:10.1371/journal.pone.0106684 pmid:25202906 pmcid:PMC4159280 fatcat:vjceomryfzdotng3nxbo7gnin4

The Trypanosoma brucei MitoCarta and its regulation and splicing pattern during development

Xiaobai Zhang, Juan Cui, Daniel Nilsson, Kapila Gunasekera, Astrid Chanfon, Xiaofeng Song, Huinan Wang, Ying Xu, Torsten Ochsenreiter
2010 Nucleic Acids Research  
Using this method, we predicted the mitochondrial localization of 468 proteins with high confidence and have experimentally verified the localization of a subset of these proteins.  ...  We present a novel computational method for genome-wide prediction of mitochondrial proteins using a support vector machine-based classifier with $90% prediction accuracy.  ...  Signal peptide and transmembrane topology.  ... 
doi:10.1093/nar/gkq618 pmid:20660476 pmcid:PMC2995047 fatcat:v3qznanbgbcdpphawv2p2vi6g4

Simultaneous classification and relevant feature identification in high-dimensional spaces: application to molecular profiling data

C. Bhattacharyya, L.R. Grate, A. Rizki, D. Radisky, F.J. Molina, M.I. Jordan, M.J. Bissell, I.S. Mian
2003 Signal Processing  
breast carcinoma transcript proÿles from patients with distant metastases ¡5 years and those with no distant metastases ¿5 years and (iii) serum sample protein proÿles from una ected and ovarian cancer  ...  It performs well when used for retrospective analysis of three cancer biology proÿling data sets, (i) small, round, blue cell tumour transcript proÿles from tumour biopsies and cell lines, (ii) sporadic  ...  The seven two-class data sets were analysed using LIKNON and a Fisher score ÿlter-MPM/SVM wrapper strategy.  ... 
doi:10.1016/s0165-1684(02)00474-7 fatcat:aov7trcdhba5vabzywnlhtz2ra

A Cell-Surface Membrane Protein Signature for Glioblastoma

Dhimankrishna Ghosh, Cory C. Funk, Juan Caballero, Nameeta Shah, Katherine Rouleau, John C. Earls, Liliana Soroceanu, Greg Foltz, Charles S. Cobbs, Nathan D. Price, Leroy Hood
2017 Cell Systems  
of GBM cell-surface proteins reveals a disrupted membrane-signaling network that can be identified from the blood of GBM patients, a subset of which can distinguish between normal and diseased individuals  ...  We present a systems strategy that facilitated the development of a molecular signature for glioblastoma (GBM), composed of 33 cell-surface transmembrane proteins.  ...  B) ELISA results from training set were modelled using Linear Discriminant Analysis (LDA).  ... 
doi:10.1016/j.cels.2017.03.004 pmid:28365151 pmcid:PMC5512565 fatcat:wpvdxu3m2zgstcvuf5utlnzoyu

A Computational Method for Prediction of Excretory Proteins and Application to Identification of Gastric Cancer Markers in Urine

Celine S. Hong, Juan Cui, Zhaohui Ni, Yingying Su, David Puett, Fan Li, Ying Xu, Vladimir Brusic
2011 PLoS ONE  
These features are used to train a classifier to distinguish the two classes of proteins.  ...  When used in conjunction with information of which proteins are differentially expressed in diseased tissues of a specific type versus control tissues, this method can be used to predict potential urine  ...  (Translated from eng) BMC Bioinformatics 6:167 (in eng). 6. Kall L, Krogh A, & Sonnhammer EL (2007) Advantages of combined transmembrane topology and signal peptide prediction-the Phobius web server.  ... 
doi:10.1371/journal.pone.0016875 pmid:21365014 pmcid:PMC3041827 fatcat:hgpfu4jk25brxikdf7faxcj5ba

Predicting domain-domain interaction based on domain profiles with feature selection and support vector machines

Alvaro J González, Li Liao
2010 BMC Bioinformatics  
Features about the domains are extracted first as the Fisher scores derived from the ipHMM and then selected using singular value decomposition (SVD).  ...  Results: In this paper, we propose a computational method to predict DDI using support vector machines (SVMs), based on domains represented as interaction profile hidden Markov models (ipHMM) where interacting  ...  discriminating signal peptides from proteins with a single transmembrane domain [34] .  ... 
doi:10.1186/1471-2105-11-537 pmid:21034480 pmcid:PMC2989984 fatcat:ozereddljjdd3jtuaocefqpage

Immune profiling with a Salmonella Typhi antigen microarray identifies new diagnostic biomarkers of human typhoid

Li Liang, Silvia Juarez, Tran Vu Thieu Nga, Sarah Dunstan, Rie Nakajima-Sasaki, D. Huw Davies, Stephen McSorley, Stephen Baker, Philip L. Felgner
2013 Scientific Reports  
Here we used a protein microarray containing 2,724 Salmonella enterica serovar Typhi antigens (.63% of proteome) and identified antibodies against 16 IgG antigens and 77 IgM antigens that were differentially  ...  About 72% of the serodiagnostic antigens were within the top 25% of the ranked antigen list using a Naïve bayes classifier.  ...  This work was supported by U01AI078213 (PLF) and a subcontract to DHD from R01AI073672 (SJMcS).  ... 
doi:10.1038/srep01043 pmid:23304434 pmcid:PMC3540400 fatcat:xivfd52tmjdp7itqyp7s6xjzya

Repertoires of G protein-coupled receptors for Ciona-specific neuropeptides

Akira Shiraishi, Toshimi Okuda, Natsuko Miyasaka, Tomohiro Osugi, Yasushi Okuno, Jun Inoue, Honoo Satake
2019 Proceedings of the National Academy of Sciences of the United States of America  
We developed an original peptide descriptor-incorporated support vector machine and used it to predict 22 neuropeptide–GPCR pairs.  ...  However, most receptors for novel peptides remain to be identified.  ...  The feature set for training and prediction was not changed from the PD-incorporated feature set used above, and the additional datasets were expected to update the discriminant functions (weight vectors  ... 
doi:10.1073/pnas.1816640116 fatcat:qcxfwm7yzzaxfihaibb2j6qc2u

Application of Support Vector Machines in Viral Biology [chapter]

Sonal Modak, Swati Mehta, Deepak Sehgal, Jayaraman Valadi
2019 Global Virology III: Virology in the 21st Century  
Several studies in virology employ high performance tools including SVM for identification of potentially important gene and protein functions.  ...  To analyse such data, rapidly gain information, and transform this information to knowledge, interdisciplinary approaches involving several different types of expertise are necessary.  ...  Their SVM based methodology classifies the samples based on their hybridization signal.  ... 
doi:10.1007/978-3-030-29022-1_12 fatcat:leaxfnxiuze2jbuyenwps7qcve
« Previous Showing results 1 — 15 out of 114 results