Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
This is project presentation for computer science degree. This project was supervised by Dr. Niharika Raj at Acharya Nagarjuna University. Its main topics are: Conclulsion, Computer, Project, Results, Methods, GP, KNN, Measure, Phase, Protein, Learning, Technique
Typology: Slides
1 / 13
This page cannot be seen from the preview
Don't miss anything!
96
5-fold Cross-validation
Methods
Fuzzy KNN
Accuracy
Accuracy
Accuracy
AACPseAACSAACAAC+ PseAACAAC+SAACPseAAC +SAACAAC+ PseAAC +SAAC
96
5-fold Cross-validation
Measures
OMPs vs. Globular
OMPs vs. alpha-helix
OMPs vs. Non-OMPs
AccuracySensitivitySpecificityMCC
AccuracySensitivitySpecificityMCC
97
97
99
Measures
Yan et al. [15]
Yan et al. [15]
Mizianty et al. [18]
Proposed Method
OMPs vs. Non-OMPs
AccuracySensitivitySpecificityMCC
99
100
C
ONCLUSIONS AND
F
UTURE
W
ORK
Our research finding revealed that computational methods formembrane proteins prediction are efficient and fast.
Research in pharmaceutical industry might be accelerated throughcomputational methods
Our research might be useful for protein structure prediction anddrugs discovery
Due to the complex nature and limited availability of membraneprotein structure, it should be the spotlight of future researchwork in the Machine learning community
102
CKNOWLEDGEMENTS
Pattern Recognition Lab, DCIS, Pakistan Institute ofEngineering and Applied Sciences Islamabad
Higher Education Commission, Pakistan
Center for Biophysics and Computational Biology, BeckmanInstitute, University of Illinois, USA
103
Zumdahi, S., 2000. Chemistry5th edition Houghton Mifflin Company
Waugh, D.F., 1954. Protein–Protein interactions. Adv. Protein Chem. 9, 325–437.
Eisenberg, D., Schwarz, E., Komaromy, M.,Wall, R., 1984. Analysis ofmembrane and surface protein sequences with the hydrophobic momentplot. J. Mol. Biol. 179, 125–142.
Chou, K.C., Cai, Y.D., 2005. Prediction of
membrane protein types by
incorporating amphipathic effects. J. Chem. Inf. Model 45, 407–413.
Chou, K.C., Shen, H.S., 2007. MemType-2L: a web server for predictingmembrane proteins and their types by incorporating evolution informationthrough Pse-PSSM. Biochem. Biophys. Res. Commun. 360, 339–345.
A. Mahdavi, and S. Jahandideh, Application of density similarities to predictmembrane protein types based on pseudo-amino acid composition. Journalof Theoretical Biology 276 (2011) 132-137.
105
Sklar, B., 2001. Digital Communications: Fundamentals and Applications.Prentice- Hall Inc.
Moller, S.; Kriventseva, E. V.; Apweiler, R. A collection of well characterizedintegral membrane proteins. Bioinformatics 2000, 16 (12), 1159–60.
Ikeda,
M.;
Arai,
M.;
Okuno,
T.;
Shimizu,
T.
TMPDB:
a
database
of
experimentally-characterized transmembrane topologies. Nucleic Acids Res.2003, 31 (1), 406–
Yan, C.; Hu, J., and Wang, Y. Discrimination of outer membrane proteinswith improved performance. BMC Bioinformatics 9 (2008) 47.
Park, K.J.; Gromiha, M.M.; Horton, P.; and Suwa, M. Discrimination ofouter Membrane proteins using support vector machines.. Bioinformatics 21(2005) 4223–4229.
106
U
108
