Data mining methods have the potential to identify groups at high risk. There are different steps of processing the data so as to extract their results consisting of data collection, data pre-processing, feature extraction, data partitioning, and data classification. There are different classification techniques like a classification tree, averaging tree, and machine learning algorithms. This paper explains the proposed model for cell survival/ death by using Random forest and boosting tree and random forest methods which are different Averaging tree techniques. The data is collected which is pre-processed by visual plots (basic statistics) and normality test (AD, KS and chi-square values). The marker proteins were selected from eleven different proteins by using statistical analysis (SER, p-value, and t-value). Lastly, averaging tree technique is applied to the data set to predict which protein or sample helps in cell survival/ death. In boosting tree, the division is on the basis of ten different concentrations of TNF, EGF, and Insulin while in RF method, the model is made for the training and testing of data on the basis of samples. 100-0-500 ng/ml yields the better results using boosting tree and from RF methods we come across that FKHR protein leads to cell death while rest proteins help in cell survival if they are present.
S Sharma, S Jain, S Bhusri, Two Class Classification of Breast Lesions using Statistical and Transform Domain features, Journal of Global Pharma Technology (JGPT), 9(7), pp 18-24, 2017.
S Jain., Communication of signals and responses leading to cell survival / cell death using Engineered Regulatory Networks. PhD Dissertation, Jaypee University of Information Technology, Solan, Himachal Pradesh, India, 2012.
A.Dhiman, A. Singh, S.Dubey and S. Jain, Design of lead II ECG Waveform and Classification performance for Morphological features using Differenct Classifiers on lead II, Research J of pharmaceutical, biological and chemical sciences, July-Aug 2016, pp. 1226-1231.
R Weiss., Cellular computation and communications using engineered genetic regulatory networks. PhD Dissertation, MIT, 2001.
S Gaudet, JA Kevin, AG John, PA Emily, LA Douglas, and SK Peter. A compendium of signals and responses triggered by prodeath and prosurvival cytokines. Manuscript M500158-MCP200, 2005.
S Jain, PK Naik, R Sharma, A Computational Modeling of cell survival/ death using VHDL and MATLAB Simulator, Digest Journal of Nanomaterials and Biostructures. 2009: 4 (4): 863- 79.
JA Kevin, AG John, G Suzanne, SK Peter, LA Douglas, YB Michael. A systems model of signaling identifies a molecular basis set for cytokine-induced apoptosis. Science. 2005; 310, 1646-53.
N Normanno, A De Luca, C Bianco, L Strizzi, M Mancino, MR Maiello, A Carotenuto, G De Feo, F Caponiqro and DS Salomon. Epidermal growth factor receptor (EGFR) signaling. Cancer Gene. 2006; 366, 2-16.
S Jain, Implementation of Marker Proteins Using Standardised Effect, Journal of Global Pharma Technology. 2017: 9(5), 22-27.
S Jain, Compedium model using frequency / cumulative distribution function for receptors of survival proteins: Epidermal growth factor and insulin, Network Biology. 2016: 6(4), 101-110.
JM Lizcano and DR Alessi. The insulin signalling pathway. Curr Biol.2002; 12, 236-38.
S Jain, PK Naik and SV Bhooshan. Mathematical modeling deciphering balance between cell survival and cell death using insulin. Network Biology. 2011; 1(1):46-58.
S Jain, Parametric and Non Parametric Distribution Analysis of AkT for Cell Survival/Death, International Journal of Artificial Intelligence and Soft Computing. 2017 : 6(1), 43- 55
MF White. Insulin Signaling in Health and Disease. Science. 2003; 302, 1710-11.
S. Bhusri, S. Jain, and J Virmani, Classification of Breast Lesions Using the Difference of Statistical Features, Research Journal of Pharmaceutical, Biological and Chemical Sciences(RJPBCS), july-aug 2016,pp. 1366.
S Jain, Regression analysis on different mitogenic pathways, Network Biology. June 2016: 6(2), 40-46 .
A. Brunet, A. Bonni, M. J. Zigmond, M. Z. Lin, P. Juo, L. S. Hu, Akt promotes cell survival by phosphorylating and inhibiting a Forkhead transcription factor. Cell, 96 (1999), 857-868.
S.K. Alam, E.J. Feleppa, M.Rondeau, A. Kalisz, and B.S. Garra,Ultrasonic multi-feature analysis procedure for computer-aided diagnosis of solid breast lesions,2011. vol. 33, no. 1, pp. 17-38.
S. Rana, S. Jain, and J. Virmani, SVM-Based characterization of focal kidney lesions from B-Mode ultrasound images, research J of pharmaceutical, biological and chemical sciences (RJPBCS). July-Aug 2016,vol. 7(4), pp.837.
Averaging trees, boosted trees, random forests, marker proteins.