报告题目：Gene Prediction with improvements using Neural network

报告人：Manaswini Pradhan (Assistant Professor)

主持人：王长波

报告时间：12月11日（周一）18:30—19:30

报告地点：中北校区理科大楼B1002室

报告摘要：

Bioinformatics plays an increasingly important role in the study of modern biology. Bioinformatics deals with the management and analysis of biological information stored in databases. The field of genomics is dependent on Bioinformatics which is a significant novel tool emerging in biology for finding facts about gene sequences, interaction of genomes, and unified working of genes in the formation of final syndrome or phenotype. The rising popularity of genome sequencing has resulted in the utilization of computational methods for gene finding in DNA sequences.

In this research work, a classification technique is used that classifies the microarray gene expression data well. In the technique used, the dimensionality of the gene expression dataset is reduced by Probabilistic PCA. Then, an Artificial Neural Network (ANN) is selected as the supervised classifier and it is enhanced using Evolutionary programming (EP) technique. The enhancement of the classifier is accomplished by optimizing the dimension of the ANN. The enhanced classifier is trained using the Back Propagation (BP) algorithm, so the BP error gets minimized. The well-trained ANN has the capacity of classifying the gene expression data to the associated classes. The technique used is evaluated by classification performance over the cancer classes, Acute myeloid Leukemia (AML) and Acute Lymphoblastic Leukemia (ALL). The classification performance of the enhanced ANN classifier is compared over the existing ANN classifier and standard SVM classifier. The method is presented to predict the dominant genes of ALL/AML cancer.  First, to train an FF-ANN, a combinational data of the input dataset is generated and its dimensionality is reduced through Probability Principal Component Analysis (PPCA). Then, the classified database of ALL/AML cancer is given as the training dataset to design the FF-ANN. After the FF-ANN is designed, the genetic algorithm is applied on the test input sequence and the fitness function is computed using the designed FF-ANN. After that, the genetic operations crossover, mutation and selection are carried out. Finally, through analysis, the optimal dominant genes are predicted.

报告人介绍：

Dr. Manaswini Pradhan received B.E. in Computer Science and Engineering, M.Tech in Computer Science from Utkal University, Odisha, India, and Ph.D. degree in the field of Information and Communication Technology from Fakir Mohan University, Odisha. Currently she is working as an Assistant Professor in P.G. Department of Information and Communication Technology, Fakir Mohan University, Orissa, India. She has been in the teaching profession for the last fifteen years, and during this period she also has acquired research experience in the area of Artificial Neural Network, Data-mining, and other topics in the broad subject of Information & Communication Technology. She has been awarded research projects by Department of Science & Technology, Govt. of India, and UGC, New Delhi. She has a published research papers in national, & international journals, a book chapter published by Taylor & Francis, Springer, IBI Global and presented papers in various conferences. She is involved in guiding M.Tech/M.Phil Computer Science scholars in the field of data mining, neural networks, bio-informatics, and application of ICT in healthcare management. Her research aptitude and acumen is of very high order.