Browsing by Author "Banjoko, A. W."
Now showing 1 - 2 of 2
Results Per Page
Sort Options
- ItemGenetic Diagnosis, Classification, and Risk Prediction in Cancer Using Next-Generation Sequencing in Oncology(CRC Press, Taylor & Francis Grou, 2024) Dauda, K. A.; Olorede, K. O.; Banjoko, A. W.; Yahya, W. B.; Ayipo, Y. O.In recent years, researchers have been overwhelmed with large-scale genomic data due to an advancement toward data-driven science called next-generation sequencing. Hence, it has been established that if the sequence of a gene is mutated, there is the possibility of unscheduled production of the protein, leading to cancer. The prediction of genes and variants into true and false pathogenic groups, extraction of the most influential genes, and identification of a pattern from this genomic data are of interest to biologists and medical professionals. However, the identification and extraction of these biomarkers and molecular signatures of different cancers among thousands of genes seem complex and problematic. Therefore, this chapter is aimed to develop an algorithm that can aid and provide efficient solutions for gene extraction, identification, and prediction in the realm of next-generation sequencing data. The proposed algorithm consists of three folds: the filtering fold using minimum redundancy maximum relevance (MRMR), the wrapper fold using the Boruta algorithm, and the last fold consisting of the use of deep learning (DL). A comparison assessment was performed on the proposed algorithm and the existing methods using five RNA-seq datasets from a cancer patient. The results revealed that the proposed algorithm significantly outperforms the existing methods in selecting fewer highly relevant genes for the cancer type while maintaining a high classification prediction accuracy.
- ItemOn the Efficiency of Maximum Likelihood and Restricted Maximum Likelihood Estimators for Linear Mixed Effects Models(Mathematical Association of Nigeria (MAN), 2016) 3. Yahya W. B.; Adeniyi I. A.; Olayemi R. M.; Dauda K. A.; Banjoko, A. W.; Olorede K. O.; Ezenweke C. P.In this work, the performances of maximum likelihood (ML) and restricted maximum likelihood (REML) estimation of linear mixed effects models were examined. The behaviours and properties of the ML and REML methods of estimating the variance-covariance components in linear mixed effects models were studied via Monte-Carlo experiment. Results revealed that both estimation techniques yielded the same estimates of the fixed effects parameters. However, ML estimates of variance-covariance components, especially for the random effects terms were more biased downwards than the REML counterparts. It was also discovered that the biasness of the ML estimates for the variance-covariance components increase as the number of fixed effects parameters in the model increase.