Daniel F. O. Onah

A multi-dimensional investigation of self-regulated learning in a blended classroom context : a case study on eLDa MOOC

Online systems such as massive open online courses (MOOCs) are new innovative learning technology in education. With the proliferation of MOOC systems, little has been mentioned about blended MOOC system and how it enhances students’ performance. Blended classroom is a form of learning taking place between two different activities of which one is online and the other is traditional teaching method using bricks and mortal classroom settings. This study reveals the effectiveness of blended classroom teaching for an undergraduate course. The module was embedded in an eLDa MOOC platform, which is a platform for delivery computing concepts, and Python programme course. This research aims to investigate students’ perceptions of self-regulated learning (SRL) habits. A multi-dimensional survey was designed to evaluate each aspect of SRL skills, motivation and attaining better grades within the course. This research analysis explores (a) cognitive process of students improving their self-regulated learning skills (b) potential of students’ preparedness and motivation to engage with the course content in a blended context (c) potential difference in addressing the relation among the methods of engagement and achievement in their weekly assessment results. The research applied an online self-regulated learning questionnaire (OSLQ) as the instrument for measuring the self-regulated learning skills of the students in the learning platform environment. In relation to developing a revised OSLQ to address the use of the instrument to measure self-regulated learning in an online blended classroom context. Data collection process was conducted on a sample of first year undergraduate students who took a seminar module via a blended course format. The results indicate the level of self-regulated learning explored from the measure of the self-regulation in the blended learning environment in this study.

G2P: Using machine learning to understand and predict genes causing rare neurological disorders

To facilitate precision medicine and neuroscience research, we developed a machine-learning technique that scores the likelihood that a gene, when mutated, will cause a neurological phenotype. We analysed 1126 genes relating to 25 subtypes of Mendelian neurological disease defined by Genomics England (March 2017) together with 154 gene-specific features capturing genetic variation, gene structure and tissue-specific expression and co-expression. We randomly re-sampled genes with no known disease association to develop bootstrapped decision-tree models, which were integrated to generate a decision tree-based ensemble for each disease subtype. Genes generating larger numbers of distinct transcripts and with higher probability of having missense mutations in normal individuals were significantly more likely to cause neurological diseases. Using mouse-mutant phenotypic data we tested the accuracy of gene-phenotype predictions and found that for 88% of all disease subtypes there was a significant enrichment of relevant phenotypic abnormalities when predicted genes were mutated in mice and in many cases mutations produced specific and matching phenotypes. Furthermore, using only newly identified genes included in the Genomics England November 2017 release, we assessed our gene-phenotype predictions and showed an 8.3 fold enrichment relative to chance for correct predictions. Thus, we demonstrate both the explanatory and predictive power of machine-learning-based models in neurological disease.