PhD Student (Computer Science) and Graduate Research Assistant | B.Sc. Eng (Hons), AMIESL
I am a data science enthusiastic who is having interests in Bioinformatics and Biomedical informatics. Apart from that, I love traveling and capturing memorable moments with my loved ones.
Next-Generation Sequencing(NGS) methods like Illumina have made it possible to sequence DNAs with high throughput at an affordable cost. The total DNA of Eukaryotic is consists of the chloroplast, mitochondrial and nuclear reads. Though many works have used chloroplast data, the remaining mitochondrial and nuclear data have been left untouched. Thus we aimed to utilize mitochondrial and nuclear data to identify species-level differences among cinnamon species.
Research Domain Criteria (RDoC) is a novel framework introduced by the National Institute of Mental Health (NIMH) for describing mental illness. Since it is a fairly recent introduction, existing biomedical literature needs to be classified by RDoC for it to be effective. Considering that manual annotation of articles is highly resource-consuming, Machine Learning and Natural Language Processing techniques can be used to ease and automate this task. Therefore we employed those techniques to develop models for information retrieval and sentence extraction with RDoC.