I am a computer scientist whose primary focus is on developing novel machine learning methods to extract useful information from complex datasets. My experience, however, has covered intellectually wide-ranging areas spanning several disciplines in computer science, biology, and chemistry.
At the undergraduate level, I focused on computer networks, and I did an internship for six months at Cisco Systems Inc., and I achieved CCNA and CCNP certification. At the Master's level, however, I joined the Computational Bioscience Research Center. I was in charge of a text-mining project to extract associations between methylated genes and diseases automatically from the scientific literature.
As an ambitious researcher, my aspiration has expanded. I wanted to investigate another research area to which my skills are transferable. I chose cheminformatics. I currently work on developing multi-label classification methods for datasets with missing labels, which requires solving several associated problems including feature selection and resampling imbalanced multi-label datasets with missing labels. The primary motivation for this project is to develop predictive multi-label classification models to predict several toxic effects of chemical compounds. Subsequently, the scope of the project has been extended to include other domains such as text, images, and biological datasets, as well as utilizing supercomputing clusters for efficient application of these methods.
Additionally, I wanted to explore another way to be influential by becoming a Teaching Assistant for Master and PhD level computer science courses. Currently, I mentor students enrolled to the Applications of Artificial Intelligence in Bioinformatics course to complete several research projects including DNA transcription initiation sites recognition, DNA PolyA signal recognition, DNA acceptor and donor splice sites recognition, and acronym finding from biomedical literature.
To know more about me visit my other profiles: