TECHNICAL SKILLS

Data Science tools/resources: Scikit - learn, SciPy, NumPy, Pandas, Jupityr notebook, Matplotlib, Spacy, Tensorflow, Keras, MS-Excel, Weka

NLP tools/resources: NLTK, OpenNLP, Spacy, Python, GATE, Wikipedia, VerbNet, WordNet, SentiWordNet, Oxford corpora

Development languages/ tools: Python, R-Programming, JAVA, Eclipse IDE, PyCharm IDE, RStudio, Agile development methodologies, such as, SCRUM, GitHub, Freedcamp

Ontology/ Semantic Web tools: Apache Jena, OWL2, Protégé, SPARQL, RDF, ROBOT, Ontofox, OntoBee, OLS, RDFLib

Database technologies: MYSQL, Versant Object Database, SQL, MS-Access

PROFESSIONAL EXPERIENCE

Data science and NLP researcher

Confidential

Responsibilities:

• Primary Role : Working as a key researcher and strategist in the areas of data science, NLP and semantic technology to develop machine learning and NLP competencies in healthcare domain.
• Stakeholders : Working closely with a n interdisciplinary team of public health researchers, epidemiologists, medical microbiologists, laboratory technologists and software developers involved in developing open source AI-driven tools and knowledge frameworks that improve data sharing and re-use in public health.
• Collaborators: Leading and working on many data-driven projects, involving Canadian and international collaborators, that have a very important role defined in our Laboratory’s current (The US FDA’s GenomeTrakr, FDA’s Resistome Tracker, The USDA Food Central database, EnteroBase, CINECA) and future collaborations.
• Data analysis, cleaning and transformation: Performed extensive analysis, cleaning, transformation and integration of structured and unstructured data scattered across disparate and diverse sources, used for data-driven solutions in the projects (refer further to data science projects in “projects” section)
• Machine Learning Modeling: Have been using advanced ML approaches in model building, development and deployment in learning-based projects in the healthcare domain (refer to data science projects in “projects” section)
• Ontology development and curation: On the semantic technology front, I am a key member of the teams developing and curating ontologies - a consortium-driven project to build a comprehensive and easily accessible global farm-to-fork ontology about food and the ontology that aims to develop a more comprehensive controlled vocabulary for infectious disease surveillance and outbreak investigations. Building ontology-driven solutions using these ontologies. (refer to ontology projects in “projects” section).
• NLP based solutions: Using state-of-art NLP techniques in text-oriented projects in healthcare domain (refer to NLP projects in “projects” section)
• Production code and project deliveries: Implemented the analyzed and designed data science, NLP and Semantic technology projects with extensive code design and production, majority of which is available as open source code. Involved in the delivery and deployment of the projects available on BioConda and GitHub.
• Key projects (as a team leader): Data Science- Classification of NCBI bio-samples (team leader), Data harmonization of public health laboratory test result codes (team leader); NLP- LexMapr: A Text Mining Tool for Translating Short Biomedical Specimen Descriptions into Ontology Terms (team leader), Semantic Technologies- Term recommendation system from free-text for food ontologies (team leader).
• Research writing/Publications: Involved in writing (and helping) research proposals (such as NSERC, MSFHR, GenomeBC, GenomeCanada, CINECA). Preparing and publishing manuscripts. Participated in conferences, workshops, scientific meetings and discussions (ISMB/ECCB, IC-Foods, ICBO). Publications in reputed journals such as Nature food journal, PLOS Computational Biology).

Senior Research Engineer

Confidential

Responsibilities:

• Primary Role : Developed and led many NLP, data science and semantic technology tasks that were part of breakthrough natural language understanding technology used in a video game - the first application where a person can speak freely with a machine. Managed and participated in multiple modules of Bot Colony game in different roles as well assisted teams working on multiple projects in Confidential Inc.
• Stakeholders : Worked with Confidential ’s core development groups: Language, Graphics, Artist, Scripting, Systems and Marketing groups and different collaborators - Telefilms Canada, BMO etc.
• NLP based solutions : Was an integral part in the development of many NLP tasks that were part of the NLU pipeline implemented in Bot Colony game.
• Data science and Machine Learning Modeling: Identified opportunities in large, rich data sets and conceived, designing and implementing statistical / predictive models and machine learning algorithms utilizing diverse sources of data to provide actionable insights in developing solutions for Gaming system.
• Ontology related projects: Involved in all phases of ontology development life cycle working on semantic technology projects that have been used extensively in different modules of Bot Colony.

Software Research Professional

Confidential, Athens, Georgia

Responsibilities:

• Primary Role : As a key NLP and semantic technology developer and researcher, I a nalyzed, designed, developed, tested, implemented and evaluated a very large and comprehensive ontology, that serves as a useful and efficient representation of the integrated knowledge about the complex proteins, called protein kinases, which are intimately involved in the genesis and behavior of cancer cells confidential.
• Data-driven analysis: Performed a large-scale integrative analysis of protein kinase data integrated from multiple disparate sources to investigate its role in cancer and published the results in reputed journal confidential.
• Interactive browsing tool: Developed tool for ontology browsing and visualization of ProKinO that is available via a standard Web browser. This tool not only provides fundamental access to the ProKinO knowledge but also certain specific capabilities sought by protein kinase community to pose queries for knowledge extraction along with general user friendly navigational capabilities confidential
• Research writing/Publications: Involved in writing research proposals (American Cancer Society and Georgia Cancer Coalition) and preparing and publishing manuscripts. The paper published in Plos One journal has been included in the most recommended papers category on protein kinases by InfoBank Library. Participated in conferences, workshops, scientific meetings and discussions (IEEE, Georgia Cancer Coalition symposia).