Tanvi Phaltane

Data scientist 1) Built a business product, saving 10% of the time and resources 2) Developed a prediction model to identify problematic compounds in an imbalanced dataset, saving 50% time of manual curators 3) Developed data solutions from the data warehouse while interacting with SME's 4) Contributed to development and deployment of machine learning models in production environment, saving 15% resources 5) Independently worked on innovative ideas to build MVPs 6) Mentoring of trainees and team members

Master thesis: Investigating role of blood microbiota in liver diseases using Bioinformatics and Machine learning approach

Projects: 1) Virtual screening of natural compounds for anti-diabetic and anti-cancer activity (Schrodinger's Glide software, AutoDock software, Discovery Studio) 2) Database development of active compounds derived from plants demonstrated to have anti-diabetic property in pre-clinical and/or clinical studies. GitHub repository: https://github.com/Tanvi-Phaltane/Database

Projects: 1) Design and implement workflow for identification of virulent proteins in a fungus using in-silico approach 2) Comparative transcriptomics data analysis of chickpea plant under biotic stress conditions in resistant and susceptible cultivars This position was limited to availability of research funds

1) Improved programming skills 2) Involved in manual and automated (Selenium) software-testing

Statistics, programming languages such as Perl, R, Java, C, structural bioinformatics, next-generation data analysis