Surjyendu R.

Data Science and engineering across business verticals, ML/AI solutions to provide comprehensive analysis and recommend solutions to address complex business problems and issues using data.

• Development of bioinformatics algorithms and pipelines to gain insights from patient multi-omics data. • Analyze and integrate various sources of medical data – insurance claims, electronic health records and other data – to provide actionable insights to research teams at pharmaceutical companies. • Create new machine learning approaches for various clinical data science analysis and prediction tasks. • Python (NumPy, Pandas), Machine Learning frameworks, Data Science, MySQL, AWS Redshift, Apache • Data handling and visualizations using R and Python dashboarding stacks. • Provided comprehensive analysis and recommend solutions to address complex healthcare problems and issues with rare diseases using data from internal and external sources and applied advanced analytical methods to assess factors impacting growth and profitability across product and service offerings. • Applied statistical and algebraic techniques to interpret key points from gathered data. • Applied theoretical expertise and machine learning innovation to create models for rare diseases to tease out hidden associations among myriad data artifacts. • Consulted with users, cloud vendors and data science teams to determine computing needs cloud migration strategies

Development of algorithms for phylogenetic tree reconstruction from NGS data. Benchmarking of established methods phylogeny inference in cancer genomics and finding ways to implement such tools in antimicrobial resistance research in bacteria. Development of novel computational techniques to characterize intra-tumor heterogeneity and reconstruct tumor evolution from NGS data. Administration of domestic cloud solution/portal for data dissemination tasks. Analysis of NGS data (RNA-Seq, TN-Seq transposon sequencing, ChIP-Seq) for antibiotic resistant bacteria experiments. Reconstructing evolutionary trees on parallel computing hardware (OpenMP, GPU CUDA), requirements engineering and testing. Statistical learning algorithm development to predict evolutionary patterns from NGS data. Benchmarking and performance analysis of parallel algorithms and performance optimization techniques to make efficient predictive analysis.

• Python (NumPy, Pandas), Machine Learning frameworks, Data Science, R statistical language, SAS, MATLAB, CUDA GPU programing, Perl, MySQL, Apache • C and C++: Efficient tree optimization algorithm to be run across thousands of CPU or GPU cores, with OpenMP and CUDA respectively. Designed and tested methods for dispatch and collection of results and benchmarking massively parallel tree enumeration algorithms. • Python: o Testing different phylogenetic tree algorithms within a unified test structure. o Context analysis of text from text of research journal articles using LDA and text analysis libraries, nltk, LDA topic modeling and scikit-learn. o SVM and SVM+ with LUPI machine learning paradigms, and random-forests using sci kit-learn, and necessary mathematical modeling. • Publications: • Manuscript titled "On the Complexity of the Weighted Fused Lasso” accepted for publication in IEEE Signal Processing Letters (2018). The published paper is available at: https://ieeexplore.ieee.org/abstract/document/8450614/ • Manuscript titled “Efficient Projection onto the Perfect Phylogeny Model” accepted for publication at NIPS, 2018. The published paper is available at: http://papers.nips.cc/paper/7665-efficient-projection-onto-the-perfect-phylogeny-model

Finding out ways to do genomics analysis, for RNA-Seq and ChIP-Seq experiments, improving present generation bioinformatics tools and coming out with new ways of analyzing next-generation sequencing data. • Software pipelines for analysis of RNA-Sequencing data i.e. statistical analysis of massive genomic data sets. o RNA sequencing methodology, ChIP sequencing, computational analysis of various types of sequencing expression data, motif analysis, gene clustering and gene network analysis. o Associated database administration tasks and software development to create frameworks for analyzing big data.

Grading test papers • Designing course structure and content • Teaching large classes of undergraduate students • Teaching assistant for graduate level Parallel and Distributed systems course. Main responsibilities were to look at the evaluation aspects of the course, such as grading assignments, and making students better understand the concepts being taught in the class and how to apply them in the real world.

• Bioinformatics research projects, 2012-present, Statistical analysis of large data sets as well as computational analysis of different types of biological and genomics data. • Analyzing novel algorithms for computation on and visualization of high throughput, genomic, sequencing data, 2013-present. • Software engineering and requirements analysis, 2012-present, eliciting software requirements from biologists about processes pertaining to large genomic data sets. • iOS mobile programming project, 2011, Evolution of legacy web server code into the iOS platform, server iPhone App. • Florida State University, December, 2010 Developed a compiler for a C-sublanguage and related components • Florida State University, 2009. Developed a small database management system • Florida State University, 2009. Developed a complete online real estate advertisement listing service website and related components using JAVA technology

B.P.Poddar Institute of Management and Technology, Kolkata, India (March, 2009). Led a team to develop a complete online shopping website solution using Java Programmed a complete online shopping website and related systems using JAVA technology • Globsyn Technologies Limited, Kolkata, India, 2008 Led a team to develop an Application to Automate Billing System of a Mobile Telecom Operator using JAVA Programmed an application to automate the Billing System of a Mobile Telecom Operator using JAVA technology • Completed a 60-hour training in core JAVA concepts, at Globsyn Technologies Limited, Kolkata, Dec 2007 -January 2008