www.fernandogelin.com

     lnkdin.me/fergelin

     github.com/fernandogelin

     fernando@fernandogelin.com

     802.310.6213

technical skills

programming languages python, r database SQL, mongoDB scripts JavaScript, CoffeeScript web HTML, CSS, Bootstrap platforms linux, macOS data formats csv, json, xml, unstructured, python dict IDE jupyter, r studio cloud AWS other bash, *nix command line, tableau

data scicence tools

python pandas, numpy, scipy, scikit-learn, matplotlib, bokeh, seaborn, graphlab-create, spark R dplyr, data.table, ggvis, ggplot, caret, shiny JavaScript D3.js, json

other skills

languages portuguese, english, spanish project management MS Project, agile, scrum bioinformatics high-throughput sequencing and analysis, r bioconductor, biopython, healthcare, GATK

Fernando Gelin

Data Scientist

Education

Project Management Certificate, Biotech Jan 2015 - Nov 2015

University of Washington, Seattle, WA / University of California, San Diego, CA

Ph.D. Biology Sep 2009 - May 2014

University of Vermont, Burlington, VT

Relevant coursework / Online training

The Data Scientist’s Toolbox R Programming Getting and Cleaning Data Exploratory Data Analysis Reproducible Research Using the Command-Line for Analysis of High Throughput Sequence Data Machine Learning Foundations: A Case Study Approach Data Manipulation at Scale: Systems and Algorithms Machine Learning: Regression Machine Learning: Classification Project Management: Standards and Processes Project Management Within a Biotech/Research Environment Applying Project Management Principles to Biomedical and Pharmaceutical Product Development Accessing Biomedical Big Data Visualization of Biomedical Big Data

Experience

Senior Research Fellow Jun 2014 - Jun 2016

Department of Psychiatry and Behavioral Sciences - University of Washington, Seattle, WA

  Analyzed human genome sequences using cutting edge bioinformatics tools such as GATK, Picard, BWA.

  Developed Python scrits for data cleaning, processing, and visualizations.

  Created a R shiny app to explore and visualize variant data.    

  Created a web application to generate protocols and calculate reagent amount for targeted sequencing reactions.    

Other Projects

Pronto Cycle Share Data Challenge      

   Data analysis and visualization of Seattle's bike share service first year of opperation.

   Tools: R dplyr, data.table, reshape2, jsonlite, leaflet, maptools web HTML, CSS, JS, D3.js.

Obesity Comorbidity Analysis   

   Obesity comorbidity analysis using PubMed articles database.

   Tools: Python pandas, numpy, json, urlib2, sqlalchemy, biopython, entrez, bokeh database PostgreSQL cloud AWS RDS.

Brainspan Viz   

   Interactive visualization of gene expression by braing region and age using data from brainspan.org (in progress).

   Tools: Python pandas, numpy, pymongo, scipy, scikit-learn, bokeh database MongoDB.

  PDF