Post Job Free

Resume

Sign in

Data Scientist / Bioinformatician

Location:
Charlotte, NC
Posted:
August 05, 2017

Contact this candidate

Resume:

EDUCATION

Masters of Science in Bioinformatics - University of North Carolina, Charlotte May 2016

Bachelor of Science in International Business - Southern New Hampshire University

DATA ANALYSIS/TECHNICAL SKILLS

Programming: Scientific Python (Pandas, Scikit-learn, Scipy etc.), R, Spark, Scala, DataBricks, AWS.

Data Bases: Database Design and Implementation, MySQL, PostgreSQL, Linux.

Machine Learning: Predictive Analytics, Theano, Tensor Flow, Keras, Time Series, Generative Texts, Multi-Layered Perceptron (MLP), Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Natural Language Processing (NLP), Data Visualization, XGBOOST.

Algorithms for Regression Problems:

Linear: Linear Regression, Ridge Regression, LASSO Regression, and ElasticNet Regression.

Non-Linear: K-Nearest Neighbors, Classification & Regression Trees, and Support Vector Machines.

Algorithms for Classification Problems:

Linear: Logistic Regression, Linear Discriminant Analysis.

Non-Linear: K-Nearest Neighbors, Naïve Bayes, CART and Support Vector Machines.

Ensemble Methods for Improving Performance:

Boosting Methods, Bagging Methods, Voting Methods

RESEARCH PROJECTS

Multi-Layered Perceptron (MLP): Logistic/Linear Regression using MLP for regression and classification problems.

Convolutional Neural Networks (CNN): image recognition and Sentiment Analysis (NLP)

Natural Language Processing: Sentiment Analysis, text preprocessing, using LSTM and CNNs. Use of NLP and various libraries to preprocess the data using porter-stemming, tokenizing, regular-expressions, beautiful soup bag of words, python, NLTK.

Recurrent Neural Networks (CNN + RNN + LSTM): Time Series, Predictive Analytics and Generative Text.

PROFESSIONAL WORK EXPERIENCE

UNCC Charlotte Department of Bioinformatics and Genomics (DHMRI) – Kannapolis Jan 16 - May 16

Research Assistant

Development and maintenance of large databases including MySQL via Python.

Data-Mining on targeted search queries in an ensemble of databases using Linguamatics software package.

Database development for molecular sequence data, connecting and extracting relevant information from various tables within the database.



Contact this candidate