Ramit Bharanikumar

GRADUATE RESEARCH ASSISTANT AT GEORGIA TECH| Phone: (404)5429041| ramitbk29@gatech.edu

I am a Bioinformatics graduate student at Georgia Tech. I'm currently working in the McDonald lab on using blood metabolite data for the stage-specific diagnosis of Ovarain Cancer. I'm also involved in a project in predicting optimal cancer drug therapies from microarray data.

As a graduate student, I've gained experience working with a range of bioinformatics tools and pipelines through the challenging coursework at Georgia Tech. As a Graduate Research Assistant in the McDonald lab, I've developed a strong understanding of Cancer Biology and experience building machine learning pipelines for early stage Ovarian cancer diagnosis.

As an undergraduate I developed a strong theoretical and practical understanding of Molecular Biology ,Genetics and Machine Learning. I built a Bioinformatics tool that predicts the strength of sigma 70 promoters in Escherichia coli and used Deep Learning to predict riboswitch classes using their sequence information. I also led my college's iGEM(international Genetically Engineered Machines Competition) held at Boston to a silver medal in 2017 and was a part of the team that won a silver medal in 2016.

When I'm not working on something at the intersection of Biology and Computer Science, you can find me running on the streets of Atlanta, reading a pop science book or trying out different grilled chicken recipes.


Bioinformatics Tools and Pipelines

Tools and Databases: Galaxy, GATK, Samtools, VCFTools, BLAST+, Salmon, T-Coffee, Sleuth, DESeq-2, Clustviz, Reactome, GEO, UCSC Genome Browser and 1000 Genomes Project

Pipelines: Variant Calling, RNA-Seq Analysis, Microarray Gene Expression Analysis, Genome Assembly, Gene Prediction, Functional Annotation, Comparative Genomics and Exome Analysis.

Languages, Libraries and OS

Languages: Python, R, Javascript and Bash

Libraries: Biopython, Bioconductor, Numpy, Tensorflow, Sci-kit Learn, Multiprocessing, regex, sigFeature, affy, limma,d3.js,seaborn, and Keras

Database Technologies: MySQL and SQLite

Cloud Technologies: AWS and Azure

Web Technologies: HTML,CSS,Flask

Version Control: Git, Github and Gitlab

OS: macOS, Windows and *nix environments


PromoterPredict: sequence-based modelling of Escherichia coli σ70 promoter strength yields logarithmic dependence between promoter strength and sequence

We present PromoterPredict, a dynamic multiple regression approach to predict the strength of Escherichia coli promoters binding the σ70 factor of RNA polymerase. σ70 promoters are ubiquitously used in recombinant DNA technology, but characterizing their strength is demanding in terms of both time and money. Using a well-characterized set of promoters, we trained a multivariate linear regression model and found that the log of the promoter strength is significantly linearly associated with a weighted sum of the –10 and –35 sequence profile scores. It was found that the two regions contributed almost equally to the promoter strength. PromoterPredict accepts –10 and –35 hexamer sequences and returns the predicted promoter strength. It is capable of dynamic learning from user-supplied data to refine the model construction and yield more confident estimates of promoter strength.

  • Language & Frameworks: Python (Biopython, Webpy), HTML, CSS, Javascript
  • Source Code Management: Github


Aug 2018 - Present
Graduate Reserach Assistant - Georgia tech

Working in the McDonald lab at Georgia Tech on using metabolite data from blood to predict the stage specific precense of Ovarian cancer and using Supervised Machine Learning models to predict optimal cancer drug therapies.

Jan 2017 - July 2018
Undergraduate Reserach Assistant - Anna University

Under the supervision of Dr.Ashok Palaniappan, used Machine Learning and Deep Learning models to classify Riboswitches without feature engineering the data. Current version of the model can classify 16 classes of Riboswitches with an accuracy of 97% across training , test and validation sets. Data was obtained from the rfam database.

Jan 2017 - Nov 2017
Team Leader - SVCE iGEM 2017

Under the supervision of Prof. Nalinkanth V. Ghone, worked on providing a gene regulator with the best properties of transcriptional and translational regulators. Characterized and validated the functionality of this gene regulator with a pH sensitive and temperature sensitive riboswitch in Escherichia coli.


Stage-specific Ovarian cancer diagnosis

The overall goal of this research project is to employ SVM coupled with an Recursive Feature Elimination (RFE) algorithm to extract a minimal set of features that are highly informative for the diagnosis of ovarian cancer using metabo- lite level data obtained from the blood sera of patients.

Alternate models for selecting definitive features such as using a Stacked Denoising Autoencoders (SDAE) to trans- form highdimensional, noisy gene expression data to a lower dimensional, meaningful representation will be built. The results from the SDAE will be compared to more the ex- isting SVM-RFE model’s performance metrics and provide an opportunity to compare deep learning models to more traditional machine learning models in extracting informative features from datasets that are small in sample size but high in dimensionality.

Link to git repo

Optimal Cancer Drug Prediction

The goal of this research project was to predict optimal cancer drug therapies using patient microaaray data and the GI50 values of individual patient's to a set of seven drugs. The model is to be further validated for more drugs using data from the CCLE. The project was implemented in the R programming language primarily using the sigFeature package.

Link to git repo

Promoter Strength Predictor

Built a bioinformtucs tool that would predict the strength of sigma 70 promoters in Escherichia coli by modelling the -10 and -35 hexamer regions of the promoter. The training data included the Anderson set sequences of promoters and their normalised strengths developed and charachterized at UC Berkley.

Link to git repo

Link to publication

Link to tool

Riboswitch Classification

Compared the performance of different Machine Learning and Deep Learning algorithms on predicting the class of a riboswitch sequence. A RNN(Recursive Neural Network) model out performed every other model in every evaluation metric. A manuscript further detailing the findings is currently under preparation.

Link to git repo


The project involved the design, construction and charechterization of novel genetic circuits for regulating gene expression including a temperature sensitive based quorum sensing system, the RNA thermometer optimised for Bacillus subtilis, a new pH riboswotch and an adaptor to convert translational regulation into transcriptional regulation.

Link to project's wiki


Lactoshield is a project devoted to providing a solution to milk spoilage at the consumer level. Genetically modified bacteria is used to produce peptide sequences that will kill other bacteria in milk, thereby prolonging the shelf life of milk.The genetic circuit of the plasmid used is designed inn such a way that the peptide is only produced at a particuarly high temperature.

Link to project's wiki


M.S. BIOINFORMATICS - Georgia Institute of Technology

GPA - 3.7/4.0

Courses: Programming for Bioinformatics, Genomics and Applied Bioinformatics, CS for Bioinformatics, Computational Genomics, Introduction to Databases, Data and Visual Analytics and Human Evolutionary Genomics.


GPA - 7.7/10.0

Courses: Bioinformatics, Molecular Biology, Cell Biology, Microbiology, Genetic Engineering, Immunology, Cancer Biology, Metabolic Engineering and Enzyme Technology.

MOOC Certifications

Machine Learning - Coursera and Stanford

Link to certification

Neural Networks and Deep Learning - Coursera and deeplearning.ai

Link to certification

R Programming - Coursera and Johns Hopkins University

Link to certification

Improving Deep Neural Networks - Coursera and deeplearning.ai

Link to certification

Structuring Machine Learning Projects - Coursera and deeplearning.ai

Link to certification

The Data Scientists toolbox - Coursera and Johns Hopkins University

Link to certification

Introduction to Genomic Technologies - Coursera and Johns Hopkins University

Link to certification

learning How to learning - Coursera and UCSD

Link to certification

Python Programming - edX and Microsoft

Link to certification