Ladan Doroud
Email: ladan.doroud@gmail.com
Address: San Francisco, CA
I am a data scientist at color.com since January 2020. My main focus in the past couple years has been on R&D as well as development of polygenic risk scores as a preventive measure for individuals from diverse populations. Prior to color, I was a staff scientist at Ancestry.com where I worked in the DNA Science team on projects involving big data and computational biology. Before I got introduced to population genetics, I was a PhD student in Computer Science at University of California, Davis where I worked with Prof. Jonathan Eisen at UC Davis Genome Center and focused on microbial interactions as a graph problem. Recently, I am more interested in human genetics and phenotype associations, algorithm development, big data and microbiome!
Programming Languages: Python, Bash, AWK, SQL Machine Learning: Scikit-learn, Tensorflow (keras) Analytics: ETL, SQL, Django, dbt, Google BigQuery, Metabase
Big Data: Hadoop and Map Reduce, Spark Computing: Amazon AWS, HPC, Slurm, Git, Jupyter
Data Scientist - Color.com (2020 - Present)
- Working on polygenic risk scores (PRS) where I exclusively owned end-to-end lifecycle of this project, starting from R&D, imputation, data analysis, modeling and clinical validations to productionizing and supporting ETL, reports and dashboards for analytics
Genomics Data Scientist (Staff Scientist) - Ancestry.com (2017 - 2020)
- Extensive algorithm and software development as well as project management for Matching, Genetic Communities as well as Health products
Co-Founder at Animal Microbiome Analytics - Funded by Indiebio (2016)
Insight Data Science (Fellowship - Summer 2016)
- Developed an optimized pipeline enhancing anomaly detection in Lending Club data and built an internal recommendation app to reduce the risk of late payoffs and loan defaults
- Delivered a risk estimator using scikit-learn’s random forest classification algorithm
- Deployed a web app online using flask, bootstrap and javascript and hosted the app on Amazon AWS
Ancestry.com Inc. (Internship - Summer 2015)
- Computational Biologist at AncestryDNA
- Large scale network analysis (community detection) to find novel IBD clusters
- Data mining and developing an efficient pipeline (using Hadoop) for SNPs/haplotype matching among 1 million customers which resulted in de bruijn graphs of the hapotypes
Udacity, Inc. (Internship - Summer 2014)
- Course Manager for Data Science Nanodegree
- Maintained and supported the following courses: Hadoop and Map Reduce, Data Science, Exploratory Data Analysis, Statistics
- Assisted in designing and gathering materials for new online courses
Jonathan Eisen’s Lab – Graduate Student Researcher 2010-Present
Designing and implementing novel approaches toward community detection and function prediction for large-scale networks of protein sequences
COSMOS program Summer 2011
Teaching assistant for California State Summer School for Mathematics and Science at UC Davis, Responsible for teaching computer programming in robotics
University of California, Davis (2010—2017)
Major: PhD: Computer Science
University of California, Davis (2010—2013)
Major: Masters: Computer Science
Shahid Beheshti University (2006—2010)
Major: Bachelors: Computer Science
[White Paper]: Genome-wide Polygenic Score Download PDF
[Paper]: Holly H. Ganz (joint first author), Ladan Doroud (joint first author), Alana J. Firl, Sarah M. Hird, Jonathan A. Eisen, Walter M. Boyce. "Community-level differences in the microbiome of healthy wild mallards and those infected by influenza A viruses". (2017) Download PDF
[Paper]: Katherine Dahlhausen, Ladan Doroud, Alana Firl, Adam Polkinghorne, Jonathan Eisen "Characterization and Temporal Shifts of Koala (Phascolarctos cinereus) Gut Microbial Communities Associated with Antibiotic Treatment". (2017) Download PDF
[Paper]: Ashley Vater , Vivian Agbonavbare , Dylan Carlin , Griselda Carruthers , Adam Chac , Ladan Doroud , Samuel Farris , Melanya Gudzeva , Guillaume Jospin , John Kitner , Jonathon Knauss , Yi Lor , Randi Pechacek , Eden Rohner , Sierra Simmons , Mayya Verescshagina , Christian Wirawan , Leonel Zagal "Draft Genome Sequences of Shewanella sp. UCD-FRSP16_17 and 9 Vibrio Strains Isolated from Abalone Feces" (2016) Download PDF
[Paper]: Dongying Wu, Ladan Doroud, and Jonathan A. Eisen. "TreeOTU: Operational Taxonomic Unit Classification Based on Phylogenetic Trees." arXiv preprint arXiv:1308.6333 (2013). PDF in arXiv.org
[Technical Book Review]: Review of the book "Mastering Gephi Network Visualisation", Packt Publishing (2014) Link to the book
[Poster]: Ladan Doroud, Jonathan A.Eisen. "Use of Extreme Sets as a Tool in Making Predictions of Protein Function from Sequence" CRA-Women Graduate Cohort Workshop (2014)
Patent: Community assignments in identity by descent networks and genetic variant origination
Google Code Jam: Won Google Code Jam to I/O 2016 contest (for Women)
Fellowship: Insight Data Science Fellows Program - 2016
Fellowship: Graduate Research Fellowship - 2015
Certificate: Center for Excellence in Teaching and Learning, UC Davis Awarded certificate in Learner-Centered Teaching: Designing Courses, Activities, and Assessments to Enhance Student Learning - 2013