Translational Informatics Data Scientist

Key Skills

Python Programming, Scala Programming, C++, Java Programming, Machine learning techniques, Data science techniques, SQL, Apache Hadoop, MapReduce, TensorFlow, PyTorch

Job Description

DNAnexus xVantage Group is passionate about partnerships and client success. Our partnership culture is as important as the technology we provide our clients. Our mission is to help our clients achieve their research and clinical goals with the DNAnexus solutions and services. Our team includes highly sought after experts including data scientists, bioinformaticians, cloud computing experts, and software engineers.

Description

This is an exciting opportunity to join DNAnexus’ growing team. We are looking for a Translational Informatics Scientist who enjoys working hands-on with other scientists, software engineers, and clients to solve informatics challenges on the UK Biobank (UKB) Research Analysis Platform (RAP) cloud platform. You will be responsible for developing computational methods and tools for large scale data analysis to get insights out of data in support of translational genomics research. The ideal candidate is a computational biologist with success in leading research projects combining next-generation sequencing data with various forms of phenotypic, transcriptomic, metabolomic, and other clinical data. They will have strong programming skills, expertise in designing scalable solutions and experience in genomic data analysis for inferring meaningful insights from large biological datasets. They will be knowledgeable and keenly intuitive about translational research including techniques for data quality control and data analysis at scale including GWAS, PheWAS, PRS and other multi-omics and machine learning analysis.

Responsibilities

• Develop and apply analytical approaches for large, complex genomic data sets in conjunction with clinical, phenotypic, and multi-omics data.
• Define solutions that meet customer requirements and research goals, working closely with program management and engineering team to drive those solutions through development, testing, and customer validation in an agile environment.
• Conceptualize and develop optimal methods/pipelines and Jupyter Notebooks for a diverse set of genomic data analysis workflows that allow domain scientists and savvy users alike to gain insights from large scale data.
• Analyze real-world datasets such as UK Biobank to understand the underlying data models and research goals.
• Research, integrate, test and validate new bioinformatics methods on the DNAnexus Platform.
• Develop reusable, well-tested software in WDL, Python, R or shell scripting.
• Design data standards and integrate normalized genomics datasets on the DNAnexus platform.
• Develop scientific use cases for presentations, and marketing material.

Requirements

• Ph.D. in computer science, bioinformatics, computational biology, genetics, or related discipline with a computational emphasis.
• 3+ years of experience in bioinformatics, biostatistics, genomics, statistical genetics, population genetics, systems biology, and/or translational research in either academic or industry settings.
• Strong programming skills with the ability to develop reusable, well-tested software with advanced level knowledge in Python, R, and bash.
• Experience with big data analytics technologies including Spark, Hive, and Hadoop, and an understanding of relational database concepts.
• Experience working with large-scale omics datasets, e.g. ENCODE, 1000 Genomes, ExAC/gnomAD, TCGA.
• Familiarity with statistical genetics methods and tools including GWAS (PLINK, HAIL, BOLT-LMM, SAIGE, RVtests, SKAT, METAL), PheWAS (PLATO, PHESANT), Polygenic Risk Score analysis (PRS), Mendelian randomization, fine mapping, pathway analysis.
• Understanding of cloud computing and high-performance computing.
• Excellent leadership qualities, interpersonal skills, and verbal and written communication skills. 
• Thrives in a fast-paced, team-oriented environment.
• Entrepreneurial “can do” attitude with the ability to find creative, pragmatic solutions.

Desired Skills

Below are the skills that are highly desirable, but are not required. DNAnexus will provide the necessary training to qualified candidates:

• Hands-on experience with data wrangling and understanding of big data ETL processes is a plus.
• Hands-on experience with large scale multi-omics data management is a plus.
• Understanding of existing techniques for managing and analyzing genomic, clinical/phenotypic, pharmacokinetic, and other molecular data (transcriptomic, metabolomic, proteomic, microbiome), and the challenges in aggregating datasets for reuse in follow on studies.
• Familiarity with commonly used reference and annotation databases such as OMIM, ClinVar, gnomAD, and multi-omic QTL databases such as GTEx, eQTLgen, SPANR, and others.
• Familiarity with integrated tools such as GDC DAVE, cBioPortal, i2b2 tranSMART, Spotfire, UCSC Genome Browser, and Ingenuity Pathway Analysis.
• Knowledge of data file structures (data dictionaries, data files, codings CSV, and others) and their usage.