BACKGROUND

RESPONSIBILITIES

• Develop genetic variant annotation systems using machine learning
• Process and analyse RNA-sequencing data, e.g. for expression analysis
• Work with cancer data-sets from collaborators and from publicly available resources
• Perform analysis on somatic (tumor) specimens and identify putative driver mutations
• Assist in the design and implementation of benchmarks for variant annotation algorithms, including Deep Genomics' in-house machine learning algorithms
• Draft manuscripts for high-impact publications

REQUIREMENTS

• B.Sc. or M.Sc. in Computer Science and/or Biology
• PhD in Bioinformatics
• Strong background in genome biology, ideally focusing on computation and analysis
• Strong publication record in top journals (e.g. Science, Nature, Cell)
• Recent experience working with RNA-sequencing and other Next Generation Sequencing (NGS) data sets for cancer, including data from The Cancer Genome Atlas (TCAG)
• Experience working with public data sets, including COSMIC, dbSNP, HapMap
• Experience working in scripting languages (Python, R, Perl), SQL databases, and Linux
• Strong understanding of machine learning concepts (training, cross validation, features, regularization, etc.) and experience with basic algorithms (e.g. regression; LASSO)
• Strong understanding of performance metrics (log likelihood, AUROC, AUPR, etc.)
• Experience using with NGS alignment (e.g. BWA, GSNAP, Bowtie, TopHat), variant calling (e.g. GATK, SAMtools, MuTect) and variant annotation tools (at least one of ANNOVAR, VEP, SnpEff)
• Experience in human genetics research data is preferred.
• Experience working with micro-RNA (miRNA) data is desired.
• Experience with pathway/gene-set enrichment analysis (e.g. GSEA) is desired.

COMPENSATION

TERMS

LOCALE

HOW TO APPLY