Persephone Biosciences is an emerging company investigating the impact of the gut microbiome on human disease, and developing engineered live therapeutic products aimed at disease treatment and prevention. Our goal is to develop a new paradigm in drug development based on artificial intelligence applied to real-world patient data. We have recently launched the Argonaut clinical trial, aimed at gathering microbiome and immune data from thousands of cancer patients and healthy controls. We are currently seeking a computational scientist to organize, analyze and interpret the large quantity of omics data generated from this and similar studies. The successful candidate will develop machine learning models to identify key biomarkers based on microbiome and immune profiling data, and use data to unravel the complexities of the gut ecosystem and improve our understanding of the mechanisms of interaction between microbial and human physiology. The candidate will be involved in all aspects of the company’s research, making decisions that will impact the company’s clinical programs.

Job responsibilities are as follows:

• Develop the computational infrastructure to store and manage patient clinical data and results of sample analysis.
• Develop and implement data analysis pipelines for next-gen sequencing data (both DNA and RNA) from metagenomic samples.
• Analyze results of immune profiling experiments such as single cell proteomics (CyTOF) and cytokine measurement.
• Develop and customize statistical and machine learning algorithms to meet complex project requirements; tasks include managing heterogeneous datasets, defining hypotheses, executing necessary tests, and optimizing algorithms and methods to specific situations.
• Use metabolic modeling or other approaches to understand the interactions among microbes in the gut community, and with the host immune system.
• Regularly interact with lab personnel, participate in experimental design, and use results of modeling and bioinformatics analysis to guide experimental work.
• Collaborate with internal and external stakeholders to proactively identify and resolve various data issues.
• Communicate results in oral and written form, including internal and external presentations, manuscripts, and patent applications.
• Depending on level, may supervise other scientists or lead small project teams.

Requirements:

• PhD in Bioengineering, Computer Science, Statistics, Data Science, or related field.
• Postdoc or industry experience preferred (title and salary will be based on experience level). • Expert in statistical analysis methods, with extensive knowledge in machine learning fundamentals, data mining technologies, and data visualization methods. • Experience developing and running machine learning models with heterogeneous biological datasets. • Extensive experience in DNA and RNA sequence analysis with data from the Illumina and Nanopore sequencing platforms, and the ability to derive biological understanding from the results. • Proficient in Python, R, or Java programming, and able to interface with cloud-based resources. • Experience constructing databases for heterogeneous datasets. • Working knowledge of microbial physiology, immunology, or cancer biology. • Innovative and independent scientific thinking, leadership, and enthusiasm.