Featured Exosome Job – Data Scientist

About Mantra Bio:

At Mantra Bio, we seek to eliminate disease-related suffering to enhance the well-being of all. We believe that the key to creating cures is targeted, tissue-specific delivery of therapeutics for dramatically increased efficacy and reduced toxicity. To achieve this, our team of biologists, data scientists, and platform engineers have created REVEALTM, a targeted cargo delivery platform that harnesses exosomes, the body’s natural cellular transport system, to create  highly tunable exosome therapeutics for some of the most devastating  diseases. The foundation of our success is our truly interdisciplinary team of experts who work collaboratively to use the power of data science to fuel and accelerate our wet-lab successes. As a team, we value Self-Empowerment, Candor, Curiosity, and Collaboration and consider our human-centric culture to be our most important asset. We are proud to count 8VC, Viking, Illumina, Allen & Company and TenCent among our investors. Mantra Bio operates out of a newly constructed facility in South San Francisco.

About the role:

Mantra Bio is seeking an experienced Data Scientist to join our Platform team to lead the development of our locational protein target discovery platform. You will be a key contributor to our exosome therapeutic programs that span both early R&D and preclinical IND efforts. The position requires broad technical experience that spans statistical and machine learning approaches in biology, medicine, or a closely related field. You will use your expertise to gain insights into EV-cellular protein binding from proteomic, transcriptomic, and genomic data by applying existing methods when appropriate, and identifying opportunities to develop new methods to accelerate our exosome targeting capabilities. You will collaborate across Mantra Bio with Protein Scientists, Process Scientists, Data Scientists, and Engineers to rapidly implement, optimize, and scale up in silico experiments that guide in vitro and in vivo targeting efforts. You are creative and curious, as well as operationally-minded, detail-oriented, and able to run multiple projects in parallel to drive the team forward.


  • Use appropriate machine learning and statistical methods to gain insights from our experimental data and publicly available proteomic, transcriptomic, and genomic resources
  • Work with target validation and protein scientists to generate hypotheses and coordinate execution of wetlab and drylab experiments to efficiently test these hypotheses
  • Critically evaluate computational and wetlab assay methods in publications used as evidence for locational protein targets
  • Effectively use public datasets and guide generation of internal experimental data to characterize and evaluate locational protein targets
  • Develop novel computational methods as needed to advance our understanding of interactions between EVs and locational protein targets
  • Create appropriate visualizations and tools to enable scientists to explore and gain actionable insights from the output of your algorithms
  • Collaborate with other Data Scientists on models, algorithms, and tools
  • Plan, prioritize, and coordinate tasks across multiple projects

What we’re looking for:

  • PhD in statistics, computer science, biomedical informatics or related field, or MS degree with 3+ years relevant experience
  • Strong track record of scientific contributions in the development of machine learning or statistical methods
  • Expertise in Python or R for machine learning and statistical modeling
  • Experience working with large datasets and creating complex data visualizations
  • Demonstrated ability to critically evaluate the quality of biological datasets based both on assays used and transparency of the data provided
  • Proven ability to foster strong interdisciplinary scientific collaborations with teams including wetlab research scientists, data scientists, and engineers
  • Highly self-motivated individual contributor able to prioritize clear, succinct, and timely communication to work effectively within a dynamic team
  • Ability to implement pipelines to run experiments and analyze results at scale is a plus
  • Experience with JupyterLab is a plus
  • Experience with mass spectrometry data or a strong desire to gain this expertise is preferred
  • Familiarity with protein structure and binding prediction methods is a plus
  • Knowledge of immunology, post-translational modifications, signaling mechanisms and other critical factors that impact translation of in vitro to in vivo results is a plus

Leave a Reply

Your email address will not be published. Required fields are marked *