Computational Scientist 3, Spatial Omics

Roche • South San Francisco, CA

5d

About The Position

The Opportunity The Research Pathology Department, an integral part of Genentech’s Research and Early Development Organization (gRED), is dedicated to ensuring that strategies for the treatment of diseases are grounded in accurate analyses of pathogenetic mechanisms. Building upon a strong foundation in digital pathology, the department is at the forefront of advancing spatial omics capabilities, integrating cutting-edge, tissue-based technologies with computational methods to enable high-resolution spatial profiling of biological systems. By collaborating with therapeutic areas and research scientists, the department supports the discovery, characterization, and development of treatments for a wide range of diseases. DPIA-SO (Digital Pathology Image Analysis-Spatial Omics) is a specialized team within Research Pathology focused on collaborative spatial omics computational analysis. The team’s mission is to provide scientists with actionable insights from high-dimensional imaging data by developing and employing transparent, reproducible, and scalable spatial analysis methods and pipelines. We are seeking a highly skilled and motivated Spatial Omics Computational Scientist to join our team. In this role, you will operate at the intersection of computer vision, machine learning, and biology. You will be responsible for architecting computational frameworks and executing them in targeted scientific projects that integrate single-cell spatial transcriptomics, high-plex proteomics, and digital pathology images across a range of therapeutic areas.

Requirements

• Advanced degree (M.S. or Ph.D.) in Computational Biology, Bioinformatics, Data Science, Imaging Science, Computer Science, or a related field.
• Proficiency in Python software engineering, including experience with Nextflow or similar workflow orchestrators for building reproducible pipelines.
• Demonstrated image processing experience, specifically with high-dimensional or tissue-based imaging data.
• Experience with machine learning techniques and modern frameworks (e.g., TensorFlow, PyTorch, scikit-learn).
• Expertise in statistical analysis and structured data analysis (e.g., high-dimensional data reduction, validation, and statistics) and data visualization.
• Excellent problem-solving skills with the ability to work independently as a technical lead and collaboratively in a multidisciplinary environment.
• Strong verbal and written communication skills to effectively present findings to diverse audiences and prepare technical reports.

Nice To Haves

• Demonstrated expertise in single-cell spatial transcriptomics and/or spatial proteomics analysis.
• Hands-on experience with specific spatial omics platforms, including 10X Genomics Xenium, Visium, and Lunaphore COMET.
• Hands-on experience with multi-modal data integration, specifically combining spatial transcriptomics, proteomics, and histology datasets.
• Experience handling large-scale image and single-cell spatial data structures.
• Familiarity with the scverse ecosystem (e.g., Scanpy, Squidpy, SpatialData, scVI) as well as computer vision libraries like OpenCV and scikit-image.
• Understanding of infrastructure for managing large-scale imaging data, including AWS cloud-based storage and distributed computing.
• Knowledge of computational pathology or digital pathology workflows and proficiency in tissue-based image processing.
• Solid understanding of tissue histology, cell biology, and tumor microenvironments.
• Familiarity with tissue imaging techniques such as multiplexed immunofluorescence, in situ hybridization, or related methods.

Responsibilities

• Serve as Technical Lead for collaborative research projects, translating abstract biological questions from scientific stakeholders into rigorous computational strategies and executable analysis plans.
• Architect and execute complex, end-to-end analytical strategies for high-dimensional spatial datasets (e.g., 10x Xenium, Visium HD, Lunaphore COMET, Akoya), moving from raw image processing to actionable biological insight.
• Develop integration frameworks to co-register and harmonize disparate modalities—fusing morphological features (H&E) with molecular data (transcriptomics/proteomics) to uncover spatial niches and cell-cell interactions.
• Develop, optimize, and apply machine learning techniques for quality control, image segmentation, feature extraction, data integration, predictive modeling, and spatial analysis.
• Engineer and optimize imaging data infrastructure, including workflows for large-scale image storage (e.g., OME-ZARR, OME-TIFF, SpatialData) and associated visualization tools.
• Collaborate closely with pathologists, wet-lab, and dry-lab researchers to interpret data, visualize results, and contribute to upstream experimental design.
• Provide training and consultation to the wider research community on spatial omics data analysis tools and workflows to democratize access to these technologies.
• Stay current with the latest advancements in spatial omics technologies, tissue imaging, and computational methods to drive continuous innovation within the team.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level