Website Katalyst Healthcares & Life Sciences
Katalyst Healthcares & Life Sciences
Company : Katalyst Healthcares & Life Sciences
Job Description:
The successful candidate will work closely with stakeholders across the IPSI (Immune Profiling & Systems Immunology in Immunology Discovery) organization to advance the Single-Cell Fibroblast Atlas initiative. The role will focus on applying AI/ML and advanced computational methods to large-scale single-cell transcriptomic, proteomics and spatial etc. datasets to define fibroblast states, map tissue-specific niches, and uncover their roles in health and disease.
Responsibilities:
- Curate, harmonize, and analyze large-scale single-cell and spatial omics datasets (internal and public) with emphasis on fibroblast biology.
- Develop and optimize predictive AI/ML models to classify fibroblast states, identify regulatory networks, and generate disease-relevant insights.
- Integrate multi-modal data (scRNA-seq, spatial etc.) to construct a comprehensive fibroblast atlas.
- Collaborate with other stakeholders.
- By building the Fibroblast Atlas, the candidate will enable target discovery while driving cross-functional projects at the interface of data science, immunology, and translational medicine impacting the portfolio.
- Support senior analysts and scientists in implementing, training, and troubleshooting AI/ML models tailored to single-cell and spatial omics data.
- Ingest, clean, and preprocess large-scale single-cell transcriptomic and spatial datasets (public and internal) for single-cell atlas workflows.
- Collaborate with immunology and computational teams to translate biological questions on fibroblast states, niches, and disease roles into computational solutions.
- Document data curation, processing, and modeling pipelines to ensure reproducibility and transparency across the atlas project.
- Assist in interpreting model outputs to generate insights into fibroblast heterogeneity, tissue-specific function.
- Contribute to time-sensitive projects with critical deliverables, supporting target discovery and prioritization within the fibroblast atlas framework.
Requirements:
- MS degree (5+ years of experience) or PhD (0+ years of experience) in a quantitative field (Bioinformatics, Computational Biology, Computer Science, Computational Genetics, Biostatistics, AI/Machine Learning, or related discipline).
- Proficiency in Python and standard ML/data science libraries.
- Experience working on HPC or cloud environments for large-scale omics and imaging datasets.
- Domain knowledge in single-cell analysis, spatial omics, or systems immunology, ideally with exposure to fibroblast or stromal cell biology.
- Strong attention to detail, documentation, and communication skills.
- Ability to independently design, execute, and troubleshoot computational workflows.
Technical Skills:
- Experience with NumPy, Pandas, Scikit-learn, Matplotlib, and Seaborn.
- Familiarity with deep learning frameworks (TensorFlow and/or PyTorch).
- Proficiency with Git for version control and collaboration.
- Hands-on experience with single-cell data analysis tools (e.g., Scanpy, Seurat, Bioconductor, or equivalent).
- Exposure to multi-modal integration methods (e.g., CITE-seq, ATAC-seq, proteomics, imaging mass cytometry, spatial transcriptomics).
- Experience with OpenCV, Scikit-image, or computer vision models for imaging datasets.
- Knowledge of cell type annotation, clustering, and trajectory inference methods.
- Experience building multi-modal AI/ML models that link transcriptomic, proteomic, and imaging data.
Top Skills:
- Implementing, training AI/ML models.
- Data pre-processing for AI compatibility.
- Domain knowledge of bioinformatics.
- Experience working with single cell and spatial data (transcriptomics, proteomics, epigenomics etc.).
- Ability to communicate results clearly.