Data Science Analyst I Cardiovascular Research Institute
Share
Job Location:
New York City, NY - USA
Monthly Salary:
Not Disclosed
Posted on:
9 hours ago
Vacancies:
1 Vacancy
Job Summary
Details of Research Project:
Single-cell and spatial transcriptomics data provide a static view of healthy and disease states. Several deep-learning models including foundation models have been developed to predict dynamic changes that can drive biological systems from disease to healthy states. However most of these methods are not geared towards heart failure and cannot readily be used for in silico perturbation. Importantly these methods do not explicitly take into account information on the drug-protein interactions.
We are seeking a highly motivated data analyst to develop and deploy active learning frameworks leveraging high-dimensional omics (e.g. transcriptomics) to accelerate identification of functional modulators of disease phenotypes. The role combines deep learning systems biology and iterative model-informed experimentation to drive biological discovery and therapeutic target nomination building on cutting-edge methodology demonstrated in recent Science publications.
Responsibilities
- Develop and Improve Active Learning Pipelines
- Lead design and implementation of deep learning-driven strategies tailored to single-cell multi-omics datasets.
- Optimize model selection acquisition functions and training procedures for phenotypic hit identification.
- Ensure scalability of algorithms for large compound libraries and complex biological endpoints.
- Integrate Transcriptomic & Phenotypic Data
- Build pipelines to preprocess integrate and embed perturb-seq transcriptomic profiles with phenotypic measurements.
- Use dimensionality reduction feature learning and representation techniques to improve model interpretability.
- Lab-in-the-Loop Iterative Discovery
- Implement iterative lab-in-the-loop refinement connecting predictive models to experimental feedback.
- Work with wet lab partners to incorporate experimental results into subsequent training rounds.
- Collaborate with experimental teams to design validation studies based on model suggestions.
- Support Biological Insight and Interpretation
- Analyze model outputs to generate biological hypotheses and mechanistic insights.
- Prioritize candidate modulators for downstream validation based on model confidence and biological relevance.
- Develop visualization tools and reports to communicate findings to interdisciplinary teams.
- Publish and Communicate Scientific Advances
- Document and publish algorithms benchmarking results and biological discoveries.
- Present findings at conferences and internal research symposiums.
- Other duties as assigned.
Qualifications
- BA or BS degree minimum in a relevant field of study (Computer Science Bioinformatics Systems Biology Computational Biology or related field with strong ML emphasis); Masters degree preferred.
- 2 years minimum is preferred
- Track record of developing and applying deep learning or active learning models in biological domains.
- Proficiency in Python ML frameworks (e.g. PyTorch TensorFlow) and statistical analysis.
- Experience working with high-dimensional omics data (e.g. RNA-seq single-cell data).
Required Experience:
IC
Key Skills
- Data Analytics
- Microsoft Access
- SQL
- Power BI
- R
- Data Visualization
- Tableau
- Data Management
- Data Mining
- SAS
- Data Analysis Skills
- Analytics
About Company
Strength through Unity and Inclusion The Mount Sinai Health System is committed to fostering an environment where everyone can contribute to excellence. We share a common dedication to delivering outstanding patient care. When you join us, you become part of Mount Sinai’s unparalleled ... View more
