Job Summary:
The data engineer will extract omics and health outcome data (genomics, transcriptomics, etc.) from the Growing Up in Singapore Towards healthy Outcomes (GUSTO) study and build knowledge graphs that describe risk factors of child mental health. They will work with engineers at BII and IHPC to visualise the knowledge graphs and build AI models to reason from the graphs.
Job Responsibilities:
- Implementation of effective data management, including quality control and data processing, across the clinical, multi-omics data in GUSTO.
- Apply genome-scale network reconstruction and constraint-based modelling to generate knowledge graphs that describe relationships between genes and mental health conditions.
- Develop and implement databases for storing knowledge graphs, like Neo4j.
- Apply visualisation tools, like Cytoscape, to rend the graphs and facilitate analysis by clinical researchers.
Job Requirements:
- A Bachelor/Master Degree in Public Health, Data Science, Statistics, Mathematics, Computer Science or related field.
- Good programming skills (Python, R, PyTorch, High Performance Computing solutions).
- Experience with advanced computational methods such as deep learning and graph neural networks for population health analytics.
- Knowledge/experience on Good Clinical Practice (GCP), Good Clinical Data Management Practices (GCDMP) guidelines and research data management.
- Good team player and communication skills for collaborative research.
- 2 - 3 years’ experience.
