Oncology Information Practice Data Science Summer Internship Cambridge, East of England, England
Job description
Oncology Information Practice Data Science Intern
Combining the Power of AI and NLP to automate information provision and clinical insight generation
About the organization
AstraZeneca is a global, biopharmaceutical business that focuses on the discovery, development, and commercialization of prescription medicines, primarily for the treatment of cardiovascular, metabolic, respiratory, inflammation, autoimmune, oncology, infection, and neuroscience diseases! AstraZeneca operates in over 100 countries and its innovative medicines are used by millions of patients worldwide. For more information, please visit www.astrazeneca.com.
Description
Oncology Information Practice department is part of Oncology Biometrics and delivers information, data, and tools to support internal decision making, regulatory submissions for the portfolio of drug projects within the Oncology R&D organization! The Oncology IP department is increasing automation for information provision and knowledge management for clinical data and insight to support oncology drug projects and decision making. The intern will contribute to our initiative that incorporates Natural language Processing (NLP), data curation, data extraction, text classification and database build on a joint project with with the NLP engineering R&D IT team and the Oncology Data Science and AI Knowledge graph team.
We are currently seeking candidates with a Master’s degree, or who are working towards acquiring a Master, or Doctorate degree in Data Science, Computer Science, Computational Linguistics for an 8–12-weeks internship contract during the summer of 2023.
Main Duties and responsibilities
We would like a passionate intern to continue building on what we have already developed and to work in collaboration with the AI engineering team from Enterprise AI and the Oncology Data Science and AI Knowledge Graph team to generate insight to support oncology drug projects and decision making.
As Data Scientist Intern you will have the opportunity to work collaboratively with IP team members, NLP engineers, and data scientists across AstraZeneca.
The position will provide you with opportunities to gain understanding of published clinical data and data sources and apply ML/NLP techniques and programming skills to help support our scientists and clinical experts push the boundaries of science to develop life changing medicines for patients. It will also help you with gaining drug development, oncology ontology and enhancing technical knowledge.
Potential Key Responsibilities:
- Collaborate with Information Practice members, NLP engineers and data scientists to apply/enhance existing ML/NLP models and pipeline approaches to build automation for extracting key information from published articles and data sources for clinical information
- Assist in building list and classification of the standard ontologies used in Oncology data and associated searches and queries
- Develop smart and reusable clinical data queries on a NLP based platform
- Assist with data quality assurance and compliance
- Assemble and prepare materials for presentations/reports.
Desirable Experience & Qualifications:
- Master's or PhD students pursuing degrees in Data Science, Computer Science, Computational Linguistics, Machine Learning
- Coding in Python
- Statistical knowledge, data science knowledge, data visualization, machine learning skills such as: regression, classification, clustering, NLP, graph theory or similar.
- Planning, organisational and time management skills.
- Collaborative, with a partnership approach
- Authorized to work in the UK
