Full-Time NLP Data Scientist/Scientific Data Engineer
Job Description
About the team/job
Safety and toxicology concerns remain one of the most persistent challenges in drug discovery. This is an exciting opportunity to join a multi-disciplinary team on a project to develop a comprehensive open source side effect resource for the scientific and pharmaceutical community, and provide structured and standardised training sets for AI/ML applications to improve early identification of safety liabilities.
You will harness modern Natural Language Processing (NLP) techniques to extract data from a range of relevant resources, such as clinical trials, publications and drug labels. You will work closely with team members to ensure development of automated pipelines and effective integration into the ChEMBL database and Open Targets Platform, to assist users in the selection of safe and efficacious drug targets.
The Chemical Biology Services team at EMBL-EBI provides world-leading chemogenomics resources to the scientific community including ChEMBL, a database of quantitative small-molecule bioactivity data curated primarily from the scientific literature widely used to support drug discovery projects in industry and academia. The Safety 2.0 project is funded by Open Targets, a unique public-private partnership working to deliver experimental data and informatics resources that enable scientists to make more informed decisions about target selection for developing safer and more effective drugs. You will interact with safety scientists from Open Targets pharmaceutical partners MSD, Genentech, GSK, Pfizer, and Sanofi to understand requirements and how to help contribute to evaluating drug and target safety. You will be embedded at the world-leading EMBL-EBI, and will work collaboratively across the Chemical Biology Services and Open Targets groups, benefitting from a range of multi-disciplinary expertise and technologies.
Your role
We are looking for two enthusiastic and talented NLP data scientists, cheminformaticians or bioinformaticians with experience in NLP and knowledge extraction to join the Open Targets Safety 2.0 project for a period of 3 years. You should enjoy delving into ways of addressing challenges in knowledge extraction and data standardisation, and want to contribute to open source code and resources.
The project will develop a new side effect resource for drug discovery based on the extraction of side effect data from a range of documents. Your role will focus on developing data extraction pipelines using NLP models and implementing modern NLP methods and technologies suitable to the extraction of safety data. The position provides a real opportunity to make a significant impact on a critical problem in drug discovery for the many users of the Open Targets Platform and an opportunity to contribute to the open source models and code associated with target safety.
This position will be situated across the Chemical Biology Services team and the Open Targets Core Team . You will work closely with other Safety 2.0 project team members to ensure effective delivery of workpackages, and collaboratively with the Chemical Biology Services team and Open Targets Core teams to ensure effective integration and longevity of pipelines and resources.
Key responsibilities
- Develop machine learning pipelines for extracting drug side effects from drug labels, clinical trials, publications and other documents
- Investigate modern NLP methodologies and propose ideas for the implementation of data extraction methods and pipelines
- Apply language models to extract and map drug-related information from unstructured text, e.g. from the scientific literature, ClinicalTrials.gov
- Implement and/or fine-tune different NLP models, e.g. NER models, transformer models, LLMs
- Integrate project workflows with existing infrastructures in the EBI Chemical Biology Services and Open Targets teams
- Prepare and evaluate benchmark datasets from the open domain as training sets for NLP models
- Work with domain experts to develop new gold standards for NLP tasks where needed
- Assist with and/or perform data curation to prepare clean and reliable training sets
- Apply and/or adapt existing methods for mapping extracted entities to biomedical ontologies, e.g. drugs, side effects/phenotypes, and diseases
- Work closely with Safety 2.0 project group members bridging the ChEMBL and Open Targets teams
- Work closely with the Open Targets Core team to ensure seamless integration of data and workflows into the Open Targets Platform and long-term sustainability
- Collaborate with the Open Targets Partners to assess, prioritise, validate and refine the developed methods
- Disseminate the outcomes of the project to the scientific community and stakeholders through presentations and publications
You have
- PhD, Masters or equivalent experience in computational linguistics, computer science, bioinformatics, or cheminformatics
- Experience with language models e.g. transformer models, LLMs, AI agents for information extraction
- Experience with document and text preprocessing, cleaning and transformation techniques including mapping to ontologies
- Experience with data structures, data models and databases
- Knowledge of cheminformatics resources and/or bioinformatics databases
- Knowledge of data analysis and machine learning
- Proficiency in Python
- Knowledge of data frameworks e.g. pySpark, pandas, Polar
- Excellent attention to detail
- Strong communication skills, both presentations and verbal
- Experience working in a team-oriented environment and working collaboratively
- Able to work independently, to manage your time and work to deadlines
You might also have;
- Experience with the application of NLP methods to cheminformatics and/or biomedical domains
- Experience with version control
- Experience in Safety/toxicology in industry or research
Apply now! Benefits and Contract Information
- Financial incentives: depending on circumstances, monthly family/marriage allowance of £278 monthly child allowance of £336 per child. Non resident allowance up to £569 per month. Annual salary review, pension scheme, death benefit, long-term care, accident-at-work and unemployment insurances
- Hybrid working arrangements
- Private medical insurance for you and your immediate family (including all prescriptions and generous dental & optical cover)
- Generous time off: 30 days annual leave per year, in addition to eight bank holidays
- Relocation package including installation grant (as applicable)
- Campus life: Free shuttle bus to and from work, on-site library, subsidised on-site gym and cafeteria, casual dress code, extensive sports and social club activities (on campus and remotely)
- Family benefits: On-site nursery, child sick leave, generous parental leave, holiday clubs on campus and monthly family and child allowances
- Contract duration: This position is a 3 year project based contract
- Salary: Monthly salary starting at £3,229 to £3,612 after tax but excl. pension & insurances) + benefits (Total package will be dependent on family circumstances)
- International applicants: We recruit internationally and successful candidates are offered visa exemptions. Read more on our page for international applicants.
- Diversity and inclusion: At EMBL-EBI, we strongly believe that inclusive and diverse teams benefit from higher levels of innovation and creative thought. We encourage applications from women, LGBTQ+ and individuals from all nationalities.
- Job location: This role is based in Hinxton, near Cambridge, UK. You will be required to relocate if you are based overseas and you will receive a generous relocation package to support you.