Senior FAIR Data Scientist, Biomedical Ontologies

Key Skills

Python Programming, Scala Programming, C++, Java Programming, Machine learning techniques, Data science techniques, SQL, Apache Hadoop, MapReduce, TensorFlow, PyTorch, R Programming, Statistics, Biostatistics

Job Description

AbbVie’s Information Research (IR) group has a mission to unlock the information that makes cures possible. Within IR, the Library Information Sciences (LIS) team builds tools and provides services that help AbbVie scientific, business and regulatory professionals interact with, manage and consume knowledge from various content sources to foster innovation in drug discovery and development. We leverage leading technologies and methods to provide AbbVie professionals with timely insights from scientific literature and other content sources.

Within LIS the Literature-based Scientific Discovery (LSD) team assists AbbVie scientists with discovering relevant insights from scientific literature. The LSD-FAIR team will be focused on supporting the development of a unique knowledge ingestion engine for a broad set of scientific literature-based inputs and creating a consistent and always-current knowledge stream for AbbVie scientists. The LSD-FAIR team will be comprised of highly technical, highly scientific individuals motivated to create industry-leading knowledge science capabilities for AbbVie. Additionally, the LSD-FAIR team will partner with a broad array of organizational partners (Data Science, AI/ML, Software Development, PMO) to co-create and deliver solutions.

To be successful on this team you must be highly motivated, interested in modeling biomedical domain knowledge at a large scale, and eager to work with scientific and technical colleagues to have a real impact. Additionally you will have to have a keen awareness of a rapidly changing meta data standard landscape and the ability to effectively drive modeling projects from conception through completion delivering these capabilities to AbbVie.

Key Responsibilities

• Translate biomedical and business language into precise, complex knowledge representations following FAIR data practices

• Work with subject matter experts to gather requirements and use cases and design ontologies capable of scaling out to meet anticipated growth
• Build and maintain ontologies and taxonomies in AbbVie's ontology management tools (Semaphone, SciBite CENTree)
• Evaluate and map appropriate and existing internal and external terminologies
• Develop and reinforce (FAIR) standards and business rules to ensure consistent and quality terminology management
• Create and optimize processes and tools to implement, update and maintain taxonomies, ontologies and data models
• Work closely with peers in BTS/IR and subject matter experts from the business to maintain Common Data Model for Biomedical Research Purposes
• Imagine and evaluate innovative knowledge & data ingestion capabilities related to literature-based content sources
• Define Data ingestion rules from commonly used tools and frameworks (e.g., Tellec, neo4j)
• Work in close partnership with our AI/ML expert group to build unique capabilities which allow us to identify knowledge patters, graphing out and connect knowledge sources from internal and external
• Support and troubleshoot automatic classification by analyzing training corpora, creating a gold standard, adjusting data models, taxonomies and rules
• Develop strong relationships with R&D leaders as well as matrix partners across BTS/IT especially with the Data Science group
• Achieve great results while overwhelmingly demonstrating key AbbVie values and behaviors

Qualifications

• Bachelors degree with 6 years or Masters with 5 years of experience or Phd in Data/Information Science, Life Sciences (Biology, Chemistry), Information Systems, Library Science, Computer Science
• Preferred - MSc in Data / Information Science, Life Sciences (Biology, Chemistry)
• Knowledge of FAIR data practices as well as emerging technologies / frameworks related to ontologies, taxonomies, natural language processing, etc.
• Comfort with commonly used programming languages (e.g. Python) and W3C frameworks
• Experience with RDF, OWL, SPARQL or similar technologies preferred
• Experience with biomedical vocabularies and taxonomies, such as MeSH, SNOMED, ICD9/10, MedDRA preferred
• Familiarity with ontology management tools (e.g. Semaphore, SciBite CENTree) and Common Data Models preferred
• Familiarity with knowledge graphing tools and frameworks (neo4j) preferred
• Comfortable with ambiguity and skilled at clarifying technical requirements
• Strong customer focus and presence
• Comfortable working with staff at all levels of the organization
• Excited about working on a global team with a very diverse customer base
• Ability to effectively communicate, both verbally and in writing to scientists and non-scientists
• Ability to balance multiple projects with multiple teams and collaborators

Significant Work Activities

Continuous sitting for prolonged periods (more than 2 consecutive hours in an 8 hour day)