Vacancy expired!
Labcorp is implementing an exciting new "big data" approach to cancer testing. We are integrating the test results from our national oncology testing business into an enterprise data warehouse to enable a variety of data mining applications. We have an excellent opportunity for a highly motivated biocuration scientist within our new Oncology Data Curation group. You will be part of a collaborative, cross-functional team bringing together software engineers, clinicians and data users to extract clinical insights from oncology data. Oncology testing data is complex and heterogenous; we need people who can bring both biomedical understanding and data management skills to the task of making this data usable. This is a great opportunity for someone with a clinical background to learn or expand their knowledge management skills. Essential Duties and Responsibilities:
- Work with other members of the curation team, as well as other teams, to design data structures in JSON and relational formats to capture the complexities of oncology data.
- Understand the meaning of specific oncology diagnostic test results to enable them to be mapped to a data model.
- Create mappings between clinical test results and data warehouse data structures to allow tests to be incorporated into the warehouse. This requires an understanding of biomedical testing, particularly in the oncology domain, as well as of data modeling.
- Learn and use software tools for data transformation (ETL tools) including Cloverleaf.
- Learn and apply clinical data standards such as FHIR, mCode, LOINC, ICD-10, UMLS, SnoMED and others as appropriate.
- Standardize disease data to biomedical controlled vocabularies and classifications.
- Expand and adapt biomedical ontologies as needed to capture expanding knowledge.
- Apply natural language processes tools to the extraction of information from test results.
- Curate, analyze, manage and harmonize large data sets and ensure data quality.
- Work closely with engineering teams and with some supervision participate in the full development cycle from product inception, research and prototyping to release in production.
- Familiarity with clinical data standards such as HL7 and FHIR.
- Understanding of cancer biology and therapies.
- Experience curating and extracting data from databases, analyzing data, integrating terminologies for biomedical ontology development is desirable.
- Experience working with relational databases and Hadoop.
- Python or Tcl programming experience.
- Experience integrating public and proprietary information sources into a knowledge architecture at scale - e.g. pharmaceutical, chemical, or biological informatics.
- Experience with scientific Natural Language Processing / Text Mining technologies.
- Detail-oriented with strong organizational, analytical and communication skills.
- Ability to interact and work well with members of other functional groups in project teams and a strong sense of project ownership.
Vacancy expired!