Data Scientist - Rare Diseases
- Full-Time
- Rockville, MD
- Axle Informatics
- Posted 2 years ago – Accepting applications
Job Description
Overview: Axle Informatics is a bioinformatics and information technology company that offers innovative computer services, informatics, and enterprise solutions to research centers and healthcare organizations around the globe. With experts in software engineering, bioinformatics and program management, we focus on developing and applying technology tools and techniques to empower decision-making and accelerate the discovery in translational research. We work with some of the top research organizations and facilities in the country including multiple institutes at the National Institutes of health (NIH).
Axle is seeking a Data Scientist for the development of informatics infrastructure that supports the Genetic and Rare Diseases (GARD) information center and development of data models to support National Center for Translational Sciences (NCATS) Office of Rare Diseases Research (ORDR)’s rare diseases informatics initiatives.
The National Institutes of Health (NIH) is the Nation’s leading medical research agency and the primary federal agency whose mission is to seek fundamental knowledge about the nature and behavior of living systems and the application of that knowledge to enhance health, lengthen life, and reduce illness and disability by supporting and making medical discoveries. NCATS is the only center at the NIH that focuses exclusively on all aspects of the translation of research with an innovative pipeline of treatment discoveries for all diseases. NCATS brings together a diverse group of scientists, including medicinal chemists, biologists, toxicologists, clinicians, and engineers to translate basic science conducted elsewhere into products and services that help improve people’s health and lives. NCATS’ mission is to improve health through smarter science that results in better treatments faster for all diseases, rare or common. Within that remit, the NCATS ORDR’s mission is to advance rare disease research to benefit patients.
Currently, there are about 7,000-10,000 known rare diseases that affect people in the US, yet only a few hundred (less than 5%) have a treatment and even fewer a cure. A rare disease is defined in US law (Orphan Drug Act (ODA) of 1983,[1] Rare Diseases Act (RDA) of 2002[2]) as a disease or condition that affects fewer than 200,000 people in the US. Most rare diseases affect far fewer patients than this, with most rare diseases affecting only a few hundreds to thousands of patients. Collectively, however, rare diseases are not rare at all, and in total are estimated to affect as many as 25-30 million patients in the US, making rare diseases a large public health consideration.
The ORDR’s GARD information center was established in 2003 under a Congressional Mandate (RDA 2002), and is a federally funded program that has an essential role in the dissemination of public health information to rare disease researchers, clinicians, and patients that is freely accessible to the public. However, obtaining accurate, comprehensive, timely, and objective information on rare diseases is often difficult, given the large number of rare diseases, rapidly evolving science (especially related to genomics), diverse data sources, and inconsistent nomenclature and ontologies for rare disease classification, among other issues. Recently, GARD has been undergoing a re-envisioning and re-design based on a Neo4j knowledge graph database that integrates rare disease data from multiple sources to keep the information on ~6,000 different rare diseases in GARD up-to-date and useful to the patient and clinical research communities. Research tools, artificial intelligent models, data visualization and informatics infrastructure based on the knowledge graph database will be developed to support rare diseases research and clinical activities, and to answer rare disease research questions likely to inform rare disease research prioritization.
[1] Orphan Drug Act of 1983, amended for prevalence 1984. Pub.L. 97-414 [2] Rare Diseases Act of 2002, Pub.L. 107-280 Responsibilities: Develop and manage an existing database and informatics infrastructure that integrates rare disease data from multiple sources, such as disease classification/ontologies coding (e.g., ICD 10), genetics, clinical characteristics/phenotypic information, diagnosis, and treatment, among others.
Apply to this Job
Axle is seeking a Data Scientist for the development of informatics infrastructure that supports the Genetic and Rare Diseases (GARD) information center and development of data models to support National Center for Translational Sciences (NCATS) Office of Rare Diseases Research (ORDR)’s rare diseases informatics initiatives.
The National Institutes of Health (NIH) is the Nation’s leading medical research agency and the primary federal agency whose mission is to seek fundamental knowledge about the nature and behavior of living systems and the application of that knowledge to enhance health, lengthen life, and reduce illness and disability by supporting and making medical discoveries. NCATS is the only center at the NIH that focuses exclusively on all aspects of the translation of research with an innovative pipeline of treatment discoveries for all diseases. NCATS brings together a diverse group of scientists, including medicinal chemists, biologists, toxicologists, clinicians, and engineers to translate basic science conducted elsewhere into products and services that help improve people’s health and lives. NCATS’ mission is to improve health through smarter science that results in better treatments faster for all diseases, rare or common. Within that remit, the NCATS ORDR’s mission is to advance rare disease research to benefit patients.
Currently, there are about 7,000-10,000 known rare diseases that affect people in the US, yet only a few hundred (less than 5%) have a treatment and even fewer a cure. A rare disease is defined in US law (Orphan Drug Act (ODA) of 1983,[1] Rare Diseases Act (RDA) of 2002[2]) as a disease or condition that affects fewer than 200,000 people in the US. Most rare diseases affect far fewer patients than this, with most rare diseases affecting only a few hundreds to thousands of patients. Collectively, however, rare diseases are not rare at all, and in total are estimated to affect as many as 25-30 million patients in the US, making rare diseases a large public health consideration.
The ORDR’s GARD information center was established in 2003 under a Congressional Mandate (RDA 2002), and is a federally funded program that has an essential role in the dissemination of public health information to rare disease researchers, clinicians, and patients that is freely accessible to the public. However, obtaining accurate, comprehensive, timely, and objective information on rare diseases is often difficult, given the large number of rare diseases, rapidly evolving science (especially related to genomics), diverse data sources, and inconsistent nomenclature and ontologies for rare disease classification, among other issues. Recently, GARD has been undergoing a re-envisioning and re-design based on a Neo4j knowledge graph database that integrates rare disease data from multiple sources to keep the information on ~6,000 different rare diseases in GARD up-to-date and useful to the patient and clinical research communities. Research tools, artificial intelligent models, data visualization and informatics infrastructure based on the knowledge graph database will be developed to support rare diseases research and clinical activities, and to answer rare disease research questions likely to inform rare disease research prioritization.
[1] Orphan Drug Act of 1983, amended for prevalence 1984. Pub.L. 97-414 [2] Rare Diseases Act of 2002, Pub.L. 107-280 Responsibilities: Develop and manage an existing database and informatics infrastructure that integrates rare disease data from multiple sources, such as disease classification/ontologies coding (e.g., ICD 10), genetics, clinical characteristics/phenotypic information, diagnosis, and treatment, among others.
- Build data models to extract data and information from existing data sources using machine learning and/or natural language processing approaches.
- Integrate the existing GARD knowledge graph database with other GARD-related information and data streams, and build robust pipelines to keep the data up to date and harmonized.
- Design and develop APIs for user access to the knowledge graph database and connect it to other NCATS and NIH databases.
- Design system and software architect as well as develop computational tools, interactive visualization interfaces and web-based applications for users to access and utilize the existing knowledge database.
- Work collaboratively with other data scientists and developers in informatics support for rare disease research.
- Identify, collect, quality check and integrate rare disease data, such as disease characteristics, genetics and healthcare systems data from diverse resources to permit data analysis. Build standard pipelines in data processing and automate the graph database update process.
- Create informatics solutions to answer research questions in rare diseases using the knowledge graph database.
- Doctoral degree in Computer Science, Data Science, Bioinformatics, Information Systems or other related field.
- PhD and 2+ years of experience in data mining and modeling, database development, software development and/or web application development.
- Experience and good understanding in working with biomedical data, such as disease characteristics, genetics and/or other healthcare systems data.
- Deep understanding of object-oriented programming.
- Experience working with Linux/Unix operating systems.
- Experience in software architect design, data mining, machine learning and/or natural language processing.
- Good understanding of the software development life cycle.
- Proficient in one or more programing languages, such as Python, Perl, Java, JavaScript, etc.
- Experience in database and web application development.
- Experience in API development, data visualization and/or parallel computing is highly preferred.
- Experience in Graph, NoSQL, and/or RDBMS database, such as Neo4j, is highly preferred.
- Experience in containers (e.g. Docker, Singularity), version control (e.g. GitHub) and workflow management (e.g. Snakemake) is highly preferred.
- Ability to work independently on day-to-day tasks with minimal supervision.
- Willing to learn new technologies and motivated to explore new solutions to address complex rare disease research questions.
- Experience with presentations and publications
Benefits
- 100% Medical, Dental & Vision premium coverage for Employees
- Paid Time Off (Including Holidays)
- Employee Referral Bonus
- 401K Match
- Tuition reimbursement and professional development opportunities
- Flexible Spending Accounts:
- Healthcare (FSA)
- Parking Reimbursement Account (PRK)
- Dependent Care Assistant Program (DCAP)
- Transportation Reimbursement Account (TRN)
The diversity of Axle’s employees is a tremendous asset. We are firmly committed to providing equal opportunity in all aspects of employment and will not tolerate any illegal discrimination or harassment based age, race, gender, religion, national origin, disability, marital status, covered veteran status, sexual orientation, status with respect to public assistance, and other characteristics protected under state, federal, or local law and to deter those who aid, abet, or induce discrimination or coerce others to discriminate.
Accessibility: If you need an accommodation as part of the employment process please contact:careers@axleinfo.com
Disclaimer: The above description is meant to illustrate the general nature of work and level of effort being performed by individual’s assigned to this position or job description. This is not restricted as a complete list of all skills, responsibilities, duties, and/or assignments required. Individuals may be required to perform duties outside of their position, job description or responsibilities as needed.