Part-Time Programmer Analysts

Penn State University • University Park, IL

2d • Remote

About The Position

The Department of Computer Science and Engineering is seeking part-time Programmer Analysts to support an NIH National Center for Advancing Translational Science-funded project called: “The Biomedical Data Translator.” https://ncats.nih.gov/research/research-activities/translator These programmers will develop the following components to be incorporated into the ARAX (https://github.com/RTXteam/RTX) system: Implement statistical and machine learning techniques to augment graph edge properties in ARAX; Create modular python wrappers to interface with NCATS (National Center for Advancing Translational Services) translator API (Application Programming Interface) endpoints (https://smart-api.info/registry) and UI (https://ui.transltr.io/) to allow ingestion of open access data into (and from) the ARAX system; Implement automated thresholding of ARAX filtering components; Create a modular, tunable weighting scheme for scoring and ranking of results to be returned by the ARAX system; Train a graph node embedding + random forest model on open access clinical and biomedical data to extend current capabilities for predicting the probability that a drug treats a disease; Maintain the ARAX code base to retain compliance with API and data standardization version updates as specified by the advisory, API, and data modeling committees; Address additional ARAX code-base issues as they are identified and assigned by faculty member.

Requirements

• Excellent interpersonal and communication skills
• Strong attention to detail
• Master’s degree plus two years of related experience, or an equivalent combination of education and experience
• Specific skills required are experience with the Neo4j graph database, interacting with REST APIs, more than three years’ experience with Python, and associated machine learning packages (such as Scikit learn)
• More than three years’ experience with Git and GitHub
• Ability to effectively work remotely with a large team of programmers and scientists
• Two years’ or more experience working with biomedical ontologies/data sets and publicly available databases

Responsibilities

• Implement statistical and machine learning techniques to augment graph edge properties in ARAX
• Create modular python wrappers to interface with NCATS (National Center for Advancing Translational Services) translator API (Application Programming Interface) endpoints (https://smart-api.info/registry) and UI (https://ui.transltr.io/) to allow ingestion of open access data into (and from) the ARAX system
• Implement automated thresholding of ARAX filtering components
• Create a modular, tunable weighting scheme for scoring and ranking of results to be returned by the ARAX system
• Train a graph node embedding + random forest model on open access clinical and biomedical data to extend current capabilities for predicting the probability that a drug treats a disease
• Maintain the ARAX code base to retain compliance with API and data standardization version updates as specified by the advisory, API, and data modeling committees
• Address additional ARAX code-base issues as they are identified and assigned by faculty member.

What This Job Offers

• Job Type: Part-time
• Career Level: Mid Level
• Number of Employees: 5,001-10,000 employees