iDASH Software/Tools

A key goal of iDASH is to develop and refine open-source software and tools to illustrate the spectrum of computational algorithms and methodologies available for biomedical and behavior researchers nationwide. Currently, there are three iDASH Driving Biological Projects (DBPs) to motivate, inform, and support innovations in research methods and approaches.

A significant collection of software tools is now accessible:

DBP tools
Imaging Informatics tools
NLP tools
Privacy tools

Name of Tool	Domain	Target User	Data type	Description
AnnIO	Imaging	Informatics researcher, Clinician	Clinical, Clinical records	A web-based application for viewing and annotating DICOM images using an ontology. It will soon be integrated into our Midas data repository.
Annotation Admin	NLP	NLP researcher or developer	Clinical records	A web-based service for managing annotation projects. Orbit Registry Description
Count Perturbation Allowing User Preferences	Privacy	Informatics researcher, Software developer	Domain-Independent	A tool for exploring parameter settings of a count query perturbation mechanism that allows inclusion of user preferences with regards to scale and location of the perturbation.
Differentially Private Logistic Regression	Privacy	Informatics researcher, Software developer	Domain-Independent	An R package that implements differentially private logistic regression.
Differentially Private Projected Histograms	Privacy	Informatics researcher, Software developer	Domain independent	The pph package provides a way to create training data for classifiers in a differentially private manner.
Genetic Query Language (GQL)	Analysis	Researcher	Genetics	A web service to query genomes from heterogeneous locations. Gathers all genomes from participating locations and runs computations locally.
iDASH Virtual Machine of Clinical NLP Tools	NLP	NLP researcher/developer, Informatics researcher, Clinician	Clinical, Clinical records	A virtual machine is built using VirtualBox and contains the following clinical NLP applications: 1) eHOST - an annotation tool 2) CTAKES - a clinical information extraction tool 3) ARC - automated retrieval console for creating document classifiers using text and NLP features Orbit Registry Description
Informed CONsent for clinical record and Sample use in research (iCONS)	Informed Consent	Researcher, Patient	Clinical studies	A web-based environment for educating patients on the research study they have been invited to participate through an electronic informed consent form. Click here to see a demo
Microrna-seq Analysis in Gpu Infrastructure (MAGI)	Analysis	Researcher	MicroRNA	A web-service for MicroRNA Analysis in GPU Environment.
NLP Evaluation Workbench	NLP	NLP researcher or developer	Clinical	An NLP application that calculates outcome measures for all secondary file annotations when compared against the primary file annotations. Input: Two files (primary and secondary) comprising annotations from clinical information extraction systems or manually-annotated reports. The files must map to the Workbench Information Model. Output: A visualization of all annotations and their outcome measures. Orbit Registry Description
Observational Cohort Event Analysis and Notification System (OCEANS)	Privacy	Informatics researcher, Clinician	Clinical, Clinical records	OCEANS aims to develop novel statistical methods to detect adverse event signals in observational cohort data from electronic health records, clinical registries, and administrative databases. This toolbox was developed to enable rapid integration and dissemination of statistical modules to support retrospective and prospective static or automated real-time medical product surveillance.
Privacy Preserving SVM (PPSVM)	Privacy	Informatics researcher	Clinical, Clinical records	PPSVM is a web service that iDASH provides for users to build an SVM model from distributed data (i.e., vertically partitioned) without accessing the raw data. The users can share results (i.e., globally trained SVM models) in a privacy-preserving manner.
Spectral Swapping	Privacy	Informatics researcher, Software developer	Domain-Independent	A python implementation of spectral swapping, a method for perturbing data for privacy purposes.