«Thanks to e-LICO and the KUPKB I can now do a job that used to take me two weeks in less than two minutes!» — Julie Klein

The goal of the e-LICO project is to build a virtual laboratory for interdisciplinary collaborative research in data mining and data-intensive sciences. The e-lab comprises three layers: the e-science and data mining layers form a generic research environment that can be adapted to different scientific domains by customizing the application layer. e-LICO uses both Taverna and RapidAnalytics/RapidMiner to design and enact data analysis workflows. It provides a variety of general-purpose and application-specific services and a broad toolkit to assist the user in designing such workflows.

The e-LICO Architecture

DM Assistant. The Data Mining Assistant recommends operators based on the current process.


Community Extension. The Community Extension allows you to share RapidMiner processes on myExperiment.org, a community portal for exchanging and discussing scientific workflows.


RapidAnalytics. RapidAnalytics is the data mining server used for executing data mining workflows within e-LICO. Besides the actual execution of workflows it also provides reporting functionality.


The Intelligent Discovery Assistant allows you to create a data mining process in RapidMiner fully automatically just by specifying input data and a goal.

Taverna is one of the platforms used to deliver the e-LICO data-mining platform to scientists.

The RapidMiner plugin for Taverna exposes all of the data-mining operators from RapidMiner as services that can be used in the Taverna workflow system.

Taverna's Intelligent Discovery Assistant (IDA) activity gives access to data-mining workflows without creating the workflow by hand.


The RapidMiner R Extension integrates RapidMiner with the widely used open source statistics package R.This way, arbitrary R scripts can be executed as a part of a RapidMiner process.

The Recommender System Extension contains operators that are suited for typical recommendation tasks.

RM Onto - Semantic Data Mining

The subgroup discovery toolkit for RapidMiner implements two algorithms for subgroup discovery: SD and CN2-SD.


Various text mining workflows executed in Taverna.


Using image mining web services and the RapidMiner image mining extension you can transform images and extract features that can later be used for classification.


The Kidney and Urinary Pathway Knowledge Base gives biologists and bioinformaticians access to a wide variety of data about the kidney and its components from gross anatomy to proteins and genes.


As a result of the VideoLectures.Net challenge organized by e-LICO, a new recommender system was built into the video platform VideoLectures.Net.

Meta mining is the process of analysing the interplay between characteristics of data sets and the performance of particular algorithms and workflows. The result of this analysis is used by the Intelligent Discovery Assistant to rank the proposed workflows.

The ontology editor eProPlan supports editing the data mining ontology. It provides specialized views to model conditions and effects of data mining operators and testing them with the IDA planner. It is a plugin for the ontology editor Protégé.


Data Mining Ontologies model machine learning algorithms, operators, tasks, and goals in order to guide the meta miner and the workflow planner. Mining results are stored in the DMEX-DB.