Applications
Analysis of a Salary Poll
KNIME has been used to analyze a salary poll from a German computer magazine. Some of the results were presented in an article in this magazine. The major part of the analysis consisted of several data preprocessing steps that occur in almost all data mining tasks. This includes data conversion (currency transformation from SFr to EURO), outlier detection, and column and row filtering.
Virtual High Throughput Screening
KNIME has also been successfully applied to vHTS data (Virtual High Throughput Screening). The challenge of processing huge amounts of data (several GB) is mastered by most KNIME nodes without any difficulties. The results of predicting the activity of yet untested compounds can be visualized by the Enrichment Plotter, for example, which was specially developed for this purpose (see figure). Another useful tool for inspecting the data is the so-called neighborgram, where the neighborhood of data points labeled as "active" are shown. (The neighborgrams exist as an additional feature for KNIME and can be downloaded here). The colors of the points indicate the activity of the molecules represented by the data points.
Cell Miner
(Experimental/Internal use - not all nodes are part of the KNIME distribution)KNIME has been used to analyze cell images. A new data cell for images has been integrated and a picture file reader node added to the repository. A segmenter node has been implemented to locate cells in the images. Multiple feature extraction nodes were used to extract data for the classifier algorithm. The learner interactively adapts to the different cell types and subsequently classifies huge numbers of images. Interested readers are referred to the publication: Nicolas Cebron, Michael R. Berthold, Adaptive Active Classification of Cell Assay Images , Knowledge Discovery in Databases: PKDD 2006 (PKDD/ECML, Berlin, Germany), vol. 4213, pp. 79-90, Springer Berlin / Heidelberg, 2006 [PDF]
