Mapping and fuzzy classification of macromolecular images using self-organizing neural networks

In this work the effectiveness of the fuzzy kohonen clustering network (FKC N) in the unsupervised classification of electron microscopic images of bio logical macromolecules is studied. The algorithm combines Kohonen's self-or ganizing feature maps (SOFM) and Fuzzy c-means (FCM) in order to obtain a p owerful clustering technique with the best properties inherited from both. Exploratory data analysis using SOFM is also presented as a step previous t o final clustering. Two different data sets obtained from the G40P helicase from B. Subtilis bacteriophage SPP1 have been used for testing the propose d method, one composed of 2458 rotational power spectra of individual image s and the other composed by 338 images from the same macromolecule. Results of FKCN are compared with self-organizing feature maps (SOFM) and manual c lassification. Experimental results prove that this new technique is suitab le for working with large, high-dimensional and noisy data sets and, thus, it is proposed to be used as a classification tool in electron microscopy. (C) 2000 Elsevier Science B.V. All rights reserved.