Kodama, an anti-cancer algorithm developed in Florence

FLORENCE, ITALY – The scientific name is Kodama (Knowledge discovery by accuracy maximization): it is developed by the FiorGen Foundation in Florence, Italy and proposes an innovative method to extract new knowledge from noisy and high-dimensional data. The ultimate research on this anti-cancer algorithm was published yesterday on the PNAS, Proceedings of the National Academy of Sciences of the United States of America, one of the world’s most-cited multidisciplinary scientific serials.

The approach differs from previous methods in that it has an integrated procedure of validation of the results through maximization of cross-validated accuracy. In many cases, this method performs better than existing feature extraction methods and offers a general framework for analyzing any kind of complex data in a broad range of sciences. Examples ranging from genomics and metabolomics to astronomy and linguistics show the versatility of the method.

Unlike other data mining methods, the peculiarity of Kodama is that it is driven by an integrated procedure of cross-validation of the results. The discovery of a local manifold’s topology is led by a classifier through a Monte Carlo procedure of maximization of cross-validated predictive accuracy. Briefly, our approach differs from previous methods in that it has an integrated procedure of validation of the results. In this way, the method ensures the highest robustness of the obtained solution.

This robustness is demonstrated on experimental datasets of gene expression and metabolomics, where Kodama compares favorably with other existing feature extraction methods.

Kodama is then applied to an astronomical dataset, revealing unexpected features. Interesting and not easily predictable features are also found in the analysis of the State of the Union speeches by American presidents: Kodama reveals an abrupt linguistic transition sharply separating all post-Reagan from all pre-Reagan speeches. The transition occurs during Reagan’s presidency and not from its beginning.

The research was published by Stefano Cacciatore, former researcher at the Magnetic Resonance Center (CERM) and Department of Chemistry, University of Florence, Italy, actually at the Department of Medical Oncology, Dana–Farber Cancer Institute, Harvard Medical School, Boston; professor Claudio Luchinat, professor at the Magnetic Resonance Center (CERM) and Department of Chemistry, University of Florence, Italy, member of the FiorGen Foundation and the researcher Leonardo Tenori, researcher of the FiorGen Foundation, Florence, Italy.