Since first coming together in late 2002, the Biomind scientific team has carried out a significant amount of bioinformatic research in a number of different areas, only a small percentage of which has made its way into Biomind's product line so far.  Some of this work has been done in collaboration with our data analysis customers, and some has been purely our own initiative.

In the meantime, what you'll find on this page are some preprints, and some semi-formal, semi-technical documents, briefly discussing a few aspects of the research work we've been doing.  

White Papers

Machine Learning Algorithms for Clinical and Research Microarray Data Analysis : Mining Microarray Data to Discover: Disease Biomarkers & Complex Genetic Relationships. January 2006

Enhancement of Gene Ontologies using Analytic Algorithms which Combine Microarray and DNA Sequence Similarity Data: Mining Microarray and Sequence Data to Enhance Gene Ontologies, January 2006

Recent publications

Application of MUTIC to the exploration of gene expression data in prostate cancer. B. Goertzel, C. Pennachin, L.S. Coelho and M.A. Mudado, Genet. Mol. Res. 6 (4): 890-900 (2007)

Clustering gene expression data via mining ensembles of classification rules evolved using moses. Looks M, Goertzel B, de Souza Coelho L, Mudado M, Pennachin C. Genetic and Evolutionary Computation Conference. (GECCO 2007): 407-414

Understanding microarray data through applying competent program evolution. Looks M, Goertzel B, de Souza Coelho L, Mudado M, Pennachin. P. Genetic and Evolutionary Computation Conference (GECCO 2007): 430

Biomind ArrayGenius and GeneGenius: Web Services Offering Microarray and SNP Data Analysis via Novel Machine Learning Methods. Ben Goertzel, Cassio Pennachin, Lucio Coelho, Leonardo Shikida, Murilo Queiroz. IAAI-07 conference, July 2007

Publications in Pharmacogenomics (search for all on PubMed)

Allostatic load is associated with symptoms in chronic fatigue syndrome patients. Goertzel BN, Pennachin C, de Souza Coelho L, Maloney EM, Jones JF, Gurbaxani B; Pharmacogenomics. 2006 Apr;7(3):485-94.

Combinations of single nucleotide polymorphisms in neuroendocrine effector and receptor genes predict chronic fatigue syndrome. Goertzel BN, Pennachin C, de Souza Coelho L, Gurbaxani B, Maloney EM, Jones JF; Pharmacogenomics. 2006 Apr;7(3):475-83.

Chronic fatigue syndrome and high allostatic load. Maloney EM, Gurbaxani BM, Jones JF, de Souza Coelho L, Pennachin C, Goertzel BN; Pharmacogenomics. 2006 Apr;7(3):467-73.

Linear data mining the Wichita clinical matrix suggests sleep and allostatic load involvement in chronic fatigue syndrome. Gurbaxani BM, Jones JF, Goertzel BN, Maloney EM; Pharmacogenomics. 2006 Apr;7(3):455-65.

Presentations at CIBB 2006 (presented) and FLINS 2006 (published)
(Third International Meeting on Computational Intelligence Methods for Bioinformatics and Statistics)
(Proceedings of the 7th International FLINS Conference)

Learning Comprehensible Classification Rules from Gene Expression Data Using Genetic Programming and Biological Ontologies. B. Goertzel, L. Coelho, C. Pennachin, I. Goertzel, M. Queiroz, F. Prosdocimi, and F. Lobo

Presentation at WCCI 2006 (IEEE World Congress on Computational Intelligence)

Identifying Complex Biological Interactions based on Categorical Gene Expression Data. Ben Goertzel, Lucio Coelho, Cassio Pennachin and Mauricio Mudada

Poster at the Second International Workshop on Formal Biomedical Knowledge Representation: "Biomedical Ontology in Action"

Inferring Gene Ontology Category Membership via Gene Expression and Sequence Similarity Data Analysis. Murilo Saraiva Queiroz, Francisco Prosdocimi, Izabela Freire Goertzel, Francisco Pereira Lobo, Cassio Pennachin and Ben Goertzel, Ph.D, (p. 98)

In 2003-2004, Biomind scientists collaborated with Drs. Davis Parker and Rafal Smigrodzki of the University of Virginia on a project involving analysis of mutations in mitochondrial DNA as related to Parkinson's Disease.  The project was quite successful and resulted in what seems to be an effective method of predicting whether a person has Parkinson's disease based on a simple pattern in the mutations in the mitochondrial genome of their nerve cells.  These results provide significant insight into the mechanisms underlying Parkinson's, and after further research, may also lead to pragmatic diagnostic tests.

This brief press release and this longer, more in-depth journalistic article describe this work and some of its history.   

A paper utilizing the results of this collaborative research was recently published by Davis Parker and Janice K. Parks in Biochemical and Biophysical Research Communications.

Recent publications in Artificial Intelligence in Medicine

Genetic algorithm for analysis of mutations in Parkinson's disease. Smigrodzki R, Goertzel B, Pennachin C, Coelho L, Prosdocimi F, Parker WD Jr.; Artif Intell Med. 2005 Nov;35(3):227-41. Epub 2005 Oct 3.