Simulating soft data to make soft data applicable to simulation.

BACKGROUND Biomedical processes are often influenced by measures considered "non-crisp", "soft" or "subjective". Despite the growing awareness of the importance of such measures, they are rarely considered in biomedical simulation. This study introduces an input generator for soft data (input generator SD) that makes soft data applicable to simulation. MATERIALS AND METHODS Machine learning approaches and standard regression techniques were applied to simulate odour intensity ratings. RESULTS The performance of all the applied methods was satisfactory and the results can be used to modify systems biological mathematical models. CONCLUSION Soft data should no longer be discounted in systems biological simulations. Exemplarily, it can be demonstrated that the input generator SD produces results that are similar to those that the simulated system can generate. Machine learning and/or appropriate conventional mathematical approaches may be applied to simulate noncrisp processes that can be used to modify mathematical models of any granularity.

[1]  S J Soong,et al.  A behavioral augmentation of natural immunity: odor specificity supports a Pavlovian conditioning model. , 1991, The International journal of neuroscience.

[2]  C F Rogers,et al.  Psychoneuroendocrine immunology: site of recognition, learning and memory in the immune system and the brain. , 1997, The International journal of neuroscience.

[3]  M. Nei,et al.  Mathematical model for studying genetic variation in terms of restriction endonucleases. , 1979, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Dominik Wodarz,et al.  A dynamical perspective of CTL cross-priming and regulation: implications for cancer immunology. , 2003, Immunology letters.

[5]  Mali Salmon-Divon,et al.  Models for Natural Killer Cell Repertoire Formation , 2003, Clinical & developmental immunology.

[6]  Chih-Jen Lin,et al.  Training v-Support Vector Regression: Theory and Algorithms , 2002, Neural Computation.

[7]  R N Hiramoto,et al.  Nk Cell and Ctl Activities Can Be Raised Via Conditioning of the Cns with Unrelated Unconditioned Stimuli: Neuroimmunomodulation , 2000, The International journal of neuroscience.

[8]  Andrew Yates,et al.  An Approach to Modelling in Immunology , 2001, Briefings Bioinform..

[9]  Anil K. Jain,et al.  On the optimal number of features in the classification of multivariate Gaussian data , 1978, Pattern Recognit..

[10]  P. Klenerman,et al.  Predicting the dynamics of antiviral cytotoxic T‐cell memory in response to different stimuli: Cell population structure and protective function , 2001, Immunology and cell biology.

[11]  R N Hiramoto,et al.  Conditioned enhancement of natural killer cell activity, but not interferon, with camphor or saccharin‐Licl conditioned stimulus , 1987, Journal of neuroscience research.

[12]  B. Chandrasekaran,et al.  On dimensionality and sample size in statistical pattern classification , 1971, Pattern Recognit..

[13]  E S Gelsema.  Pattern recognition and artificial intelligence in medical research and clinical practice. , 1989, Methods of information in medicine.

[14]  Janice M Morse.  The Hardening of Soft Data , 2004, Qualitative health research.

[15]  Stephanie Forrest,et al.  A stochastic model of cytotoxic T cell responses. , 2004, Journal of theoretical biology.

[16]  Sofia Johansson,et al.  Computational modeling of human natural killer cell development suggests a selection process regulating coexpression of KIR with CD94/NKG2A. , 2005, Molecular immunology.

[17]  Adler Rh.  Die Anamneseerhebung – ein «unmögliches» Unterfangen , 2004 .

[18]  W Hausotter.  [Expert assessment of chronic fatigue syndrome]. , 1996, Versicherungsmedizin.

[19]  Siegfried J. Pöppl,et al.  ACMD: A Practical Tool for Automatic Neural Net Based Learning , 2001, ISMDA.

[20]  M Scherrer,et al.  [Hard and soft data in medicine; their processing by the physician and by the computer]. , 1979, Schweizerische medizinische Wochenschrift.

[21]  R. Linder,et al.  Generation of classification criteria for chronic fatigue syndrome using an artificial neural network and traditional criteria set. , 2002, In vivo.

[22]  Alan S. Perelson,et al.  Recruitment Times, Proliferation, and Apoptosis Rates during the CD8+ T-Cell Response to Lymphocytic Choriomeningitis Virus , 2001, Journal of Virology.

[23]  Nikolas P. Galatsanos,et al.  A similarity learning approach to content-based image retrieval: application to digital mammography , 2004, IEEE Transactions on Medical Imaging.

[24]  Mali Salmon-Divon,et al.  Generation of the natural killer cell repertoire: The sequential vs. the two-step selection model , 2003, Bulletin of mathematical biology.

[25]  Huiqing Liu,et al.  A comparative study on feature selection and classification methods using gene expression profiles and proteomic patterns. , 2002, Genome informatics. International Conference on Genome Informatics.

[26]  S. Soong,et al.  Conditioning of the allogeneic cytotoxic lymphocyte response , 1993, Pharmacology Biochemistry and Behavior.

[27]  Andrew J. McMichael,et al.  Clonal Selection, Clonal Senescence, and Clonal Succession: The Evolution of the T Cell Response to Infection with a Persistent Virus1 , 2002, The Journal of Immunology.

[28]  S. Soong,et al.  Conditioning of the secondary cytotoxic T-lymphocyte response to YC8 tumor , 1995, Pharmacology Biochemistry and Behavior.

[29]  Thomas Serre,et al.  Hierarchical classification and feature reduction for fast face detection with support vector machines , 2003, Pattern Recognit..

[30]  M. Baalen,et al.  Impact of antigen expression kinetics on the effectiveness of HIV‐specific cytotoxic T lymphocytes , 2002, European journal of immunology.