Modeling of proteins

Résumé

In paper I the four proposed assumptions in the context of categorical variable mapping in protein classification problems: (1) translation, (2) permutation, (3) constant, and (4) eigenvalues were tested. The results suggest that these four assumptions are valid. In paper II the proposed approach is able to generate an accuracy, sensitivity and specify of classification forecasts of 97.69%, 95.02% and 98.26%, respectively, illustrating that a combination of DNA methylation with nonlinear methods such as artificial neural networks might be useful in the task of identifying patients with a carcinoma. In paper III it was shown that gene expression data can be successfully analyzed with machine learning techniques in order to differentiate healthy patients and patients with interstitial lung disease systemic sclerosis (ILD-SSc). In paper IV, following a machine learning approach, it was possible to identify a list of genes that appear to be related to inflammatory bowel disease