Anaxomics' TPMS technology allows the biomolecular characterization of treatments and patients by groups, and tracing the mechanism of action associated to each one.
Clinical practitioners have long known that patients vary widely in their responses to drug therapy, not only in obtaining therapeutic effect, but also in suffering from adverse drug reactions. Accordingly, biomedical investigation has revealed that multifactorial diseases are mediated by several pathophysiological pathways with variable contribution to the overall pathogenic process. Different medicines indicated for the same disease may be more effective on certain groups of patients than on others depending on their mechanism of action (MoA) and the unique characteristics of the individuals. Thus, a correct patient stratification is key to identify the best niche in the market for each compound.
The analysis of a population by subgroups of individuals is extremely complex due to the enormous variability between patients and the limited ability of statistical approaches to deal with analytical variables. Anaxomics' TPMS complements conventional statistical analysis through individually modelling the patients and then segmenting them according to qualitative or quantitative characteristics that are somehow related to the mechanism of the drug under study.
The biomolecular analysis identifies the unique mechanism of action (MoA) of each drug (see below) under study, including common patterns and differential elements. Then, it sifts through the population of individuals in order to define clusters of patients whose physiological response to the drugs match the MoAs previously identified (1A). Characteristics associated with the MoA in these subgroups (degree of efficacy or safety profile) can be determined, providing a mechanistic rationale for clinical observations.
The patients are then placed into clusters based on their unique molecular profile (1B). This analysis will be done by using non-lineal classifiers and artificial intelligence techniques in order to identify not obvious relationship between patients.