Applying our technology on metabolomics data will allow you to tackle some common problematics of the healthcare industry and of the (pre-)clinical studies:
- Complex signatures highlighting.
- Profile features deduction (disease’s stage, treatment’s response, …).
- Metabolomics pathways indication.
To figure out how our technology works on metabolomics data, we have selected the following liver cancer example.
The input is a database of patients, described with concentrations of metabolites, partitioned into two subsets: one with the diseased patients and another one with the healthy controls. The aim of the study is to extract the (combinations of) intervals of metabolites concentrations affecting the liver cancer. As each patient provides an unique metabolites concentration, for each metabolite the first step is to get groups of concentrations belonging to the same database’s subset.
Therefore, our algorithm produces the most common patients descriptions, preserving as much as possible the subset partition and making the extraction of contrasting (combinations of) intervals easier. As usual, we provide a way to facilitate the analyses of output results by designing a useful visualization.
The first way to analyse the output results is to take each (combination of) interval(s) alone and to discuss its contrast into the database and its influence on the liver cancer. However, our output results are fully understandable and more information can be deduced by cross-referencing the (combinations of) intervals together.
QUIID provides a way to navigate into the set of (combinations of) intervals.