One of the greatest challenges in the field of human genetics is to assess genetic variants in regard to their functional effect on the translated protein. The entire genome contains several thousand 'mutations', which ultimately make up the genetic diversity of the different individuals. However, the majority of these 'mutations' are not considered pathogenic, instead they are responsible for the genetic singularity of every human being. These non-pathogenic 'mutations' are referred to as genetic variants and occur in a relatively large percentage within the global population.

The difficulty is to evaluate now variants that are present only in a small percentage of the human population and may therefore be pathogenic, i.e. disease-causing. These are mostly so-called missense variants, in which one nucleotide in a specific DNA sequence is exchanged for another. This can lead to an amino acid exchange in the resulting protein. Whether this has an effect on the proper protein function, thus being potentially pathogenic, depends on e.g. the similarity of the substituted amino acids. To some extent, it is possible to simulate and assess these events using mathematical algorithms, but the reliability of these predictions is still very limited so far.