Determining the stability of a substance or substance mixture

1 . A computer-implemented method for determining the stability of substances or substance mixtures, the method comprising the following steps:

a data acquisition step in which a computer program receives raw and/or metadata for multiple product candidates, each product candidate comprises a starting value measurement data set and at least one further measurement data set, the starting value measurement data set and each measurement data set of the at least one further measurement data set representing a respective chemical profile of a respective substance or substance mixture of the respective product candidate, wherein the data acquisition step comprises obtaining, for each product candidate, the at least one further measurement data set by performing one or more of the following measurements on the product candidate: middle infrared spectroscopy, near infrared spectroscopy, UV/VIS spectroscopy, Raman spectroscopy, liquid chromatography, high performance liquid chromatography, ultra high performance liquid chromatography, gas chromatography, and/or mass spectrometry;

a data evaluation step comprising for each further measurement data set:

determining, by the computer program, the starting value measurement data set of the respective substance or substance mixture on the basis of raw and/or metadata of the starting value measurement data set; and

quantifying, by the computer program, a change in the respective substance or substance mixture over time with respect to the starting value measurement data set and the at least one further measurement data set by means of a mathematical distance measure, wherein the mathematical distance measure is selectable by a user and wherein the user can select multiple mathematical distance measures for the quantification of the change in the respective substance or substance mixture, wherein the quantification of the change in the respective substance or substance mixture is performed on the basis of each selected mathematical distance measure; and

performing, by the computer program, an additional qualitative analysis for the at least one further measurement data set, which is not included in the quantification of the change by means of the mathematical distance measure and produces distance values; and

a data output step in which the computer program graphically displays the change in the respective substance or substance mixture for each further measurement data set, wherein the data output step comprises:

displaying the change in the respective substance or substance mixture as a box plot; and

displaying the result of the additional qualitative analysis;

determining, by the computer program, a time at which the distance values reach a plateau value by fitting a kinetic curve to the distance values, wherein the plateau is indicated by asymptotic approximation of the calculated distance values; and

outputting an indication that a process can be terminated based on the determined time at which the distance values reach the plateau value.

2 . The method of claim 1 , further comprising:

training a machine learning model using at least one of unsupervised or supervised machine learning; and

wherein the data evaluation step comprises, for each further measurement data set, using the machine learning model to evaluate the further measurement data set.

3 . The method of claim 1 , wherein the at least one further measurement data set comprises at least one of:

data obtained by UV/VIS spectroscopy;

data obtained by Raman spectroscopy;

a (U) HPLC fingerprint;

a GC fingerprint;

a peak table from a chromatographic procedure;

at least one physical, biological or chemical parameter.

4 . The method of claim 1 , wherein the quantification of the change in the respective substance or substance mixture is based on a totality of the ingredients of the respective substance or substance mixture.

5 . The method of claim 1 , wherein the mathematical distance measure is selected from the following group: Euclidean distance, Mahalanobis distance, Manhattan distance, Pearson distance and/or Gower distance.

6 . The method of claim 1 , further comprising: a data preprocessing step comprising:

performing a stray light correction of the at least one further measurement data set;

carrying out a centering, normalization and/or scaling of the at least one further measurement data set; and/or

performing a principal component analysis.

7 . The method of claim 1 , wherein the data output step comprises:

displaying means, medians, 0.25/0.75 quantiles, dispersion measures, highlighting possible outlier candidates; and/or

performing at least one statistical test.

8 . The method of claim 1 , wherein the substance or substance mixture comprises solid and/or liquid and/or gaseous substances.

9 . The method of claim 1 , wherein the substance or substance mixture comprises biological, chemical, plant, animal, human substances or mixtures of substances, pharmaceutical compositions, plant medicinal products, chemical and/or biological medicinal products, cells, cell therapeutics, blood, blood products, organs, medicinal teas, verbena extract, thyme, rosemary and chamomile medicinal drug mixtures as an ethanolic extract or in powder form, drops, tablets, dragees, capsules, powders, granules, solutions, suspensions, juices, meat or minced meat, fruit juice, food supplements, cosmetics, emulsions, ointments and/or creams, as well as packaging, packaging materials, films, and/or polyvinyl chloride.

10 . A non-transitory computer program product comprising instructions which, when executed by a computer, cause the computer to carry out the method of claim 1 .

11 . A device comprising means for carrying out the method of claim 1 .