In the field of data science, bioinformatics is particularly concerned with microbiology and genetics and the analysis of biological sequences.
Statistical models and Machine Learning techniques are used to evaluate the large corpus of data from the experiments performed. By processing the data in parallel and using efficient algorithms, it is possible to evaluate the data faster and easier.
Thus, Data Science aids bioinformatics to achieve results faster and with less effort.

In Economics, data science methods are used to evaluate and analyze large amounts of data, e.g., statistical data.
Machine learning methods are often used to create forecasts. A current research project, for example, is the evaluation of shitstorms in social networks. This involves determining the factors that characterize such a shitstorm.
With automated analyses of these factors, this detection has to take place before such a shitstorm can spread with the aim to make early countermeasures possible.
Data Science in Economics contributes to a more pleasant interaction on the internet.

In Medical Informatics, methods of data science are used, e.g., to evaluate clinical studies.
In this process, different data are brought together and prepared for evaluation. Thus, for example, they are checked for plausibility.
In the long term, data science in Medical Informatics will also be used to derive forecasts from the results obtained and could thus revolutionize medical research in the future.

Digital Humanities is a very broad research field that deals with digitization and its methods for the humanities in the broadest sense.
Data Science is also used here in the analysis of existing research data, e.g. the analysis of ancient religious texts. In addition, new methods are being explored, such as the conception of virtual exhibitions in museums or ways of presenting research results.
Another example is archaeology, in which historical sites are reconstructed or missing parts of sculptures are digitally added.
Data science thus also offers the humanities a broad spectrum of applications and new methods for analyzing already existing data.

Breeding informatics is concerned with harnessing Big Data for the improvement of animal and plant breeding and related fields.

For example, genomic variants that provide desirable animal or plant traits are filtered out of several 100 gigabytes of sequence data. This knowledge can be used in breeding programs to identify the most promising individuals for reproduction.
In addition, machine learning techniques are used to detect abnormal behavior in livestock in real time from camera image sequences and take action.

Precision farming, for example, involves determining and administering the right amount of fertilizer for each crop individually. Impact assessments of climate change on native animal and plant diversity are also conducted, and countermeasures are proposed.

Breeding informatics thus ensures that we will be able to feed more and more people on Earth in the future while also practicing more sustainable agriculture.

further Information will follow

further Information will follow