Need for thorough and cheap data analysis formed Biogenity
CEO Kenneth Kastaniegaard co-founded Biogenity in the summer of 2018 based on a need that became obvious throughout his Ph.D. studies in biomedical engineering. In short, he saw an opportunity for a company providing thorough and cheap data analysis.
The omics technologies advance vastly and dominate discovery-based studies for biomarkers. These methods may deliver above 10.000 readings per sample, thus generating a large amount of data. This may be overwhelming for a researcher who is not a data-specialist. Scientific journals within the field provide many of those examples, where the researcher base the choice of statistics applied on assumptions and instead of tests that show the correct method to apply. Ultimately, this means that the message published might be wrong, and thus the suggested biomarkers for a disease or disease-biology.
Machine Learning-based tools increase in numbers. They may increase the output of the possible achievement from data analysis, which also increase in numbers. The means that a researcher needs to be a ‘data scientist’ to be able to select analyses, which are relevant to apply to the particular questions. Employing a data scientist is not a luxury that all research teams or biotech SMEs can afford.
Making data easy to manage and interpret
Biogenity's vision is to make data easy to manage and interpret, providing a deeper and more clear understanding of the data to make advanced data analyses accessible for all sizes of enterprises and Researchers with one mission: To fuel and focus the search of new biomarkers for diagnosis and for following treatment and progression of diseases.
Biogenity offers data analysis of gene and protein expressions. The researcher gets a full analysis of the data with State-of-the-Art bio statistical methods. We use Machine Learning methods including several clustering methods like K-means to achieve a deeper insight. This enables discovery of subgroups and sub-studies within a single study, which enables the expansion of the analysis and potential discovery of personalised medicine-based features.
The results of the analysis ends up in a rapport with graphic representations of the data. The rapport explains the decisions made and what using the various methods used imply. The output of the analysis comprises folders containing tables and figures; the exact calculated values from ex. regulation of different proteins and graphic illustrations of every regulation by Boxplot.
Providing cheap access to data analytics
For Biogenity, it is all about contributing to research by helping SMEs and the public sector gain cheap access to premium expression data analytics. The important objective is to make data analysis easily accessible. Compared to most providers of data analysis our core competence lies in the analytical work of expression data.
To help biotech SMEs achieve high success rates in early-stage drug development
Biogenity’s analysis of expression data is already on the market. Next step is a biomarker validation tool based on Big Data and Machine Learning. The goal is to launch a commercial version in 2020, positioning Biogenity to become the global go-to agency for SMEs when validating drug and diagnostic tools.
To get a drug candidate through the first stage of clinical testing may have a very success low rate at high costs. A big data validation prior to clinical trial can increase the success rate significantly, which the large pharmaceutical companies make use of. Due to high costs, this has not previously been an opportunity for about 20,000 SMEs.
Biogenity’s goal is to provide SMEs the same opportunity to identify drug targets quickly and more precisely. The company’s engine identifies unique patterns in more than 50 diseases by analysing data from more than 4.000 research experiments, and this approach is not limited to particular diseases. It compares patterns from all the available diseases, disclosing what is unique for the particular disease. The engine may also be able to come up with new disease targets for already working drugs.
Who wants to join a case study?
Biogenity currently seeks partners, who want to participate in a case study to Beta-test “The Big Data Validation of Biomarkers”, and to explore shared funding opportunities. In addition, Biogenity wants to expand the network of people, who works with gene and protein expression analysis and agrees to the importance of proper data analysis.
So stakeholders, who may be able to help make people aware of Biogenity’s product and at the same time interested in learning about the newest methods within Machine Learning.
Currently Biogenity expands the Advisory Board; they seek a person with business experience in the field as well as a person with knowledge in Machine Learning in order to debate new methods and their gains/pains.