Drug target discovery and personalized medicine are challenging areas of research. The knowledge and necessary skills needed to excel in these fields are difficult on many different levels, and each level has its own further complexities. At MNM, our recipe for success is to push forward the boundaries of research while integrating 4 main areas: bioscience, bioinformatics, data science, and computer science. Here's how we do it.
The first task is to understand the biochemical and biophysical mechanisms on a molecular level, but also have the ability to thoroughly explain the biological characteristics of specific cancers. This is by no means easy, but our bioscientists keep track of the most recent advancements in these fields, combining the knowledge of many research groups and trying to map it against our proprietary insights to propose the next important steps on our way to explain cancer.
The biological complexity of oncogenesis is reflected in the data we process. The data needs to be analyzed in order to identify descriptors we could later use for cohort stratification and drug target discovery. This is where our bioinformaticians come first. They're technology-oriented experts who can speak biology, but also understand programmatic code. They cooperate with bioscientists on a daily basis and program detailed biological concepts using multi-omics data.
Artificial intelligence has proven potential and lies at the core of our insights’ generation process. Despite the immense progress in this field and lots of available solutions, off-the-shelf algorithms are only applicable to small parts of this process. This is where our data scientists use their expertise to help bioscientists in building and navigating the complex landscape of cancer. Together, they develop novel techniques for drug target discovery and cohort selection using the data and the descriptors engineered by the bioinformaticians.
To achieve progress in this area, we need to ensure that bioscientists, bioinformaticians, and data scientists can come together to efficiently interact, communicate and use their own specialized sets of tools. This is where our ARETEai platform comes into play. ARETEai is built by our platform team (DevOps experts) which focuses on configuring modern cloud infrastructure that can dynamically scale and expose dedicated interfaces for various user types and hide the complexity of the system when necessary. Biologists mostly use graphical interfaces to carry out standardized analyzes, or to visualize and evaluate insights. Bioinformaticians develop genomic and feature extraction pipelines in a scalable ecosystem that's able to handle big data. Data scientists develop many custom analyzes using specialized frameworks and libraries, which involves a lot of iterative combinations, advanced, resource-intensive prototyping, and trying novel techniques.
ARETEai is a platform that serves all of these 3 types of users, facilitating interdisciplinarity as well as collaboration. We make our platform as flexible as possible and make sure the architecture of the system is relatively simple. The ARETEai platform is an important step in finding common ground for different experts working towards a single goal - better outcomes of personalized medicine.
