Mass spectrometry driven proteomics allows deep insights into the working of cells. Still, the vast majority of proteoforms, representing the full heterogeneity of molecular forms of protein products in a sample, currently remain undetected in proteomics experiments. This lack of information strongly restricts our knowledge of disease progression, possible biomarkers, and therapeutic targets across a large number of diseases. Several machine learning approaches have been developed for proteomics data, but not being trained end-to-end, they cannot capture the full wealth of proteomic mass spectra and commonly remain unexplained black boxes. Within explAInProt, my team and I will develop representations of spectra that allow deploying explainable, end-to-end machine learning models on the wealth of proteomic data available, regarding both bottom-up and topdown spectra to identify novel protein variants. Explanations will allow identifying the origin of predictions and allow reducing bias and building up the trustworthiness of AI systems required for clinical applications. To verify results, we will pioneer orthogonal real-time strategies based on selective sequencing approaches and calling of amino acids that we will introduce for nanopore sequencing devices as a complementary acquisition method. All combined, this will allow to drastically increase our knowledge about the current dark matter of mass spectrometry driven proteomics: those proteins and peptides that are non-canonically modified, non-tryptic, have potentially multiple amino acid substation, or no close match in databases or result from structural variants such as fusion proteins that they remain undetected in current analyses. We will highlight applicability in two areas of particular concern in current approaches: the detection of structural variants in proteomic mass spectra and the characterization of novel microbial organisms without sufficient database information.

SEPTON aims to address the gap in the generic technologies and processes referring to the IT network infrastructure with a holistic approach towards reinforcing NMD security within the healthcare centre premises. The project will advance cutting-edge solutions in healthcare cybersecurity targeting the aforementioned health providers and particularly focusing on networked medical devices (NMDs). The SEPTON approach will result in a comprehensive cybersecurity toolkit providing tools and mechanisms to be used in hospitals and care centres for a) the protection of networked medical devices, including wearable and implantable devices, and using techniques such as polymorphism b) the secure and privacy preserving data exchanges between NMDs, utilising techniques such as blockchain, differential privacy and encryption c) behavioural anomaly detection, utilising a cybersecurity analytics framework coupled with machine learning techniques and hardware acceleration for increased performance and d) NMD vulnerability assessment. The usability of the proposed solutions will be tested in a realistic setup via extensive pilot trials, facilitated by the participation of two healthcare organisations

We live in a crucial historical moment, with tremendous challenges ahead, from climate change to the energy crisis. ELIAS emerges from the belief that AI will be a key discipline to help us tackle these challenges. At the same time, the development of AI entails deep ethical and societal concerns that need to be addressed. As for fundamental research, ELIAS will address key scientific questions about how AI can reduce computational costs, serves to model effects of policy decisions on society, and impacts individuals. ELIAS will strive for a deep integration of the fundamental research that takes place in academia and the more applications-focused research from industry. ELIAS builds on and expands the highly successful and internationally recognized European Laboratory for Learning and Intelligent Systems (ELLIS). ELIAS will further develop the excellence criteria and the pillars in ELLIS and implement actions that will support AI researchers and young talents at different stages of their careers. Furthermore, ELIAS will develop a Sciencentrepreneurship track, with the purpose of attracting and empowering talents at the interface of scientific innovation and business and establish original AI solutions that move towards a sustainable long-term future for our planet, contribute to a cohesive society, and respect individual rights. The outcome of ELIAS will be to establish Europe as a leader in AI research in which impact on the environment, society and the individual are integral considerations during development. We will measure the success of this endeavor in terms of key indicators, including the number of new cross-institutional collaborations, the number of cross-disciplinary collaborations, the number of industry-academic partnerships, publications in top conferences and journals, patents, and the number of projects that have resulted in deployed technologies.