Technological Infrastructures

The Data Engineering Laboratory (LADE) at Area Science Park has recently published an article in Nature – Scientific Data on protein sequence annotation. Thanks to technological advances in genomic sequencing, the number of known protein sequences has grown exponentially. Many of these sequences come from metagenomic projects that analyze environmental and clinical samples. Among the most relevant datasets in this field stands the Unified Human Gastrointestinal Proteome (UHGP) catalog, with a variety of applications in medicine and biology. However, the limited annotation of these sequences reduces their effectiveness. To address this issue, the DPCfam-UHGP dataset was developed, classifying UHGP sequences into protein families that typically group proteins sharing the same biological function. The dataset contains 10,778 families, generated through DPCfam clustering, an unsupervised method that organizes sequences into single- or multi-domain architectures. This project, part of Federico Barone‘s doctoral research supervised by Alessio Ansuini and Alberto Cazzaniga, exemplifies the fruitful interaction between data management and data science. In this context, the construction of a curated database of gastrointestinal proteins enabled more refined cataloging through advanced machine learning algorithms, allowing continuous database updates in fruitful feedback loop aimed at promoting new discoveries. The DPCfam-UHGP50 dataset, accessible through a web server, was developed following the best FAIR (Findable, Accessible, Interoperable, Reusable) practices, with the aim of fostering new discoveries in the field of human gastrointestinal tract metagenomics. Previously, LADE had already produced the DPCfam-UR50 database, accompanied by a publication in PLOS – Computational Biology.

The Data Engineering Laboratory (LADE) at Area Science Park has recently published an innovative study into Bioinformatics, opening up new perspectives in the study of proteins, the fundamental building blocks of life. In fact, Francesca Cuturello, Marco Celoria, Alessio Ansuini and Alberto Cazzaniga, the authors of the study, have demonstrated how artificial intelligence can predict the impact of genetic mutations on protein stability, helping to get a better understanding of the mechanisms underlying many diseases and potentially developing new treatments. The genome of living beings is constantly mutating due to external agents or random events and this leads us to observe changes in the sequences of the proteins they synthesise. Conducted as part of the Pathogen Readiness Platform for CERIC-ERIC (PRP@CERIC) project, the study uses AI models similar to GPT, applied to proteomics. These models are based on the analogy between a protein sequence and a sentence, with amino acids acting as “words”, allowing algorithms trained on hundreds of millions of protein sequences to be applied. Using this technique, the LADE researchers were able to predict how small variations in the amino acid sequence, such as those induced by mutations, can affect protein stability. A particularly innovative aspect is the use of the MSA Transformer model, which utilises information on the ancestral relationships between protein sequences to enhance the accuracy of predictions. The algorithm developed by LADE offers cutting-edge performance and will be made available to the scientific community to encourage further advancements in this field. “Predicting the effect of protein mutations through artificial intelligence allows us to explore, with great precision, complex biological phenomena that, until recently, were difficult to observe directly”, explains Francesca Cuturello, the study’s lead author. “This technology is a step forward towards innovative therapeutic solutions for a wide range of diseases.” The team’s work has already received widespread recognition, including Francesca Cuturello’s invitation to the prestigious Research Retreat “Physics of Biological Data Analysis” at the Aspen Center for Physics and it will be presented at other international research centres, such as the ICTP and the Leibniz Center for Informatics. For more information about LADE’s activities, click here.

Francesco Ortu was awarded the Artificial Intelligence Prize from the University of Trieste for his thesis “Interpreting How Large Language Models Handle Facts and Counterfactuals through Mechanistic Interpretability” as part of the Master’s program in “Data Science and Scientific Computing”. This work was developed at the Institute for Research and Technological Innovation (RIT) of Area Science Park. The study focuses on how generative language models, like those behind ChatGPT, react when presented with text containing false information. The work was published in the Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics and presented last August in Bangkok at one of the most important conferences on Computational Linguistics and Artificial Intelligence for Natural Language. “Research on interpretability,” explains Francesco Ortu, “aims to bridge the gap between empirical approaches and our scientific understanding of the inner workings of generative language models (LLMs). So far, most existing research in this area has focused on how models copy or recall factual knowledge. In our study, we analyzed how information propagates within the neural network, identifying the ‘neurons’ that choose whether to promote or suppress false information proposed by the user.” Congratulations to Francesco, with best wishes for pursuing exciting discoveries during his PhD, which will soon begin at the Laboratory of Data Engineering in Area Science Park.

Thanks to Data Science, today we can analyse and manipulate an enormous amount of data, derived from the most disparate platforms: From social networks to medical records, from geolocators to streaming services. All with the aim of extracting new knowledge and value. The data scientist uses advanced mathematical and physical techniques to find correlations, causal relationships, and interactions among data, developing hypotheses to test, and gradually improving analysis algorithms. Many of the techniques used are inspired by the results of fundamental physics, ranging from the physics of complex systems to high-energy physics. These fruitful correlations and their repercussions on society, the economy, the world of work, and industry will be explored during the international conference “Data Science in Fundamental Physics and its bridge to industry & society”, which will be held in Santiago De Compostela (Spain) from 3 to 7 June. It is organised by the Galician Institute of High Energy Physics (Instituto Galego de Fisica de Altas Enerxias, IGFAE). Matteo Biagetti, a research physicist at LADE – the Data Engineering Laboratory active in Artificial Intelligence and Data Management, will represent Area Science Park and his research activities in the field. The conference will highlight career opportunities within the field of fundamental physics and its synergies with the job market. It will also include a session where companies can present their needs related to Data Science. By bringing together both aspects, this occasion aims at creating a framework for the mutual exchange of knowledge and will allow the development of practical synergies from Data Science to fundamental physics and from Data Science to industry. More information on the event: Data Science in Fundamental Physics and the Bridge to Industry (usc.es) Find out about the LADE and its team of researchers

The Clean Hydrogen Partnership Joint Undertaking, the unique public private partnership supporting research and innovation (R&I) activities in hydrogen technologies in Europe, has confirmed the preliminary results of the Horizon Europe call for Large Scale Hydrogen Valleys. The North Adriatic Hydrogen Valley project, the transnational project created by the alliance between Croatia, Slovenia and the Autonomous Region of Friuli Venezia Giulia in Italy, has received a positive technical evaluation and is now eligible to move on to the grant negotiation phase. If all goes well the project will be eligible for a grant of up to €25 Million in direct funding. The results of the negotiation phase are expected by early February. The “North Adriatic Hydrogen Valley” with the participation of the Slovenian and Croatian governments, and the Autonomous Region of Friuli Venezia Giulia is the first transnational project aimed at developing a dedicated hydrogen valley. The project came about following an agreement between Croatia, Slovenia and the Autonomous Region of Friuli Venezia Giulia, with the aim of establishing a framework for cooperation in developing environmentally friendly hydrogen-production technologies. This collaboration will not only contribute to transitioning to an integrated ecosystem involving the energy, industry and transport sectors, but will also allow cooperation in research and innovation, to develop a hydrogen supply chain. The partnership, led by Slovenian Utility company HSE, includes 34 organisations representing key actors from Government, Research and Business communities and covers the entire value chain from production through storage and distribution to final end use of Hydrogen as a key energy vector in multiple sectors. Key industry players from all three countries will develop pilot projects for the production of over 5000 tonnes per year of green hydrogen from renewable energy sources and its storage, distribution and usage for the decarbonisation of important industrial sectors such as steel and cement production as well as sustainable transport solutions. Massimiliano Fedriga, President of the Friuli Venezia Giulia Autonomous Region “I welcome with great satisfaction the achievement of a result of the highest value which concerns the entire regional territorial system which has committed itself, with great conviction, to building the foundations for the construction of a hydrogen valley on a transnational scale with the aim to accelerate the energy transition process. The “North Adriatic Hydrogen Valley” project was born thanks to the long standing collaboration between the research and innovation hubs of Friuli Venezia Giulia, Slovenia and Croatia which, providing a unique example on a macro-regional scale, have been able to pool knowledge and skills, and thanks also to the investments that industry in the three territories has already planned which require large-scale coordination capacity to produce significant effects in terms of employment and the well-being of our communities. I trust that the positive evaluation of the project at European level will lead in due course to a grant award and also bodes well for other opportunities that the Region intends to exploit in a synergistic way, starting with the investments envisaged by the Italian Recovery and Resilience Plan for the production and use of hydrogen”. Davor Filipović, Minister of Economy and Sustainable Development of the Republic of Croatia “The “North Adriatic Hydrogen Valley” project is a logical first step in the implementation of Croatian Hydrogen Strategy until 2050. The importance of hydrogen in Croatia is increasing and numerous Croatian companies have started to develop hydrogen projects. The “North Adriatic Hydrogen Valley” will upraise hydrogen economy and mark all three territories as hydrogen friendly. The added value of the valley is the successful cooperation among the three territories that will ensure faster implementation of numerous projects and open new horizons for our companies and universities. We need to be aware that hydrogen, produced mostly in Europe, could become a significant source of energy and a strong tool for the decrease of energy import dependency as one of the most important issues for boosting EU economy. Our goal is clear: we aim to be an important global player based on clean and sustainable economy. Bojan Kumer, Ministry of Infrastructure of the Republic of Slovenia After a long period of joint efforts of all partners from Slovenia, Croatia and Friuli Venezia Giulia, we are very pleased that the North Adriatic Hydrogen Valley was positively evaluated by the Clean Hydrogen Partnership Joint Undertaking. This is another step towards ensuring more sustainable and green-house gas emission-free economies in the North Adriatic basin. By developing hydrogen-based ecosystem, we will complement other solutions towards emission-free economy. All the analyses and research so far show that for the successful implementation of such a large and complex project, joining forces cross-border is very important. Not only that it makes the realisation of such a complex project possible, it also paves the way to new opportunities for future cooperation with our partners for Croatia and Italy and hopefully also the broader region. It is also worth mentioning that this project is a result of joint efforts by the state and regional administrations, industry, research institutions and the public, the so-called quadruple helix model. This broad collaboration is indeed a guarantee for the success of this project and for the further development of hydrogen-based solutions for broader use. Tomaž Štokelj, CEO of Holding Slovenske elektrarne d.o.o – HSE, Lead Partner Holding Slovenske elektrarne (HSE), the largest Slovenian power producer and the main producer of renewable electrical energy, is proud to be one of the leading partners in The North Adriatic Hydrogen Valley project, an industry driven initiative which has resulted as common effort of institutional, industry and research partners from the territory of Friuli Venezia Giulia Region in Italy, Croatia, and Slovenia. Company ECUBES has had a vison of hydrogen ecosystem in year 2015, which has been developed to Zero Emission Mobility Corridor Slovenia project in 2018 and which was also a basis for RESHUB project concept in sector of defence. Ministry of Infrastructure and Ministry of Environment and Spatial Planning of Republic of Slovenia have declared their support to Zero Emission Mobility Corridor Slovenia in 2020 with an aim to develop a national hydrogen ecosystem. Development of the North Adriatic Hydrogen Valley project initiative has been accelerated through the first Hydrogen Ecosystem North Adriatic conferences held in Nova Gorica in November 2021. Letter of intent signed by State secretaries of Slovenia and Croatia and the President of Friuli Venezia Giulia Autonomous Region in early 2022 has formed joint working group at the institutional level. This has enabled main framework for successful fusion of partial and local activities in hydrogen technologies of the territory into one common project of 34 partners. HSE has taken a role of the leading partner in the project with honour. Development of hydrogen-based solutions is important for energy sector and its green transformation, as energy storage is a prerequisite for decarbonization and large-scale employment of renewables. The North Adriatic Hydrogen Valley project also represents a tight cooperation between institutional, industry and research partners, which will result in accelerated development of the territory and faster transition into energy resilient and carbon dioxide emission neutral society, in line with HSE’s mission and vision. Caterina Petrillo, Area Science Park President “The project is the result of formidable teamwork where the contributions provided by each of the partners, based on their respective skills and experience, have been integrated and harmonized to imagine the future of the so-called “Hydrogen Economy”. The development of the North Adriatic Hydrogen Valley concept saw a marked acceleration in 2021 when the University of Trieste drove the addition of research institutions to the growing partnership which already included companies and government institutions from Slovenia and Croatia as well as Friuli Venezia Giulia. Area Science Park made available to the project its many years of consolidated experience in scientific cooperation, in particular in South-eastern Europe, as well as its ability to build public-private partnerships between research centres and innovative companies with production in strategic sectors for growth. Furthermore, this project represents a great opportunity for the institution to further develop applied skills in the sector of innovative materials.”