Foundation Models (FMs) hold transformative potential to accelerate scientific discovery, yet reaching their full capacity in complex, highly multimodal domains such as genomics, drug discovery, and materials science requires a deeper consideration of the contextual nature of the scientific knowledge . We revisit the synergy between FMs and Multimodal Knowledge Graph (MKG) representation and learning, exploring their potential to enhance predictive and generative tasks in biomedical contexts like drug discovery. We seek to exploit MKGs to improve generative AI models’ ability to capture intricate domain-specific relations and facilitate multimodal fusion. This integration promises to accelerate discovery workflows by providing more meaningful multimodal knowledge-enhanced representations and contextual evidence. Despite this potential, challenges and opportunities remain, including fusing multiple sequential, structural and knowledge modalities and models leveraging the strengths of each; developing scalable architectures for multi-task multi-dataset learning; creating end-to-end workflows to enhance the trustworthiness of biomedical FMs using knowledge from heterogeneous datasets and scientific literature; the domain data bottleneck and the lack of a unified representation between natural language and chemical representations; and benchmarking, specifically the transfer learning to tasks with limited data (e.g., unseen molecules and proteins, rear diseases). Finally, fostering openness and collaboration is key to accelerate scientific breakthroughs.

Recent research on predicting the binding affinity between drug molecules and proteins use representations learned, through unsupervised learning techniques, from large databases of molecule SMILES and protein sequences. While these representations have significantly enhanced the predictions, they are usually based on a limited set of modalities, and they do not exploit available knowledge about existing relations among molecules and proteins. Our study reveals that enhanced representations, derived from multimodal knowledge graphs describing relations among molecules and proteins, lead to state-of-the-art results in well-established benchmarks (first place in the leaderboard for Therapeutics Data Commons benchmark ``Drug-Target Interaction Domain Generalization Benchmark", with an improvement of 8 points with respect to previous best result). Moreover, our results significantly surpass those achieved in standard benchmarks by using conventional pre-trained representations that rely only on sequence or SMILES data. We release our multimodal knowledge graphs, integrating data from seven public data sources, and which contain over 30 million triples. Pretrained models from our proposed graphs and benchmark task source code are also released.

This paper presents a data-driven method for transit network design that relies on a large sample of user location data available from mobile phone telecommunication networks. Such data provide opportunistic sensing and the means for transit operators to match supply with mobility demand inferred from mobile phone locations. In contrast to previous methods of transit network design, the proposed method is entirely data driven, leveraging the large-sample properties of disaggregate mobile phone network data and mobility pattern mining. The method works by deriving frequent patterns of movements from anonymized mobile phone location data and merging them to generate candidate route designs. Additional routines for optimal route selection and service frequency setting are then employed to select a network configuration made up of routes that maximizes systemwide traveler utility. Using data from half a million mobile phone users in Abidjan from the telco operator Orange, we demonstrated to provide resource-neutral system improvement of 27% in terms of end-user journey times.

The deep penetration of mobile phones offers cities the ability to opportunistically monitor citizens' mobility and use data-driven insights to better plan and manage services. With large scale data on mobility patterns, operators can move away from the costly, mostly survey based, transportation planning processes, to a more data-centric view, that places the instrumented user at the center of development. In this framework, using mobile phone data to perform transit analysis and optimization represents a new frontier with significant societal impact, especially in developing countries. In this paper we present AllAboard, an intelligent tool that analyses cellphone data to help city authorities in visually exploring urban mobility and optimizing public transport. This is performed within a self contained tool, as opposed to the current solutions which rely on a combination of several distinct tools for analysis, reporting, optimisation and planning. An interactive user interface allows transit operators to visually explore the travel demand in both space and time, correlate it with the transit network, and evaluate the quality of service that a transit network provides to the citizens at very fine grain. Operators can visually test scenarios for transit network improvements, and compare the expected impact on the travellers' experience. The system has been tested using real telecommunication data for the city of Abidjan, Ivory Coast, and evaluated from a data mining, optimisation and user prospective.

We present an approach to access and consolidate complex information spanning multiple specialist domains and make it available to non-experts. We are using a combination of business rules and contextual exploration to reduce interface complexity and improve consumability. We present a use case and a prototype on top of a real-world enterprise solution for coordinating Social care and Health care. We evaluate our system through a user study. Our results indicate that our approach reduces the time required to obtain business results compared to a baseline graph exploration approach.

This paper presents STAR-CITY, a system supporting semantic traffic analytics and reasoning for city. STAR-CITY, which integrates (human and machine-based) sensor data using variety of formats, velocities and volumes, has been designed to provide insight on historical and real-time traffic conditions, all supporting efficient urban planning. Our system demonstrates how the severity of road traffic congestion can be smoothly analyzed, diagnosed, explored and predicted using semantic web technologies. We present how semantic diagnosis and predictive reasoning, both using and interpreting semantics of data to deliver useful, accurate and consistent inferences, have been exploited and adapted systematized in an intelligent user interface. Our prototype of semantics-aware traffic analytics and reasoning, experimented in Dublin City Ireland, works and scales efficiently with historical together with real live and heterogeneous stream data.

The deep penetration of mobile phones offers cities the ability to opportunistically monitor citizensfi mobility and use data-driven insights to better plan and manage services. In this context, transit operators can leverage pervasive mobile sensing to better match observed demand for travel with their service offerings. In this paper we present AllAboard, an intelligent tool that analyses cellphone data to helps city authorities in exploring urban mobility and optimizing public transport. An interactive user interface allows transit operators to explore the travel demand in both space and time, evaluate the quality of service that a transit network provides to the citizens, and test scenarios for transit network improvements. The system has been tested using real telecommunication data for the city of Abidjan, Ivory Coast, and evaluated from a data mining, optimization and user prospective.

The dynamics of social events happening in large metropolitan areas are extremely complex. Location-based user generated data could be an exceptionally rich source of information about events, however the vastness and the heterogeneity of such information makes it almost impossible for city managers to have a comprehensive view. Some events are planned and advertised only among restricted communities, for many it is problematic to estimate the number of attendees, and in general it is very difficult to have information about citizen mobility in areas nearby or where events happen. In this paper, we describe EXSED, an interactive intelligent tool to support the visual exploration of social events dynamics along the spatial, temporal and organizational dimensions. Major functionalities include: (i) studying events that are either officially/unofficially planned and with global/local scope, (ii) extract discussion topics for an event and investigate their temporal and spatial profile, (iii) estimate event attendees and correlate their mobility patterns with the event evolution. We present preliminary results of a field study with officials from Dublin City Council (Ireland), who evaluated our tool on real world user-generated tweeter data and events in the city.

This paper describes an approach for a composition of Web services based on their semantic descriptions. The process section of OWL-S service descriptions is built with references to ontology concepts which represent service input and output data types. We present an engine that receives a request containing a concept (OC) corresponding to a service output and a set of concepts (ICs) corresponding to a service inputs. The engine produces a sequence of services whose first element has ICs as inputs and whose last element has OC as output. The result of the composition is described as a BPEL process.