STRATUM is a Horizon Europe multi-partner project developing a clinically validated, real-time 3D decision support tool for brain tumour surgery. The system integrates Hyperspectral Imaging (HSI), AI-based multimodal data fusion, and heterogeneous High-Performance Computing (HPC) architectures combining Graphics Processing Units (GPUs), Field-Programmable Gate Arrays (FPGAs), and Processing-In-Memory (PIM) technologies. A touchless augmented reality interface facilitates safe and intuitive intraoperative interaction. The distinguishing characteristic of STRATUM is its end-to-end co-designed approach, which integrates advanced computing, state-of-the-art imaging and clinical expertise into a unified Point-of-Care (PoC) platform. Utilising a structured co-creation methodology involving surgeons, engineers, and social scientists, the project ensures usability, safety and regulatory compliance from its early design stages to its clinical validation. The usability of STRATUM will be tested in three hospitals located in different European regions with diverse conditions and regulations. This will allow to collect advice and remarks from surgical staff in a continuous co-creation and co-tuning protocol. Beyond its clinical objectives, STRATUM contributes to the advancement of heterogeneous computing for real-time diagnostics, AI acceleration in critical medical environments and energy-efficient system integration. Furthermore, it delivers open datasets, validated AI pipelines, and performance benchmarks with a view to fostering future research and industrial innovation in digital surgery. The STRATUM project establishes a replicable model for intelligent, human-centred computing integrating microelectronics, AI and medicine.The paper presents an overview of the project in terms of aims, concepts and technologies and the description of the state of the work when approaching the end of the second of the five years planned. Specifically, the outcomes of the steps related to the collaboration with surgeons and medical staff (co-creation process) and the intelligent Graphical User Interface (GUI) development will be described. The latter allows for contactless interaction of the surgeon with several functions that have already been developed in the system.

Integrated digital diagnostics can support complex surgical procedures in many anatomical sites, brain tumour surgery being the most complex. STRATUM is a 5-year Horizon Europe funded project with the goal of developing an innovative 3D decision support tool for brain tumour surgeries, based on real-time multimodal data processing using artificial intelligence algorithms. The proposed tool is envisioned as an energy-efficient Point-of-Care computing system to be integrated within neurosurgical workflows to aid surgeons to make informed, efficient, and accurate decisions during surgical procedures. The expected long-term impact of STRATUM is to reduce the duration of surgical procedures, thus decreasing patients' risks, but also optimising the resources of European health care systems.

SUMMARY: Nuclear magnetic resonance (NMR)-based metabolomics is widely used to obtain metabolic fingerprints of biological systems. While targeted workflows require previous knowledge of metabolites, prior to statistical analysis, untargeted approaches remain a challenge. Computational tools dealing with fully untargeted NMR-based metabolomics are still scarce or not user-friendly. Therefore, we developed AlpsNMR (Automated spectraL Processing System for NMR), an R package that provides automated and efficient signal processing for untargeted NMR metabolomics. AlpsNMR includes spectra loading, metadata handling, automated outlier detection, spectra alignment and peak-picking, integration and normalization. The resulting output can be used for further statistical analysis. AlpsNMR proved effective in detecting metabolite changes in a test case. The tool allows less experienced users to easily implement this workflow from spectra to a ready-to-use dataset in their routines. AVAILABILITY AND IMPLEMENTATION: The AlpsNMR R package and tutorial is freely available to download from http://github.com/sipss/AlpsNMR under the MIT license. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: The detection of regulatory regions in candidate sequences is essential for the understanding of the regulation of a particular gene and the mechanisms involved. This paper proposes a novel methodology based on information theoretic metrics for finding regulatory sequences in promoter regions. RESULTS: This methodology (SIGMA) has been tested on genomic sequence data for Homo sapiens and Mus musculus. SIGMA has been compared with different publicly available alternatives for motif detection, such as MEME/MAST, Biostrings (Bioconductor package), MotifRegressor, and previous work such Qresiduals projections or information theoretic based detectors. Comparative results, in the form of Receiver Operating Characteristic curves, show how, in 70% of the studied Transcription Factor Binding Sites, the SIGMA detector has a better performance and behaves more robustly than the methods compared, while having a similar computational time. The performance of SIGMA can be explained by its parametric simplicity in the modelling of the non-linear co-variability in the binding motif positions. CONCLUSIONS: Sequence Information Gain based Motif Analysis is a generalisation of a non-linear model of the cis-regulatory sequences detection based on Information Theory. This generalisation allows us to detect transcription factor binding sites with maximum performance disregarding the covariability observed in the positions of the training set of sequences. SIGMA is freely available to the public at http://b2slab.upc.edu.

This paper presents the preliminary results obtained when using a mobile robot to measure gas and wind intensity in an indoor area by means of several attached sensors such as a LIDAR, an e-nose, and an anemometer. The robot navigation was performed by means of a random path planning and the robot self location was performed by means of an SLAM procedure. This paper presents the first preliminary results obtained in a set of measurement experiments. In all cases, the indoor area has a fixed artificial simulated airflow and an induced gas leak source placed in different locations of the experimentation area. Results have shown different gas diffusion profiles in the different experiments performed.

One of the main causes of car accidents is drowsiness. There have been many studies regarding driving monitoring systems in the past few years, although most of them are focused in simulator environments. This paper presents a system to detect drowsiness patterns in real driving environments, where many external conditions need to be taken into account. Initial tests were done in simulator, followed by tests in real vehicles. Although two different approaches have been developed, this paper is focused in the inadequate driving identification based on the steering movements. Its sub-modules are also presented, with a special focus on the active driving detector.

MOTIVATION: The identification of the sites at which transcription factors (TFs) bind to Deoxyribonucleic acid (DNA) is an important problem in molecular biology. Many computational methods have been developed for motif finding, most of them based on position-specific scoring matrices (PSSMs) which assume the independence of positions within a binding site. However, some experimental and computational studies demonstrate that interdependences within the positions exist. RESULTS: In this article, we introduce a novel motif finding method which constructs a subspace based on the covariance of numerical DNA sequences. When a candidate sequence is projected into the modeled subspace, a threshold in the Q-residuals confidence allows us to predict whether this sequence is a binding site. Using the TRANSFAC and JASPAR databases, we compared our Q-residuals detector with existing PSSM methods. In most of the studied TF binding sites, the Q-residuals detector performs significantly better and faster than MATCH and MAST. As compared with Motifscan, a method which takes into account interdependences, the performance of the Q-residuals detector is better when the number of available sequences is small.

Statistical methods like Principal Components Analysis (PCA) or Partial Least Squares (PLS) and multiscale approaches, have been reported to be very useful in the task of fault diagnosis of malfunctioning sensors for several types of faults. In this work, we compare the performance of PCA and Multiscale-PCA on a fault based on a change of sensor sensitivity. This type of fault affects chemical gas sensors and it is one of the effects of the sensor poisoning. These two methods will be applied on a dataset composed by the signals of 17 conductive polymer gas sensors, measuring three analytes at several concentration levels during 10 months. Therefore, additionally to performance's comparison, both method's stability along the time will be tested. The comparison between both techniques will be made regarding three aspects; detection, identification of the faulty sensors and correction of faulty sensors response.

In this paper, we propose a biologically inspired architecture for a Hopfield-like associative memory applied to artificial olfaction. The proposed algorithm captures the projection between two neural layers of the insect olfactory system (Antennal Lobe and Mushroom Body) with a kernel based projection. We have tested its classification performance as a function of the size of the training set and the time elapsed since training and compared it with that obtained with a Support Vector Machine.