Search

Background: In this study, we evaluated the lipidome alterations caused by type 1 diabetes (T1D) and type 2 diabetes (T2D), by determining lipids significantly associated with diabetes overall and in both sexes, and lipids associated with the glycaemic state. Methods: An untargeted lipidomic analysis was performed to measure the lipid profiles of 360 subjects (91 T1D, 91 T2D, 74 with prediabetes and 104 controls (CT)) without cardiovascular and/or chronic kidney disease. Ultra-high performance liquid chromatography-electrospray ionization mass spectrometry (UHPLC-ESI-MS) was conducted in two ion modes (positive and negative). We used multiple linear regression models to (1) assess the association between each lipid feature and each condition, (2) determine sex-specific differences related to diabetes, and (3) identify lipids associated with the glycaemic state by considering the prediabetes stage. The models were adjusted by sex, age, hypertension, dyslipidaemia, body mass index, glucose, smoking, systolic blood pressure, triglycerides, HDL cholesterol, LDL cholesterol, alternate Mediterranean diet score (aMED) and estimated glomerular filtration rate (eGFR); diabetes duration and glycated haemoglobin (HbA1c) were also included in the comparison between T1D and T2D. Results: A total of 54 unique lipid subspecies from 15 unique lipid classes were annotated. Lysophosphatidylcholines (LPC) and ceramides (Cer) showed opposite effects in subjects with T1D and subjects with T2D, LPCs being mainly up-regulated in T1D and down-regulated in T2D, and Cer being up-regulated in T2D and down-regulated in T1D. Also, Phosphatidylcholines were clearly down-regulated in subjects with T1D. Regarding sex-specific differences, ceramides and phosphatidylcholines exhibited important diabetes-associated differences due to sex. Concerning the glycaemic state, we found a gradual increase of a panel of 1-deoxyceramides from normoglycemia to prediabetes to T2D. Conclusions: Our findings revea, This work was funded by Spanish Ministry of Health, Instituto de Salud Carlos III (Madrid, Spain) grants PI15/0625 (to DM and EC), PI17/01362 (to NA), PI18/0328 (to DM), FEDER “Una manera de hacer Europa”, and by Fundació La Marató de TV3 2016 (303/C/2016) (201602.30.31) (to NA). Spanish Ministry of Economy and Competitiveness, grant PID2021-122952OB-I00 funded by AEI 10.13039/501100011033 and by ERDF A way of making Europe, Instituto de Salud Carlos III (grant AC22/00035); and the CERCA Programme / Generalitat de Catalunya (to AP). This research was supported by CIBER-Consorcio Centro de Investigación Biomèdica en Red-CIBERDEM (leading group CB15/00071) and Biomedical Research Networking Center in Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Instituto de Salud Carlos III, Ministry of Science and Innovation. Institut de Recerca de l’Hospital de la Santa Creu i Sant Pau is accredited by the Generalitat de Catalunya as Centre de Recerca de Catalunya (CERCA). B2SLab is certified as 2021 SGR 01052., Peer Reviewed, Postprint (published version)

Many residential environments have been equipped with sensing technologies both to provide assistance to older people who have opted for aging-in-place and to provide information to caregivers and family. However, such technologies are often accompanied by physical discomfort, privacy concerns, and complexity of use. We explored the feasibility of monitoring home activity using chemical sensors that pose fewer privacy concerns than, for example, video-cameras and which do not suffer from blind spots. We built a monitoring device that integrates a sensor array and IoT capabilities to gather the necessary data about a resident in his/her living space. Over a period of 3 months, we uninterruptedly measured the living space of a typical elder person living on his/her own. To record the level of activity during the same period and obtain a ground truth for the activity, a set of motion sensors were also deployed in the house. Home activity was extracted from a PCA space moving-window which translated sensor data into the event space; this also compensated for environmental and sensor drift. Our results show that it is possible to monitor the person’s home activity and detect sudden deviations from it using a low-cost, non-invasive, system based on gas sensors that gather data on the air composition in the living space. We made the dataset publicly available at https://archive.ics.uci.edu/ml/index.php2., This work was supported by the Spanish Ministry of Economy and Competitiveness (www.mineco.gob.es) PID2021-122952OB-I00, DPI2017-89827-R, Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), initiatives of Instituto de Investigación Carlos III (ISCIII), Share4Rare project (Grant Agreement 780262), ISCIII (grant AC22/00035), ACCIÓ (grant Innotec ACE014/20/000018) and Pla de Doctorats Industrials de la Secretaria d’Universitats i Recerca del Departament d’Empresa i Coneixement de la Generalitat de Catalunya (2022 DI 014), and the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie (grant No. 101029808). JF also acknowledges the CERCA Program/Generalitat de Catalunya and the Serra Húnter Program. B2SLab is certified as 2017 SGR 952., Peer Reviewed, Postprint (published version)

Recent research on remote tracking environments has strengthened smart home IoT ecosystems by the integration of multiple sensing tools that capture not only contextual data in a private setting, but also information about its residents. This shift paves the way for remote health industries, as information traditionally out of reach is available 24/7. Gas sensing, moving away from privacy-invasive tracking paradigms, emerges within this context, inspiring the monitoring of activities of daily living (ADLs) that could facilitate the remote healthcare supervision of the elderly. In this paper, we present how a gas sensing array based on low-cost commercial metal oxide (MOX) gas sensors has been assembled for the development of Principal Component Analysis (PCA) model which detects cooking activity within a household. Our resulting unobtrusive tracking system requiring no user input and posing no privacy concerns, suitable to other ADL use cases, highlights how AI-equipped IoT cloud infrastructures and accurate gas sensors are called to revolutionise remote healthcare., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 861782. This work was supported in part by the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 101029808, No 101007653 and No. 801342 (Tecniospring INDUSTRY). This work was supported by the Spanish Ministry of Economy and Competitiveness DPI2017-89827-R, ACCIÓ (Innotec ACE014/20/000018) and Share4Rare project (Grant Agreement 780262). With the support from CERCA Programme / Generalitat de Catalunya., Peer Reviewed, Postprint (author's final draft)

Molecular classification of medulloblastoma is critical for the treatment of this brain tumor. Array-based DNA methylation profiling has emerged as a powerful approach for brain tumor classification. However, this technology is currently not widely available. We present a machine-learning decision support system (DSS) that enables the classification of the principal molecular groups—WNT, SHH, and non-WNT/non-SHH—directly from quantitative PCR (qPCR) data. We propose a framework where the developed DSS appears as a user-friendly web-application—EpiGe-App—that enables automated interpretation of qPCR methylation data and subsequent molecular group prediction. The basis of our classification strategy is a previously validated six-cytosine signature with subgroup-specific methylation profiles. This reduced set of markers enabled us to develop a methyl-genotyping assay capable of determining the methylation status of cytosines using qPCR instruments. This study provides a comprehensive approach for rapid classification of clinically relevant medulloblastoma groups, using readily accessible equipment and an easy-to-use web-application., The study was supported by Associations of Parents and Families of Children with Cancer and by funding of the Spanish Ministry of for Science, Innovation and University (grant PI20/00519; PI CL) and the Foundation La Marató TV3 (grant 201921-30; PI CL). We acknowledge the multidisciplinary team who helped in the molecular analyses and care of patients, and the BioBank Hospital Sant Joan de Déu of the Spanish BioBank Network for sample procurement. We also acknowledge Marta Fortuny for communication strategy advice and Eduard Puig for legal assistance and data protection regulations. Authors acknowledge the SJD Fundraising Team., Peer Reviewed, Article signat per 23 autors/es: Soledad Gómez-González, Joshua Llano, Marta Garcia, Alicia Garrido-Garcia, Mariona Suñol, Isadora Lemos, Sara Perez-Jaume, Noelia Salvador, Nagore Gene-Olaciregui, Raquel Arnau Galán, Vicente Santa-María, Marta Perez-Somarriba, Alicia Castañeda, José Hinojosa, Ursula Winter, Francisco Barbosa Moreira, Fabiana Lubieniecki, Valeria Vazquez, Jaume Mora, Ofelia Cruz, Andrés Morales La Madrid, Alexandre Perera, Cinzia Lavarino., Postprint (published version)

Lifestyle interventions have positive neuroprotective effects in aging. However, there are still open questions about how changes in resting-state functional connectivity (rsFC) contribute to cognitive improvements. The Projecte Moviment is a 12-week randomized controlled trial of a multimodal data acquisition protocol that investigated the effects of aerobic exercise (AE), computerized cognitive training (CCT), and their combination (COMB). An initial list of 109 participants was recruited from which a total of 82 participants (62% female; age¿=¿58.38¿±¿5.47) finished the intervention with a level of adherence¿>¿80%. Only in the COMB group, we revealed an extended network of 33 connections that involved an increased and decreased rsFC within and between the aDMN/pDMN and a reduced rsFC between the bilateral supplementary motor areas and the right thalamus. No global and especially local rsFC changes due to any intervention mediated the cognitive benefits detected in the AE and COMB groups. Projecte Moviment provides evidence of the clinical relevance of lifestyle interventions and the potential benefits when combining them., Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. Projecte Moviment is a project funded by the Spanish Ministry of Economy and Competitiveness under two grants: Neuroplasticity in the adulthood: physical exercise and cognitive training (PSI2013-47724-P) and Integrative omics study on the neurobiological effects of physical activity and cognitive stimulation (PSI2016-77475-R). It has also been rewarded with three pre-doctoral fellowships (FPU014/01460, FI-2016, and FI-2018). It was supported by the ICREA Academia Program to MM., SID is supported by a Beatriu de Pinós fellowship (2020 BP 00116). This work was supported by the Spanish Ministry of Economy and Competitiveness (www. mineco.gob.es) PID2021-122952OB-I00, Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), initiatives of Instituto de Investigación Carlos III (ISCIII), and Share4Rare project (Grant Agreement 780262)., Peer Reviewed, Postprint (published version)

Els criteris RANO són l'estàndard actual per fer el seguiment dels pacients amb tumors cerebrals ja que permeten avaluar l'evolució del tractament mitjançant l'obtenció dels diàmetres perpendiculars màxims al pla axial. Això no obstant, aquests criteris presenten una certa ambigüitat inter i intraoperador a l'hora de treure conclusions, que pot donar lloc a errors. Fent ús de les noves eines de segmentació automàtica de tumors mitjançant ML i IA, es vol desenvolupar una eina capaç d'obtenir les mètriques RANO de manera automatitzada de manera que s'obtinguin uns resultats precisos per aportar objectivitat, estandardització i reproductibilitat. Partint de les dades extretes del repositori públic de la Universitat de Califòrnia San Francisco Preoperative Diffuse Glioma MRI i l'eina de segmentació automàtica HD-GLIO, s'ha elaborat un algorisme capaç d'obtenir el diàmetre màxim en el pla axial, així com el seu valor en unitats del sistema mètric decimal i la visualització dels resultats en imatges de RM., Los criterios RANO son el estándar actual para realizar el seguimiento de los pacientes con tumores cerebrales ya que permiten evaluar la evolución del tratamiento mediante la obtención de los diámetros perpendiculares máximos en el plano axial. No obstante, estos criterios presentan cierta ambigüedad inter- e intraoperador a lo hora de sacar conclusiones, que puede dar lugar a errores. Haciendo uso de las nuevas herramientas de segmentación automática de tumores mediante ML e IA, se quiere desarrollar una herramienta capaz de obtener las métricas RANO de forma automatizada de forma que se obtengan unos resultados precisos para aportar objetividad, estandarización y reproducibilidad. Partiendo de los datos extraídos del repositorio público de The University of California San Francisco Preoperative Diffuse Glioma MRI y la herramienta de segmentación automática HD-GLIO, se ha elaborado un algoritmo capaz de obtener el diámetro máximo en el plano axial, así como su valor en unidades del sistema métrico decimal y la visualización de los resultados en imágenes de RM., The RANO criteria are the current standard for monitoring patients with brain tumours as they allow assessment of treatment progress by obtaining the maximum perpendicular diameters in the axial plane. However, these criteria present some inter- and intra-operator ambiguity when drawing conclusions, which can lead to errors. Making use of new tools for automatic tumour segmentation using ML and AI, the aim is to develop a tool capable of obtaining RANO metrics in an automated way in order to obtain accurate results that provide objectivity, standardisation and reproducibility. Based on data extracted from the public repository of The University of California San Francisco Preoperative Diffuse Glioma MRI and the HD-GLIO automatic segmentation tool, an algorithm has been developed capable of obtaining the maximum diameter in the axial plane, as well as its value in units of the decimal metric system and the visualisation of the results in MR images.

Quan es tracta d'esports de motor, la traçada és un factor molt important en el temps per volta. L'objectiu d'aquest projecte consisteix en determinar la trajectòria a seguir al llarg d'un circuit i la velocitat a la qual recórrer-la per un Formula Student autònom. Per fer-ho, es presenten dos algoritmes amb característiques diferents en funció del temps de còmput disponible els quals milloren el temps per volta que s'obtindria al traçar pel centre de la pista. És habitual, a l'hora de dissenyar traçades, utilitzar constructes geomètrics com la curvatura o la longitud si bé la definició d'aquesta depèn només d'una altra magnitud: el temps. En el present treball es proposa optimitzar directament aquesta mètrica, i es demostra que és possible de fer-ho mitjançant algoritmes evolutius obtenint millores significatives respecte al plantejament purament geomètric. A més, s'utilitza una eina de generació aleatòria de circuits per tal de poder avaluar estadísticament els algoritmes presentats així com d'altres d'articles d'índole similar. Aquesta comparativa no només es duu a terme teòricament, sinó que s'utilitza una simulació del vehicle per comprovar la factibilitat de les trajectòries obtingudes. Als resultats es pot observar com la tècnica proposada presenta avantatges a l'hora d'obtenir el comportament desitjat així com també un millor temps per volta, és a dir, una millor traçada., When it comes to motorsports, the racing line is a crucial factor in lap time. The goal of this project is to determine the trajectory to be followed along a circuit and the velocity at which to travel it for an autonomous Formula Student vehicle. To do so, two algorithms with different characteristics based on the available computing time are presented, which improve the lap time that would be obtained by tracing the center of the track. When designing racing lines, it is common to use geometric constructs such as curvature or length, although the definition of the optimal path comes down to only one other magnitude: time. This project proposes directly optimizing this metric and demonstrates that it is indeed possible to do so using evolutionary algorithms, obtaining significant improvements over purely geometric approaches. In addition, a tool for random circuit generation is used to statistically evaluate the algorithms presented as well as other similar articles. This comparison is not only carried out theoretically but also uses a vehicle simulation to verify the feasibility of the obtained trajectories. The results show that the proposed technique has advantages in achieving the desired behavior as well as a better lap time, that is, a better racing line.

Metabolomics, which is defined as the comprehensive analysis of metabolites in a biological system, has lots of applications that are leading to an important step forward in medicine. Since it is still an emerging field, researchers are trying to create computational tools that improve the processing, analysis and interpretation of metabolomics data. In this project, we have developed a new library in R based on MAIT (Metabolite Automatic Identification Toolkit) R package. Our algorithm provides a set of state-of-the-art tools to perform the whole metabolomics workflow, from raw liquid-chromatography coupled to mass spectrometry (LC-MS) data to the biological interpretation.

This thesis is focused on the analysis of the results of the paper KÖHLER, Sebastian, et al. Clinical diagnostics in human genetics with semantic similarity searches in ontologies(1) and the improvement of them. The method studied uses symptoms from the "Human Phenotype Ontology" 2022 (HPO) (2) and tries to predict the disease using another database from the same website (3). This comparison is performed using semantic similarity methods that will be explained in the next chapters. While trying to reproduce the results, many difficulties were found to reach that goal. After many auditions of the code that run the simulation, the performance was not close to that shown in the paper. However, an implementation of this method is already available online by the own authors of the article. This is called the Phenomizer. After generating hundreds of simulated patients following the rules specified in the paper, and using this data in the Phenomizer, one conclusion can be extracted from it, the results are not consistent with the data specified in the article. When imprecision is added to the symptoms (randomly replacing a symptom by one of their ancestors), performance is much worse than stated. On the other hand, adding noise (symptoms unrelated to the disease) has little effect on the output and the performance is coherent with the paper. To try to improve the performance, some other semantic similarity methods were tested using a specialized library called Semantic Measures Library and Toolkit (3). No significant improvements were detected in this investigation, the method used in the article was the best in terms of results quality. The last important point that is clashing with the article is the fact that they use a p-value calculated from the semantic similarity score to obtain the rankings of more probable diseases for the given set of symptoms. According to the paper, the p-value method is better than using simply the similarity scores. However, in all the tests

Type 2 diabetes mellitus (T2DM) is a highly heterogeneous chronic disease with different pathophysiological and genetic characteristics affecting its progression, associated complications and response to therapies. The advances in deep learning (DL) techniques and the availability of a large amount of healthcare data allow us to investigate T2DM characteristics and evolution with a completely new approach, studying common disease trajectories rather than cross sectional values. We used an Kernelized-AutoEncoder algorithm to map 5 years of data of 11,028 subjects diagnosed with T2DM in a latent space that embedded similarities and differences between patients in terms of the evolution of the disease. Once we obtained the latent space, we used classical clustering algorithms to create longitudinal clusters representing different evolutions of the diabetic disease. Our unsupervised DL clustering algorithm suggested seven different longitudinal clusters. Different mean ages were observed among the clusters (ranging from 65.3±11.6 to 72.8±9.4). Subjects in clusters B (Hypercholesteraemic) and E (Hypertensive) had shorter diabetes duration (9.2±3.9 and 9.5±3.9 years respectively). Subjects in Cluster G (Metabolic) had the poorest glycaemic control (mean glycated hemoglobin 7.99±1.42%), while cluster E had the best one (mean glycated hemoglobin 7.04±1.11%). Obesity was observed mainly in clusters A (Neuropathic), C (Multiple Complications), F (Retinopathy) and G. A dashboard is available at dm2.b2slab.upc.edu to visualize the different trajectories corresponding to the 7 clusters., This work was supported by the Spanish Ministry of Economy and Competitiveness (www.mineco.gob.es) TEC2014-60337-R, DPI2017-89827-R, Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), Spain , initiatives of Instituto de Investigación Carlos III (ISCIII), and Share4Rare project (Grant Agreement 780262). This study was possible thanks to the commitment of physicians and nurses working in the Catalan Health Institute to provide optimal care to patients with diabetes. CIBER of Diabetes and Associated Metabolic Diseases (CIBERDEM) is an initiative from Instituto de Salud Carlos III, Madrid, Spain. This analysis is part of the DiaCare Project of Novo Nordisk and the Fundació TicSalut (Departament de Salut, Generalitat de Catalunya), in collaboration with Grupo Pulso, for the benefit of people with type 2 diabetes., Peer Reviewed, Postprint (published version)

This master thesis has two aims. The first main objective is to study and obtain robust voxel-wise (3D) radiomic features for lung cancer and with them compute the habitats (unsupervised clusters) to unravel tumor heterogeneity and facilitate a personalized treatment for each patient and to see the progression of the disease over time.The goal is to obtain robust radiomic features that can be generalized to every database with lung cancer data. The second main objective is to develop a CT-radiomic signature (i.e., imaging phenotype) that will predict the tumor immune profile obtained from the RNA analysis of biopsied sample and allow to identify patients with lung cancer who will respond to immunotherapy.

Supplementary material related to this article can be found online at https://doi.org/10.1016/j.eswa.2022.117446., In the medical domain there exists a terminological gap between patients and caregivers and the healthcare professionals. This gap may hinder the success of the communication between healthcare consumers and professionals in the field, with negative emotional and clinical consequences. In this work, we build a machine learning-based tool for the automatic translation between the terminology used by laypeople and that of the Human Phenotype Ontology (HPO). HPO is a structured vocabulary of phenotypic abnormalities found in human disease. Our method uses a vector space to represent an HPO-specific embedding as the output space for a neural network model trained on vector representations of layperson versions and other textual descriptors of medical terms. We explored different output embeddings coupled to different neural network architectures for the machine translation stage. We compute a similarity measure to evaluate the ability of the model to assign an HPO term to a layperson input. The best-performing models resulted with a similarity higher than 0.7 for more than 80% of the terms, with a median between 0.98 and 1. The translator model is made available in a web application at this link: https://hpotranslator.b2slab.upc.edu., This work was supported by the Spanish Ministry of Economy and Competitiveness (www.mineco.gob.es) TEC2014-60337-R, DPI2017-89827-R, Networking Biomedical Research Centre in the subject area of Bioengineering, Biomaterials and Nanomedicine (CIBER-BBN), initiatives of Instituto de Investigación Carlos III (ISCIII), and Share4Rare project (Grant Agreement 780262). This work was partially funded by ACCIÓ (Innotec ACE014/20/000018). B2SLab is certified as 2017 SGR 952. The authors thank the NVIDIA Corporation for the donation of a Titan Xp GPU used to run the models presented in this article. J. Fonollosa acknowledges the support from the Serra Húnter program., Peer Reviewed, Postprint (published version)

Over recent years hate speech has rapidly spread over the internet, concretely this work centered on Hateful Memes dataset, a problem that requires both visual and linguistic understanding of the meme to classify it correctly. In order to detect hate speech easily, AI can help. This work has presented a method that can help with it. The approach consists of an architecture that starts in-painting the memes from text, then extracting relevant features (including race), and finally training two models based on transformers (BERT and ERNIE-VIl) in order to ensemble it and get the hatefulness of the meme. At the end of the work, the results are analyzed in order to help the community that deals with similar multimodal problems

Early in the COVID-19 pandemic, the Diamond Princess became the center of the largest outbreak outside the original epicenter in China. This outbreak which left 712 passengers infected and 14 dead, followed by subsequent outbreaks affecting over one-third of the active ships in the cruise industry's global fleet, quickly became a crisis that captured public attention and dominated mainstream news and social media. This study investigates the perception of cruising during these outbreaks by analyzing the tweets on cruising using Natural Language Processing (NLP). The findings show a prevalent negative sentiment in most of the analyzed tweets, while the criticisms directed at the cruise industry were based on perceptions and stereotypes of the industry before the pandemic. The study provides insight into the concerns raised in these conversations and highlights the need for new business models outside the pre-pandemic mass-market model and to genuinely make cruising more environmentally friendly., Peer Reviewed, Postprint (published version)

Background: During the COVID-19 pandemic, lockdown strategies have been widely used to contain SARS-CoV-2 virus spread. Children and adolescents are especially vulnerable to suffering psychological effects as result of such measures. In Spain, children were enforced to a strict home lockdown for 42 days during the first wave. Here, we studied the effects of lockdown in children and adolescents through an online questionnaire. Methods: A cross-sectional study was conducted in Spain using an open online survey from July (after the lockdown resulting from the first pandemic wave) to November 2020 (second wave). We included families with children under 16 years-old living in Spain. Parents answered a survey regarding the lockdown effects on their children and were instructed to invite their children from 7 to 16 years-old (mandatory scholar age in Spain) to respond a specific set of questions. Answers were collected through an application programming interface system, and data analysis was performed using R. Results: We included 1,957 families who completed the questionnaires, covering a total of 3,347 children. The specific children’s questionnaire was completed by 167 kids (7–11 years-old), and 100 adolescents (12–16 years-old). Children, in general, showed high resilience and capability to adapt to new situations. Sleeping problems were reported in more than half of the children (54%) and adolescents (59%), and these were strongly associated with less time doing sports and spending more than 5 h per day using electronic devices. Parents perceived their children to gain weight (41%), be more irritable and anxious (63%) and sadder (46%). Parents and children differed significantly when evaluating children’s sleeping disturbances. Conclusions: Enforced lockdown measures and isolation can have a negative impact on children and adolescent’s mental health and well-being. In future waves of the current pandemic, or in the light of potential epidemics of new emerging infecti, Peer Reviewed, Postprint (published version)

With the growth of digital education, students increasingly interact in a variety of ways. The potential effects of these interactions on their learning process are not fully understood and the outcomes may depend on the tool used. This study explores the communication patterns and learning effectiveness developed by students using two basic synchronous and asynchronous communication tools in e-learning environments, specifically business simulation games., Peer Reviewed, Postprint (author's final draft)

This work presents a dual approach to object recognition: 2D computer vision on images on the one hand, and 3D point cloud processing on the other. The recognition of objects has been applied to a synthetic “supermarket” shelf (called testbench) with household items, carefully chosen so that they have simple geometry and texture information for the algorithms to use. Specifically, the objects to detect are Pepsi and Coca-Cola cans, Milk bricks and a detergent bottle. After tackling both approaches a combined 2D and 3D approach is performed. Regarding the 2D object detection part this work takes a very pragmatic approach. First it tackles the issue of the tooling behind creating and curating image datasets, which is an overlooked aspect in many works. It does so by creating a Graphical User Interface with advanced functionality. Then, it starts off the with the simplest detection methods, like Template Matching, all the way to Convolutional Neural Networks, assessing the results of each and their tradeoffs. Regarding the 3D object recognition many vital aspects of point cloud processing are treated first, mainly filtering and compositions of clouds. Then, object recognition itself is addressed, and its limitations are explained. Finally, the 2D and 3D approaches are combined in a modular manner that is quite uncommon in the literature, so as to leverage the strengths and weaknesses of each method, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura

El Centro de Investigación en Ingeniería Biomédica (CREB) de la Universidad Politécnica de Cataluña (UPC) ha creado una red de I+D+i en tecnologías de la salud denominado XarTEC Salut. Entre sus iniciativas, destaca la idea de crear una incubadora común desde Barcelona de tecnologías innovadoras del sector de la salud creadas en países mediterráneos. En este trabajo, se seleccionan 5 países del arco mediterráneo que no pertenecen a Europa con el objetivo de estudiar una posible vía expansión de la incubadora. Estos países seleccionados pertenecen a la región MENA (Middle East and North Africa), y son los siguientes: Argelia, Líbano, Túnez, Egipto y Marruecos El Centro de Investigación en Ingeniería Biomédica (CREB) de la Universidad Politécnica de Cataluña (UPC) ha creado una red de I+D+i en tecnologías de la salud denominado XarTEC Salut. Entre sus iniciativas, destaca la idea de crear una incubadora común desde Barcelona de tecnologías innovadoras del sector de la salud creadas en países mediterráneos. En este trabajo, se seleccionan 5 países del arco mediterráneo que no pertenecen a Europa con el objetivo de estudiar una posible vía expansión de la incubadora. Estos países seleccionados pertenecen a la región MENA (Middle East and North Africa), y son los siguientes: Argelia, Líbano, Túnez, Egipto y Marruecos Primero de todo, se realiza un estudio general económico y social de los países seleccionados. Para ello, se presentan sus principales indicadores macroeconómicos, su clasificación según el Índice de Democracia Global, su clasificación según el Índice de Desarrollo Humano y su clasificación según el Índice de Competitividad Global. Además, se muestran algunos rankings de interés científico, económico y social, que pueden ayudar al lector a acabar de entender el panorama actual en dichos países. Posteriormente, se realiza un mapeo exhaustivo de las principales universidades, hospitales y centros de investigación de cada país. Unas largas listas de institucion, Objectius de Desenvolupament Sostenible::8 - Treball Decent i Creixement Econòmic::8.3 - Promoure polítiques orientades al desenvolupament que donin suport a les activitats productives, la creació d’ocupació digna, l’emprenedoria, la creativitat i la innovació, i encoratjar la regularització i el creixement de les microempreses i les petites i mitjanes empreses, a través, entre d’altres, de l’accés a serveis financers, Objectius de Desenvolupament Sostenible::9 - Indústria, Innovació i Infraestructura

Untargeted metabolomics using liquid chromatography coupled to mass spectrometry (LC–MS) allows the detection of thousands of metabolites in biological samples. However, LC–MS data annotation is still considered a major bottleneck in the metabolomics pipeline since only a small fraction of the metabolites present in the sample can be annotated with the required confidence level. Here, we introduce mWISE (metabolomics wise inference of speck entities), an R package for context-based annotation of LC–MS data. The algorithm consists of three main steps aimed at (i) matching mass-to-charge ratio values to the Kyoto Encyclopedia of Genes and Genomes (KEGG) database, (ii) clustering and filtering the potential KEGG candidates, and (iii) building a final prioritized list using diffusion in graphs. The algorithm performance is evaluated with three publicly available studies using both positive and negative ionization modes. We have also compared mWISE to other available annotation algorithms in terms of their performance and computation time. In particular, we explored four different configurations for mWISE, and all four of them outperform xMSannotator (a state-of-the-art annotator) in terms of both performance and computation time. Using a diffusion configuration that combines the biological network obtained from the FELLA R package and raw scores, mWISE shows a sensitivity mean (standard deviation) across data sets of 0.63 (0.07), while xMSannotator achieves a sensitivity of 0.55 (0.19). We have also shown that the chemical structures of the compounds proposed by mWISE are closer to the original compounds than those proposed by xMSannotator. Finally, we explore the diffusion prioritization separately, showing its key role in the annotation process. mWISE is freely available on GitHub (https://github.com/b2slab/mWISE) under a GPL license., Peer Reviewed, Postprint (author's final draft)

Background: Rare disease communities are spread around the globe and segmented by their condition. Little research has been performed on the majority of rare diseases. Most patients who are affected by a rare disease have no research on their condition because of a lack of knowledge due to absence of common groups in the research community. // Objective: We aimed to develop a safe and secure community of rare disease patients, without geographic or language barriers, to promote research. Methods: Cocreation design methodology was applied to build Share4Rare, with consultation and input through workshops from a variety of stakeholders (patients, caregivers, clinicians, and researchers). // Results: The workshops allowed us to develop a layered version of the platform based on educating patients and caregivers with publicly accessible information, a secure community for the patients and caregivers, and a research section with the purpose of collecting patient information for analysis, which was the core and final value of the platform. // Conclusions: Rare disease research requires global collaboration in which patients and caregivers have key roles. Collective intelligence methods implemented in digital platforms reduce geographic and language boundaries and involve patients in a unique and universal project. Their contributions are essential to increase the amount of scientific knowledge that experts have on rare diseases. Share4Rare has been designed as a global platform to facilitate the donation of clinical information to foster research that matters to patients with rare conditions. The codesign methods with patients have been essential to create a patient-centric design., This work has been funded by the European Research Council under the European Union Horizon 2020 research and innovation program (grant agreement number H2020-780262-SHARE4RARE). BN acknowledges the support from Sant Joan de Déu Barcelona Children’s Hospital., Peer Reviewed, Postprint (published version)

In silico analysis of biological activity data has become an essential technique in pharmaceutical development. Specifically, the so-called proteochemometric models aim to share information between targets in machine learning ligand–target activity prediction models. However, bioactivity data sets used in proteochemometric modeling are usually imbalanced, which could potentially affect the performance of the models. In this work, we explored the effect of different balancing strategies in deep learning proteochemometric target–compound activity classification models while controlling for the compound series bias through clustering. These strategies were (1) no_resampling, (2) resampling_after_clustering, (3) resampling_before_clustering, and (4) semi_resampling. These schemas were evaluated in kinases, GPCRs, nuclear receptors, and proteases from BindingDB. We observed that the predicted proportion of positives was driven by the actual data balance in the test set. Additionally, it was confirmed that data balance had an impact on the performance estimates of the proteochemometric model. We recommend a combination of data augmentation and clustering in the training set (semi_resampling) to mitigate the data imbalance effect in a realistic scenario. The code of this analysis is publicly available at https://github.com/b2slab/imbalance_pcm_benchmark., Peer Reviewed, Postprint (published version)