ChatSubs: A dataset of dialogues in Spanish, Catalan, Basque and Galician extracted from movie subtitles for developing advanced conversational models.

The ChatSubs dataset [5] contains dialogue data in Spanish and three of Spain's co-official languages (Catalan, Basque, and Galician). It has been obtained from OpenSubtitles, from which we have gathered the movie subtitles in our languages of interest and processed them to generate clearly segmented dialogues and their turns. The data processing code is publicly accessible. The result is 206.706 JSON files with more than 20 million dialogues and 96 million turns, which represents one of the biggest dialogue corpus available, as other similar datasets in better resourced languages do not reach 500k dialogues or present less defined conversations. Thus, the ChatSubs dataset is an ideal resource for research teams that are interested in training dialogue models in Spanish, Catalan, Basque, and Galician.

Predicting the evolution of COVID-19 mortality risk: A Recurrent Neural Network approach.

Background: In December 2020, the COVID-19 disease was confirmed in 1,665,775 patients and caused 45,784 deaths in Spain. At that time, health decision support systems were identified as crucial against the pandemic. Methods: This study applies Deep Learning techniques for mortality prediction of COVID-19 patients. Two datasets with clinical information were used. They included 2,307 and 3,870 COVID-19 infected patients admitted to two Spanish hospitals. Firstly, we built a sequence of temporal events gathering all the clinical information for each patient, comparing different data representation methods. Next, we used the sequences to train a Recurrent Neural Network (RNN) model with an attention mechanism exploring interpretability. We conducted an extensive hyperparameter search and cross-validation. Finally, we ensembled the resulting RNNs to enhance sensitivity. Results: We assessed the performance of our models by averaging the performance across all the days in the sequences. Additionally, we evaluated day-by-day predictions starting from both the hospital admission day and the outcome day. We compared our models with two strong baselines, Support Vector Classifier and Random Forest, and in all cases our models were superior. Furthermore, we implemented an ensemble model that substantially increased the system's sensitivity while producing more stable predictions. Conclusions: We have shown the feasibility of our approach to predicting the clinical outcome of patients. The result is an RNN-based model that can support decision-making in healthcare systems aiming at interpretability. The system is robust enough to deal with real-world data and can overcome the problems derived from the sparsity and heterogeneity of data.

First description of a natural infection with spleen and kidney necrosis virus in zebrafish.

Zebrafish has become a popular research model in the last years, and several diseases affecting zebrafish research facilities have been reported. However, only one case of naturally occurring viral infections was described for this species. In 2015, infectious spleen and kidney necrosis virus (ISKNV) was detected in zebrafish from a research facility in Spain. Affected fish showed lethargy, loss of appetite, abnormal swimming, distention of the coelomic cavity and, in the most severe cases, respiratory distress, pale gills and petechial haemorrhages at the base of fins. Cytomegaly was the most relevant histopathological finding in organs and tissues, sometimes associated to degenerative and necrotic changes. ISKNV belongs to the relatively newly defined genus Megalocytivirus, family Iridoviridae, comprising large, icosahedral cytoplasmic DNA viruses. This is the first case of naturally occurring Megalocytivirus infection in zebrafish research facilities, associated with morbidity. The virus has been identified based on both pathologic and genetic evidence, to better understand the pathogenesis of the infection in zebrafish and the phylogenetic relationship with other iridoviruses. Given the ability of megalocytiviruses to cross-species boundaries, it seems necessary to implement stringent biosecurity practices as these infections may invalidate experimental data and have major impact on laboratory and cultured fish.

Dinuclear RuII(bipy)2 Derivatives: Structural, Biological, and in Vivo Zebrafish Toxicity Evaluation.

Ruthenium-based drugs exhibit interesting properties as potential anticancer pharmaceuticals. We herein present the synthesis and characterization of a new family of ruthenium complexes with formulas [{Ru(bipy)2}2(µ-L)][CF3SO3]4 (L = bptz, 1a) and [{Ru(bipy)2}2(µ-L)][CF3SO3]2 (L = arphos, 2a; dppb, 3a; dppf, 4a), which were synthesized from the Ru(II) precursor compound cis-Ru(bipy)2Cl2. The complexes were characterized by elemental analysis, mass spectrometry, 1H and 31P{1H} NMR, IR spectroscopy, and conductivity measurements. The molecular structures for three Ru(II) compounds were determined by single-crystal X-ray diffraction. The newly developed compounds interact with CT-DNA by intercalation, in particular, 2a, 3a, and 4a, which also seemed to induce some extent of DNA degradation. This effect seemed to be related with the formation of reactive oxygen species. The cytotoxic activity was evaluated against A2780, MCF7, and MDAMB231 human tumor cells. Compounds 2a and 4a were the most cytotoxic with activity compared to cisplatin (∼2 µM, 72 h) in the A2780 cisplatin sensitive cells. All the compounds induced A2780 cell death by apoptosis, however, to a lesser extent for compounds 4a and 2a. For these compounds, the mechanism of cell death in addition to apoptosis seemed to involve autophagy. In vivo toxicity was evaluated using the zebrafish embryo model. LC50 estimates varied from 5.397 (3a) to 39.404 (1a) mg/L. Considering the in vivo toxicity in zebrafish embryos and the in vitro cytotoxicity in cancer cells, compound 1a seems to be the safest having no effect on dechirionation and presenting a good antiproliferative activity against ovarian carcinoma cells.