Maria Eduarda Almeida

Abstract
Early detection of gastrointestinal lesions such as intestinal metaplasia (IM), dysplasia, and polyps remains challenging due to their subtle appearance and the scarcity of well-annotated medical image datasets. To address this limitation, we introduce Cut Instance Mixing (CIM), a domain-specific data augmentation method designed to generate anatomically plausible lesion-containing images through the identification of biologically relevant regions of interest and seamless lesion blending using Poisson image editing and gradient-based mixing. CIM was evaluated across three distinct endoscopic datasets (IM, dysplasia, and polyps) using a ResNet50 classifier and five-fold cross-validation. The proposed method consistently outperformed state-of-the-art augmentation techniques. In IM classification, CIM with alpha = 0.8 achieved the highest performance (AUC: 0.879, Accuracy: 0.823), surpassing MixUp, CutMix and random copy-paste. In dysplasia detection, CIM reached near-perfect results (AUC: 0.997, Accuracy: 0.966), and demonstrated strong generalization on an external polyp dataset (AUC: 0.830, Accuracy: 0.769). Grad-CAM analyses further confirmed that CIM preserves clinically relevant features, improving model attention on lesion regions. These findings demonstrate that CIM enables the generation of realistic and biologically coherent synthetic samples, effectively mitigating data imbalance and enhancing classification robustness. The method is architecture-agnostic and broadly applicable to tasks requiring anatomically consistent augmentation, providing a promising direction for improving deep learning systems in gastrointestinal imaging.

Abstract
Extreme hypersaline environments harbour a unique biodiversity capable of surviving in such habitats, including halophilic and halotolerant bacteria. Microbial adaptations to these environments comprehend two main strategies: the salt-in that involves a high intracellular concentration of salts (e.g., potassium), and the salt-out that relies on the accumulation of small organic compounds (e.g., glycine betaine and trehalose). These evolutionary haloadaptations, combined with natural population competitiveness, often promotes the production of distinctive antimicrobial compounds, highlighting hypersaline environments as promising rich sources of novel natural products with biotechnological potential. Aiming at enlarging the knowledge on the microbiota of two Portuguese salterns (Aveiro and Olh & atilde;o), microbial isolation was performed using salt and saline sediment samples. A total of 39 microbial isolates were obtained in a saline medium, affiliated with Bacillota, Pseudomonadota, Actinomycetota, and Rhodothermaeota and the archaeal phylum Euryarchaeota. All isolates are generally common in saline habitats, with most (79%) exhibiting a halotolerant profile. Regarding the presence of biosynthetic related genes, 28% of the isolates lacked type I genes for polyketide synthases or non-ribosomal peptide synthetases, 36% contained at least one of these genes, and 36% possessed both. This study provides evidence of the biotechnological potential of the microbiota from two Portuguese salterns.

Abstract
Background The Endoscopic Grading of Gastric Intestinal Metaplasia (EGGIM) classification correlates with histological assessment of gastric intestinal metaplasia and enables stratification of gastric cancer risk. We developed and evaluated an artificial intelligence (AI) approach for EGGIM estimation. Methods Two datasets (A and B) with 1280 narrow-band imaging images were used for per-image analysis. Still images with manually selected patches of 224 x 224 pixels, annotated by experts, were used. Dataset A was retrospectively collected from clinical routine; Dataset B (used for per-patient analysis) was prospectively collected and included 65 fully documented patients. To mimic clinical practice, a deep neural network classified image patches into three EGGIM classes (0, 1, 2) and calculated the total per-patient EGGIM score (0-10). Results On per-image analysis, an accuracy of 87% (95%CI 71%-100%) was obtained. Per-patient EGGIM estimation had an average error of 1.15 (out of 10) and showed 88% (95%CI 80%-96%) accurate clinical decisions for surveillance (EGGIM >= 5), with 85% (95%CI 75%-94%) specificity, no false negatives, and positive and negative predictive values of 62% (95%CI 32%-92%) and 100% (95%CI 100%-100%), respectively. Conclusions EGGIM was estimated with high accuracy using AI tools in endoscopic image analyses. Automated assessment of EGGIM may provide a greener strategy for gastric cancer risk stratification, prospective studies, and interventional trials.

Abstract
The deep-sea covers over 70% of the Earth’s surface and harbors predominantly uncharacterized bacterial communities. Actinobacteria are the major prokaryotic source of bioactive natural products that find their way into drug discovery programs, and the deep-sea is a promising source of biotechnologically relevant actinobacteria. Previous studies on actinobacteria in deep-sea sediments were either regionally restricted or did not combine a community characterization with the analysis of their bioactive potential. Here we characterized the actinobacterial communities of upper layers of deep-sea sediments from the Arctic and the Atlantic (Azores and Madeira) ocean basins, employing 16S rRNA metabarcoding, and studied the biosynthetic potential of cultivable actinobacteria retrieved from those samples. Metabarcoding analysis showed that the actinobacterial composition varied between the sampled regions, with higher abundance in the Arctic samples but higher diversity in the Atlantic ones. Twenty actinobacterial genera were detected using metabarcoding, as a culture-independent method, while culture-dependent methods only allowed the identification of nine genera. Isolation of actinobacteria resulted on the retrieval of 44 isolates, mainly associated with Brachybacterium, Microbacterium, and Brevibacterium genera. Some of these isolates were only identified on a specific sampled region. Chemical extracts of the actinobacterial isolates were subsequently screened for their antimicrobial, anticancer and anti-inflammatory activities. Extracts from two Streptomyces strains demonstrated activity against Candida albicans. Additionally, eight extracts (obtained from Brachybacterium, Brevibacterium, Microbacterium, Rhodococcus, and Streptomyces isolates) showed significant activity against at least one of the tested cancer cell lines (HepG2 and T-47D). Furthermore, 15 actinobacterial extracts showed anti-inflammatory potential in the RAW 264.4 cell model assay, with no concomitant cytotoxic response. Dereplication and molecular networking analysis of the bioactive actinobacterial extracts showed the presence of some metabolites associated with known natural products, but one of the analyzed clusters did not show any match with the natural products described as responsible for these bioactivities. Overall, we were able to recover taxonomically diverse actinobacteria with different bioactivities from the studied deep-sea samples. The conjugation of culture-dependent and -independent methods allows a better understanding of the actinobacterial diversity of deep-sea environments, which is important for the optimization of approaches to obtain novel chemically-rich isolates. Copyright © 2023 Ribeiro, Antunes, Alexandrino, Tomasino, Almeida, Hilário, Urbatzka, Leão, Mucha and Carvalho.

Abstract
A bacterial strain was isolated from a brackish water sample of Tagus river, Alcochete, Portugal and was designated TO1_6(T). It forms light pink colonies on M13 medium supplemented with N-acetylglucosamine. Cells are pear-shaped to spherical, form rosettes and divide by budding. Strain TO1_6(T) presents a mesophilic and neutrophilic profile, with optimum growth at 20 to 25 degrees C and pH 7.0 to 7.5, and vitamin supplementation is not required to promote its growth. The genome of the novel isolate is 7.77 Mbp in size and has a DNA G+C content of 56.3%. Based on its 16S rRNA gene sequence, this strain is affiliated with the phylum Planctomycetota. Further taxonomic characterization using additional phylogenetic markers, namely rpoB gene sequence (encoding the beta-subunit of the DNA-dependent RNA polymerase), as well as Percentage of conserved proteins, average nucleotide identity and average amino acid identity, suggest the affiliation of strain TO1_6(T) to the genus Stieleria, a recently described taxon in the family Pirellulaceae, order Pirellulales and class Planctomycetia. Based on the genotypic, phylogenetic and physiological characterization, we here describe a new species represented by the type strain TO1_6(T) (=CECT 30432(T), =LMG 32465(T)), for which the name Stieleria tagensis sp. nov. is proposed.