Upper mesophotic reef fish assemblages at Bahía de Banderas, Mexico

There is no information on the species associated with the mesophotic reefs of Banderas Bay, located in the central Mexican Pacific. This study analysed the reef fish assemblage from three depths (50, 60 and 70 m) in three sampling sites of the southern submarine canyon of the Bay: Los Arcos, Bajo de Emirio and Majahuitas. Several analyses were performed to test the hypothesis that there are important differences in fish abundance and species composition between sites and depths. Twenty-two species of bony fishes grouped in 14 families were recorded. PERMANOVA results showed that there were no significant differences in fish diversity parameters between sites, indicating a certain uniformity in their distribution. However, nine species were exclusive to one site and depth (five singleton species with only one individual recorded and four unique species recorded only once). On the other hand, there were significant differences between depths, mainly between 50 and 70 m. Diversity decreases with depth and species composition changes. SIMPER, Shade Plot and NMDS analysis show the most representative species at each depth, with at least half of the species (11) recorded only at 50 m and four species at the deeper levels (60 - 70 m). The observed assemblage includes several of the most caught species in the shallow water artisanal fishery, which is the most traditional and common type of fishery in the Bay. In addition, the Pomacanthuszonipectus (Cortés angelfish) is of particular interest, as it has a special protection status in the official Mexican standard (NOM-059-SEMARNAT, 2010) due to its use as an ornamental species in aquaria. We hypothesised that the mesophotic zone may serve as a refuge for these fishes, so we propose that the information obtained is an important basis for new research aimed at the sustainable management of fisheries in the area.

Unraveling the Complex Interactions: Machine Learning Approaches to Predict Bacterial Survival against ZnO and Lanthanum-Doped ZnO Nanoparticles

The rise in antibiotic-resistant bacteria is a global health challenge. Due to their unique properties, metal oxide nanoparticles show promise in addressing this issue. However, optimizing these properties requires a deep understanding of complex interactions. This study incorporated data-driven machine learning to predict bacterial survival against lanthanum-doped ZnO nanoparticles. The effect of incorporation of lanthanum ions on ZnO was analyzed. Even with high lanthanum concentration, no significant variations in structural, morphological, and optical properties were observed. The antibacterial activity of La-doped ZnO nanoparticles against Gram-positive and Gram-negative bacteria was qualitatively and quantitatively evaluated. Nanoparticles induce 60%, 95%, and 55% bacterial death against Escherichia coli, Pseudomonas aeruginosa, and Staphylococcus aureus, respectively. Algorithms such as Multilayer Perceptron, K-Nearest Neighbors, Gradient Boosting, and Extremely Random Trees were used to predict the bacterial survival percentage. Extremely Random Trees performed the best among these models with 95.08% accuracy. A feature relevance analysis extracted the most significant attributes to predict the bacterial survival percentage. Lanthanum content and particle size were irrelevant, despite what can be assumed. This approach offers a promising avenue for developing effective and tailored strategies to reduce the time and cost of developing antimicrobial nanoparticles.

Multivariate water quality analysis of Lake Cajititlán, Mexico

Lake Cajititlán is a shallow body of water located in an endorheic basin in western Mexico. This lake receives excess fertilizer runoff from agriculture and approximately 2.3 Hm³ per year of poorly treated wastewater from three municipal treatment plants. Thirteen water quality parameters were monitored at five sampling points within the lake over 9 years. The objective of this work was to characterize the spatial and temporal variations of the water quality and to identify the sources of data variability in order to assess the influence and the impact of different natural and anthropogenic processes. One-way ANOVA tests, principal component analysis (PCA), cluster analysis (CA), and discriminant analysis (DA) were implemented. The one-way ANOVA showed that biochemical oxygen demand and pH present statistically significant spatial variations and that alkalinity, total chloride, conductivity, chemical oxygen demand, total hardness, ammonia, pH, total dissolved solids, and temperature present statistically significant temporal variations. PCA results explained both natural and anthropogenic processes and their relationship with water quality data. The CA results suggested there is no significant spatial variation in the water quality of the lake because of lake mixing caused by wind. The most significant parameters for spatial variations were pH, NO₃^-, and NO₂^-, consistent with the configuration of point and nonpoint sources that affect the lake's water quality. The temporal DA results suggested that conductivity, hardness, NO₂^-, pH, and temperature were the most significant parameters to discriminate between seasons. The temporal behavior of these parameters was associated with the transport pathways of seasonal contaminants.

Discriminant analysis and machine learning approach for evaluating and improving the performance of immunohistochemical algorithms for COO classification of DLBCL

Background

Diffuse large B-cell lymphoma (DLBCL) is classified into germinal center-like (GCB) and non-germinal center-like (non-GCB) cell-of-origin groups, entities driven by different oncogenic pathways with different clinical outcomes. DLBCL classification by immunohistochemistry (IHC)-based decision tree algorithms is a simpler reported technique than gene expression profiling (GEP). There is a significant discrepancy between IHC-decision tree algorithms when they are compared to GEP.

Methods

To address these inconsistencies, we applied the machine learning approach considering the same combinations of antibodies as in IHC-decision tree algorithms. Immunohistochemistry data from a public DLBCL database was used to perform comparisons among IHC-decision tree algorithms, and the machine learning structures based on Bayesian, Bayesian simple, Naïve Bayesian, artificial neural networks, and support vector machine to show the best diagnostic model. We implemented the linear discriminant analysis over the complete database, detecting a higher influence of BCL6 antibody for GCB classification and MUM1 for non-GCB classification.

Results

The classifier with the highest metrics was the four antibody-based Perfecto–Villela (PV) algorithm with 0.94 accuracy, 0.93 specificity, and 0.95 sensitivity, with a perfect agreement with GEP (κ = 0.88, P < 0.001). After training, a sample of 49 Mexican-mestizo DLBCL patient data was classified by COO for the first time in a testing trial.

Conclusions

Harnessing all the available immunohistochemical data without reliance on the order of examination or cut-off value, we conclude that our PV machine learning algorithm outperforms Hans and other IHC-decision tree algorithms currently in use and represents an affordable and time-saving alternative for DLBCL cell-of-origin identification.

Electronic supplementary material

The online version of this article (10.1186/s12967-019-1951-y) contains supplementary material, which is available to authorized users.