Abstract
Nearest neighbor search (NNS) is one of the main concerns in data stream applications since similarity queries can be used in multiple scenarios. Online NNS is usually performed on a sliding window by lazily scanning every element currently stored in the window. This paper proposes Sliding Window-based Incremental Nearest Neighbors (SWINN), a graph-based online search index algorithm for speeding up NNS in potentially never-ending and dynamic data stream tasks. Our proposal broadens the application of online NNS-based solutions, as even moderately large data buffers become impractical to handle when a naive NNS strategy is selected. SWINN enables efficient handling of large data buffers by using an incremental strategy to build and update a search graph supporting any distance metric. Vertices can be added and removed from the search graph. To keep the graph reliable for search queries, lightweight graph maintenance routines are run. According to experimental results, SWINN is significantly faster than performing a naive complete scan of the data buffer while keeping competitive search recall values. We also apply SWINN to online classification and regression tasks and show that our proposal is effective against popular online machine learning algorithms.

Abstract
Purpose 2-[F-18]FDG PET/CT plays an important role in the management of pulmonary nodules. Convolutional neural networks (CNNs) automatically learn features from images and have the potential to improve the discrimination between malignant and benign pulmonary nodules. The purpose of this study was to develop and validate a CNN model for classification of pulmonary nodules from 2-[F-18]FDG PET images.Methods One hundred thirteen participants were retrospectively selected. One nodule per participant. The 2-[F-18]FDG PET images were preprocessed and annotated with the reference standard. The deep learning experiment entailed random data splitting in five sets. A test set was held out for evaluation of the final model. Four-fold cross-validation was performed from the remaining sets for training and evaluating a set of candidate models and for selecting the final model. Models of three types of 3D CNNs architectures were trained from random weight initialization (Stacked 3D CNN, VGG-like and Inception-v2-like models) both in original and augmented datasets. Transfer learning, from ImageNet with ResNet-50, was also used.Results The final model (Stacked 3D CNN model) obtained an area under the ROC curve of 0.8385 (95% CI: 0.6455-1.0000) in the test set. The model had a sensibility of 80.00%, a specificity of 69.23% and an accuracy of 73.91%, in the test set, for an optimised decision threshold that assigns a higher cost to false negatives.Conclusion A 3D CNN model was effective at distinguishing benign from malignant pulmonary nodules in 2-[F-18]FDG PET images.

Abstract
We propose a model that forecasts market correlation structure from link- and node-based financial network features using machine learning. For such, market structure is modeled as a dynamic asset network by quantifying time-dependent co-movement of asset price returns across company constituents of major global market indices. We provide empirical evidence using three different network filtering methods to estimate market structure, namely Dynamic Asset Graph, Dynamic Minimal Spanning Tree and Dynamic Threshold Networks. Experimental results show that the proposed model can forecast market structure with high predictive performance with up to 40%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$40\%$$\end{document} improvement over a time-invariant correlation-based benchmark. Non-pair-wise correlation features showed to be important compared to traditionally used pair-wise correlation measures for all markets studied, particularly in the long-term forecasting of stock market structure. Evidence is provided for stock constituents of the DAX30, EUROSTOXX50, FTSE100, HANGSENG50, NASDAQ100 and NIFTY50 market indices. Findings can be useful to improve portfolio selection and risk management methods, which commonly rely on a backward-looking covariance matrix to estimate portfolio risk.

Abstract
MotivationAccurate determination and quantification of the taxonomic composition of microbial communities, especially at the species level, is one of the major issues in metagenomics. This is primarily due to the limitations of commonly used 16S rRNA reference databases, which either contain a lot of redundancy or a high percentage of sequences with missing taxonomic information. This may lead to erroneous identifications and, thus, to inaccurate conclusions regarding the ecological role and importance of those microorganisms in the ecosystem.ResultsThe current study presents MIMt, a new 16S rRNA database for archaea and bacteria's identification, encompassing 47 001 sequences, all precisely identified at species level. In addition, a MIMt2.0 version was created with only curated sequences from RefSeq Targeted loci with 32 086 sequences. MIMt aims to be updated twice a year to include all newly sequenced species. We evaluated MIMt against Greengenes, RDP, GTDB and SILVA in terms of sequence distribution and taxonomic assignments accuracy. Our results showed that MIMt contains less redundancy, and despite being 20 to 500 times smaller than existing databases, outperforms them in completeness and taxonomic accuracy, enabling more precise assignments at lower taxonomic ranks and thus, significantly improving species-level identification.

Abstract
Catharanthus roseus leaves produce a range of monoterpenoid indole alkaloids (MIAs) that include low levels of the anticancer drugs vinblastine and vincristine. The MIA pathway displays a complex architecture spanning different subcellular and cell type localizations, and is under complex regulation. As a result, the development of strategies to increase the levels of the anticancer MIAs has remained elusive. The pathway involves mesophyll specialized idioblasts where the late unsolved biosynthetic steps are thought to occur. Here, protoplasts of C. roseus leaf idioblasts were isolated by fluorescence-activated cell sorting, and their differential alkaloid and transcriptomic profiles were characterized. This involved the assembly of an improved C. roseus transcriptome from short- and long-read data, IDIO+. It was observed that C. roseus mesophyll idioblasts possess a distinctive transcriptomic profile associated with protection against biotic and abiotic stresses, and indicative that this cell type is a carbon sink, in contrast to surrounding mesophyll cells. Moreover, it is shown that idioblasts are a hotspot of alkaloid accumulation, suggesting that their transcriptome may hold the key to the in-depth understanding of the MIA pathway and the success of strategies leading to higher levels of the anticancer drugs. Catharanthus mesophyll idioblasts are a hotspot of alkaloid accumulation. The idioblast transcriptome is associated with stress responses and provides a roadmap towards the increase of anticancer alkaloid levels.

Abstract
Missing data is an issue that can negatively impact any task performed with the available data and it is often found in real -world domains such as healthcare. One of the most common strategies to address this issue is to perform imputation, where the missing values are replaced by estimates. Several approaches based on statistics and machine learning techniques have been proposed for this purpose, including deep learning architectures such as generative adversarial networks and autoencoders. In this work, we propose a novel siamese neural network suitable for missing data imputation, which we call Siamese Autoencoder-based Approach for Imputation (SAEI). Besides having a deep autoencoder architecture, SAEI also has a custom loss function and triplet mining strategy that are tailored for the missing data issue. The proposed SAEI approach is compared to seven state-of-the-art imputation methods in an experimental setup that comprises 14 heterogeneous datasets of the healthcare domain injected with Missing Not At Random values at a rate between 10% and 60%. The results show that SAEI significantly outperforms all the remaining imputation methods for all experimented settings, achieving an average improvement of 35%. This work is an extension of the article Siamese Autoencoder-Based Approach for Missing Data Imputation [1] presented at the International Conference on Computational Science 2023. It includes new experiments focused on runtime, generalization capabilities, and the impact of the imputation in classification tasks, where the results show that SAEI is the imputation method that induces the best classification results, improving the F1 scores for 50% of the used datasets.