Evolution of the Quorum network and the mobilome (plasmids and bacteriophages) in clinical strains of Acinetobacter baumannii during a decade.

In this study, we compared eighteen clinical strains of A. baumannii belonging to the ST-2 clone and isolated from patients in the same intensive care unit (ICU) in 2000 (9 strains referred to collectively as Ab_GEIH-2000) and 2010 (9 strains referred to collectively as Ab_GEIH-2010), during the GEIH-REIPI project (Umbrella BioProject PRJNA422585). We observed two main molecular differences between the Ab_GEIH-2010 and the Ab_GEIH-2000 collections, acquired over the course of the decade long sampling interval and involving the mobilome: i) a plasmid harbouring genes for blaOXA 24/40 ß-lactamase and abKA/abkB proteins of a toxin-antitoxin system; and ii) two temperate bacteriophages, Ab105-1ϕ (63 proteins) and Ab105-2ϕ (93 proteins), containing important viral defence proteins. Moreover, all Ab_GEIH-2010 strains contained a Quorum functional network of Quorum Sensing (QS) and Quorum Quenching (QQ) mechanisms, including a new QQ enzyme, AidA, which acts as a bacterial defence mechanism against the exogenous 3-oxo-C12-HSL. Interestingly, the infective capacity of the bacteriophages isolated in this study (Ab105-1ϕ and Ab105-2ϕ) was higher in the Ab_GEIH-2010 strains (carrying a functional Quorum network) than in the Ab_GEIH-2000 strains (carrying a deficient Quorum network), in which the bacteriophages showed little or no infectivity. This is the first study about the evolution of the Quorum network and the mobilome in clinical strains of Acinetobacter baumannii during a decade.

Genomic Evolution of Two Acinetobacter baumannii Clinical Strains from ST-2 Clones Isolated in 2000 and 2010 (ST-2_clon_2000 and ST-2_clon_2010).

Acinetobacter baumannii is a successful nosocomial pathogen due to its ability to persist in hospital environments by acquiring mobile elements such as transposons, plasmids, and phages. In this study, we compared two genomes of A. baumannii clinical strains isolated in 2000 (ST-2_clon_2000) and 2010 (ST-2_clon_2010) from GenBank project PRJNA308422.

Using machine learning techniques and genomic/proteomic information from known databases for defining relevant features for PPI classification.

In modern proteomics, prediction of protein-protein interactions (PPIs) is a key research line, as these interactions take part in most essential biological processes. In this paper, a new approach is proposed to PPI data classification based on the extraction of genomic and proteomic information from well-known databases and the incorporation of semantic measures. This approach is carried out through the application of data mining techniques and provides very accurate models with high levels of sensitivity and specificity in the classification of PPIs. The well-known support vector machine paradigm is used to learn the models, which will also return a new confidence score which may help expert researchers to filter out and validate new external PPIs. One of the most-widely analyzed organisms, yeast, will be studied. We processed a very high-confidence dataset by extracting up to 26 specific features obtained from the chosen databases, half of them calculated using two new similarity measures proposed in this paper. Then, by applying a filter-wrapper algorithm for feature selection, we obtained a final set composed of the eight most relevant features for predicting PPIs, which was validated by a ROC analysis. The prediction capability of the support vector machine model using these eight features was tested through the evaluation of the predictions obtained in a set of external experimental, computational, and literature-collected datasets.

Generating balanced learning and test sets for function approximation problems.

In function approximation problems, one of the most common ways to evaluate a learning algorithm consists in partitioning the original data set (input/output data) into two sets: learning, used for building models, and test, applied for genuine out-of-sample evaluation. When the partition into learning and test sets does not take into account the variability and geometry of the original data, it might lead to non-balanced and unrepresentative learning and test sets and, thus, to wrong conclusions in the accuracy of the learning algorithm. How the partitioning is made is therefore a key issue and becomes more important when the data set is small due to the need of reducing the pessimistic effects caused by the removal of instances from the original data set. Thus, in this work, we propose a deterministic data mining approach for a distribution of a data set (input/output data) into two representative and balanced sets of roughly equal size taking the variability of the data set into consideration with the purpose of allowing both a fair evaluation of learning's accuracy and to make reproducible machine learning experiments usually based on random distributions. The sets are generated using a combination of a clustering procedure, especially suited for function approximation problems, and a distribution algorithm which distributes the data set into two sets within each cluster based on a nearest-neighbor approach. In the experiments section, the performance of the proposed methodology is reported in a variety of situations through an ANOVA-based statistical study of the results.