Gene networks have become a powerful tool for the comprehensive examination of gene expression patterns. Thanks to these networks generated by means of inference algorithms, it is possible to study different biological processes and even identify new biomarkers for such diseases. These biomarkers are essential for the discovery of new treatments for genetic diseases such as cancer. In this work, we introduce an algorithm for genetic network inference based on an ensemble method that improves the robustness of the results by combining two main steps: first, the evaluation of the relationship between pairs of genes using three different co-expression measures, and, subsequently, a voting strategy. The utility of this approach was demonstrated by applying it to a human dataset encompassing breast and prostate cancer-associated stromal cells. Two gene networks were computed using microarray data, one for breast cancer and one for prostate cancer. The results obtained revealed, on the one hand, distinct stromal cell behaviors in breast and prostate cancer and, on the other hand, a list of potential biomarkers for both diseases. In the case of breast tumor, ST6GAL2, RIPOR3, COL5A1, and DEPDC7 were found, and in the case of prostate tumor, the genes were GATA6-AS1, ARFGEF3, PRR15L, and APBA2. These results demonstrate the usefulness of the ensemble method in the field of biomarker discovery.

The construction of gene co-expression networks is an essential tool in Bioinformatics for discovering useful biological knowledge. There are a multitude of methodologies related to the construction of this type of network, and one of them is EnGNet, which carries out a joint and greedy approach to the reconstruction of large gene coexpression networks. This work introduces CyEnGNet-App, a Cytoscape application designed to integrate and leverage the EnGNet algorithm. The application allows dynamic interaction and visualisation of gene networks and integration with other Cytoscape applications. CyEnGNet-App is a valuable addition to the field of Bioinformatics, improving the reconstruction of genetic networks and providing a more accessible and efficient user experience in Cytoscape.

Nowadays, Biclustering is one of the most widely used machine learning techniques to discover local patterns in datasets from different areas such as energy consumption, marketing, social networks or bioinformatics, among them. Particularly in bioinformatics, Biclustering techniques have become extremely time-consuming, also being huge the number of results generated, due to the continuous increase in the size of the databases over the last few years. For this reason, validation techniques must be adapted to this new environment in order to help researchers focus their efforts on a specific subset of results in an efficient, fast and reliable way. The aforementioned situation may well be considered as Big Data context. In this sense, multiple machine learning techniques have been implemented by the application of Graphic Processing Units (GPU) technology and CUDA architecture to accelerate the processing of large databases. However, as far as we know, this technology has not yet been applied to any bicluster validation technique. In this work, a multi-GPU version of one of the most used bicluster validation measure, Mean Squared Residue (MSR), is presented. It takes advantage of all the hardware and memory resources offered by GPU devices. Because of to this, gMSR is able to validate a massive number of biclusters in any Biclustering-based study within a Big Data context.

Recommender Systems help users in making decision in different fields such as purchases or what movies to watch. User-Based Collaborative Filtering (UBCF) approach is one of the most commonly used techniques for developing these software tools. It is based on the idea that users who have previously shared similar tastes will almost certainly share similar tastes in the future. As a result, determining the nearest users to the one for whom recommendations are sought (active user) is critical. However, the massive growth of online commercial data has made this task especially difficult. As a result, Biclustering techniques have been used in recent years to perform a local search for the nearest users in subgroups of users with similar rating behaviour under a subgroup of items (biclusters), rather than searching the entire rating database. Nevertheless, due to the large size of these databases, the number of biclusters generated can be extremely high, making their processing very complex. In this paper we propose BinRec, a novel UBCF approach based on Biclustering. BinRec simplifies the search for neighbouring users by determining which ones are nearest to the active user based on the number of biclusters shared by the users. Experimental results show that BinRec outperforms other state-of-the-art recommender systems, with a remarkable improvement in environments with high data sparsity. The flexibility and scalability of the method position it as an efficient alternative for common collaborative filtering problems such as sparsity or cold-start.