BioDeepfuse: a hybrid deep learning approach with integrated feature extraction techniques for enhanced non-coding RNA classification.

The accurate classification of non-coding RNA (ncRNA) sequences is pivotal for advanced non-coding genome annotation and analysis, a fundamental aspect of genomics that facilitates understanding of ncRNA functions and regulatory mechanisms in various biological processes. While traditional machine learning approaches have been employed for distinguishing ncRNA, these often necessitate extensive feature engineering. Recently, deep learning algorithms have provided advancements in ncRNA classification. This study presents BioDeepFuse, a hybrid deep learning framework integrating convolutional neural networks (CNN) or bidirectional long short-term memory (BiLSTM) networks with handcrafted features for enhanced accuracy. This framework employs a combination of k-mer one-hot, k-mer dictionary, and feature extraction techniques for input representation. Extracted features, when embedded into the deep network, enable optimal utilization of spatial and sequential nuances of ncRNA sequences. Using benchmark datasets and real-world RNA samples from bacterial organisms, we evaluated the performance of BioDeepFuse. Results exhibited high accuracy in ncRNA classification, underscoring the robustness of our tool in addressing complex ncRNA sequence data challenges. The effective melding of CNN or BiLSTM with external features heralds promising directions for future research, particularly in refining ncRNA classifiers and deepening insights into ncRNAs in cellular processes and disease manifestations. In addition to its original application in the context of bacterial organisms, the methodologies and techniques integrated into our framework can potentially render BioDeepFuse effective in various and broader domains.

Information Theory for Biological Sequence Classification: A Novel Feature Extraction Technique Based on Tsallis Entropy.

In recent years, there has been an exponential growth in sequencing projects due to accelerated technological advances, leading to a significant increase in the amount of data and resulting in new challenges for biological sequence analysis. Consequently, the use of techniques capable of analyzing large amounts of data has been explored, such as machine learning (ML) algorithms. ML algorithms are being used to analyze and classify biological sequences, despite the intrinsic difficulty in extracting and finding representative biological sequence methods suitable for them. Thereby, extracting numerical features to represent sequences makes it statistically feasible to use universal concepts from Information Theory, such as Tsallis and Shannon entropy. In this study, we propose a novel Tsallis entropy-based feature extractor to provide useful information to classify biological sequences. To assess its relevance, we prepared five case studies: (1) an analysis of the entropic index q; (2) performance testing of the best entropic indices on new datasets; (3) a comparison made with Shannon entropy and (4) generalized entropies; (5) an investigation of the Tsallis entropy in the context of dimensionality reduction. As a result, our proposal proved to be effective, being superior to Shannon entropy and robust in terms of generalization, and also potentially representative for collecting information in fewer dimensions compared with methods such as Singular Value Decomposition and Uniform Manifold Approximation and Projection.

MarineMetagenomeDB: a public repository for curated and standardized metadata for marine metagenomes.

BACKGROUND: Metagenomics is an expanding field within microbial ecology, microbiology, and related disciplines. The number of metagenomes deposited in major public repositories such as Sequence Read Archive (SRA) and Metagenomic Rapid Annotations using Subsystems Technology (MG-RAST) is rising exponentially. However, data mining and interpretation can be challenging due to mis-annotated and misleading metadata entries. In this study, we describe the Marine Metagenome Metadata Database (MarineMetagenomeDB) to help researchers identify marine metagenomes of interest for re-analysis and meta-analysis. To this end, we have manually curated the associated metadata of several thousands of microbial metagenomes currently deposited at SRA and MG-RAST. RESULTS: In total, 125 terms were curated according to 17 different classes (e.g., biome, material, oceanic zone, geographic feature and oceanographic phenomena). Other standardized features include sample attributes (e.g., salinity, depth), sample location (e.g., latitude, longitude), and sequencing features (e.g., sequencing platform, sequence count). MarineMetagenomeDB version 1.0 contains 11,449 marine metagenomes from SRA and MG-RAST distributed across all oceans and several seas. Most samples were sequenced using Illumina sequencing technology (84.33%). More than 55% of the samples were collected from the Pacific and the Atlantic Oceans. About 40% of the samples had their biomes assigned as 'ocean'. The 'Quick Search' and 'Advanced Search' tabs allow users to use different filters to select samples of interest dynamically in the web app. The interactive map allows the visualization of samples based on their location on the world map. The web app is also equipped with a novel download tool (on both Windows and Linux operating systems), that allows easy download of raw sequence data of selected samples from their respective repositories. As a use case, we demonstrated how to use the MarineMetagenomeDB web app to select estuarine metagenomes for potential large-scale microbial biogeography studies. CONCLUSION: The MarineMetagenomeDB is a powerful resource for non-bioinformaticians to find marine metagenome samples with curated metadata and stimulate meta-studies involving marine microbiomes. Our user-friendly web app is publicly available at https://webapp.ufz.de/marmdb/ .