Motivation: We previously proposed a paradigm shift in genomic data management, based on the Genomic Data Model (GDM) for mediating existing data formats and on the GenoMetric Query Language (GMQL) for supporting, at a high level of abstraction, data extraction and the most common data-driven computations required by tertiary data analysis of Next Generation Sequencing datasets. Here, we present a new GMQL-based system with enhanced accessibility, portability, scalability and performance. Results: The new system has a well-designed modular architecture featuring: (i) an intermediate representation supporting many different implementations (including Spark, Flink and SciDB); (ii) a high-level technology-independent repository abstraction, supporting different repository technologies (e.g., local file system, Hadoop File System, database or others); (iii) several system interfaces, including a user-friendly Web-based interface, a Web Service interface, and a programmatic interface for Python language. Biological use case examples, using public ENCODE, Roadmap Epigenomics and TCGA datasets, demonstrate the relevance of our work. Availability and implementation: The GMQL system is freely available for non-commercial use as open source project at: http://www.bioinformatics.deib.polimi.it/GMQLsystem/. Supplementary information: Supplementary data are available at Bioinformatics online.

ViruSurf, available at http://gmql.eu/virusurf/, is a large public database of viral sequences and integrated and curated metadata from heterogeneous sources (RefSeq, GenBank, COG-UK and NMDC); it also exposes computed nucleotide and amino acid variants, called from original sequences. A GISAID-specific ViruSurf database, available at http://gmql.eu/virusurf_gisaid/, offers a subset of these functionalities. Given the current pandemic outbreak, SARS-CoV-2 data are collected from the four sources; but ViruSurf contains other virus species harmful to humans, including SARS-CoV, MERS-CoV, Ebola and Dengue. The database is centered on sequences, described from their biological, technological and organizational dimensions. In addition, the analytical dimension characterizes the sequence in terms of its annotations and variants. The web interface enables expressing complex search queries in a simple way; arbitrary search queries can freely combine conditions on attributes from the four dimensions, extracting the resulting sequences. Several example queries on the database confirm and possibly improve results from recent research papers; results can be recomputed over time and upon selected populations. Effective search over large and curated sequence data may enable faster responses to future threats that could arise from new viruses.

Many valuable resources developed by world-wide research institutions and consortia describe genomic datasets that are both open and available for secondary research, but their metadata search interfaces are heterogeneous, not interoperable and sometimes with very limited capabilities. We implemented GenoSurf, a multi-ontology semantic search system providing access to a consolidated collection of metadata attributes found in the most relevant genomic datasets; values of 10 attributes are semantically enriched by making use of the most suited available ontologies. The user of GenoSurf provides as input the search terms, sets the desired level of ontological enrichment and obtains as output the identity of matching data files at the various sources. Search is facilitated by drop-down lists of matching values; aggregate counts describing resulting files are updated in real time while the search terms are progressively added. In addition to the consolidated attributes, users can perform keyword-based searches on the original (raw) metadata, which are also imported; GenoSurf supports the interplay of attribute-based and keyword-based search through well-defined interfaces. Currently, GenoSurf integrates about 40 million metadata of several major valuable data sources, including three providers of clinical and experimental data (TCGA, ENCODE and Roadmap Epigenomics) and two sources of annotation data (GENCODE and RefSeq); it can be used as a standalone resource for targeting the genomic datasets at their original sources (identified with their accession IDs and URLs), or as part of an integrated query answering system for performing complex queries over genomic regions and metadata.

Thousands of new experimental datasets are becoming available every day; in many cases, they are produced within the scope of large cooperative efforts, involving a variety of laboratories spread all over the world, and typically open for public use. Although the potential collective amount of available information is huge, the effective combination of such public sources is hindered by data heterogeneity, as the datasets exhibit a wide variety of notations and formats, concerning both experimental values and metadata. Thus, data integration is becoming a fundamental activity, to be performed prior to data analysis and biological knowledge discovery, consisting of subsequent steps of data extraction, normalization, matching and enrichment; once applied to heterogeneous data sources, it builds multiple perspectives over the genome, leading to the identification of meaningful relationships that could not be perceived by using incompatible data formats. In this paper, we first describe a technological pipeline from data production to data integration; we then propose a taxonomy of genomic data players (based on the distinction between contributors, repository hosts, consortia, integrators and consumers) and apply the taxonomy to describe about 30 important players in genomic data management. We specifically focus on the integrator players and analyse the issues in solving the genomic data integration challenges, as well as evaluate the computational environments that they provide to follow up data integration by means of visualization and analysis tools.

Variant visualization plays an important role in supporting the viral evolution analysis, extremely valuable during the COVID-19 pandemic. VirusViz is a web-based application for comparing variants of selected viral populations and their sub-populations; it is primarily focused on SARS-CoV-2 variants, although the tool also supports other viral species (SARS-CoV, MERS-CoV, Dengue, Ebola). As input, VirusViz imports results of queries extracting variants and metadata from the large database ViruSurf, which integrates information about most SARS-CoV-2 sequences publicly deposited worldwide. Moreover, VirusViz accepts sequences of new viral populations as multi-FASTA files plus corresponding metadata in CSV format; a bioinformatic pipeline builds a suitable input for VirusViz by extracting the nucleotide and amino acid variants. Pages of VirusViz provide metadata summarization, variant descriptions, and variant visualization with rich options for zooming, highlighting variants or regions of interest, and switching from nucleotides to amino acids; sequences can be grouped, groups can be comparatively analyzed. For SARS-CoV-2, we manually collect mutations with known or predicted levels of severity/virulence, as indicated in linked research articles; such critical mutations are reported when observed in sequences. The system includes light-weight project management for downloading, resuming, and merging data analysis sessions. VirusViz is freely available at http://gmql.eu/virusviz/.

Breast Cancer comprises multiple subtypes implicated in prognosis. Existing stratification methods rely on the expression quantification of small gene sets. Next Generation Sequencing promises large amounts of omic data in the next years. In this scenario, we explore the potential of machine learning and, particularly, deep learning for breast cancer subtyping. Due to the paucity of publicly available data, we leverage on pan-cancer and non-cancer data to design semi-supervised settings. We make use of multi-omic data, including microRNA expressions and copy number alterations, and we provide an in-depth investigation of several supervised and semi-supervised architectures Obtained accuracy results show simpler models to perform at least as well as the deep semi-supervised approaches on our task over gene expression data. When multi-omic data types are combined together, performance of deep models shows little (if any) improvement in accuracy, indicating the need for further analysis on larger datasets of multi-omic data as and when they become available. From a biological perspective, our linear model mostly confirms known gene-subtype annotations. Conversely, deep approaches model non-linear relationships, which is reflected in a more varied and still unexplored set of representative omic features that may prove useful for breast cancer subtyping.