Melidis, D. P. | bioRxiv Science

bioRxiv2020

ViruSurf: an integrated database to investigate viral sequences

ViruSurf, available at http://gmql.eu/virusurf/, is a large public database of viral sequences and integrated and curated metadata from heterogeneous sources (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.

genomics↗

bioRxiv2020

dom2vec: Assessable domain embeddings and their use for protein prediction tasks

MotivationWord embedding approaches have revolutionized Natural Language Processing NLP research. These approaches aim to map words to a low-dimensional vector space in which words with similar linguistic features are close in the vector space. These NLP approaches also preserve local linguistic features, such as analogy. Embedding-based approaches have also been developed for proteins. To date, such approaches treat amino acids as words, and proteins are treated as sentences of amino acids. These approaches have been evaluated either qualitatively, via visual inspection of the embedding space, or extrinsically, via performance on a downstream task. However, it is difficult to directly assess the intrinsic quality of the learned embeddings. ResultsIn this paper, we introduce dom2vec, an approach for learning protein domain embeddings. We also present four intrinsic evaluation strategies which directly assess the quality of protein domain embeddings. We leverage the hierarchy relationship of InterPro domains, known secondary structure classes, Enzyme Commission class information, and Gene Ontology annotations in these assessments. These evaluations allow us to assess the quality of learned embeddings independently of a particular downstream task. Importantly, allow us to draw an analog between the local linguistic features in nature languages and the domain structure and function information in domain architectures, thus providing data-driven insights into the context found in the language of domain architectures. We also show that dom2vec embeddings outperform, or are comparable with, state-of-the-art approaches on downstream tasks. AvailabilityThe protein domain embeddings vectors and the entire code to reproduce the results are available at https://github.com/damianosmel/dom2vec. Contactmelidis@l3s.uni-hannover.de

bioinformatics↗