Dataset Information

Common sleep data pipeline for combined data sets.

ABSTRACT: Over the past few years, sleep research has shown impressive performance of deep neural networks in the area of automatic sleep-staging. Recent studies have demonstrated the necessity of combining multiple data sets to obtain sufficiently generalizing results. However, working with large amounts of sleep data can be challenging, both from a hardware perspective and because of the different preprocessing steps necessary for distinct data sources. Here we review the possible obstacles and present an open-source pipeline for automatic data loading. Our solution includes both a standardized data store as well as a 'data serving' portion which can be used to train neural networks on the standardized data, allowing for different configuration options for different studies and machine learning designs. The pipeline, including implementation, is made public to ensure better and more reproducible sleep research.

SUBMITTER: Strom J

PROVIDER: S-EPMC11302895 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Common sleep data pipeline for combined data sets.

Strøm Jesper J Engholm Andreas Larsen AL Lorenzen Kristian Peter KP Mikkelsen Kaare B KB

PloS one 20240806 8

Over the past few years, sleep research has shown impressive performance of deep neural networks in the area of automatic sleep-staging. Recent studies have demonstrated the necessity of combining multiple data sets to obtain sufficiently generalizing results. However, working with large amounts of sleep data can be challenging, both from a hardware perspective and because of the different preprocessing steps necessary for distinct data sources. Here we review the possible obstacles and present ...[more]

PMID: 39106236

Similar Datasets

Project description:Protein localization is paramount to protein function, and the intracellular movement of proteins underlies the regulation of numerous cellular processes. Given advances in spatial proteomics, the investigation of protein localization at a global scale has become attainable. Also becoming apparent is the need for dedicated analytical frameworks that allow the discovery of global intracellular protein movement events. Here, we describe TRANSPIRE, a computational pipeline that facilitates TRanslocation ANalysis of SPatIal pRotEomics data sets. TRANSPIRE leverages synthetic translocation profiles generated from organelle marker proteins to train a probabilistic Gaussian process classifier that predicts changes in protein distribution. This output is then integrated with information regarding co-translocating proteins and complexes and enriched gene ontology associations to discern the putative regulation and function of movement. We validate TRANSPIRE performance for predicting nuclear-cytoplasmic shuttling events. Analyzing an existing data set of nuclear and cytoplasmic proteomes during Kaposi Sarcoma-associated herpesvirus (KSHV)-induced cellular mRNA decay, we confirm that TRANSPIRE readily discerns expected translocations of RNA binding proteins. We next investigate protein translocations during infection with human cytomegalovirus (HCMV), a β-herpesvirus known to induce global organelle remodeling. We find that HCMV infection induces broad changes in protein localization, with over 800 proteins predicted to translocate during virus replication. Evident are protein movements related to HCMV modulation of host defense, metabolism, cellular trafficking, and Wnt signaling. For example, the low-density lipoprotein receptor (LDLR) translocates to the lysosome early in infection in conjunction with its degradation, which we validate by targeted mass spectrometry. Using microscopy, we also validate the translocation of the multifunctional kinase DAPK3, a movement that may contribute to HCMV activation of Wnt signaling.

Project description:The chromophyte algae are a large and biologically diverse assemblage of brown seaweeds, diatoms, and other golden algae classified in 13 taxonomic classes. One subgroup (diatoms, pedinellids, pelagophytes, silicoflagellates, and certain enigmatic genera) is characterized by a highly reduced flagellar apparatus. The flagellar apparatus lacks microtubular and fibrous roots, and the flagellum basal body is attached directly to the nucleus. We hypothesize that the flagellar reduction is the result of a single evolutionary series of events. Cladistic analysis of ultrastructural and biochemical data reveals a monophyletic group that unites all taxa with a reduced flagellar apparatus, supporting our hypothesis. Phylogenetic analyses of 18S rRNA gene sequence data provide strong resolution within most of the major groups of chromophytes but only weakly resolve relationships among those groups. Some of the molecularly based most parsimonious trees, however, also unite the taxa with a reduced flagellar apparatus, although the diatoms are not included in this lineage. This grouping is further supported by a posteriori character weighting of the molecular data, suggesting that flagellar reduction occurred at least twice in parallel evolutionary series of events. To further test our hypothesis of a single evolutionary reduction in the flagellar apparatus, we combine the two data sets and subject the hybrid data matrix to parsimony analysis. The resulting trees unite the diatoms with the other reduced flagellar apparatus algae in a monophyletic group. This result supports our hypothesis of a single evolutionary reduction and indicates the existence of a previously unrecognized lineage of algae characterized by a highly reduced flagellar apparatus. Further, this study suggests that the traditional classification of the diatoms with the chrysophytes and xanthophytes in the division (= phylum) Chrysophyta, as presented in most textbooks, is unsatisfactory and that a significantly different classification should be employed.

Dataset Information

Common sleep data pipeline for combined data sets.

Publications

Common sleep data pipeline for combined data sets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets