Convolutional neural network modelling: advancing identification of true mRNA cleavage sites
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA685865 | ENA |
REPOSITORIES: ENA
Similar Datasets
Project description:Degradome sequencing is commonly used to generate high-throughput information on mRNA cleavages by small RNAs. Here we developed an extension module based on a deep learning convolutional neural network (CNN) in a machine learning environment to discriminate false from true cleavage sites applied on datasets from potato (Solanum tuberosum, St) and the oomycete pathogen Phytophthora infestans (Pi). The core of the CNN module is a stochastic gradient descent optimizer with cyclical learning rate (CLR) which together with Bayesian optimization scored a validation accuracy of 100%. To verify the recognition of cleavage sites we applied the module on Arabidopsis thaliana microRNA cleavages. Our module managed to recognize all cleavages, confirming the reliability of the module. When applying this new model to evaluate our data, 7.3% of all cleavage windows represented true cleavages distributed as 214 sites in P. infestans and 444 sites in potato. The sRNA landscape of the potato-P. infestans interaction is complex with uneven sRNA production and cleavage regions. In total, 222 endogenous Pi-sRNAs, 565 endogenous St-sRNAs, 91 trans-acting Pi-sRNAs and 14 trans-acting St-sRNAs were discovered from our datasets. Groups of self-regulatory sRNAs, and sRNAs generated from effector sequences like RXLR and Crinklers suggest dual effector functions. In the potato genome, resistance genes were most targeted mainly as self-regulation but also as results of a trans-action event. Our new analytic model is freely accessible for anyone working on complex biological systems.
2021-05-05 | GSE163382 | GEO
Project description:Defining Giardia lamblia cleavage sites
| PRJNA713373 | ENA
Project description:True mangrove rhizospheres Raw sequence reads
| PRJNA826370 | ENA
Project description:3'-end sequencing and Oxford Nanopore Technologies long-read sequencing of trophozoite RNA to define mRNA cleavage sites
2022-03-09 | GSE168675 | GEO
Project description:Degradome sequencing is commonly used to generate high-throughput information on mRNA cleavage sites mediated by small RNAs (sRNA). In our datasets of potato (Solanum tuberosum, St) and Phytophthora infestans (Pi), initial predictions generated high numbers of cleavage site predictions, which highlighted the need of improved analytic tools. Here, we present an R package based on a deep learning convolutional neural network (CNN) in a machine learning environment to optimize discrimination of false from true cleavage sites. When applying smartPARE to our datasets on potato during the infection process by the late blight pathogen, 7.3% of all cleavage windows represented true cleavages distributed on 214 sites in P. infestans and 444 sites in potato. The sRNA landscape of the two organisms is complex with uneven sRNA production and cleavage regions widespread in the two genomes. Multiple targets and several cases of complex regulatory cascades, particularly in potato, was revealed. We conclude that our new analytic approach is useful for anyone working on complex biological systems and with the interest of identifying cleavage sites particularly inferred by sRNA classes beyond miRNAs.
| S-EPMC8073297 | biostudies-literature
Project description:halophilic archaeon True-ADL genome sequencing project
| PRJNA53493 | ENA
Project description:The Microprocessor plays an essential role in canonical miRNA biogenesis by facilitating cleavage of stem-loop structures in primary transcripts to yield pre-miRNAs. Although miRNA biogenesis has been extensively studied through biochemical and molecular genetic approaches, it has yet to be addressed to what extent the current miRNA biogenesis models hold true in intact cells. To address the issues of in vivo recognition and cleavage by the Microprocessor, we investigate RNAs that are associated with DGCR8 and Drosha by using immunoprecipitation coupled with next-generation sequencing. Here, we present global protein-RNA interactions with unprecedented sensitivity and specificity. Our data indicate that precursors of canonical miRNAs and miRNA-like hairpins are the major substrates of the Microprocessor. As a result of specific enrichment of nascent cleavage products, we are able to pinpoint the Microprocessor-mediated cleavage sites per se at single-nucleotide resolution. Unexpectedly, a 2-nt 3M-bM-^@M-^Y overhang invariably exists at the ends of cleaved bases instead of nascent pre-miRNAs. Besides canonical miRNA precursors, we find that two novel miRNA-like structures embedded in mRNAs are cleaved to yield pre-miRNA-like hairpins, uncoupled from miRNA maturation. Our data provide a framework for in vivo Microprocessor-mediated cleavage and a foundation for experimental and computational studies on miRNA biogenesis in living cells. CLIP-seq for DGCR8 and Drosha, RIP-seq for DGCR8, sequencing of AGO2-assocated miRNA
2014-10-02 | E-GEOD-61979 | biostudies-arrayexpress
Project description:Identification C3 cleavage sites by alpha-Thrombin. Goal of the experiment is the validation of predicted cleavage sites by HTPS
2021-02-04 | PXD022971 | Pride
Project description:Messenger RNAs are regulated by a variety of degradation mechanisms in mammalian cells. In the canonical animal microRNA pathway, microRNAs in complex with Argonaute proteins bind to many mRNA targets with imperfect complementarity, leading to degradation of the mRNA through the regular decay machinery. The ancestral “slicer” endonuclease activity of Argonaute2 itself, which requires more extensive complementarity with the target RNA, is not used in this pathway, and has only been observed in two microRNA-guided cases. Nevertheless, the cleavage capacity of mammalian Ago2 is conserved and essential for viability. Here, we assess the endonucleolytic function of Ago2 and other nucleases by identifying cleavage products retaining 5`-phosphate groups in mouse ES cells on a transcriptome-wide scale. We detect a significant signature of Ago2-dependent cleavage events and validate several targets. Unexpectedly, a broader class of Ago2-independent cleavage sites is also observed, indicating participation of additional nucleases in this mode of mRNA regulation. Within this class, we identify a cohort of Drosha-dependent mRNA cleavage events, including one in the Dgcr8 mRNA, that functionally regulate mRNA levels in mES cells. Together, these results highlight the underappreciated role of endonucleolytic cleavage in controlling mRNA fates in mammals. Global 5`-phosphate-dependent RACE in WT, Ago2-KO and Drosha-excised mouse ES cells and human 293S cells
2010-06-25 | E-GEOD-21975 | biostudies-arrayexpress
Project description:Type II topoisomerases (topos) are a ubiquitous and essential class of enzymes that form transient enzyme-bound double-stranded breaks on DNA called cleavage complexes. The location and frequency of these cleavage complexes on DNA is important for cellular function, genomic stability, and a number of clinically important anticancer and antibacterial drugs, e.g., quinolones. We developed a simple high-accuracy end-sequencing (SHAN-seq) method to sensitively map type II topo cleavage complexes on DNA in vitro. Using SHAN-seq, we detected Escherichia coli gyrase and topoisomerase IV cleavage complexes at hundreds of sites on supercoiled pBR322 DNA, approximately one site every ten bp, with frequencies that varied by two-to-three orders of magnitude. These sites included previously identified sites and 20-50 fold more new sites. We show that the location and frequency of cleavage complexes at these sites are enzyme-specific and vary substantially in the presence of the quinolone, ciprofloxacin, but not with DNA supercoil chirality, i.e., negative vs. positive supercoiling. SHAN-seq’s exquisite sensitivity provides an unprecedented single-nucleotide resolution view of the distribution of gyrase and topoisomerase IV cleavage complexes on DNA. Moreover, the discovery that these enzymes can cleave DNA at orders of magnitude more sites than the relatively few previously known sites resolves the apparent paradox of how these enzymes resolve topological problems throughout the genome.
2024-08-06 | GSE267149 | GEO