Ontology highlight
ABSTRACT:
PROVIDER: PRJNA1045106 | ENA |
REPOSITORIES: ENA
Dataset's files
| Action | DRS | |||
|---|---|---|---|---|
| SRR26949421_1.fastq.gz | Fastqsanger.gz | |||
| SRR26949421_2.fastq.gz | Fastqsanger.gz | |||
| SRR26949422_1.fastq.gz | Fastqsanger.gz | |||
| SRR26949422_2.fastq.gz | Fastqsanger.gz | |||
| SRR26949423_1.fastq.gz | Fastqsanger.gz |
Items per page: 5 1 - 5 of 6 |
Similar Datasets
Project description:Current clinical antibiotics are largely broad-spectrum agents that promote intestinal dysbiosis and colonisation of Enterobacteriaceae, which are often drug-resistant. Indeed, dysbiosis creates an ideal niche for adherent-invasive Escherichia coli (AIEC) in patients with inflammatory bowel disease (IBD). There is an urgent and unmet need for novel narrow-spectrum and microbiome-sparing antibiotics. Here, we screened >10,000 molecules for antibacterial activity against AIEC and discovered enterololin, an antibacterial compound with targeted activity against Enterobacteriaceae species. Molecular substructure- and deep learning-guided mechanism of action investigations revealed that enterololin perturbs lipoprotein trafficking through a mechanism involving the LolCDE complex. Moreover, enterololin can suppress an AIEC infection in mouse models, while largely preserving the overall microbiome composition. This work highlights the utility of deep learning methods for predicting molecular interactions, thereby accelerating mechanism of action elucidation of novel molecules, and identifies a promising Enterobacteriaceae-specific antibacterial candidate for further development to treat challenging infections in IBD patients.
2025-08-27 | GSE300731 | GEO
Project description:Accurate prediction of cell cycle phases is important in understanding how certain diseases (e.g. cancer) develop and respond to treatment. It is also essential for reducing the confounding effects in single-cell RNA sequencing (scRNA-Seq) data analysis. We evaluated both traditional machine learning techniques and deep learning approaches for predicting cell cycle phases from scRNA-seq data. Models were trained on consensus predictions from four popular cell cycle analysis tools, namely, CellCycleScore, ccAF, Revelio, and Tricycle, then applied to unlabeled scRNA-seq data generated from human leukemia cell lines. We evaluated model performance using publicly available datasets, GSE146773 (human leukemia cells, 1,151 cells) and GSE64016 (human embryonic stem cells, 213 cells), both labeled with their respective cell cycle phases through experiments. In addition to the four tools, we assessed traditional machine learning models (AdaBoost, Random Forest, and LightGBM), deep learning models including multiple dense networks DNN (2-5), CNN, Hybrid CNN-Dense, Feature embedding, and ensemble models. DNN 3 achieved the highest accuracy, reaching 75.16% on the GSE146773 dataset and 70.85% on GSE64016. This outperformed existing tools such as Revelio (68.34% on GSE146773, 68.2% on GSE64016), CellCycleScore (66.54% on GSE146773, 53.84% on GSE64016), ccAF (45% on GSE146773, 40% on GSE64016), ccAFv2 (47.23% on GSE146773, 43.72% on GSE64016), Tricycle (53.23% on GSE146773, 58.7% on GSE64016), and Cyclum (38.52% on GSE146773, 26.3% for GSE64016). These results signify the potential of deep learning models for robust cell cycle phase prediction in scRNA-seq data.
2025-10-22 | GSE293316 | GEO
Project description:Engineered RNA elements are programmable tools capable of detecting small molecules, proteins, and nucleic acids. Predicting the behavior of these tools remains a challenge, a situation that could be addressed through enhanced pattern recognition from deep learning. Thus, we investigate Deep Neural Networks (DNN) to predict toehold switch function as a canonical riboswitch model in synthetic biology. To facilitate DNN training, we synthesized and characterized in vivo a dataset of 91,534 toehold switches spanning 23 viral genomes and 906 human transcription factors. DNNs trained on nucleotide sequences outperformed (R2=0.43-0.70) previous state-of-the-art thermodynamic and kinetic models (R2=0.04-0.15) and allowed for human-understandable attention-visualizations (VIS4Map) to identify success and failure modes. This deep learning approach constitutes a major step forward in engineering and understanding of RNA synthetic biology.
2020-08-12 | GSE149225 | GEO
Project description:Interventions: Gold Standard:MMR status detection by immunohistochemistry;Index test:deep learning model predicting MMR status of patients with colorectal cancer
Primary outcome(s): AUROC
Study Design: Diagnostic test for accuracy
| 114063 | ecrin-mdr-crc
Project description:International guidelines recommend deciding the treatment of colorectal lesions based on the estimated histology by endoscopic optical diagnosis. However, the theoretical and practical knowledge on optical diagnosis is not widely expanded
The mail goal of this randomised controlled trial is to compare the pooled sensitivity of optical diagnosis for predicting deep submucosal invasion in large non-pedunculated polyps > 20 mm assessed in routine colonoscopies of gastroenterologists attending a e-learning module (intervention group) vs gastroenterologists who do not (control group)
The main questions the study aims to answer are:
* Is the pooled sensitivity of optical diagnosis for predicting deep submucosal invasion in large non-pedunculated polyps assessed in routine colonoscopies increased in those gastroenterologists participating in the e-learning module?
* Is the pooled diagnostic accuracy of optical diagnosis for predicting deep sm invasion in large non-pedunculated polyps ≥ 20 mm assessed in routine colonoscopies increased in those gastroenterologists participating in the e-learning module?
* In lesions with submucosal invasion, is the en bloc and complete resection rate (R0) increased in those gastroenterologists participating in the e-learning module?
* In lesions referred to surgery, is the pooled benign polyps rate decreased in those gastroenterologists participating in the e-learning module?
* In lesions treated with advanced en bloc procedures (ESD, TAMIS, fullthickness resection), is the pooled rate of histology with high-grade dysplasia, intramucosal cancer or submucosal invasion increased in those gastroenterologists participating in the e-learning module?
* In lesions treated with piecemeal endoscopic resection, is the pooled rate of histology with high-grade dysplasia, intramucosal cancer or submucosal invasion decreased in those gastroenterologists participating in the e-learning module?
* Is the diagnostic accuracy for predicting deep submucosal invasion in a test with pictures increased after participating in the e-learning module?
The participants (or subjects of study) are gastroenterologists. They will be randomised to do the e-learning course (intervention group) or not (control group).
Researchers will compare clinical outcomes of gastroenterologists participating in the e-learning module vs gastroenterologists not participating in the e-learning module to see if:
* the pooled sensitivity of optical diagnosis for predicting deep submucosal invasion in large non-pedunculated polyps > 20 mm assessed in routine colonoscopies is increased.
* the pooled diagnostic accuracy of optical diagnosis for predicting deep sm invasion in large non-pedunculated polyps > 20 mm is increased.
* the en bloc and complete resection rate (R0) is increased in lesions with submucosal invasion.
* the pooled benign polyps rate decreased in lesions referred to surgery.
* the pooled rate of histology with high-grade dysplasia, intramucosal cancer or submucosal invasion increased in lesions treated with advanced en bloc procedures (ESD, TAMIS, fullthickness resection).
* the pooled rate of histology with high-grade dysplasia, intramucosal cancer or submucosal invasion decreased in lesions treated with piecemeal endoscopic resection.
* the diagnostic accuracy for predicting deep submucosal invasion in a test with pictures after participating is increased.
| 3397 | ecrin-mdr-crc
Project description:HydRA: Deep-learning models for predicting RNA-binding capacity from protein interaction association context and protein sequence
| PRJNA916520 | ENA
Project description:The escalating crisis of multiresistant bacteria demands the rapid discovery of novel antibiotics that transcend the limitations imposed by the biased chemical space of current libraries. To address this challenge, we introduce an innovative deep learning-driven pipeline for de novo antibiotic design. This unique approach leverages a chemical language model, trained on a diverse chemical space encompassing drug-like molecules and natural products, coupled with transfer learning on diverse antibiotic scaffolds to efficiently generate structurally unprecedented antibiotic candidates. Through the use of predictive modeling and expert curation, we prioritized and synthesized the most promising and readily available candidates. Notably, our efforts culminated in a lead candidate demonstrating potent activity against methicillin-resistant Staphylococcus aureus. Iterative refinement through automated synthesis of 40 derivatives yielded a suite of active compounds, including 30 with activity against S. aureus and 17 against Escherichia coli. Among these, lead compound D8 exhibited remarkable submicromolar and single-digit micromolar potency against the aforementioned pathogens, respectively. Mechanistic investigations point to the generation of radical species as its primary mode of action. This work showcases the power of our innovative deep learning framework to significantly accelerate and expand the horizons of antibiotic drug discovery.
2025-10-06 | PXD066005 | Pride
Project description:Generating and analyzing overlapping peptides through multienzymatic digestion is an efficient procedure for de novo protein using from bottom-up mass spectrometry (MS). Despite improved instrumentation and software, de novo MS data analysis remains challenging. In recent years, deep learning models have represented a performance breakthrough. Incorporating that technology into de novo protein sequencing workflows require machine-learning models capable of handling highly diverse MS data. In this study, we analyzed the requirements for assembling such generalizable deep learning models by systematically varying the composition and size of the training set. We assessed the generated models' performances using two test sets composed of peptides originating from the multienzyme digestion of samples from various species. The peptide recall values on the test sets showed that the deep learning models generated from a collection of highly N- and C-termini diverse peptides generalized 76% more over the termini-restricted ones. Moreover, expanding the training set's size by adding peptides from the multienzymatic digestion with five proteases of several species samples led to a 2-3 fold generalizability gain. Furthermore, we tested the applicability of these multienzyme deep learning (MEM) models by fully de novo sequencing the heavy and light monomeric chains of five commercial antibodies (mAbs). MEMs extracted over 10000 matching and overlapped peptides across six different proteases mAb samples, achieving a 100% sequence coverage for 8 of the ten polypeptide chains. We foretell that the MEMs' proven improvements to de novo analysis will positively impact several applications, such as analyzing samples of high complexity, unknown nature, or the peptidomics field.
2023-01-16 | PXD037803 | Pride