We present a novel system that leverages curators in the loop to develop a dataset and model for detecting structure features and functional annotations at residue-level from standard publication text. Our approach involves the integration of data from multiple resources, including PDBe, EuropePMC, PubMedCentral, and PubMed, combined with annotation guidelines from UniProt, and LitSuggest and HuggingFace models as tools in the annotation process. A team of seven annotators manually curated ten articles for named entities, which we utilized to train a starting PubmedBert model from HuggingFace. Using a human-in-the-loop annotation system, we iteratively developed the best model with commendable performance metrics of 0.90 for precision, 0.92 for recall, and 0.91 for F1-measure. Our proposed system showcases a successful synergy of machine learning techniques and human expertise in curating a dataset for residue-level functional annotations and protein structure features. The results demonstrate the potential for broader applications in protein research, bridging the gap between advanced machine learning models and the indispensable insights of domain experts.
- MeSH
- databáze proteinů MeSH
- lidé MeSH
- proteiny * chemie MeSH
- strojové učení * MeSH
- Check Tag
- lidé MeSH
- Publikační typ
- časopisecké články MeSH
- dataset MeSH
The archiving and dissemination of protein and nucleic acid structures as well as their structural, functional and biophysical annotations is an essential task that enables the broader scientific community to conduct impactful research in multiple fields of the life sciences. The Protein Data Bank in Europe (PDBe; pdbe.org) team develops and maintains several databases and web services to address this fundamental need. From data archiving as a member of the Worldwide PDB consortium (wwPDB; wwpdb.org), to the PDBe Knowledge Base (PDBe-KB; pdbekb.org), we provide data, data-access mechanisms, and visualizations that facilitate basic and applied research and education across the life sciences. Here, we provide an overview of the structural data and annotations that we integrate and make freely available. We describe the web services and data visualization tools we offer, and provide information on how to effectively use or even further develop them. Finally, we discuss the direction of our data services, and how we aim to tackle new challenges that arise from the recent, unprecedented advances in the field of structure determination and protein structure modeling.
- MeSH
- databáze proteinů MeSH
- konformace proteinů MeSH
- nukleové kyseliny * MeSH
- proteiny * chemie MeSH
- Publikační typ
- časopisecké články MeSH
- práce podpořená grantem MeSH
- Geografické názvy
- Evropa MeSH
Digestion, ISSN 0012-2823 vol. 75, suppl. 1, 2007
100 s. : il., tab. ; 28 cm
- MeSH
- amputace MeSH
- anamnéza MeSH
- diabetická noha mikrobiologie patologie terapie MeSH
- dospělí MeSH
- fyzikální vyšetření MeSH
- infekce patologie terapie MeSH
- kohortové studie MeSH
- lidé MeSH
- rizikové faktory MeSH
- sociální problémy MeSH
- socioekonomické faktory MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- Publikační typ
- srovnávací studie MeSH
BACKGROUND: Helicobacter pylori (H. pylori) produces large amounts of ammonia. Based on higher readings obtained with an ammonia-sensitive electrode when compared to a specific enzymatic assay, it has been claimed that H. pylori also produces potentially toxic volatile amines. METHOD: We measured ammonia concentrations (NH3) in gastric aspirates from 11 H. pylori positive subjects (22-40 y, 6 M), using an ammonia electrode sensitive to ammonia and amines, and an enzymatic assay specific for ammonia. Continuous aspiration was performed overnight and 220 aspirates were analyzed before and 6 weeks after cure of H. pylori. Gastric samples were diluted 1:3 (before cure) and 1:1 (after cure) according to dilution curves constructed prior to the assays. RESULTS: Median (95% CI) NH3 detected by the electrode/enzymatic assay were 4.34 mM[4.12-4.61]/4.50 mM [4.28-4.68] (p > .05) before cure and 0.54 mM[0.42-0.60]/0.73 mM[0.71-0.81] after cure (p > .05). Intra-class correlation coefficient between the two methods was 0.91 before cure and 0.90 after cure (p < .001). Without dilution, the enzymatic assay was linear for NH3 from 0.01 to 1 mM and saturated at 2.5 mM; the electrode was linear for NH3 from 0.01 to 20 mM. When appropriate dilutions were performed, the enzymatic assay was accurate for NH3 greater than 2.5 mM. CONCLUSION: In subjects with H. pylori infection there is a high NH3 in gastric juice; production of volatile amines appears to be negligible in vivo. An ammonia-sensitive electrode and a specific enzymatic assay are both suitable methods for determining NH3 in the gastric juice of subjects with H. pylori infection.
- MeSH
- aminy * analýza MeSH
- amoniak * analýza metabolismus MeSH
- biosenzitivní techniky MeSH
- dospělí MeSH
- Helicobacter pylori enzymologie metabolismus MeSH
- infekce vyvolané Helicobacter pylori * mikrobiologie MeSH
- lidé středního věku MeSH
- lidé MeSH
- žaludeční šťáva * MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
