1. Learning deep representations of enzyme thermal adaptationGang Li, Filip Buric, Jan Zrimec, Sandra Viknander, Jens Nielsen, Aleksej Zelezniak, Martin K. M. Engqvist, 2022, izvirni znanstveni članek Povzetek: Temperature is a fundamental environmental factor that shapes the evolution of organisms. Learning thermal determinants of protein sequences in evolution thus has profound significance for basic biology, drug discovery, and protein engineering. Here, we use a data set of over 3 million BRENDA enzymes labeled with optimal growth temperatures (OGTs) of their source organisms to train a deep neural network model (DeepET). The protein-temperature representations learned by DeepET provide a temperature-related statistical summary of protein sequences and capture structural properties that affect thermal stability. For prediction of enzyme optimal catalytic temperatures and protein melting temperatures via a transfer learning approach, our DeepET model outperforms classical regression models trained on rationally designed features and other deep-learning-based representations. DeepET thus holds promise for understanding enzyme thermal adaptation and guiding the engineering of thermostable enzymes.
Ključne besede: bioinformatics, deep neural networks, enzyme catalytic temperatures, optimal growth temperatures, protein thermostability, transfer learning
Objavljeno v DiRROS: 17.07.2024; Ogledov: 79; Prenosov: 55
 Celotno besedilo (2,61 MB)
Gradivo ima več datotek! Več... |
2. Evidence-based unification of potato gene models with the UniTato collaborative genome browserMaja Zagorščak, Jan Zrimec, Carissa Bleker, Nadja Francesca Nolte, Mojca Juteršek, Živa Ramšak, Kristina Gruden, Marko Petek, 2024, izvirni znanstveni članek Povzetek: Potato (Solanum tuberosum) is the most popular tuber crop and a model organism. A variety of gene models for potato exist, and despite frequent updates, they are not unified. This hinders the comparison of gene models across versions, limits the ability to reuse experimental data without significant re-analysis, and leads to missing or wrongly annotated genes. Here, we unify the recent potato double monoploid v4 and v6 gene models by developing an automated merging protocol, resulting in a Unified poTato genome model (UniTato). We subsequently established an Apollo genome browser (unitato.nib.si) that enables public access to UniTato and further community-based curation. We demonstrate how the UniTato resource can help resolve problems with missing or misplaced genes and can be used to update or consolidate a wider set of gene models or genome information. The automated protocol, genome annotation files, and a comprehensive translation table are provided at github.com/NIB-SI/unitato.
Ključne besede: bioinformatics analysis, plant genome annotation, gene model annotations, Phureja group, GFF files, poTato genome model, UniTato
Objavljeno v DiRROS: 11.06.2024; Ogledov: 129; Prenosov: 103
Celotno besedilo (2,48 MB)
Gradivo ima več datotek! Več... |
3. RNA-dependent cysteine biosynthesis in bacteria and archaeaTakahito Mukai, Ana Crnković, Takuya Umehara, Natalia N. Ivanova, Nikos C. Kyrpides, Dieter Söll, 2017, izvirni znanstveni članek Ključne besede: amino acyl-tRNA synthetases, archaea, archaeal proteins, bacteria, computational biology, crystallography, X-ray, genetic code, genome, archaeal, genome, bacterial, phosphoserine, protein binding, protein biosynthesis, RNA, archaeal, RNA, bacterial, RNA, transfer, amino acyl, RNA, transfer, cys, sulfur/metabolism, biochemistry, bioinformatics, cysteine biosynthesis, genetic code, translation
Objavljeno v DiRROS: 07.05.2020; Ogledov: 1877; Prenosov: 1372
Celotno besedilo (1,15 MB)
Gradivo ima več datotek! Več... |
