Dataset Information

Deep Learning Based Prediction of Gas Chromatographic Retention Indices for a Wide Variety of Polar and Mid-Polar Liquid Stationary Phases.

ABSTRACT: Prediction of gas chromatographic retention indices based on compound structure is an important task for analytical chemistry. The predicted retention indices can be used as a reference in a mass spectrometry library search despite the fact that their accuracy is worse in comparison with the experimental reference ones. In the last few years, deep learning was applied for this task. The use of deep learning drastically improved the accuracy of retention index prediction for non-polar stationary phases. In this work, we demonstrate for the first time the use of deep learning for retention index prediction on polar (e.g., polyethylene glycol, DB-WAX) and mid-polar (e.g., DB-624, DB-210, DB-1701, OV-17) stationary phases. The achieved accuracy lies in the range of 16-50 in terms of the mean absolute error for several stationary phases and test data sets. We also demonstrate that our approach can be directly applied to the prediction of the second dimension retention times (GC × GC) if a large enough data set is available. The achieved accuracy is considerably better compared with the previous results obtained using linear quantitative structure-retention relationships and ACD ChromGenius software. The source code and pre-trained models are available online.

SUBMITTER: Matyushin DD

PROVIDER: S-EPMC8430916 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundBurkholderia cepacia is a Gram-negative pathogen that causes serious respiratory infections in immunocompromised patients and individuals with cystic fibrosis. This bacterium is known to release extracellular proteins that may be involved in virulence.Methodology/principal findingsIn the present study, B. cepacia grown to mid-logarithmic and early-stationary phases were investigated on their ability to invade and survive intracellularly in A549 lung epithelial cells in order to discern the fate of these bacteria in the pathogenesis of B. cepacia lung infections in in vitro condition. The early-stationary phase B. cepacia was demonstrated to be more invasive than mid-logarithmic phase. In addition, culture supernatants of B. cepacia obtained from these phases of growth were also demonstrated to cause different cytotoxic potency on the A549 human lung epithelial cells. Profiling of the supernatants using the gel-based proteomics approach identified 43 proteins that were commonly released in both the growth phases and 40 proteins newly-released at the early-stationary phase. The latter proteins may account for the higher cytotoxic activity of the early-stationary culture supernatant compared to that obtained at the mid-logarithmic phase. Among the newly-released proteins in the early-stationary phase supernatant were flagellar hook-associated domain protein (FliD), flagellar hook-associated protein (FlgK), TonB-dependent siderophore (Fiu), Elongation factor G (FusA), phosphoglycerate kinase (Pgk) and sulfatase (AslA) which are known for their virulence.Conclusion/significanceDifferences in the ability of B. cepacia to invade and survive intracellularly inside the epithelial cells at different phases of growth may improve our understanding of the varied disease progressions associated with B. cepacia infections. In addition, the identified culture supernatant proteins may be used as targets for the development of new strategies to control B. cepacia infection using agents that can block their release.

Dataset Information

Deep Learning Based Prediction of Gas Chromatographic Retention Indices for a Wide Variety of Polar and Mid-Polar Liquid Stationary Phases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets