scholarly journals Classification of two species of Gram-positive bacteria through hyperspectral microscopy coupled with machine learning

2021 ◽  
Author(s):  
Kunxing Liu ◽  
Ze Ke ◽  
Peining Chen ◽  
Si-Qi Zhu ◽  
Hao Yin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gram Positive ◽  
Gram Positive Bacteria

Signatures of the ATP-binding pocket as a basis for structural classification of the serine/threonine protein kinases of gram-positive bacteria

2012 ◽  
Vol 80 (5) ◽  
pp. 1363-1376 ◽  
Author(s):  
Natalia V. Zakharevich ◽  
Dmitry I. Osolodkin ◽  
Irena I. Artamonova ◽  
Vladimir A. Palyulin ◽  
Nikolay S. Zefirov ◽  
...  
Keyword(s):  
Protein Kinases ◽  
Binding Pocket ◽  
Atp Binding ◽  
Structural Classification ◽  
Gram Positive ◽  
Gram Positive Bacteria

Classification of Bacteriocins from Gram-Positive Bacteria

2011 ◽  
pp. 29-53 ◽  
Author(s):  
Mary C. Rea ◽  
R. Paul Ross ◽  
Paul D. Cotter ◽  
Colin Hill
Keyword(s):  
Gram Positive ◽  
Gram Positive Bacteria

PeNGaRoo, a combined gradient boosting and ensemble learning framework for predicting non-classical secreted proteins

2019 ◽  
Author(s):  
Yanju Zhang ◽  
Sha Yu ◽  
Ruopeng Xie ◽  
Jiahui Li ◽  
André Leier ◽  
...  
Keyword(s):  
Machine Learning ◽  
Secreted Proteins ◽  
Gradient Boosting ◽  
Ensemble Model ◽  
Gram Positive ◽  
Gram Positive Bacteria ◽  
Single Feature ◽  
Gradient Boosting Machine ◽  
Benchmark Datasets ◽  
Feature Based

Abstract Motivation Gram-positive bacteria have developed secretion systems to transport proteins across their cell wall, a process that plays an important role during host infection. These secretion mechanisms have also been harnessed for therapeutic purposes in many biotechnology applications. Accordingly, the identification of features that select a protein for efficient secretion from these microorganisms has become an important task. Among all the secreted proteins, ‘non-classical’ secreted proteins are difficult to identify as they lack discernable signal peptide sequences and can make use of diverse secretion pathways. Currently, several computational methods have been developed to facilitate the discovery of such non-classical secreted proteins; however, the existing methods are based on either simulated or limited experimental datasets. In addition, they often employ basic features to train the models in a simple and coarse-grained manner. The availability of more experimentally validated datasets, advanced feature engineering techniques and novel machine learning approaches creates new opportunities for the development of improved predictors of ‘non-classical’ secreted proteins from sequence data. Results In this work, we first constructed a high-quality dataset of experimentally verified ‘non-classical’ secreted proteins, which we then used to create benchmark datasets. Using these benchmark datasets, we comprehensively analyzed a wide range of features and assessed their individual performance. Subsequently, we developed a two-layer Light Gradient Boosting Machine (LightGBM) ensemble model that integrates several single feature-based models into an overall prediction framework. At this stage, LightGBM, a gradient boosting machine, was used as a machine learning approach and the necessary parameter optimization was performed by a particle swarm optimization strategy. All single feature-based LightGBM models were then integrated into a unified ensemble model to further improve the predictive performance. Consequently, the final ensemble model achieved a superior performance with an accuracy of 0.900, an F-value of 0.903, Matthew’s correlation coefficient of 0.803 and an area under the curve value of 0.963, and outperforming previous state-of-the-art predictors on the independent test. Based on our proposed optimal ensemble model, we further developed an accessible online predictor, PeNGaRoo, to serve users’ demands. We believe this online web server, together with our proposed methodology, will expedite the discovery of non-classically secreted effector proteins in Gram-positive bacteria and further inspire the development of next-generation predictors. Availability and implementation http://pengaroo.erc.monash.edu/. Supplementary information Supplementary data are available at Bioinformatics online.

CW-PRED: A HMM-Based Method for the Classification of Cell Wall-Anchored Proteins of Gram-Positive Bacteria

2012 ◽  
pp. 285-290 ◽  
Author(s):  
Danai K. Fimereli ◽  
Konstantinos D. Tsirigos ◽  
Zoi I. Litou ◽  
Theodore D. Liakopoulos ◽  
Pantelis G. Bagos ◽  
...  
Keyword(s):  
Cell Wall ◽  
Gram Positive ◽  
Gram Positive Bacteria

Classification of Staphylococcus Aureus FabI Inhibitors by Machine Learning Techniques

2019 ◽  
Vol 4 (4) ◽  
pp. 1-14
Author(s):  
Vinicius Gonçalves Maltarollo
Keyword(s):  
Machine Learning ◽  
Acid Metabolism ◽  
Acyl Carrier Protein ◽  
Machine Learning Techniques ◽  
Gram Positive Bacteria ◽  
Phase Ii Clinical Trials ◽  
Learning Techniques ◽  
Bioactive Ligands ◽  
Key Enzyme

Enoyl-acyl carrier protein reductase (FabI) is a key enzyme in the fatty acid metabolism of gram-positive bacteria and is considered a potential target for new antibacterial drugs development. Indeed, triclosan is a widely employed antibacterial and AFN-1252 is currently under phase-II clinical trials, both are known as FabI inhibitors. Nowadays, there is an urgent need for new drug discovery due to increasing antibacterial resistance. In the present study, classification models using machine learning techniques were generated to distinguish SaFabI inhibitors from non-inhibitors successfully (e.g., Mathews correlation coefficient values equal to 0.837 and 0.789 calculated with internal and external validations). The interpretation of a selected model indicates that larger compounds, number of N atoms and the distance between central amide and naphthyridinone ring are important to biological activity, corroborating previous studies. Therefore, these obtained information and generated models can be useful for design/discovery of novel bioactive ligands as potential antibacterial agents.

Protein Subcellular Localization Feature of Essential/Nonessential Genes in 28 Prokaryotes

2014 ◽  
Vol 644-650 ◽  
pp. 5197-5201
Author(s):  
Xiao Liu ◽  
Xiao Li Geng ◽  
Hong Ling Tang
Keyword(s):  
Subcellular Localization ◽  
Protein Sequences ◽  
Essential Genes ◽  
Protein Subcellular Localization ◽  
Gram Positive ◽  
Gram Positive Bacteria ◽  
Nonessential Gene ◽  
Nonessential Genes

This study aimed to pursue the correlation between essential/nonessential gene and protein subcellular localization. The protein sequences of the essential/nonessential genes of 28 prokaryotes in Database of Essential Genes were analyzed by PSORTb3.0. Results show that proteins of essential genes locate in cytoplasm with relatively high percentage, i.e., in the range of 40% to 55%. Percentages of the proteins of essential genes locate in cytoplasma membrane are lower than that of nonessential genes, which mostly are about 15%. However, the values of proteins of nonessential genes are mostly about 20%, and that of Gram-positive bacteria are close to 30%. The distributions of protein subcellular localization of the essential/nonessential genes are different evidently. This could be used for classification of essential and nonessential genes.

Influence of Cell Wall Composition on the Fossilisation of Bacteria and the Implications for the Search for Early Life Forms

1997 ◽  
Vol 161 ◽  
pp. 491-504 ◽  
Author(s):  
Frances Westall
Keyword(s):  
Cell Wall ◽  
Life Forms ◽  
Cation Binding ◽  
Positive Bacterium ◽  
Gram Positive ◽  
Gram Positive Bacteria ◽  
Transmission Electron ◽  
Hydrothermal Sediments ◽  
Identification Of Bacteria ◽  
The Difference

AbstractThe oldest cell-like structures on Earth are preserved in silicified lagoonal, shallow sea or hydrothermal sediments, such as some Archean formations in Western Australia and South Africa. Previous studies concentrated on the search for organic fossils in Archean rocks. Observations of silicified bacteria (as silica minerals) are scarce for both the Precambrian and the Phanerozoic, but reports of mineral bacteria finds, in general, are increasing. The problems associated with the identification of authentic fossil bacteria and, if possible, closer identification of bacteria type can, in part, be overcome by experimental fossilisation studies. These have shown that not all bacteria fossilise in the same way and, indeed, some seem to be very resistent to fossilisation. This paper deals with a transmission electron microscope investigation of the silicification of four species of bacteria commonly found in the environment. The Gram positiveBacillus laterosporusand its spore produced a robust, durable crust upon silicification, whereas the Gram negativePseudomonas fluorescens, Ps. vesicularis, andPs. acidovoranspresented delicately preserved walls. The greater amount of peptidoglycan, containing abundant metal cation binding sites, in the cell wall of the Gram positive bacterium, probably accounts for the difference in the mode of fossilisation. The Gram positive bacteria are, therefore, probably most likely to be preserved in the terrestrial and extraterrestrial rock record.

Microanatomy of the Periplasm of Bacillus Licheniformis

1971 ◽  
Vol 29 ◽  
pp. 262-263
Author(s):  
B.K. Ghosh
Keyword(s):  
Cell Wall ◽  
Plasma Membrane ◽  
Bacillus Licheniformis ◽  
External Environment ◽  
Permeability Barrier ◽  
Periplasmic Space ◽  
Modified Technique ◽  
Gram Positive ◽  
Gram Negative ◽  
Gram Positive Bacteria

Periplasm of bacteria is the space outside the permeability barrier of plasma membrane but enclosed by the cell wall. The contents of this special milieu exterior could be regulated by the plasma membrane from the internal, and by the cell wall from the external environment of the cell. Unlike the gram-negative organism, the presence of this space in gram-positive bacteria is still controversial because it cannot be clearly demonstrated. We have shown the importance of some periplasmic bodies in the secretion of penicillinase from Bacillus licheniformis.In negatively stained specimens prepared by a modified technique (Figs. 1 and 2), periplasmic space (PS) contained two kinds of structures: (i) fibrils (F, 100 Å) running perpendicular to the cell wall from the protoplast and (ii) an array of vesicles of various sizes (V), which seem to have evaginated from the protoplast.

Sign in / Sign up

Export Citation Format

Share Document