PredT4SE-Stack: Prediction of Bacterial Type IV Secreted Effectors From Protein Sequences Using a Stacked Ensemble Method

Abstract Background: Classification of certain proteins with specific functions is momentous for biological research. Encoding approaches of protein sequences for feature extraction play an important role in protein classification. Many computational methods (namely classifiers) are used for classification on protein sequences according to various encoding approaches. Commonly, protein sequences keep certain labels corresponding to different categories of biological functions (e.g., bacterial type IV secreted effectors or not), which makes protein prediction a fantasy. As to protein prediction, a kernel set of protein sequences keeping certain labels certified by biological experiments should be existent in advance. However, it has been hardly ever seen in prevailing researches. Therefore, unsupervised learning rather than supervised learning (e.g. classification) should be considered. As to protein classification, various classifiers may help to evaluate the effectiveness of different encoding approaches. Besides, variable selection from an encoded feature representing protein sequences is an important issue that also needs to be considered.Results: Focusing on the latter problem, we propose a new method for variable selection from an encoded feature representing protein sequences. Taking a benchmark dataset as a case, experiments are made to identify bacterial type IV secreted effectors from protein sequences, which indicates the effectiveness of our method. Conclusions: Certain variables other than an encoded feature they belong to do work for discrimination between different types of proteins. In addition, ensemble classifiers with an automatic assignment of different base classifiers do achieve a better classification result.

Download Full-text

Variable selection from a feature representing protein sequences: a case of classification on bacterial type IV secreted effectors

BMC Bioinformatics ◽

10.1186/s12859-020-03826-6 ◽

2020 ◽

Vol 21 (1) ◽

Author(s):

Jian Zhang ◽

Lixin Lv ◽

Donglei Lu ◽

Denan Kong ◽

Mohammed Abdoh Ali Al-Alashaari ◽

...

Keyword(s):

Variable Selection ◽

Protein Sequences ◽

Biological Research ◽

Protein Classification ◽

Ensemble Classifiers ◽

Type Iv ◽

Protein Prediction ◽

Kernel Set ◽

Bacterial Type

Abstract Background Classification of certain proteins with specific functions is momentous for biological research. Encoding approaches of protein sequences for feature extraction play an important role in protein classification. Many computational methods (namely classifiers) are used for classification on protein sequences according to various encoding approaches. Commonly, protein sequences keep certain labels corresponding to different categories of biological functions (e.g., bacterial type IV secreted effectors or not), which makes protein prediction a fantasy. As to protein prediction, a kernel set of protein sequences keeping certain labels certified by biological experiments should be existent in advance. However, it has been hardly ever seen in prevailing researches. Therefore, unsupervised learning rather than supervised learning (e.g. classification) should be considered. As to protein classification, various classifiers may help to evaluate the effectiveness of different encoding approaches. Besides, variable selection from an encoded feature representing protein sequences is an important issue that also needs to be considered. Results Focusing on the latter problem, we propose a new method for variable selection from an encoded feature representing protein sequences. Taking a benchmark dataset containing 1947 protein sequences as a case, experiments are made to identify bacterial type IV secreted effectors (T4SE) from protein sequences, which are composed of 399 T4SE and 1548 non-T4SE. Comparable and quantified results are obtained only using certain components of the encoded feature, i.e., position-specific scoring matix, and that indicates the effectiveness of our method. Conclusions Certain variables other than an encoded feature they belong to do work for discrimination between different types of proteins. In addition, ensemble classifiers with an automatic assignment of different base classifiers do achieve a better classification result.

Download Full-text

Faculty Opinions recommendation of Definition of a bacterial type IV secretion pathway for a DNA substrate.

Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature ◽

10.3410/f.1019206.216470 ◽

2004 ◽

Author(s):

Tracy Palmer

Keyword(s):

Type Iv Secretion ◽

Secretion Pathway ◽

Type Iv ◽

Definition Of ◽

Dna Substrate ◽

Bacterial Type

Download Full-text

Two type IV secretion systems with different functions in Burkholderia cenocepacia K56-2

Microbiology ◽

10.1099/mic.0.033043-0 ◽

2009 ◽

Vol 155 (12) ◽

pp. 4005-4013 ◽

Cited By ~ 13

Author(s):

Ruifu Zhang ◽

John J. LiPuma ◽

Carlos F. Gonzalez

Keyword(s):

Type Iv Secretion ◽

Burkholderia Cenocepacia ◽

Target Cells ◽

Secretion Systems ◽

Type Iv ◽

Plasmid Mobilization ◽

Type Iv Secretion Systems ◽

Derivative Plasmid ◽

Chromosome Ii ◽

Bacterial Type

Bacterial type IV secretion systems (T4SS) perform two fundamental functions related to pathogenesis: the delivery of effector molecules to eukaryotic target cells, and genetic exchange. Two T4SSs have been identified in Burkholderia cenocepacia K56-2, a representative of the ET12 lineage of the B. cepacia complex (Bcc). The plant tissue watersoaking (Ptw) T4SS encoded on a resident 92 kb plasmid is a chimera composed of VirB/D4 and F-specific subunits, and is responsible for the translocation of effector(s) that have been linked to the Ptw phenotype. The bc-VirB/D4 system located on chromosome II displays homology to the VirB/D4 T4SS of Agrobacterium tumefaciens. In contrast to the Ptw T4SS, the bc-VirB/D4 T4SS was found to be dispensable for Ptw effector(s) secretion, but was found to be involved in plasmid mobilization. The fertility inhibitor Osa did not affect the secretion of Ptw effector(s) via the Ptw system, but did disrupt the mobilization of a RSF1010 derivative plasmid.

Download Full-text

Disarming Bacterial Type IV Secretion

Chemistry & Biology ◽

10.1016/j.chembiol.2012.08.002 ◽

2012 ◽

Vol 19 (8) ◽

pp. 934-936 ◽

Cited By ~ 3

Author(s):

Todd A. Cameron ◽

Patricia C. Zambryski

Keyword(s):

Type Iv Secretion ◽

Type Iv ◽

Bacterial Type

Download Full-text

Assembly and function of the archaeal flagellum

Biochemical Society Transactions ◽

10.1042/bst0390064 ◽

2011 ◽

Vol 39 (1) ◽

pp. 64-69 ◽

Cited By ~ 48

Author(s):

Abhrajyoti Ghosh ◽

Sonja-Verena Albers

Keyword(s):

Evolutionary Relationship ◽

Type Iv Pili ◽

Assembly Systems ◽

Sequence Information ◽

Type Iv ◽

Core Proteins ◽

Domains Of Life ◽

Interaction Map ◽

Archaeal Flagellum ◽

Bacterial Type

Motility is a common behaviour in prokaryotes. Both bacteria and archaea use flagella for swimming motility, but it has been well documented that structures of the flagellum from these two domains of life are completely different, although they contribute to a similar function. Interestingly, information available to date has revealed that structurally archaeal flagella are more similar to bacterial type IV pili rather than to bacterial flagella. With the increasing genome sequence information and advancement in genetic tools for archaea, identification of the components involved in the assembly of the archaeal flagellum is possible. A subset of these components shows similarities to components from type IV pilus-assembly systems. Whereas the molecular players involved in assembly of the archaeal flagellum are being identified, the mechanics and dynamics of the assembly of the archaeal flagellum have yet to be established. Recent computational analysis in our laboratory has identified conserved highly charged loop regions within one of the core proteins of the flagellum, the membrane integral protein FlaJ, and predicted that these are involved in the interaction with the assembly ATPase FlaI. Interestingly, considerable variation was found among the loops of FlaJ from the two major subkingdoms of archaea, the Euryarchaeota and the Crenarchaeota. Understanding the assembly pathway and creating an interaction map of the molecular players in the archaeal flagellum will shed light on the details of the assembly and also the evolutionary relationship to the bacterial type IV pili-assembly systems.

Download Full-text