Named Entity Recognition for Bacterial Type IV Secretion Systems

Abstract

Research on specialized biological systems is often hampered by a lack of consistent terminology, especially across species. In bacterial Type IV secretion systems genes within one set of orthologs may have over a dozen different names. Classifying research publications based on biological processes, cellular components, molecular functions, and microorganism species should improve the precision and recall of literature searches allowing researchers to keep up with the exponentially growing literature, through resources such as the Pathosystems Resource Integration Center (PATRIC, patricbrc.org). We developed named entity recognition (NER) tools for four entities related to Type IV secretion systems: 1) bacteria names, 2) biological processes, 3) molecular functions, and 4) cellular components. These four entities are important to pathogenesis and virulence research but have received less attention than other entities, e.g., genes and proteins. Based on an annotated corpus, large domain terminological resources, and machine learning techniques, we developed recognizers for these entities. High accuracy rates (>80%) are achieved for bacteria, biological processes, and molecular function. Contrastive experiments highlighted the effectiveness of alternate recognition strategies; results of term extraction on contrasting document sets demonstrated the utility of these classes for identifying T4SS-related documents.

The expanding bacterial type IV secretion lexicon

“…To curate the available information and for high-throughput prospecting for new T4SSs, various web-based algorithms have been described. We list some here for the interested reader: i) Named entity recognition for bacterial T4SSs (http://www.nactem.ac.uk/T4SS_NER/top.py, http://patricbrc.vbi.vt.edu/portal/partic/NACTEM) (Ananiadou et al, 2011), ii) AtlasT4SS (htt://www.t4ss.lncc.br), a curated database for T4SSs (Souza et al, 2012), iii) MobilomeFINDER (http://mml.sjtu.edu.cn/MobilomeFINDER), for identification of bacterial genomic islands (Ou et al, 2007), iv) A T4SS identification program (http://t4ss.bioinfoicdc.org/), (Zhang et al, 2012) v) (http://www.tau.ac.il/~tlap/LegionellaMachineLearning), a machine learning approach for genome-scale identification of L. pneumophila effectors (Burstein et al, 2009), and vi) identification of Anaplasma marginale T4SS effectors (Lockwood et al, 2011). …”

Secretome of obligate intracellularRickettsia

“…Despite the extensive diversity (in gene composition and organization) that underlies the hundreds of known T4SSs (Alvarez-Martinez & Christie, 2009) , as well as tremendous ambiguity in annotation of T4SS genes (Ananiadou et al ., 2011) , T4SSs have been primarily classified into four groups: F, P, I, and GI (Juhas et al ., 2008) . The widespread F-T4SSs and P-T4SSs are defined by the archetypes encoded by the F plasmid of E .…”

“…GI-T4SSs are distinct systems that function in the transfer of genomic islands with which they are associated (Juhas et al ., 2007, Juhas et al ., 2008) . The number of genes encoding analogous components between different groups is minimal (Ananiadou et al ., 2011) , with one IM/cytosolic ATPase (VirB4 family) ubiquitous across all groups (Alvarez-Martinez & Christie, 2009) . A recent phylogenetics-based classification scheme utilizing the VirB4 family proteins proposed an additional four groups, encompassing the diverse T4SSs encoded within genomes from Cyanobacteria, Bacteroidetes, Firmicutes, Actinobacteria, Tenericutes, and Archaea (Guglielmini et al ., 2013) .…”

Agrobacterium-Mediated Transformation

“…T-DNA integration followed by transgene expression is the final and crucial stage in the genetic transformation mediated by Agrobacterium. The molecular T-complex traveling, modified from [38].…”