Microbial phenomics information extractor (MicroPIE): A natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources

Jin Mao, Lisa R. Moore, Carrine E. Blank, Elvis Hsin Hui Wu, Marcia Ackerman, Sonali Ranade, Hong Cui

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: The large-scale analysis of phenomic data (i.e., full phenotypic traits of an organism, such as shape, metabolic substrates, and growth conditions) in microbial bioinformatics has been hampered by the lack of tools to rapidly and accurately extract phenotypic data from existing legacy text in the field of microbiology. To quickly obtain knowledge on the distribution and evolution of microbial traits, an information extraction system needed to be developed to extract phenotypic characters from large numbers of taxonomic descriptions so they can be used as input to existing phylogenetic analysis software packages. Results: We report the development and evaluation of Microbial Phenomics Information Extractor (MicroPIE, version 0.1.0). MicroPIE is a natural language processing application that uses a robust supervised classification algorithm (Support Vector Machine) to identify characters from sentences in prokaryotic taxonomic descriptions, followed by a combination of algorithms applying linguistic rules with groups of known terms to extract characters as well as character states. The input to MicroPIE is a set of taxonomic descriptions (clean text). The output is a taxon-by-character matrix-with taxa in the rows and a set of 42 pre-defined characters (e.g., optimum growth temperature) in the columns. The performance of MicroPIE was evaluated against a gold standard matrix and another student-made matrix. Results show that, compared to the gold standard, MicroPIE extracted 21 characters (50%) with a Relaxed F1 score > 0.80 and 16 characters (38%) with Relaxed F1 scores ranging between 0.50 and 0.80. Inclusion of a character prediction component (SVM) improved the overall performance of MicroPIE, notably the precision. Evaluated against the same gold standard, MicroPIE performed significantly better than the undergraduate students. Conclusion: MicroPIE is a promising new tool for the rapid and efficient extraction of phenotypic character information from prokaryotic taxonomic descriptions. However, further development, including incorporation of ontologies, will be necessary to improve the performance of the extraction for some character types.

Original languageEnglish (US)
Article number528
JournalBMC Bioinformatics
Volume17
Issue number1
DOIs
StatePublished - Dec 13 2016

Fingerprint

Natural Language Processing
Extractor
Natural Language
Processing
Students
Microbiology
Information Storage and Retrieval
Growth temperature
Bioinformatics
Linguistics
Growth
Computational Biology
Information Systems
Software packages
Support vector machines
Ontology
Gold
Software
Temperature
Substrates

Keywords

  • Algorithm evaluation
  • Character matrices
  • Information extraction
  • Machine learning
  • Microbial phenotypes
  • Natural language processing
  • Phenotypic data extraction
  • Prokaryotic taxonomic descriptions
  • Support vector machine
  • Text mining

ASJC Scopus subject areas

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

Microbial phenomics information extractor (MicroPIE) : A natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources. / Mao, Jin; Moore, Lisa R.; Blank, Carrine E.; Wu, Elvis Hsin Hui; Ackerman, Marcia; Ranade, Sonali; Cui, Hong.

In: BMC Bioinformatics, Vol. 17, No. 1, 528, 13.12.2016.

Research output: Contribution to journalArticle

Mao, Jin ; Moore, Lisa R. ; Blank, Carrine E. ; Wu, Elvis Hsin Hui ; Ackerman, Marcia ; Ranade, Sonali ; Cui, Hong. / Microbial phenomics information extractor (MicroPIE) : A natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources. In: BMC Bioinformatics. 2016 ; Vol. 17, No. 1.
@article{a1eb874a77114beb841db89adfa9b2cf,
title = "Microbial phenomics information extractor (MicroPIE): A natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources",
abstract = "Background: The large-scale analysis of phenomic data (i.e., full phenotypic traits of an organism, such as shape, metabolic substrates, and growth conditions) in microbial bioinformatics has been hampered by the lack of tools to rapidly and accurately extract phenotypic data from existing legacy text in the field of microbiology. To quickly obtain knowledge on the distribution and evolution of microbial traits, an information extraction system needed to be developed to extract phenotypic characters from large numbers of taxonomic descriptions so they can be used as input to existing phylogenetic analysis software packages. Results: We report the development and evaluation of Microbial Phenomics Information Extractor (MicroPIE, version 0.1.0). MicroPIE is a natural language processing application that uses a robust supervised classification algorithm (Support Vector Machine) to identify characters from sentences in prokaryotic taxonomic descriptions, followed by a combination of algorithms applying linguistic rules with groups of known terms to extract characters as well as character states. The input to MicroPIE is a set of taxonomic descriptions (clean text). The output is a taxon-by-character matrix-with taxa in the rows and a set of 42 pre-defined characters (e.g., optimum growth temperature) in the columns. The performance of MicroPIE was evaluated against a gold standard matrix and another student-made matrix. Results show that, compared to the gold standard, MicroPIE extracted 21 characters (50{\%}) with a Relaxed F1 score > 0.80 and 16 characters (38{\%}) with Relaxed F1 scores ranging between 0.50 and 0.80. Inclusion of a character prediction component (SVM) improved the overall performance of MicroPIE, notably the precision. Evaluated against the same gold standard, MicroPIE performed significantly better than the undergraduate students. Conclusion: MicroPIE is a promising new tool for the rapid and efficient extraction of phenotypic character information from prokaryotic taxonomic descriptions. However, further development, including incorporation of ontologies, will be necessary to improve the performance of the extraction for some character types.",
keywords = "Algorithm evaluation, Character matrices, Information extraction, Machine learning, Microbial phenotypes, Natural language processing, Phenotypic data extraction, Prokaryotic taxonomic descriptions, Support vector machine, Text mining",
author = "Jin Mao and Moore, {Lisa R.} and Blank, {Carrine E.} and Wu, {Elvis Hsin Hui} and Marcia Ackerman and Sonali Ranade and Hong Cui",
year = "2016",
month = "12",
day = "13",
doi = "10.1186/s12859-016-1396-8",
language = "English (US)",
volume = "17",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Microbial phenomics information extractor (MicroPIE)

T2 - A natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources

AU - Mao, Jin

AU - Moore, Lisa R.

AU - Blank, Carrine E.

AU - Wu, Elvis Hsin Hui

AU - Ackerman, Marcia

AU - Ranade, Sonali

AU - Cui, Hong

PY - 2016/12/13

Y1 - 2016/12/13

N2 - Background: The large-scale analysis of phenomic data (i.e., full phenotypic traits of an organism, such as shape, metabolic substrates, and growth conditions) in microbial bioinformatics has been hampered by the lack of tools to rapidly and accurately extract phenotypic data from existing legacy text in the field of microbiology. To quickly obtain knowledge on the distribution and evolution of microbial traits, an information extraction system needed to be developed to extract phenotypic characters from large numbers of taxonomic descriptions so they can be used as input to existing phylogenetic analysis software packages. Results: We report the development and evaluation of Microbial Phenomics Information Extractor (MicroPIE, version 0.1.0). MicroPIE is a natural language processing application that uses a robust supervised classification algorithm (Support Vector Machine) to identify characters from sentences in prokaryotic taxonomic descriptions, followed by a combination of algorithms applying linguistic rules with groups of known terms to extract characters as well as character states. The input to MicroPIE is a set of taxonomic descriptions (clean text). The output is a taxon-by-character matrix-with taxa in the rows and a set of 42 pre-defined characters (e.g., optimum growth temperature) in the columns. The performance of MicroPIE was evaluated against a gold standard matrix and another student-made matrix. Results show that, compared to the gold standard, MicroPIE extracted 21 characters (50%) with a Relaxed F1 score > 0.80 and 16 characters (38%) with Relaxed F1 scores ranging between 0.50 and 0.80. Inclusion of a character prediction component (SVM) improved the overall performance of MicroPIE, notably the precision. Evaluated against the same gold standard, MicroPIE performed significantly better than the undergraduate students. Conclusion: MicroPIE is a promising new tool for the rapid and efficient extraction of phenotypic character information from prokaryotic taxonomic descriptions. However, further development, including incorporation of ontologies, will be necessary to improve the performance of the extraction for some character types.

AB - Background: The large-scale analysis of phenomic data (i.e., full phenotypic traits of an organism, such as shape, metabolic substrates, and growth conditions) in microbial bioinformatics has been hampered by the lack of tools to rapidly and accurately extract phenotypic data from existing legacy text in the field of microbiology. To quickly obtain knowledge on the distribution and evolution of microbial traits, an information extraction system needed to be developed to extract phenotypic characters from large numbers of taxonomic descriptions so they can be used as input to existing phylogenetic analysis software packages. Results: We report the development and evaluation of Microbial Phenomics Information Extractor (MicroPIE, version 0.1.0). MicroPIE is a natural language processing application that uses a robust supervised classification algorithm (Support Vector Machine) to identify characters from sentences in prokaryotic taxonomic descriptions, followed by a combination of algorithms applying linguistic rules with groups of known terms to extract characters as well as character states. The input to MicroPIE is a set of taxonomic descriptions (clean text). The output is a taxon-by-character matrix-with taxa in the rows and a set of 42 pre-defined characters (e.g., optimum growth temperature) in the columns. The performance of MicroPIE was evaluated against a gold standard matrix and another student-made matrix. Results show that, compared to the gold standard, MicroPIE extracted 21 characters (50%) with a Relaxed F1 score > 0.80 and 16 characters (38%) with Relaxed F1 scores ranging between 0.50 and 0.80. Inclusion of a character prediction component (SVM) improved the overall performance of MicroPIE, notably the precision. Evaluated against the same gold standard, MicroPIE performed significantly better than the undergraduate students. Conclusion: MicroPIE is a promising new tool for the rapid and efficient extraction of phenotypic character information from prokaryotic taxonomic descriptions. However, further development, including incorporation of ontologies, will be necessary to improve the performance of the extraction for some character types.

KW - Algorithm evaluation

KW - Character matrices

KW - Information extraction

KW - Machine learning

KW - Microbial phenotypes

KW - Natural language processing

KW - Phenotypic data extraction

KW - Prokaryotic taxonomic descriptions

KW - Support vector machine

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85003475345&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85003475345&partnerID=8YFLogxK

U2 - 10.1186/s12859-016-1396-8

DO - 10.1186/s12859-016-1396-8

M3 - Article

C2 - 27955641

AN - SCOPUS:85003475345

VL - 17

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 528

ER -