The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text

Publication type:
Journal article
Metadata:
Autoren
  • Martin Krallinger
  • Miguel Vazquez
  • Florian Leitner
  • David Salgado
  • Andrew Chatr-aryamontri
  • Andrew Winter
  • Livia Perfetto
  • Leonardo Briganti
  • Luana Licata
  • Marta Iannuccelli
  • Luisa Castagnoli
  • Gianni Cesareni
  • Mike Tyers
  • Gerold Schneider
  • Fabio Rinaldi
  • Robert Leaman
  • Graciela Gonzalez
  • Sergio Matos
  • Sun Kim
  • W John Wilbur
  • Luis Rocha
  • Hagit Shatkay
  • Ashish V Tendulkar
  • Shashank Agarwal
  • Feifan Liu
  • Xinglong Wang
  • Rafal Rak
  • Keith Noto
  • Charles Elkan
  • Zhiyong Lu
  • Rezarta Islamaj Dogan
  • Jean-Fred Fontaine
  • Miguel A Andrade-Navarro
  • Alfonso Valencia
Autoren-URL
https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000303932700003&DestLinkType=FullRecord&DestApp=WOS_CPL
DOI
10.1186/1471-2105-12-S8-S3
Externe Identifier
  • Clarivate Analytics Document Solution ID: 940ZX
  • PubMed Identifier: 22151929
ISSN
1471-2105
Zeitschrift
BMC BIOINFORMATICS
Artikelnummer
ARTN S3
Datum der Veröffentlichung
2011
Status
Published
Titel
The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text
Sub types
  • Article
Ausgabe der Zeitschrift
12

Data source: Web of Science (Lite)

Other metadata sources:
Autoren
  • Martin Krallinger
  • Miguel Vazquez
  • Florian Leitner
  • David Salgado
  • Andrew Chatr-aryamontri
  • Andrew Winter
  • Livia Perfetto
  • Leonardo Briganti
  • Luana Licata
  • Marta Iannuccelli
  • Luisa Castagnoli
  • Gianni Cesareni
  • Mike Tyers
  • Gerold Schneider
  • Fabio Rinaldi
  • Robert Leaman
  • Graciela Gonzalez
  • Sergio Matos
  • Sun Kim
  • W John Wilbur
  • Luis Rocha
  • Hagit Shatkay
  • Ashish V Tendulkar
  • Shashank Agarwal
  • Feifan Liu
  • Xinglong Wang
  • Rafal Rak
  • Keith Noto
  • Charles Elkan
  • Zhiyong Lu
  • Rezarta Islamaj Dogan
  • Jean-Fred Fontaine
  • Miguel A Andrade-Navarro
  • Alfonso Valencia
DOI
10.1186/1471-2105-12-s8-s3
eISSN
1471-2105
Ausgabe der Veröffentlichung
S8
Zeitschrift
BMC Bioinformatics
Sprache
en
Artikelnummer
S3
Online publication date
2011
Datum der Veröffentlichung
2011
Status
Published
Herausgeber
Springer Science and Business Media LLC
Herausgeber URL
http://dx.doi.org/10.1186/1471-2105-12-s8-s3
Datum der Datenerfassung
2021
Titel
The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text
Ausgabe der Zeitschrift
12

Data source: Crossref

Abstract
<h4>Background</h4>Determining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them.<h4>Results</h4>A total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthew's Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%.<h4>Conclusions</h4>The results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.
Addresses
  • Structural Biology and BioComputing Programme, Spanish National Cancer Research Centre (CNIO), Madrid, Spain. mkrallinger@cnio.es
Autoren
  • Martin Krallinger
  • Miguel Vazquez
  • Florian Leitner
  • David Salgado
  • Andrew Chatr-Aryamontri
  • Andrew Winter
  • Livia Perfetto
  • Leonardo Briganti
  • Luana Licata
  • Marta Iannuccelli
  • Luisa Castagnoli
  • Gianni Cesareni
  • Mike Tyers
  • Gerold Schneider
  • Fabio Rinaldi
  • Robert Leaman
  • Graciela Gonzalez
  • Sergio Matos
  • Sun Kim
  • W John Wilbur
  • Luis Rocha
  • Hagit Shatkay
  • Ashish V Tendulkar
  • Shashank Agarwal
  • Feifan Liu
  • Xinglong Wang
  • Rafal Rak
  • Keith Noto
  • Charles Elkan
  • Zhiyong Lu
  • Rezarta Islamaj Dogan
  • Jean-Fred Fontaine
  • Miguel A Andrade-Navarro
  • Alfonso Valencia
DOI
10.1186/1471-2105-12-s8-s3
eISSN
1471-2105
Externe Identifier
  • PubMed Identifier: 22151929
  • PubMed Central ID: PMC3269938
Funding acknowledgements
  • Swiss National Science Foundation: 118396
  • Biotechnology and Biological Sciences Research Council: BB/G013160/1
  • Intramural NIH HHS:
  • NLM NIH HHS: 5R01LM009836
  • Telethon: GGP09243
  • Swiss National Science Foundation: 100014
  • NIH HHS: R01 OD010929
  • NLM NIH HHS: 5R01LM010125
  • NIGMS NIH HHS: R01 GM077402
Open access
true
ISSN
1471-2105
Zeitschrift
BMC bioinformatics
Schlüsselwörter
  • Animals
  • Humans
  • Proteins
  • Algorithms
  • PubMed
  • Databases, Protein
  • Periodicals as Topic
  • Data Mining
Sprache
eng
Medium
Electronic
Online publication date
2011
Open access status
Open Access
Paginierung
S3
Datum der Veröffentlichung
2011
Status
Published
Publisher licence
CC BY
Datum der Datenerfassung
2011
Titel
The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text.
Sub types
  • Research Support, N.I.H., Intramural
  • Research Support, Non-U.S. Gov't
  • research-article
  • Journal Article
  • Research Support, N.I.H., Extramural
Ausgabe der Zeitschrift
12 Suppl 8

Files

https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S8-S3 https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/22151929/pdf/?tool=EBI https://europepmc.org/articles/PMC3269938?pdf=render

Data source: Europe PubMed Central

Abstract
BACKGROUND: Determining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them. RESULTS: A total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthew's Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%. CONCLUSIONS: The results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.
Autoren
  • Martin Krallinger
  • Miguel Vazquez
  • Florian Leitner
  • David Salgado
  • Andrew Chatr-Aryamontri
  • Andrew Winter
  • Livia Perfetto
  • Leonardo Briganti
  • Luana Licata
  • Marta Iannuccelli
  • Luisa Castagnoli
  • Gianni Cesareni
  • Mike Tyers
  • Gerold Schneider
  • Fabio Rinaldi
  • Robert Leaman
  • Graciela Gonzalez
  • Sergio Matos
  • Sun Kim
  • W John Wilbur
  • Luis Rocha
  • Hagit Shatkay
  • Ashish V Tendulkar
  • Shashank Agarwal
  • Feifan Liu
  • Xinglong Wang
  • Rafal Rak
  • Keith Noto
  • Charles Elkan
  • Zhiyong Lu
  • Rezarta Islamaj Dogan
  • Jean-Fred Fontaine
  • Miguel A Andrade-Navarro
  • Alfonso Valencia
Autoren-URL
https://www.ncbi.nlm.nih.gov/pubmed/22151929
DOI
10.1186/1471-2105-12-S8-S3
eISSN
1471-2105
Externe Identifier
  • PubMed Central ID: PMC3269938
Funding acknowledgements
  • NIH HHS: R01 OD010929
  • NLM NIH HHS: 5R01LM009836
  • Telethon: GGP09243
  • NLM NIH HHS: 5R01LM010125
  • Biotechnology and Biological Sciences Research Council: BB/G013160/1
  • NIGMS NIH HHS: R01 GM077402
  • Intramural NIH HHS:
Ausgabe der Veröffentlichung
Suppl 8
Zeitschrift
BMC Bioinformatics
Schlüsselwörter
  • Algorithms
  • Animals
  • Data Mining
  • Databases, Protein
  • Humans
  • Periodicals as Topic
  • Proteins
  • PubMed
Sprache
eng
Country
England
Paginierung
S3
PII
1471-2105-12-S8-S3
Datum der Veröffentlichung
2011
Status
Published online
Datum, an dem der Datensatz öffentlich gemacht wurde
2012
Titel
The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text.
Sub types
  • Journal Article
  • Research Support, N.I.H., Extramural
  • Research Support, N.I.H., Intramural
  • Research Support, Non-U.S. Gov't
Ausgabe der Zeitschrift
12 Suppl 8

Data source: PubMed

Beziehungen:
Property of

Tools