CoChat
Sign Up
PreprintCited by 14Biomedical Text Mining and OntologiesGenomics and Phylogenetic StudiesResearch Data Management Practices

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

A machine learning framework for discovery and enrichment of metagenomics metadata from open access publications

Open access
Nassar, Maaly, Rogers, Alexander B., Talo', Francesco, Sanchez, Santiago, Shafique, Zunaira, Finn, Robert D., McEntyre, Johanna·2022·GigaScience
DOI 10.21203/rs.3.rs-1396476/v1PMC PMC9366992

Preprint — published as 10.1093/gigascience/giac077 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Metagenomics is a culture-independent method for studying the microbes inhabiting a particular environment. Comparing the composition of samples (functionally/taxonomically), either from a longitudinal study or cross-sectional studies can provide clues into how the microbiota has adapted to the environment. However, a recurring challenge, especially when comparing results between independent studies, is that key metadata about the sample and molecular methods used to extract and sequence the genetic material are often missing from sequence records, making it difficult to account for confounding factors. Nevertheless, this missing metadata may be found in the narrative of publications describing the research. Here, we describe a machine learning framework that automatically extracts essential metadata for a wide range of metagenomics studies from the literature contained in Europe PMC. This framework has enabled the extraction of metadata from 114,099 publications in Europe PMC, including 19,900 publications describing metagenomics studies in ENA and MGnify.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.21203/rs.3.rs-1396476/v1

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1: Receiver operating characteristic (ROC) curves of biome classifiers, using TF-IDF (A) or Doc2VecMGnify (B) as training features.
Figure 1: Receiver operating characteristic (ROC) curves of biome classifiers, using TF-IDF (A) or Doc2VecMGnify (B) as training features.CC BY · PubMed Central
Figure 2: Screenshot of Europe PMC article. Annotations panel with metagenomics entities and annotations (right). Highlighted annotations in full-text using SciLite tool (left) (SciLite article view from PMC8791192).
Figure 2: Screenshot of Europe PMC article. Annotations panel with metagenomics entities and annotations (right). Highlighted annotations in full-text using SciLite tool (left) (SciLite article view from PMC8791192).CC BY · PubMed Central
Figure 3: Composite screenshot showing annotations-enriched metadata for a MGnify study. Annotated publications are highlighted within a study (left) and annotations are shown in context (right).
Figure 3: Composite screenshot showing annotations-enriched metadata for a MGnify study. Annotated publications are highlighted within a study (left) and annotations are shown in context (right).CC BY · PubMed Central
Figure 4: A clustered stacked bar plot showing the overlap of metadata terms between ENA (author submitted terms that are part of the study) and those derived from Europe PMC (EPMC) articles using our framework. For each study, we have evaluated 20 of the most populated MIxS fields in 19,209 studies, to establish if the metadata provided by both sources were identical (green), nonidentical (yellow), or provided by one of the metadata sources only (unique, red). For each MIxS field, each stacked bar shows the number of studies having identical, nonidentical, and unique metadata from each source.
Figure 4: A clustered stacked bar plot showing the overlap of metadata terms between ENA (author submitted terms that are part of the study) and those derived from Europe PMC (EPMC) articles using our framework. For each study, we have evaluated 20 of the most populated MIxS fields in 19,209 studies, to establish if the metadata provided by both sources were identical (green), nonidentical (yellow), or provided by one of the metadata sources only (unique, red). For each MIxS field, each stacked bar shows the number of studies having identical, nonidentical, and unique metadata from each source.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Metadata

Authors
Nassar, M., Rogers, A. B., Talo', F., Sanchez, S., Shafique, Z., Finn, R. D., & McEntyre, J.
Affiliations
  • European Bioinformatics Institute (GB)
  • EMBL's European Bioinformatics Institute (EMBL-EBI)
Corresponding author
McEntyre, Johanna
ORCID
Venue
GigaScience
Publisher
Springer Science and Business Media LLC
Published
2022-02-25
Volume
11
ISSN
2047-217X (ISSN-L)
DOI
10.21203/rs.3.rs-1396476/v1
PMC
PMC9366992
OpenAlex
W4291017647
Cited by
14
References
1
Citations by year
2026: 1 · 2025: 5 · 2024: 2 · 2023: 4 · 2022: 2
FWCI
1.06
Type
journal article
Language
en
Open access
Licence
Locations
  • GigaScience (publishedVersion, cc-by)
  • Research Square (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
  • Wellcome Trust (221523)
  • European Bioinformatics Institute (221523)
  • Directorate for Biological Sciences
  • Biotechnology and Biological Sciences Research Council (BB/S009043/1)
Topics
  • Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Physical Sciences › Computer Science › Information Systems › Research Data Management Practices
Keywords
machine learning, open access publications, Europe PMC, MGnify, European Nucleotide Archive, metadata enrichment, confounding factors
MeSH terms
Machine Learning, Metadata, Cross-Sectional Studies, Longitudinal Studies, Access to Information, Metagenomics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review