POST /figure-legends

Get the raw text of a paper's figure legends, an annotation of the methodological details included in them (which might not exist in the methods section).

Input: DOI or a PDF of a scientific paper.

Request

Content-Type: multipart/form-data

Accepted keys: doi and file

JSON Body (if using DOI):

{
  "doi": "10.1038/s41592-020-01005-z"
}

JSON Body (if uploading a PDF):

file: "path_to_file.pdf"

Note: If both a doi and a file key are present in the request, the API uses the file key by default.

Response

{
  "doi": "10.3390/ijms22031484",
  "paper_input_type": "doi",
  "pdf_url": "https://europepmc.org/articles/pmc7867340?pdf=render",
  "pmcid": "PMC7867340",
  "figure_legends_text": [
      {
        "id": "Figure 1",
        "title": "Identification of a high-confidence IncRNA repertoire for vascular smooth muscle cells (VSMCs) in physiological and pathological states.",
        "body": "(a) Strategy to supplement GENCODE annotation with newly assembled transcripts and annotate IncRNAs. (b) Proportion of GENCODE and newly assembled IncRNA transcripts with structures matching FANTOM CAT annotation. (c) Proportion of GENCODE and newly assembled IncRNAs with a matching CAGE sequencing (CAGEseq) site in FANTOM CAT database. (d) Method to detect newly assembled IncRNAs in carotid plaque RNAseq. (e) Newly assembled IncRNAs derived from VSMC datasets detected in whole plaque tissue.",
        "full_legend_text": "Figure 1. Identification of a high-confidence IncRNA repertoire for vascular smooth muscle cells (VSMCs) in physiological and pathological states. (a) Strategy to supplement GENCODE annotation with newly assembled transcripts and annotate IncRNAs. (b) Proportion of GENCODE and newly assembled IncRNA transcripts with structures matching FANTOM CAT annotation. (c) Proportion of GENCODE and newly assembled IncRNAs with a matching CAGE sequencing (CAGEseq) site in FANTOM CAT database. (d) Method to detect newly assembled IncRNAs in carotid plaque RNAseq. (e) Newly assembled IncRNAs derived from VSMC datasets detected in whole plaque tissue."
      },
  ],
  "figure_legends_with_method_details": [
    {
      "id": "Figure 1",
      "title": "Identification of a high-confidence IncRNA repertoire for vascular smooth muscle cells (VSMCs) in physiological and pathological states.",
      "body": "(a) Strategy to supplement GENCODE annotation with newly assembled transcripts and annotate IncRNAs. (b) Proportion of GENCODE and newly assembled IncRNA transcripts with structures matching FANTOM CAT annotation. (c) Proportion of GENCODE and newly assembled IncRNAs with a matching CAGE sequencing (CAGEseq) site in FANTOM CAT database. (d) Method to detect newly assembled IncRNAs in carotid plaque RNAseq. (e) Newly assembled IncRNAs derived from VSMC datasets detected in whole plaque tissue.",
      "full_legend_text": "Figure 1. Identification of a high-confidence IncRNA repertoire for vascular smooth muscle cells (VSMCs) in physiological and pathological states. (a) Strategy to supplement GENCODE annotation with newly assembled transcripts and annotate IncRNAs. (b) Proportion of GENCODE and newly assembled IncRNA transcripts with structures matching FANTOM CAT annotation. (c) Proportion of GENCODE and newly assembled IncRNAs with a matching CAGE sequencing (CAGEseq) site in FANTOM CAT database. (d) Method to detect newly assembled IncRNAs in carotid plaque RNAseq. (e) Newly assembled IncRNAs derived from VSMC datasets detected in whole plaque tissue.",
      "method_details": [
        {
          "category": "DataProcessing",
          "methodological_item_name": "GENCODE Annotation Supplementation",
          "description": "GENCODE annotation was supplemented with newly assembled transcripts."
        },
        {
          "category": "DataProcessing",
          "methodological_item_name": "LncRNA Annotation",
          "description": "Annotation of IncRNAs (long non-coding RNAs) was performed."
        },
        {
          "category": "Procedure",
          "methodological_item_name": "Transcript Assembly",
          "description": "Process used to assemble new transcripts (implied by 'newly assembled transcripts')."
        },
        {
          "category": "DataAnalysis",
          "methodological_item_name": "Transcript Structure Matching",
          "description": "Structures of GENCODE and newly assembled IncRNA transcripts were matched against FANTOM CAT annotation."
        },
        {
          "category": "ResourceUsed",
          "methodological_item_name": "FANTOM CAT Annotation/Database",
          "description": "Used as a reference for matching transcript structures and CAGE sequencing sites."
        },
        {
          "category": "ExperimentalTechnique",
          "methodological_item_name": "CAGE Sequencing (CAGEseq)",
          "description": "Data from CAGE sequencing (CAGEseq) was used (specifically CAGE sites from FANTOM CAT database) for validation."
        },
        {
          "category": "DataAnalysis",
          "methodological_item_name": "LncRNA Detection Method",
          "description": "A specific method was used to detect newly assembled lncRNAs in specific samples."
        },
        {
          "category": "DataFormat",
          "methodological_item_name": "RNA Sequencing (RNAseq) Data",
          "description": "Data type used for detection of newly assembled lncRNAs."
        },
        {
          "category": "DataSource/Sample",
          "methodological_item_name": "Carotid Plaque Tissue Samples",
          "description": "Sample source for detection of newly assembled lncRNAs."
        },
        {
          "category": "DataSource/Sample",
          "methodological_item_name": "Source of Input Data for Assembly/Identification",
          "description": "Newly assembled lncRNAs were derived from VSMC datasets."
        }
      }
    ]
  },
  {
    // additional figures if they exist
  }
}