FREYA WP2 User Story 9	As a bibliometrician, I want to know all the co-authors of a particular researcher, so that I can do a network analysis of the researcher's collaborations.

A number of useful analyses are made possible by identifying co-authorship groups of a given researcher, for example identifying other active scientists in the researcher's field of study, or groups of closely collaborating (and often co-funded) author affiliations.

This notebook uses the DataCite GraphQL API to retrieve all publications of Dr Sarah Teichmann.

Goal: By the end of this notebook, for a researcher of interest, you should be able to:

• Display an interactive sankey plot of the researcher's publication co-authors, e.g.
  
• Download a file containing their publication DOIs;
• Load the above file into VOSviewer and then construct and visualise the researcher's co-authorship network, following the steps listed in the notebook, e.g.
  

Install libraries and prepare GraphQL client

%%capture
# Install required Python packages
!pip install gql requests numpy plotly

# Prepare the GraphQL client
import requests
from IPython.display import display, Markdown
from gql import gql, Client
from gql.transport.requests import RequestsHTTPTransport

_transport = RequestsHTTPTransport(
    url='https://api.datacite.org/graphql',
    use_json=True,
)

client = Client(
    transport=_transport,
    fetch_schema_from_transport=True,
)

Define and run GraphQL query

Define the GraphQL query to find all publications including co-authors for Dr Sarah Teichmann:

# Generate the GraphQL query: find all publications, including co-authors or researcher id: "https://orcid.org/0000-0002-6294-6366"
query_params = {
    "researcherId" : "https://orcid.org/0000-0002-6294-6366",
    "maxWorks" : 300
}

query = gql("""query getResearcherPublication($researcherId: ID!, $maxWorks: Int!)
{
  person(id: $researcherId) {
    id
    name
    publications(first:$maxWorks) {
      totalCount
      published {
        title
        count
      }
      nodes {
        id
        type
        versionOfCount
        titles {
          title
        }
        creators {
          id
          name
        }
      }
    }
  }
}
""")

Run the above query via the GraphQL client

import json
data = client.execute(query, variable_values=json.dumps(query_params))

Display total number of publications by the researcher

Display the total number of the researcher's outputs to date.

# Get the total number of publication to date
publications = data['person']['publications']
display(Markdown(str(publications['totalCount'])))

95

Plot the researcher's publications co-authors

Display a sankey plot of the co-authors sharing at least two publications with the researcher, highlighting them by frequency of co-authorship.

import plotly.graph_objects as go
import plotly.io as pio
import plotly.express as px
from IPython.display import IFrame

# Retrieve creator names and ORCID ids from all publications
all_creator_ids = []
all_creator_ids_set = set([])
creator_id2name = {}
publications = data['person']['publications']
for r in publications['nodes']:
    if r['versionOfCount'] > 0:
        # If the current output is a version of another one, exclude it
        continue
    creator_ids = list(filter(None, [s['id'] for s in r['creators']]))
    all_creator_ids_set.update(creator_ids)
    all_creator_ids.append(creator_ids)
    for creator in r['creators']:
        if (creator['id'] not in creator_id2name and creator['id'] is not None):
            creator_id2name[creator['id']] = creator['name']
            
# Collect creator names into all_unique_creator_names - these will be labels in the sankey plot
# Initialise coauthorship_matrix, that will be used to populate lists needed for the sankey plot
all_unique_creator_ids = list(all_creator_ids_set)
length = len(all_unique_creator_ids)
coauthorship_matrix = []
all_unique_creator_names = []
for id in all_unique_creator_ids:
    all_unique_creator_names.append(creator_id2name[id])
    coauthorship_matrix.append([0] * length)
    
# Populate coauthorship_matrix
for cids in all_creator_ids:
    for cid in cids:
        c_pos = all_unique_creator_ids.index(cid)
        for cid in cids:
            co_pos = all_unique_creator_ids.index(cid)
            if c_pos != co_pos:
                coauthorship_matrix[c_pos][co_pos] += 1
                
# Use coauthorship_matrix to populate lists needed for the sankey diagram: sourceIndexes, targetIndexes and linkWeights
# For Plotly colour swatches, see: https://plotly.com/python/builtin-colorscales/
colRange = px.colors.sequential.matter;
maxColIndex = len(colRange)
sourceIndexes = []
targetIndexes = []
linkWeights = []
linkColours = []
for c_pos, r in enumerate(coauthorship_matrix):
    # On the left hand side of sankey retain only the researcher in question
    if all_unique_creator_ids[c_pos] != query_params['researcherId']:
        continue
    for co_pos, weight in enumerate(r):
            if coauthorship_matrix[c_pos][co_pos] > 1:
                # Include links to co-authors of at least 2 publications                 
                sourceIndexes.append(c_pos)
                targetIndexes.append(co_pos)
                linkWeights.append(weight)
                linkColours.append(colRange[min(maxColIndex, weight)])

# Create a sankey plot 
fig = go.Figure(data=[go.Sankey(
    node = dict(
      pad = 15,
      thickness = 20,
      line = dict(color = "black", width = 0.5),
      label = all_unique_creator_names,
      color = "rgba(136,65,157, 0.6)"
    ),
    link = dict(
      source = sourceIndexes, # indices correspond to labels in all_unique_creator_names
      target = targetIndexes, # ditto
      value = linkWeights,
      color = linkColours
  ))])

fig.update_layout(title_text="", font_size=10)
# Write interactive plot out to html file
# pio.write_html(fig, file='out.html')

# Display plot from the saved html file
display(Markdown("### [%s](%s)'s first degree co-authors:" % (creator_id2name[query_params['researcherId']], query_params['researcherId'])))
# IFrame(src="./out.html", width=1000, height=800)
fig.show()

Teichmann, Sarah's first degree co-authors:

Download a file containing publication DOIs

This file can be loaded into VOSviewer tool in order to construct and visualise the researcher's co-authorship network, using the following steps (see the image below):

1. Select File tab on the right, then click on Create button
2. In the Choose type of data window, select Create a map based on biobliographic data
3. In the Choose data source window, select Download data through API
4. In the Specify search query or select file select DOI tab, then API: Crossref, then in the DOI files text box type in or select the path to the file of DOIs you downloaded.
5. Click on Finish button to construct and display the network.

import pandas as pd
from IPython.display import Javascript
from requests.utils import requote_uri

# Collect publication DOIs so that it can be downloaded
dois = []
publications = data['person']['publications']
for n in publications['nodes']:
    if n['versionOfCount'] > 0:
        # If the current output is a version of another one, exclude it
        continue
    dois.append(n['id'])
df = pd.DataFrame(dois, columns = None)
file_name = "%s_dois.csv" % query_params['researcherId'].split("/")[-1]

js_download = """
var csv = '%s';

var filename = '%s';
var blob = new Blob([csv], { type: 'application/x-bibtex;charset=utf-8;' });
if (navigator.msSaveBlob) { // IE 10+
    navigator.msSaveBlob(blob, filename);
} else {
    var link = document.createElement("a");
    if (link.download !== undefined) { // feature detection
        // Browsers that support HTML5 download attribute
        var url = URL.createObjectURL(blob);
        link.setAttribute("href", url);
        link.setAttribute("download", filename);
        link.style.visibility = 'hidden';
        document.body.appendChild(link);
        link.click();
        document.body.removeChild(link);
    }
}
""" % (df.to_csv(index=False, header=False).replace('\n','\\n').replace("\'","\\'").replace("\"","").replace("\r",""), file_name)
    
# display(Javascript(js_download))

# This section contains an example of co-authorship network for Dr Sarah Teichmann's publications - hence the conditional logic below
if query_params['researcherId'] == "https://orcid.org/0000-0002-6294-6366":
    display(Markdown("""
## [Dr Sarah Teichmann](https://orcid.org/0000-0002-6294-6366)'s co-authorship network as shown in VOSviewer
Interestingly, the network (excluding publications with author lists longer than 25) shows clusters with at least three versions of the researcher's author name:
- Teichmann Sarah A.
- Teichmann Sarah A
- Teichmann Sarah
![VOSviewer Network](VOSviewer_network.png)
"""))

Dr Sarah Teichmann's co-authorship network as shown in VOSviewer

Interestingly, the network (excluding publications with author lists longer than 25) shows clusters with at least three versions of the researcher's author name:

• Teichmann Sarah A.
• Teichmann Sarah A
• Teichmann Sarah