diff --git a/input/input_fj.py b/input/input_fj.py
new file mode 100644
index 0000000000000000000000000000000000000000..00bb0126e2ae1abf6563bf99a16cc585b6d88077
--- /dev/null
+++ b/input/input_fj.py
@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+"""
+Functions for information retrieval of articles from the ACS journal JCIM
+
+"""
+
+__author__ = "Florian Jochens"
+__email__ = "fj@andaco.de"
+__status__ = "Production"
+#__copyright__ = ""
+#__credits__ = ["", "", "", ""]
+#__license__ = ""
+#__version__ = ""
+#__maintainer__ = ""
+
+from bs4 import BeautifulSoup as bs
+import requests as req
+import sys
+from pathlib import Path
+
+class Publication:
+ #_registry = []
+ _citations = []
+
+ def __init__(self, title, publication_date, contributors, doi_url,
+ subjects, num_citations):
+ #self._registry.append(self)
+ self.title = title
+ self.publication_date = publication_date
+ self.contributors = contributors
+ self.doi_url = doi_url
+ self.subjects = subjects
+ self.num_citations = num_citations
+
+class Citation:
+ def __init__(self, title, journal, contributors, doi_url):
+ self.title = title
+ self.journal = journal
+ self.contributors = contributors
+ self.doi_url = doi_url
+
+def get_article_info(soup):
+ header = soup.find('div', class_ = 'article_header-left pull-left')
+ article_title = header.find('span', class_ = 'hlFld-Title').text
+ publication_date = header.find('span', class_ = 'pub-date-value').text
+ for link in header.find('div', class_ = 'article_header-doiurl'):
+ doi_url = link.get('href')
+ subs = header.find('div', class_ = 'article_header-taxonomy')
+ subjects = []
+ for sub in subs.find_all('a'):
+ subjects.append(sub.get('title'))
+ cons = header.find('ul', class_ = 'loa')
+ contributors = []
+ for con in cons.find_all('span', class_ = 'hlFld-ContribAuthor'):
+ contributors.append(con.text)
+ numc = header.find('div', class_ = 'articleMetrics_count')
+ if not numc.a:
+ num_citations = 0
+ else:
+ num_citations = numc.a.text
+
+ pub = Publication(article_title, publication_date, contributors, doi_url,
+ subjects, num_citations)
+ return pub
+
+def get_download_url():
+ export = soup.find('div', class_ = 'cit-download-dropdown_content')
+ url = 'https://pubs.acs.org'
+ for link in export.find_all('a'):
+ if link.get('title') == 'Citation and references':
+ url += link.get('href')
+ print(url)
+ return url
+
+def download(url): # Download citation and references file
+ if url.find('='):
+ filename = url.rsplit('=', 1)[1]
+ path = Path(('./files/' + filename))
+ if path.is_file():
+ print("File already exists")
+ else:
+ print("File does not exist")
+
+def get_citation_info(pub, num_citations, soup):
+ pub._citations = []
+ details = soup.find('ol', class_ = 'cited-content_cbyCitation')
+ titles = []
+ for title in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-title'):
+ titles.append(title.text.replace('.', ''))
+ journal_names = []
+ for name in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_journal-name'):
+ journal_names.append(name.text)
+ doi_urls = []
+ for url in details.find_all('a'):
+ doi_urls.append(url.get('href'))
+ contributors = []
+ for contrib in details.find_all('span',
+ class_ = 'cited-content_cbyCitation_article-contributors'):
+ contributors.append(contrib.text)
+ for i in range(0, int(num_citations)):
+ pub._citations.append(Citation(titles[i], journal_names[i],
+ contributors[i], doi_urls[i]))
+def print_pub_info(pub):
+ print(f'''Article title: {pub.title}
+Publication date: {pub.publication_date}
+DOI-URL: {pub.doi_url}
+
+Subjects:''')
+ print(*(pub.subjects), sep = ", ")
+ print('\nContributors:')
+ print(*(pub.contributors), sep = ", ")
+
+ if int(pub.num_citations) > 0:
+ if int(pub.num_citations) == 1:
+ print(f'\nThis publication is cited by the following publication:\n')
+ else:
+ print(f'\nThis publication is cited by the following {pub.num_citations} publications:\n')
+ for citation in pub._citations:
+ print(f'''
+ Title: {citation.title}
+ Journal: {citation.journal}
+ Contributors: {citation.contributors}
+ DOI-URL: {citation.doi_url}
+ ''')
+ else:
+ print('\nThis publication is not cited by any other publication.')
+
+def input(url):
+ html_text = req.get(url).text
+ soup = bs(html_text, 'html.parser')
+
+ pub = get_article_info(soup)
+ if int(pub.num_citations) > 0:
+ get_citation_info(pub, int(pub.num_citations), soup)
+ return pub
+
+#if len(sys.argv) != 2:
+# sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+# exit(1)
+#url = sys.argv[1]
+#pub = input(url)
+#print_pub_info(pub)
diff --git a/verarbeitung/Processing.py b/verarbeitung/Processing.py
index bfa533a3161063b7ec82231cbc2c34950336eb11..cdde51f5842fe5351ee2ec83c3ceac89f250b3ee 100644
--- a/verarbeitung/Processing.py
+++ b/verarbeitung/Processing.py
@@ -1,10 +1,18 @@
# -*- coding: utf-8 -*-
"""
-Created on Wed Nov 3 16:54:43 2021
+Functions to generate a graph resembling citations between multiple JCIM ACS journals
-@author: Malte Schokolowski
"""
+__authors__ = "Donna Löding, Alina Molkentin, Xinyi Tang, Judith Große, Malte Schokolowski"
+__email__ = "cis-project2021@zbh.uni-hamburg.de"
+__status__ = "Production"
+#__copyright__ = ""
+#__credits__ = ["", "", "", ""]
+#__license__ = ""
+#__version__ = ""
+#__maintainer__ = ""
+
from bs4 import BeautifulSoup as bs
import requests as req
import sys
@@ -12,106 +20,124 @@ from pathlib import Path
from input_fj import input
from json_demo import output_to_json
+# adds every publication from input list to graph structure
+# doi_input_list: list of publication dois from user
-
-def process_main(doi_input_array, depth):
- # ERROR-Handling doi_array = NULL
- if (len(doi_input_array) == 0):
- print("Error, no input data")
-
- # ERROR- wenn für die Tiefe eine negative Zahl eingegeben wird
- if (depth < 0):
- print("Error, depth of search must be positive")
-
-
- # Leeres Array für die Knoten(nodes) wird erstellt.
- # Leeres Array für die Kanten(edges) wird erstellt.
- global nodes, edges
- nodes = []
- edges = []
-
- # Jede Publikation aus dem Input-Array wird in den Knoten-Array(nodes) eingefügt.
- for pub_doi in doi_input_array:
+# TO-DO: Listenelemente auf Korrektheit überprüfen
+def initialize_nodes_list(doi_input_list):
+ for pub_doi in doi_input_list:
pub = input(pub_doi)
not_in_nodes = True
- for node in nodes:
+ for node in nodes: # checks if a pub is already in nodes
if (pub.doi_url == node.doi_url):
not_in_nodes = False
break
if (not_in_nodes):
nodes.append(pub)
else:
- doi_input_array.remove(pub_doi)
+ doi_input_list.remove(pub_doi)
- process_rec_depth(doi_input_array, 0, depth)
- output_to_json(nodes,edges)
- return(nodes,edges)
+
+# adds a node for every publication
+# adds edges for citations between publications
+def create_graph_structure(pub, search_depth, search_depth_max):
+ for citation in pub._citations:
+ # Für jede citation, die in der entsprecheneden Klasseninstanz der Publikation gespeichert sind,
+ # wird geprüft, ob diese bereits als Knoten existiert.
+ # Wenn die citation noch nicht im Knoten-Array(nodes) existiert UND die maximale Tiefe
+ # noch nicht erreicht wurde, wird diese als Knoten im Knoten-Array gespeichert. Zusätzlich
+ # wird die Verbindung zur Publikation als Tupel im Kanten-Array(edges) gespeichert.
+ not_in_nodes = True
+ for node in nodes:
+ if (citation.doi_url == node.doi_url):
+ not_in_nodes = False
+ break
+ if (not_in_nodes):
+ if (search_depth <= search_depth_max):
+ nodes.append(citation)
+ edges.append([pub.doi_url,citation.doi_url])
+
+ # Wenn die citaion bereits im Knoten-Array existiert, wird nur die Verbindung zur Publikation
+ # als Tupel im Kanten-Array(edges) gespeichert.
+ else:
+ edges.append([pub.doi_url,citation.doi_url])
-def process_rec_depth(array, depth, depth_max):
+# recursive function to implement depth-first-search on citations
+# doi_list: input list of dois
+# search_depth: current search_depth of dfs
+# search_depth_max: maximal search_depth for search_depth-first-search
+def process_rec(doi_list, search_depth, search_depth_max):
# Die Tiefe wird bei jedem rekursiven Aufruf um 1 erhöht.
- depth += 1
+ search_depth += 1
# Für jede Publikation im Input-Array wird ein Klassenobjekt erstellt.
- for pub_doi in array:
+ for pub_doi in doi_list:
pub = input(pub_doi)
-
- # Für jede citation, die in der entsprecheneden Klasseninstanz der Publikation gespeichert sind,
- # wird geprüft, ob diese bereits als Knoten existiert.
- for citation in pub._citations:
-
- # Wenn die citation noch nicht im Knoten-Array(nodes) existiert UND die maximale Tiefe
- # noch nicht erreicht wurde, wird diese als Knoten im Knoten-Array gespeichert. Zusätzlich
- # wird die Verbindung zur Publikation als Tupel im Kanten-Array(edges) gespeichert.
- not_in_nodes = True
- for node in nodes:
- if (citation.doi_url == node.doi_url):
- not_in_nodes = False
- break
- if (not_in_nodes):
- if (depth <= depth_max):
- nodes.append(citation)
- edges.append([pub.doi_url,citation.doi_url])
-
- # Wenn die citaion bereits im Knoten-Array existiert, wird nur die Verbindung zur Publikation
- # als Tupel im Kanten-Array(edges) gespeichert.
- else:
- edges.append([pub.doi_url,citation.doi_url])
-
+ create_graph_structure(pub, search_depth, search_depth_max)
# Wenn die maximale Tiefe noch nicht erreicht wurde, werden alle citations aus der Publikation
# in ein Array geschrieben und mit diesem die Funktion erneut aufgerufen.
- if (depth < depth_max):
- cit_arr = []
+ if (search_depth < search_depth_max):
+ cit_list = []
for citation in pub._citations:
# Momentan werden nur die citations mit acs in der URL gespeichert, da wir von anderen
# Quellen die Infotmationen nicht extrahieren können.
if ("acs" in citation.doi_url):
- cit_arr.append(citation.doi_url)
+ cit_list.append(citation.doi_url)
+
+ # Rekursiver Aufruf der Funktion.
+ process_rec(cit_list, search_depth, search_depth_max)
+
+
+
+
+def process_main(doi_input_list, search_depth):
+ # ERROR-Handling doi_array = NULL
+ if (len(doi_input_list) == 0):
+ print("Error, no input data")
+
+ # ERROR- wenn für die Tiefe eine negative Zahl eingegeben wird
+ if (search_depth < 0):
+ print("Error, search_depth of search must be positive")
+
+
+ # Leeres Array für die Knoten(nodes) wird erstellt.
+ # Leeres Array für die Kanten(edges) wird erstellt.
+ global nodes, edges
+ nodes = []
+ edges = []
+
+ initialize_nodes_list(doi_input_list)
+ process_rec(doi_input_list, 0, search_depth)
+
+ output_to_json(nodes,edges)
+
+ # Nur fürs interne testen
+ return(nodes,edges)
+
- # Rekusriver Aufruf der Funktion.
- process_rec_depth(cit_arr, depth, depth_max)
-
-
# Programmtest, weil noch keine Verbindung zum Input besteht.
-arr = []
-arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
-arr.append('https://doi.org/10.1021/acs.jmedchem.0c01332')
-#arr.append('https://doi.org/10.1021/acs.jcim.0c00741')
-
-#arr.append('https://doi.org/10.1021/ci700007b')
-#arr.append('https://doi.org/10.1021/acs.jcim.5b00292')
-#url = sys.argv[1]
-#arr.append[url]
-
-nodes,edges = process_main(arr,1)
-
-print("Knoten:\n")
-for node in nodes:
- print(node.title, "\n")
-print("\nKanten:\n")
-for edge in edges:
- print(edge,"\n")
\ No newline at end of file
+def test_print():
+ arr = []
+ arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+ arr.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249')
+ arr.append('https://doi.org/10.1021/acs.jmedchem.0c01332')
+ #arr.append('https://doi.org/10.1021/acs.jcim.0c00741')
+
+ #arr.append('https://doi.org/10.1021/ci700007b')
+ #arr.append('https://doi.org/10.1021/acs.jcim.5b00292')
+ #url = sys.argv[1]
+ #arr.append[url]
+
+ nodes,edges = process_main(arr,1)
+
+ print("Knoten:\n")
+ for node in nodes:
+ print(node.title, "\n")
+ print("\n Kanten:\n")
+ for edge in edges:
+ print(edge,"\n")
+
\ No newline at end of file
diff --git a/verarbeitung/__pycache__/input_fj.cpython-38.pyc b/verarbeitung/__pycache__/input_fj.cpython-38.pyc
index fb7f56fc9742c5d19e2fff3d15c51dc4d59e1b1a..ae6b213cdfdd6a2c2fef9b9f68e2d1d431413958 100644
Binary files a/verarbeitung/__pycache__/input_fj.cpython-38.pyc and b/verarbeitung/__pycache__/input_fj.cpython-38.pyc differ
diff --git a/verarbeitung/__pycache__/json_demo.cpython-38.pyc b/verarbeitung/__pycache__/json_demo.cpython-38.pyc
index 519d14366f17ebf12bfdc3f6ae2e985ad9d6d229..e61f915490a7d068eb80a1c95d95752082231775 100644
Binary files a/verarbeitung/__pycache__/json_demo.cpython-38.pyc and b/verarbeitung/__pycache__/json_demo.cpython-38.pyc differ
diff --git a/verarbeitung/json_demo.py b/verarbeitung/json_demo.py
index 77ce148c8b3898c97472f2c43f1750b99a0ae9a1..6c91cee66105d20acfa93f997c80d40ad0e2d507 100644
--- a/verarbeitung/json_demo.py
+++ b/verarbeitung/json_demo.py
@@ -10,10 +10,8 @@ def output_to_json(V,E):
new_dict = dict()
new_dict["name"] = node.title
new_dict["author"] = node.contributors
- new_dict["year"] = node.publication_date
+ #new_dict["year"] = node.publication_date
new_dict["doi"] = node.doi_url
-
-
list_of_node_dicts.append(new_dict)
for edge in E:
new_dict_2 = dict()
@@ -23,7 +21,7 @@ def output_to_json(V,E):
dict_of_all["nodes"] = list_of_node_dicts
dict_of_all["links"] = list_of_edge_dicts
#return(dict_of_all)
- with open('json_text.txt','w') as outfile:
+ with open('json_text.json','w') as outfile:
json.dump(dict_of_all, outfile)
diff --git a/verarbeitung/json_text.json b/verarbeitung/json_text.json
new file mode 100644
index 0000000000000000000000000000000000000000..41455139941f560a6da139fae4c185ac19acdee0
--- /dev/null
+++ b/verarbeitung/json_text.json
@@ -0,0 +1 @@
+{"nodes": [{"name": "Comparing Molecular Patterns Using the Example of SMARTS: Applications and Filter Collection Analysis", "author": ["Emanuel S. R. Ehmki", "Robert Schmidt", "Farina Ohm", "Matthias Rarey"], "doi": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"name": "Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems ", "author": "John A. Keith, Valentin Vassilev-Galindo, Bingqing Cheng, Stefan Chmiela, Michael Gastegger, Klaus-Robert M\u00fcller, Alexandre Tkatchenko. ", "doi": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"name": "Disconnected Maximum Common Substructures under Constraints ", "author": "Robert Schmidt, Florian Krull, Anna Lina Heinzke, Matthias Rarey. ", "doi": "https://doi.org/10.1021/acs.jcim.0c00741"}, {"name": "Evolution of Novartis\u2019 Small Molecule Screening Deck Design ", "author": "Ansgar Schuffenhauer, Nadine Schneider, Samuel Hintermann, Douglas Auld, Jutta Blank, Simona Cotesta, Caroline Engeloch, Nikolas Fechner, Christoph Gaul, Jerome Giovannoni, Johanna Jansen, John Joslin, Philipp Krastel, Eugen Lounkine, John Manchester, Lauren G. Monovich, Anna Paola Pelliccioli, Manuel Schwarze, Michael D. Shultz, Nikolaus Stiefl, Daniel K. Baeschlin. ", "doi": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"name": "Comparing Molecular Patterns Using the Example of SMARTS: Theory and Algorithms ", "author": "Robert Schmidt, Emanuel S. R. Ehmki, Farina Ohm, Hans-Christian Ehrlich, Andriy Mashychev, Matthias Rarey. ", "doi": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"name": "Machine learning accelerates quantum mechanics predictions of molecular crystals ", "author": "Yanqiang Han, Imran Ali, Zhilong Wang, Junfei Cai, Sicheng Wu, Jiequn Tang, Lin Zhang, Jiahao Ren, Rui Xiao, Qianqian Lu, Lei Hang, Hongyuan Luo, Jinjin Li. ", "doi": "https://doi.org/10.1016/j.physrep.2021.08.002"}, {"name": "The Growing Importance of Chirality in 3D Chemical Space Exploration and Modern Drug Discovery Approaches for Hit-ID ", "author": "Ilaria Proietti Silvestri, Paul J. J. Colbon. ", "doi": "https://doi.org/10.1021/acsmedchemlett.1c00251"}, {"name": "Target-Based Evaluation of \u201cDrug-Like\u201d Properties and Ligand Efficiencies ", "author": "Paul D. Leeson, A. Patricia Bento, Anna Gaulton, Anne Hersey, Emma J. Manners, Chris J. Radoux, Andrew R. Leach. ", "doi": "https://doi.org/10.1021/acs.jmedchem.1c00416"}, {"name": "BonMOLi\u00e8re: Small-Sized Libraries of Readily Purchasable Compounds, Optimized to Produce Genuine Hits in Biological Screens across the Protein Space ", "author": "Neann Mathai, Conrad Stork, Johannes Kirchmair. ", "doi": "https://doi.org/10.3390/ijms22157773"}, {"name": "Accelerating high-throughput virtual screening through molecular pool-based active learning ", "author": "David E. Graff, Eugene I. Shakhnovich, Connor W. Coley. ", "doi": "https://doi.org/10.1039/D0SC06805E"}, {"name": "Compound Screening ", "author": "Shin Numao, Gianluca Etienne, Goran Malojcic, Enrico Schmidt, Christoph E. Dumelin. ", "doi": "https://doi.org/10.1016/B978-0-12-820472-6.00078-5"}], "links": [{"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jcim.0c00741"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00249", "target": "https://doi.org/10.1016/j.physrep.2021.08.002"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acsmedchemlett.1c00251"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jmedchem.1c00416"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.3390/ijms22157773"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1039/D0SC06805E"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1016/B978-0-12-820472-6.00078-5"}]}
\ No newline at end of file