input_old/pub.py

+class Publication:
+    #_registry = []
+    #_citations = []
+    #_references = []
+    
+    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
+        self.num_references = num_references
+    	self._citations = []
+    	self._references = []
+
+class Citation:
+    def __init__(self, title, journal, contributors, doi_url):
+        self.title = title
+        self.journal = journal
+        self.contributors = contributors
+        self.doi_url = doi_url
+
+class References:
+    def __init__(self, title, journal, contributors, doi_url):
+        self.title = title
+        self.journal = journal
+        self.contributors = contributors
+        self.doi_url = doi_url
+

input/test.py → input_old/test.py

@@ -4,7 +4,7 @@ from input_fj import input, print_pub_info
 import sys
 
 if len(sys.argv) != 3:
-    sys.stderr.write('Usage: {} <url>\n'.format(sys.argv[0]))
+    sys.stderr.write('Usage: {} <url> <url>\n'.format(sys.argv[0]))
     exit(1)
 url = sys.argv[1]
 url2 = sys.argv[2]

input_old/x

+Article title:    Feasibility of Active Machine Learning for Multiclass Compound Classification
+Publication date: January 7, 2016
+DOI-URL:          https://doi.org/10.1021/acs.jcim.5b00332
+
+Subjects:
+Algorithms, Molecules, Drug discovery, Screening assays, Receptors
+
+Contributors:
+Tobias Lang, Florian Flachsenberg, Ulrike von Luxburg, Matthias Rarey
+
+This publication is cited by the following 30 publications:
+
+
+    Title:        Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery 
+    Journal:      Chemical Reviews
+    Contributors: Xin Yang, Yifei Wang, Ryan Byrne, Gisbert Schneider, Shengyong Yang. 
+    DOI-URL:      https://doi.org/10.1021/acs.chemrev.8b00728
+            
+
+    Title:        De Novo Molecule Design by Translating from Reduced Graphs to SMILES 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Peter Pogány, Navot Arad, Sam Genway, Stephen D. Pickett. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.8b00626
+            
+
+    Title:        Designing Algorithms To Aid Discovery by Chemical Robots 
+    Journal:      ACS Central Science
+    Contributors: Alon B. Henson, Piotr S. Gromski, Leroy Cronin. 
+    DOI-URL:      https://doi.org/10.1021/acscentsci.8b00176
+            
+
+    Title:        Modeling Kinase Inhibition Using Highly Confident Data Sets 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Sorin Avram, Alina Bora, Liliana Halip, Ramona Curpăn. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.7b00729
+            
+
+    Title:        Predictive Models for Fast and Effective Profiling of Kinase Inhibitors 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Alina  Bora, Sorin  Avram, Ionel  Ciucanu, Marius  Raica, and Stefana  Avram  . 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.5b00646
+            
+
+    Title:        Evaluation of categorical matrix completion algorithms: toward improved active learning for drug discovery 
+    Journal:      Bioinformatics
+    Contributors: Huangqingbo  Sun, Robert F  Murphy, . 
+    DOI-URL:      https://doi.org/10.1093/bioinformatics/btab322
+            
+
+    Title:        An Artificial Intelligence Approach Based on Hybrid CNN-XGB Model to Achieve High Prediction Accuracy through Feature Extraction, Classification and Regression for Enhancing Drug Discovery in Biomedicine 
+    Journal:      International Journal of Biology and Biomedical Engineering
+    Contributors: Mukesh  Madanan, Biju T.  Sayed, Nurul Akhmal  Mohd Zulkefli, Nitha C.  Velayudhan. 
+    DOI-URL:      https://doi.org/10.46300/91011.2021.15.22
+            
+
+    Title:        Artificial Intelligence in Medicinal Chemistry 
+    Journal:      
+    Contributors: Edward  Griffen, Alexander  Dossetter, Andrew  Leach, Shane  Montague. 
+    DOI-URL:      https://doi.org/10.1002/0471266949.bmc267
+            
+
+    Title:        Practical Chemogenomic Modeling and Molecule Discovery Strategies Unveiled by Active Learning 
+    Journal:      
+    Contributors: J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1016/B978-0-12-801238-3.11533-8
+            
+
+    Title:        Machine learning phases and criticalities without using real data for training 
+    Journal:      Physical Review B
+    Contributors: D.-R.  Tan, F.-J.  Jiang. 
+    DOI-URL:      https://doi.org/10.1103/PhysRevB.102.224434
+            
+
+    Title:        Active learning effectively identifies a minimal set of maximally informative and asymptotically performant cytotoxic structure–activity patterns in NCI-60 cell lines 
+    Journal:      RSC Medicinal Chemistry
+    Contributors: Takumi  Nakano, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1039/D0MD00110D
+            
+
+    Title:        Active learning efficiently converges on rational limits of toxicity prediction and identifies patterns for molecule design 
+    Journal:      Computational Toxicology
+    Contributors: Ahsan  Habib Polash, Takumi  Nakano, Christin  Rakers, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1016/j.comtox.2020.100129
+            
+
+    Title:        Practical considerations for active machine learning in drug discovery 
+    Journal:      Drug Discovery Today: Technologies
+    Contributors: Daniel  Reker. 
+    DOI-URL:      https://doi.org/10.1016/j.ddtec.2020.06.001
+            
+
+    Title:        Designing compact training sets for data-driven molecular property prediction through optimal exploitation and exploration 
+    Journal:      Molecular Systems Design & Engineering
+    Contributors: Bowen  Li, Srinivas  Rangarajan. 
+    DOI-URL:      https://doi.org/10.1039/C9ME00078J
+            
+
+    Title:        Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification 
+    Journal:      Molecules
+    Contributors: Ahsan Habib  Polash, Takumi  Nakano, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.3390/molecules24152716
+            
+
+    Title:        Capturing and applying knowledge to guide compound optimisation 
+    Journal:      Drug Discovery Today
+    Contributors: Matthew  Segall, Tamsin  Mansley, Peter  Hunt, Edmund  Champness. 
+    DOI-URL:      https://doi.org/10.1016/j.drudis.2019.02.004
+            
+
+    Title:        A novel graph kernel on chemical compound classification 
+    Journal:      Journal of Bioinformatics and Computational Biology
+    Contributors: Qiangrong  Jiang, Jiajia  Ma. 
+    DOI-URL:      https://doi.org/10.1142/S0219720018500269
+            
+
+    Title:        Accelerating Drug Discovery Using Convolution Neural Network Based Active Learning 
+    Journal:      
+    Contributors: Pengfei  Liu, Kwong-Sak  Leung. 
+    DOI-URL:      https://doi.org/10.1109/TENCON.2018.8650298
+            
+
+    Title:        An Adaptive Lightweight Security Framework Suited for IoT 
+    Journal:      
+    Contributors: Menachem  Domb. 
+    DOI-URL:      https://doi.org/10.5772/intechopen.73712
+            
+
+    Title:        Adaptive mining and model building of medicinal chemistry data with a multi-metric perspective 
+    Journal:      Future Medicinal Chemistry
+    Contributors: JB  Brown. 
+    DOI-URL:      https://doi.org/10.4155/fmc-2018-0188
+            
+
+    Title:        Chemogenomic Active Learning's Domain of Applicability on Small, Sparse qHTS Matrices: A Study Using Cytochrome P450 and Nuclear Hormone Receptor Families 
+    Journal:      ChemMedChem
+    Contributors: Christin  Rakers, Rifat Ara  Najnin, Ahsan Habib  Polash, Shunichi  Takeda, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.1002/cmdc.201700677
+            
+
+    Title:        Automating drug discovery 
+    Journal:      Nature Reviews Drug Discovery
+    Contributors: Gisbert  Schneider. 
+    DOI-URL:      https://doi.org/10.1038/nrd.2017.232
+            
+
+    Title:        Classifiers and their Metrics Quantified 
+    Journal:      Molecular Informatics
+    Contributors: J. B.  Brown. 
+    DOI-URL:      https://doi.org/10.1002/minf.201700127
+            
+
+    Title:        Active Search for Computer-aided Drug Design 
+    Journal:      Molecular Informatics
+    Contributors: Dino  Oglic, Steven A.  Oatley, Simon J. F.  Macdonald, Thomas  Mcinally, Roman  Garnett, Jonathan D.  Hirst, Thomas  Gärtner. 
+    DOI-URL:      https://doi.org/10.1002/minf.201700130
+            
+
+    Title:        Selection of Informative Examples in Chemogenomic Datasets 
+    Journal:      
+    Contributors: Daniel  Reker, J. B.  Brown. 
+    DOI-URL:      https://doi.org/10.1007/978-1-4939-8639-2_13
+            
+
+    Title:        The value of prior knowledge in machine learning of complex network systems 
+    Journal:      Bioinformatics
+    Contributors: Dana  Ferranti, David  Krane, David  Craft, . 
+    DOI-URL:      https://doi.org/10.1093/bioinformatics/btx438
+            
+
+    Title:        Lightweight adaptive Random-Forest for IoT rule generation and execution 
+    Journal:      Journal of Information Security and Applications
+    Contributors: Menachem  Domb, Elisheva  Bonchek-Dokow, Guy  Leshem. 
+    DOI-URL:      https://doi.org/10.1016/j.jisa.2017.03.001
+            
+
+    Title:        Active learning for computational chemogenomics 
+    Journal:      Future Medicinal Chemistry
+    Contributors: Daniel  Reker, Petra  Schneider, Gisbert  Schneider, JB  Brown. 
+    DOI-URL:      https://doi.org/10.4155/fmc-2016-0197
+            
+
+    Title:        Small Random Forest Models for Effective Chemogenomic Active Learning 
+    Journal:      Journal of Computer Aided Chemistry
+    Contributors: Christin  Rakers, Daniel  Reker, J.B.  Brown. 
+    DOI-URL:      https://doi.org/10.2751/jcac.18.124
+            
+
+    Title:        Large-Scale Off-Target Identification Using Fast and Accurate Dual Regularized One-Class Collaborative Filtering and Its Application to Drug Repurposing 
+    Journal:      PLOS Computational Biology
+    Contributors: Hansaim  Lim, Aleksandar  Poleksic, Yuan  Yao, Hanghang  Tong, Di  He, Luke  Zhuang, Patrick  Meng, Lei  Xie, . 
+    DOI-URL:      https://doi.org/10.1371/journal.pcbi.1005135
+            
+Article title:    Matched Molecular Series: Measuring SAR Similarity
+Publication date: May 1, 2017
+DOI-URL:          https://doi.org/10.1021/acs.jcim.6b00709
+
+Subjects:
+Substituents, Mathematical methods, Structure activity relationship, Biological databases
+
+Contributors:
+Emanuel S. R. Ehmki, Christian Kramer
+
+This publication is cited by the following 5 publications:
+
+
+    Title:        Matched Molecular Series Analysis for ADME Property Prediction 
+    Journal:      Journal of Chemical Information and Modeling
+    Contributors: Mahendra Awale, Sereina Riniker, Christian Kramer. 
+    DOI-URL:      https://doi.org/10.1021/acs.jcim.0c00269
+            
+
+    Title:        Approaches using AI in medicinal chemistry 
+    Journal:      
+    Contributors: Christian  Tyrchan, Eva  Nittinger, Dea  Gogishvili, Atanas  Patronov, Thierry  Kogej. 
+    DOI-URL:      https://doi.org/10.1016/B978-0-12-822249-2.00002-5
+            
+
+    Title:        Bioactivity Prediction Based on Matched Molecular Pair and Matched Molecular Series Methods 
+    Journal:      Current Pharmaceutical Design
+    Contributors: Xiaoyu  Ding, Chen  Cui, Dingyan  Wang, Jihui  Zhao, Mingyue  Zheng, Xiaomin  Luo, Hualiang  Jiang, Kaixian  Chen. 
+    DOI-URL:      https://doi.org/10.2174/1381612826666200427111309
+            
+
+    Title:        BRADSHAW: a system for automated molecular design 
+    Journal:      Journal of Computer-Aided Molecular Design
+    Contributors: Darren V. S.  Green, Stephen  Pickett, Chris  Luscombe, Stefan  Senger, David  Marcus, Jamel  Meslamani, David  Brett, Adam  Powell, Jonathan  Masson. 
+    DOI-URL:      https://doi.org/10.1007/s10822-019-00234-8
+            
+
+    Title:        The use of matched molecular series networks for cross target structure activity relationship translation and potency prediction 
+    Journal:      MedChemComm
+    Contributors: Christopher E.  Keefer, George  Chang. 
+    DOI-URL:      https://doi.org/10.1039/C7MD00465F
+            

verarbeitung/Processing.py

+# -*- coding: utf-8 -*-
+"""
+Created on Wed Nov  3 16:54:43 2021
+
+@author: Malte Schokolowski
+"""
+
+from bs4 import BeautifulSoup as bs
+import requests as req
+import sys  
+from pathlib import Path
+from input_fj import input
+from json_demo import output_to_json
+
+
+
+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:
+        pub = input(pub_doi)
+        not_in_nodes = True
+        for node 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)
+
+    process_rec_depth(doi_input_array, 0, depth)
+
+    output_to_json(nodes,edges)
+    return(nodes,edges)
+    
+    
+def process_rec_depth(array, depth, depth_max):  
+    # Die Tiefe wird bei jedem rekursiven Aufruf um 1 erhöht.
+    depth += 1
+
+    # Für jede Publikation im Input-Array wird ein Klassenobjekt erstellt.
+    for pub_doi in array:
+        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])
+            
+        # 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 = []
+            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)
+
+            # 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

verarbeitung/json_demo.py

+#!/usr/bin/env python3
+import json
+from input_fj import input
+
+def output_to_json(V,E):
+    list_of_node_dicts = list()
+    list_of_edge_dicts = list()
+    dict_of_all = dict()
+    for node in V:
+        new_dict = dict()
+        new_dict["name"] = node.title
+        new_dict["author"] = node.contributors
+        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()
+        new_dict_2["source"] = edge[0]
+        new_dict_2["target"] = edge[1]
+        list_of_edge_dicts.append(new_dict_2)
+    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:
+        json.dump(dict_of_all, outfile)
+  
+
+#knoten = ["doi1", "doi2", "doi3"]
+#kanten = [[1,2],[3,4],[5,6]]
+#output_to_json(knoten,kanten)
+