diff --git a/verarbeitung/construct_new_graph/initialize_graph.py b/verarbeitung/construct_new_graph/initialize_graph.py index ba86e8bc979de42c388c5e8fe0e4ced9282500f0..27cf455e60d598e1c012de8d9a050d50cf457ca5 100644 --- a/verarbeitung/construct_new_graph/initialize_graph.py +++ b/verarbeitung/construct_new_graph/initialize_graph.py @@ -96,7 +96,7 @@ def complete_inner_edges(): edges.append([node.doi_url,reference.doi_url]) -def init_graph_construction(doi_input_list, search_depth, search_height, test_var = False): +def init_graph_construction(doi_input_list, search_depth, search_height, test_var = False, input_nodes = [], input_edges = []): ''' :param doi_input_list: input list of doi from UI :type doi_input_list: List[String] @@ -128,8 +128,8 @@ def init_graph_construction(doi_input_list, search_depth, search_height, test_va # creates empty lists to save nodes and edges global nodes, edges - nodes = [] - edges = [] + nodes = input_nodes + edges = input_edges # initializes nodes/edges from input and gets a list with publication objects for citations and references returned references_obj_list, citations_obj_list = initialize_nodes_list(doi_input_list,search_depth, search_height, test_var) diff --git a/verarbeitung/process_main.py b/verarbeitung/process_main.py index 4e0678386b6da3ee18d4a0f7b0c271f3167c93fd..db17e1f5694fb87e805a073c8839054cedc95c47 100644 --- a/verarbeitung/process_main.py +++ b/verarbeitung/process_main.py @@ -16,7 +16,7 @@ __status__ = "Production" import sys from pathlib import Path -from os import error +from os import error, path sys.path.append("../") @@ -42,13 +42,13 @@ def Processing(url_list, search_depth, search_height, json_file = 'json_text.jso ''' # updates graph if json file is known in directory otherwise starts new graph construction - try: - with open(json_file) as f: - nodes, edges = update_graph(url_list, json_file, search_depth, search_height) - - except IOError: - nodes, edges = init_graph_construction(url_list, search_depth, search_height) + json_file = Path(json_file) + if json_file.is_file(): + nodes, edges = update_graph(url_list, json_file, search_depth, search_height) + else: + nodes, edges = init_graph_construction(url_list, search_depth, search_height) + # exports graph to given json file name output_to_json(nodes, edges, json_file) \ No newline at end of file diff --git a/verarbeitung/start_script.py b/verarbeitung/start_script.py index bee6bf12ce9ca15f157d357a507ed0ff33c96a77..6e5854f4ffff81c2056595cdd0365c7909acf3cd 100644 --- a/verarbeitung/start_script.py +++ b/verarbeitung/start_script.py @@ -8,4 +8,5 @@ doi_list = [] doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.9b00249') #doi_list.append('https://doi.org/10.1021/acs.jcim.9b00249') doi_list.append('https://pubs.acs.org/doi/10.1021/acs.jcim.1c00203') -Processing(doi_list, 3, 3, 'test.json') \ No newline at end of file +doi_list.append('https://doi.org/10.1021/acs.jmedchem.0c01332') +Processing(doi_list, 2, 2, 'test.json') diff --git a/verarbeitung/test.json b/verarbeitung/test.json index e87f9bf7924d1b970578681e663709a0fe398226..45ff7a4c5e3673cdb4d6a90e17a5b7ef579aeae4 100644 --- a/verarbeitung/test.json +++ b/verarbeitung/test.json @@ -1 +1 @@ -{"nodes": [{"doi": "https://doi.org/10.1021/acs.jcim.9b00249", "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"], "year": "May 24, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Input", "depth": 0, "citations": 4}, {"doi": "https://doi.org/10.1021/acs.chemrev.1c00107", "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"], "year": "July 7, 2021", "journal": "Chem. Rev.", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.0c00741", "name": "Disconnected Maximum Common Substructures under Constraints", "author": ["Robert Schmidt", "Florian Krull", "Anna Lina Heinzke", "Matthias Rarey"], "year": "December 16, 2020", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jmedchem.0c01332", "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"], "year": "November 3, 2020", "journal": "Journal of Medicinal Chemistry", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.9b00250", "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"], "year": "May 23, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 1, "citations": 7}, {"doi": "https://doi.org/10.1021/acs.jcim.1c00203", "name": "AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings", "author": ["Jerome Eberhardt", "Diogo Santos-Martins", "Andreas F. Tillack", "Stefano Forli"], "year": "July 19, 2021", "journal": "Journal of Chemical Information and Modeling", "group": "Input", "depth": 0, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jctc.0c01006", "name": "Accelerating AutoDock4 with GPUs and Gradient-Based Local Search", "author": ["Diogo Santos-Martins", "Leonardo Solis-Vasquez", "Andreas F Tillack", "Michel F Sanner", "Andreas Koch", "Stefano Forli"], "year": "January 6, 2021", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jctc.9b00557", "name": "Docking Flexible Cyclic Peptides with AutoDock CrankPep", "author": ["Yuqi Zhang", "Michel F. Sanner"], "year": "September 11, 2019", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci300604z", "name": "Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking Exercise", "author": ["David Ryan Koes", "Matthew P. Baumgartner", "Carlos J. Camacho"], "year": "February 4, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jctc.5b00834", "name": "Vina-Carb: Improving Glycosidic Angles during Carbohydrate Docking", "author": ["Anita K. Nivedha", "David F. Thieker", "Spandana Makeneni", "Huimin Hu", "Robert J. Woods"], "year": "January 8, 2016", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci700036j", "name": "Lennard-Jones Potential and Dummy Atom Settings to Overcome the AUTODOCK Limitation in Treating Flexible Ring Systems", "author": ["Stefano Forli", "Maurizio Botta"], "year": "June 22, 2007", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 4}, {"doi": "https://doi.org/10.1021/ci500209e", "name": "AutoDock4Zn: An Improved AutoDock Force Field for Small-Molecule Docking to Zinc Metalloproteins", "author": ["Diogo Santos-Martins", "Stefano Forli", "Maria Jo\u00e3o Ramos", "Arthur J. Olson"], "year": "June 15, 2014", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/jm2005145", "name": "A Force Field with Discrete Displaceable Waters and Desolvation Entropy for Hydrated Ligand Docking", "author": ["Stefano Forli", "Arthur J. Olson"], "year": "December 9, 2011", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 4}, {"doi": "https://doi.org/10.1021/ci300399w", "name": "Consensus Docking: Improving the Reliability of Docking in a Virtual Screening Context", "author": ["Douglas R. Houston", "Malcolm D. Walkinshaw"], "year": "January 27, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jp9723574", "name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 1. Theory", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jp972358w", "name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 2. Applications to Simple Fluids", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jcim.0c00675", "name": "ZINC20\u2014A Free Ultralarge-Scale Chemical Database for Ligand Discovery", "author": ["John J. Irwin", "Khanh G. Tang", "Jennifer Young", "Chinzorig Dandarchuluun", "Benjamin R. Wong", "Munkhzul Khurelbaatar", "Yurii S. Moroz", "John Mayfield", "Roger A. Sayle"], "year": "October 29, 2020", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jmedchem.7b01243", "name": "Structural Biology-Inspired Discovery of Novel KRAS\u2013PDE\u03b4 Inhibitors", "author": ["Yan Jiang", "Chunlin Zhuang", "Long Chen", "Junjie Lu", "Guoqiang Dong", "Zhenyuan Miao", "Wannian Zhang", "Jian Li", "Chunquan Sheng"], "year": "September 20, 2017", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm300687e", "name": "Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking", "author": ["Michael M. Mysinger", "Michael Carchia", "John. J. Irwin", "Brian K. Shoichet"], "year": "June 20, 2012", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 3}, {"doi": "https://doi.org/10.1021/acs.jcim.8b00312", "name": "Evaluation of AutoDock and AutoDock Vina on the CASF-2013 Benchmark", "author": ["Thomas Gaillard"], "year": "July 10, 2018", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.9b00778", "name": "Autodock Vina Adopts More Accurate Binding Poses but Autodock4 Forms Better Binding Affinity", "author": ["Nguyen Thanh Nguyen", "Trung Hai Nguyen", "T. Ngoc Han Pham", "Nguyen Truong Huy", "Mai Van Bay", "Minh Quan Pham", "Pham Cam Nam", "Van V. Vu", "Son Tung Ngo"], "year": "December 30, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/jm0306430", "name": "Glide:\u2009 A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking Accuracy", "author": ["Richard A. Friesner", "Jay L. Banks", "Robert B. Murphy", "Thomas A. Halgren", "Jasna J. Klicic", "Daniel T. Mainz", "Matthew P. Repasky", "Eric H. Knoll", "Mee Shelley", "Jason K. Perry", "David E. Shaw", "Perry Francis", "Peter S. Shenkin"], "year": "February 27, 2004", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm020406h", "name": "Surflex:\u2009 Fully Automatic Flexible Molecular Docking Using a Molecular Similarity-Based Search Engine", "author": ["Ajay N. Jain"], "year": "January 21, 2003", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci300493w", "name": "ID-Score: A New Empirical Scoring Function Based on a Comprehensive Set of Descriptors Related to Protein\u2013Ligand Interactions", "author": ["Guo-Bo Li", "Ling-Ling Yang", "Wen-Jing Wang", "Lin-Li Li", "Sheng-Yong Yang"], "year": "February 9, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm049314d", "name": "A Knowledge-Based Energy Function for Protein\u2212Ligand, Protein\u2212Protein, and Protein\u2212DNA Complexes", "author": ["Chi Zhang", "Song Liu", "Qianqian Zhu", "Yaoqi Zhou"], "year": "February 16, 2005", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acsomega.1c04320", "name": "Novel Anti-Hepatitis B Virus Activity of Euphorbia schimperi and Its Quercetin and Kaempferol Derivatives", "author": ["Mohammad K. Parvez", "Sarfaraz Ahmed", "Mohammed S. Al-Dosari", "Mazin A. S. Abdelwahid", "Ahmed H. Arbab", "Adnan J. Al-Rehaily", "Mai M. Al-Oqail"], "year": "October 21, 2021", "journal": "ACS Omega", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jpcb.1c08383", "name": "Molecular Simulations of Aqueous Electrolytes: Role of Explicit Inclusion of Charge Transfer into Force Fields", "author": ["Max L. Berkowitz"], "year": "November 22, 2021", "journal": "Journal of Physical Chemistry B", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jpca.1c06264", "name": "Topological Characterization and Graph Entropies of Tessellations of Kekulene Structures: Existence of Isentropic Structures and Applications to Thermochemistry, Nuclear Magnetic Resonance, and Electron Spin Resonance", "author": ["S. Ruth Julie Kavitha", "Jessie Abraham", "Micheal Arockiaraj", "Joseph Jency", "Krishnan Balasubramanian"], "year": "September 1, 2021", "journal": "J. Phys. Chem. A", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acsmedchemlett.1c00251", "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"], "year": "July 16, 2021", "journal": "ACS Med. Chem. Lett.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jmedchem.1c00416", "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"], "year": "May 13, 2021", "journal": "Journal of Medicinal Chemistry", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jcim.1c00226", "name": "Automatic Identification of Lansoprazole Degradants under Stress Conditions by LC-HRMS with MassChemSite and WebChembase", "author": ["Stefano Bonciarelli", "Jenny Desantis", "Laura Goracci", "Lydia Siragusa", "Ismael Zamora", "Elisabeth Ortega-Carrasco"], "year": "June 1, 2021", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.chemrestox.0c00006", "name": "Computational Approaches to Identify Structural Alerts and Their Applications in Environmental Toxicology and Drug Discovery", "author": ["Hongbin Yang", "Chaofeng Lou", "Weihua Li", "Guixia Liu", "Yun Tang"], "year": "February 24, 2020", "journal": "Chem. Res. Toxicol.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.est.9b06379", "name": "Toward a Global Understanding of Chemical Pollution: A First Comprehensive Analysis of National and Regional Chemical Inventories", "author": ["Zhanyun Wang", "Glen W. Walker", "Derek C. G. Muir", "Kakuko Nagatani-Yoshida"], "year": "January 22, 2020", "journal": "Environ. Sci. Technol.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/ci049714+", "name": "ZINC \u2212 A Free Database of Commercially Available Compounds for Virtual Screening", "author": ["John J. Irwin", "Brian K. Shoichet"], "year": "December 14, 2004", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 3}, {"doi": "https://doi.org/10.1021/ci3001277", "name": "ZINC: A Free Tool to Discover Chemistry for Biology", "author": ["John J. Irwin", "Teague Sterling", "Michael M. Mysinger", "Erin S. Bolstad", "Ryan G. Coleman"], "year": "May 15, 2012", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.5b00559", "name": "ZINC 15 \u2013 Ligand Discovery for Everyone", "author": ["Teague Sterling", "John J. Irwin"], "year": "October 19, 2015", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/ci7004498", "name": "Application of Belief Theory to Similarity Data Fusion for Use in Analog Searching and Lead Hopping", "author": ["Steven W. Muchmore", "Derek A. Debe", "James T. Metz", "Scott P. Brown", "Yvonne C. Martin", "Philip J. Hajduk"], "year": "April 17, 2008", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/jm020155c", "name": "Do Structurally Similar Molecules Have Similar Biological Activity?", "author": ["Yvonne C. Martin", "James L. Kofron", "Linda M. Traphagen"], "year": "August 13, 2002", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -2, "citations": 2}, {"doi": "https://doi.org/10.1021/jm9602928", "name": "The Properties of Known Drugs. 1. Molecular Frameworks", "author": ["Guy W. Bemis", "Mark A. Murcko"], "year": "July 19, 1996", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/ci025599w", "name": "Molecular Shape Diversity of Combinatorial Libraries:\u2009 A Prerequisite for Broad Bioactivity\u2020", "author": ["Wolfgang H. B. Sauer", "Matthias K. Schwarz"], "year": "March 14, 2003", "journal": "J. Chem. Inf. Comput. Sci.", "group": "Reference", "depth": -2, "citations": 3}], "links": [{"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00250", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.0c01006"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.9b00557"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.5b00834"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300399w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp9723574"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp972358w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.0c00675"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jmedchem.7b01243"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm0306430"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm020406h"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300493w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm049314d"}, {"source": "https://doi.org/10.1021/acsomega.1c04320", "target": "https://doi.org/10.1021/acs.jcim.1c00203"}, {"source": "https://doi.org/10.1021/acs.jpcb.1c08383", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acs.jpca.1c06264", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acsmedchemlett.1c00251", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.jmedchem.1c00416", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00226", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.chemrestox.0c00006", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.est.9b06379", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"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.0c00675", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci3001277"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/acs.jcim.5b00559"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci7004498"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/jm020155c"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/jm9602928"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci025599w"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/ci3001277"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00312", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.9b00557", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00312", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00778", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/ci7004498", "target": "https://doi.org/10.1021/jm020155c"}, {"source": "https://doi.org/10.1021/acsmedchemlett.1c00251", "target": "https://doi.org/10.1021/ci025599w"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/ci025599w"}]} \ No newline at end of file +{"nodes": [{"doi": "https://doi.org/10.1021/acs.jcim.9b00249", "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"], "year": "May 24, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Input", "depth": 0, "citations": 4}, {"doi": "https://doi.org/10.1021/acs.chemrev.1c00107", "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"], "year": "July 7, 2021", "journal": "Chem. Rev.", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.0c00741", "name": "Disconnected Maximum Common Substructures under Constraints", "author": ["Robert Schmidt", "Florian Krull", "Anna Lina Heinzke", "Matthias Rarey"], "year": "December 16, 2020", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jmedchem.0c01332", "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"], "year": "November 3, 2020", "journal": "Journal of Medicinal Chemistry", "group": "Input", "depth": 0, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.9b00250", "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"], "year": "May 23, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 1, "citations": 7}, {"doi": "https://doi.org/10.1021/acs.jcim.1c00203", "name": "AutoDock Vina 1.2.0: New Docking Methods, Expanded Force Field, and Python Bindings", "author": ["Jerome Eberhardt", "Diogo Santos-Martins", "Andreas F. Tillack", "Stefano Forli"], "year": "July 19, 2021", "journal": "Journal of Chemical Information and Modeling", "group": "Input", "depth": 0, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jctc.0c01006", "name": "Accelerating AutoDock4 with GPUs and Gradient-Based Local Search", "author": ["Diogo Santos-Martins", "Leonardo Solis-Vasquez", "Andreas F Tillack", "Michel F Sanner", "Andreas Koch", "Stefano Forli"], "year": "January 6, 2021", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jctc.9b00557", "name": "Docking Flexible Cyclic Peptides with AutoDock CrankPep", "author": ["Yuqi Zhang", "Michel F. Sanner"], "year": "September 11, 2019", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci300604z", "name": "Lessons Learned in Empirical Scoring with smina from the CSAR 2011 Benchmarking Exercise", "author": ["David Ryan Koes", "Matthew P. Baumgartner", "Carlos J. Camacho"], "year": "February 4, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jctc.5b00834", "name": "Vina-Carb: Improving Glycosidic Angles during Carbohydrate Docking", "author": ["Anita K. Nivedha", "David F. Thieker", "Spandana Makeneni", "Huimin Hu", "Robert J. Woods"], "year": "January 8, 2016", "journal": "Journal of Chemical Theory and Computation", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci700036j", "name": "Lennard-Jones Potential and Dummy Atom Settings to Overcome the AUTODOCK Limitation in Treating Flexible Ring Systems", "author": ["Stefano Forli", "Maurizio Botta"], "year": "June 22, 2007", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 4}, {"doi": "https://doi.org/10.1021/ci500209e", "name": "AutoDock4Zn: An Improved AutoDock Force Field for Small-Molecule Docking to Zinc Metalloproteins", "author": ["Diogo Santos-Martins", "Stefano Forli", "Maria Jo\u00e3o Ramos", "Arthur J. Olson"], "year": "June 15, 2014", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/jm2005145", "name": "A Force Field with Discrete Displaceable Waters and Desolvation Entropy for Hydrated Ligand Docking", "author": ["Stefano Forli", "Arthur J. Olson"], "year": "December 9, 2011", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 4}, {"doi": "https://doi.org/10.1021/ci300399w", "name": "Consensus Docking: Improving the Reliability of Docking in a Virtual Screening Context", "author": ["Douglas R. Houston", "Malcolm D. Walkinshaw"], "year": "January 27, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jp9723574", "name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 1. Theory", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jp972358w", "name": "Inhomogeneous Fluid Approach to Solvation Thermodynamics. 2. Applications to Simple Fluids", "author": ["Themis Lazaridis"], "year": "April 14, 1998", "journal": "Journal of Physical Chemistry B", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jcim.0c00675", "name": "ZINC20\u2014A Free Ultralarge-Scale Chemical Database for Ligand Discovery", "author": ["John J. Irwin", "Khanh G. Tang", "Jennifer Young", "Chinzorig Dandarchuluun", "Benjamin R. Wong", "Munkhzul Khurelbaatar", "Yurii S. Moroz", "John Mayfield", "Roger A. Sayle"], "year": "October 29, 2020", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acs.jmedchem.7b01243", "name": "Structural Biology-Inspired Discovery of Novel KRAS\u2013PDE\u03b4 Inhibitors", "author": ["Yan Jiang", "Chunlin Zhuang", "Long Chen", "Junjie Lu", "Guoqiang Dong", "Zhenyuan Miao", "Wannian Zhang", "Jian Li", "Chunquan Sheng"], "year": "September 20, 2017", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm300687e", "name": "Directory of Useful Decoys, Enhanced (DUD-E): Better Ligands and Decoys for Better Benchmarking", "author": ["Michael M. Mysinger", "Michael Carchia", "John. J. Irwin", "Brian K. Shoichet"], "year": "June 20, 2012", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 3}, {"doi": "https://doi.org/10.1021/acs.jcim.8b00312", "name": "Evaluation of AutoDock and AutoDock Vina on the CASF-2013 Benchmark", "author": ["Thomas Gaillard"], "year": "July 10, 2018", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.9b00778", "name": "Autodock Vina Adopts More Accurate Binding Poses but Autodock4 Forms Better Binding Affinity", "author": ["Nguyen Thanh Nguyen", "Trung Hai Nguyen", "T. Ngoc Han Pham", "Nguyen Truong Huy", "Mai Van Bay", "Minh Quan Pham", "Pham Cam Nam", "Van V. Vu", "Son Tung Ngo"], "year": "December 30, 2019", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 2}, {"doi": "https://doi.org/10.1021/jm0306430", "name": "Glide:\u2009 A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking Accuracy", "author": ["Richard A. Friesner", "Jay L. Banks", "Robert B. Murphy", "Thomas A. Halgren", "Jasna J. Klicic", "Daniel T. Mainz", "Matthew P. Repasky", "Eric H. Knoll", "Mee Shelley", "Jason K. Perry", "David E. Shaw", "Perry Francis", "Peter S. Shenkin"], "year": "February 27, 2004", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm020406h", "name": "Surflex:\u2009 Fully Automatic Flexible Molecular Docking Using a Molecular Similarity-Based Search Engine", "author": ["Ajay N. Jain"], "year": "January 21, 2003", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci300493w", "name": "ID-Score: A New Empirical Scoring Function Based on a Comprehensive Set of Descriptors Related to Protein\u2013Ligand Interactions", "author": ["Guo-Bo Li", "Ling-Ling Yang", "Wen-Jing Wang", "Lin-Li Li", "Sheng-Yong Yang"], "year": "February 9, 2013", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/jm049314d", "name": "A Knowledge-Based Energy Function for Protein\u2212Ligand, Protein\u2212Protein, and Protein\u2212DNA Complexes", "author": ["Chi Zhang", "Song Liu", "Qianqian Zhu", "Yaoqi Zhou"], "year": "February 16, 2005", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -1, "citations": 1}, {"doi": "https://doi.org/10.1021/acsomega.1c04320", "name": "Novel Anti-Hepatitis B Virus Activity of Euphorbia schimperi and Its Quercetin and Kaempferol Derivatives", "author": ["Mohammad K. Parvez", "Sarfaraz Ahmed", "Mohammed S. Al-Dosari", "Mazin A. S. Abdelwahid", "Ahmed H. Arbab", "Adnan J. Al-Rehaily", "Mai M. Al-Oqail"], "year": "October 21, 2021", "journal": "ACS Omega", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jpcb.1c08383", "name": "Molecular Simulations of Aqueous Electrolytes: Role of Explicit Inclusion of Charge Transfer into Force Fields", "author": ["Max L. Berkowitz"], "year": "November 22, 2021", "journal": "Journal of Physical Chemistry B", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jpca.1c06264", "name": "Topological Characterization and Graph Entropies of Tessellations of Kekulene Structures: Existence of Isentropic Structures and Applications to Thermochemistry, Nuclear Magnetic Resonance, and Electron Spin Resonance", "author": ["S. Ruth Julie Kavitha", "Jessie Abraham", "Micheal Arockiaraj", "Joseph Jency", "Krishnan Balasubramanian"], "year": "September 1, 2021", "journal": "J. Phys. Chem. A", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acsmedchemlett.1c00251", "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"], "year": "July 16, 2021", "journal": "ACS Med. Chem. Lett.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jmedchem.1c00416", "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"], "year": "May 13, 2021", "journal": "Journal of Medicinal Chemistry", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jcim.1c00226", "name": "Automatic Identification of Lansoprazole Degradants under Stress Conditions by LC-HRMS with MassChemSite and WebChembase", "author": ["Stefano Bonciarelli", "Jenny Desantis", "Laura Goracci", "Lydia Siragusa", "Ismael Zamora", "Elisabeth Ortega-Carrasco"], "year": "June 1, 2021", "journal": "Journal of Chemical Information and Modeling", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.chemrestox.0c00006", "name": "Computational Approaches to Identify Structural Alerts and Their Applications in Environmental Toxicology and Drug Discovery", "author": ["Hongbin Yang", "Chaofeng Lou", "Weihua Li", "Guixia Liu", "Yun Tang"], "year": "February 24, 2020", "journal": "Chem. Res. Toxicol.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.est.9b06379", "name": "Toward a Global Understanding of Chemical Pollution: A First Comprehensive Analysis of National and Regional Chemical Inventories", "author": ["Zhanyun Wang", "Glen W. Walker", "Derek C. G. Muir", "Kakuko Nagatani-Yoshida"], "year": "January 22, 2020", "journal": "Environ. Sci. Technol.", "group": "Citedby", "depth": 2, "citations": 0}, {"doi": "https://doi.org/10.1021/ci049714+", "name": "ZINC \u2212 A Free Database of Commercially Available Compounds for Virtual Screening", "author": ["John J. Irwin", "Brian K. Shoichet"], "year": "December 14, 2004", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 3}, {"doi": "https://doi.org/10.1021/ci3001277", "name": "ZINC: A Free Tool to Discover Chemistry for Biology", "author": ["John J. Irwin", "Teague Sterling", "Michael M. Mysinger", "Erin S. Bolstad", "Ryan G. Coleman"], "year": "May 15, 2012", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 2}, {"doi": "https://doi.org/10.1021/acs.jcim.5b00559", "name": "ZINC 15 \u2013 Ligand Discovery for Everyone", "author": ["Teague Sterling", "John J. Irwin"], "year": "October 19, 2015", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/ci7004498", "name": "Application of Belief Theory to Similarity Data Fusion for Use in Analog Searching and Lead Hopping", "author": ["Steven W. Muchmore", "Derek A. Debe", "James T. Metz", "Scott P. Brown", "Yvonne C. Martin", "Philip J. Hajduk"], "year": "April 17, 2008", "journal": "Journal of Chemical Information and Modeling", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/jm020155c", "name": "Do Structurally Similar Molecules Have Similar Biological Activity?", "author": ["Yvonne C. Martin", "James L. Kofron", "Linda M. Traphagen"], "year": "August 13, 2002", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -2, "citations": 2}, {"doi": "https://doi.org/10.1021/jm9602928", "name": "The Properties of Known Drugs. 1. Molecular Frameworks", "author": ["Guy W. Bemis", "Mark A. Murcko"], "year": "July 19, 1996", "journal": "Journal of Medicinal Chemistry", "group": "Reference", "depth": -2, "citations": 1}, {"doi": "https://doi.org/10.1021/ci025599w", "name": "Molecular Shape Diversity of Combinatorial Libraries:\u2009 A Prerequisite for Broad Bioactivity\u2020", "author": ["Wolfgang H. B. Sauer", "Matthias K. Schwarz"], "year": "March 14, 2003", "journal": "J. Chem. Inf. Comput. Sci.", "group": "Reference", "depth": -2, "citations": 3}], "links": [{"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00250", "target": "https://doi.org/10.1021/acs.jcim.9b00249"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.0c01006"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.9b00557"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jctc.5b00834"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300399w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp9723574"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jp972358w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.0c00675"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jmedchem.7b01243"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm0306430"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm020406h"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/ci300493w"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00203", "target": "https://doi.org/10.1021/jm049314d"}, {"source": "https://doi.org/10.1021/acsomega.1c04320", "target": "https://doi.org/10.1021/acs.jcim.1c00203"}, {"source": "https://doi.org/10.1021/acs.jpcb.1c08383", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acs.jpca.1c06264", "target": "https://doi.org/10.1021/acs.chemrev.1c00107"}, {"source": "https://doi.org/10.1021/acsmedchemlett.1c00251", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.jmedchem.1c00416", "target": "https://doi.org/10.1021/acs.jmedchem.0c01332"}, {"source": "https://doi.org/10.1021/acs.chemrev.1c00107", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.1c00226", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.chemrestox.0c00006", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"source": "https://doi.org/10.1021/acs.est.9b06379", "target": "https://doi.org/10.1021/acs.jcim.9b00250"}, {"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.0c00675", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci3001277"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/acs.jcim.5b00559"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci7004498"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/jm020155c"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/jm9602928"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00675", "target": "https://doi.org/10.1021/ci025599w"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/ci3001277"}, {"source": "https://doi.org/10.1021/acs.jcim.5b00559", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00312", "target": "https://doi.org/10.1021/ci300604z"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.9b00557", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/ci700036j"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci500209e"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00312", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/ci500209e", "target": "https://doi.org/10.1021/jm2005145"}, {"source": "https://doi.org/10.1021/acs.jcim.0c00741", "target": "https://doi.org/10.1021/jm300687e"}, {"source": "https://doi.org/10.1021/acs.jcim.9b00778", "target": "https://doi.org/10.1021/acs.jcim.8b00312"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/acs.jcim.9b00778"}, {"source": "https://doi.org/10.1021/acs.jctc.0c01006", "target": "https://doi.org/10.1021/ci049714+"}, {"source": "https://doi.org/10.1021/ci7004498", "target": "https://doi.org/10.1021/jm020155c"}, {"source": "https://doi.org/10.1021/acsmedchemlett.1c00251", "target": "https://doi.org/10.1021/ci025599w"}, {"source": "https://doi.org/10.1021/acs.jmedchem.0c01332", "target": "https://doi.org/10.1021/ci025599w"}]} diff --git a/verarbeitung/update_graph/connect_new_input.py b/verarbeitung/update_graph/connect_new_input.py index 3f11e591db737bd11f2a261213973a2bf297ed1c..b87b85690ba820ce059bbec03cab158a3209953f 100644 --- a/verarbeitung/update_graph/connect_new_input.py +++ b/verarbeitung/update_graph/connect_new_input.py @@ -16,69 +16,138 @@ __status__ = "Production" import sys from pathlib import Path from os import error + sys.path.append("../") from .import_from_json import input_from_json -from verarbeitung.construct_new_graph.initialize_graph import initialize_nodes_list, complete_inner_edges -from verarbeitung.construct_new_graph.add_citations_rec import add_citations -from verarbeitung.construct_new_graph.export_to_json import output_to_json +from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction +from verarbeitung.construct_new_graph.add_citations_rec import add_citations, get_cit_type_list, create_global_lists_cit + -def connect_old_and_new_input(json_file, new_doi_list, search_depth, search_height, test_var = False): +def find_furthermost_citations(node, old_search_depth, cit_type): ''' - :param json_file: json file with old graph - :type json_file: json file + :param node: node which is known but not from input group + :type node: Publication - :param new_doi_list: additional dois which has to be connected to the old graph - :type new_doi_list: list of strings + :param old_search_depth: depth to search for references from old construction call + :type old_search_depth: int - :param search_depth: depth to search for references - :type search_depth: int + :param cit_type: determines whether the function call is for a reference or citation + :type cit_type: String - :param search_height: height to search for citations - :type search_height: int + function to find the furthermost citation/reference for given node which is from the same group + ''' + citations_saved = get_cit_type_list(node, cit_type) + + # group of node and old search depth/height determines how often the loop needs to be repeated + for depth in range(old_search_depth - abs(node.group)): + new_citations = [] + for citation in citations_saved: + for cit_node in nodes: + if citation.doi_url == cit_node.doi_url: + for new_cit in get_cit_type_list(cit_node, cit_type): + for new_cit_node in nodes: + if new_cit.doi_url == new_cit_node.doi_url: + new_citations.append(node) + citations_saved = new_citations + + # returns the references/citations which needs to be processed to complete contruction + return(citations_saved) + +def complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var): + ''' + :param inserted_nodes: list of nodes which are inserted to new input array + :type inserted_nodes: List[String] - :param test_var: variable to differenciate between test and url call - :type test_var: boolean + :param old_search_depth: depth to search for references from old construction call + :type old_search_depth: int - connetcs the old graph and the new input dois to a complete new graph - ''' - global nodes, edges - nodes = [] - edges = [] + :param old_search_height: height to search for citations from old construction call + :type old_search_height: int - nodes, edges = input_from_json(json_file) + :param new_search_depth: depth to search for references from new construction call + :type new_search_depth: int - complete_changed_group_nodes(new_doi_list, search_depth, search_height, test_var) - - # initializes nodes/edges from input and gets a list with publication objects for citations and references returned - references_obj_list, citations_obj_list = initialize_nodes_list(new_doi_list,search_depth, search_height, test_var) + :param new_search_height: height to search for citations from new construction call + :type new_search_height: int - # function calls to begin recursive processing up to max depth/height - add_citations(nodes, edges, citations_obj_list, 1, search_height, "Citation", test_var) - add_citations(nodes, edges, references_obj_list, 1, search_depth, "Reference", test_var) + :param test_var: variable to differenciate between test and url call + :type test_var: boolean - # adds edges between reference group and citation group of known publications - complete_inner_edges(test_var) + completes the references and citations for nodes which were known in non input group + ''' + #changed_group_node_citations = [] + #changed_group_node_references = [] - # calls a skript to save nodes and edges of graph in .json file - output_to_json(nodes,edges, test_var) + # saves which nodes were handled because they were known before + handled_inserted_nodes = [] + for node in nodes: - return(nodes, edges) + # moves known reference node to input and completes citations and references for this node + if (node.group < 0) and (node.doi_url in inserted_nodes): + node_citations = create_global_lists_cit(nodes, edges, node, 1, new_search_height, "Citation", test_var) + add_citations(nodes, edges, node_citations, 1, new_search_height, "Citation", test_var) + old_max_references = find_furthermost_citations(node, old_search_depth, "Reference") + add_citations(nodes, edges, old_max_references, old_search_depth, new_search_depth, "Reference", test_var) + node.group = 0 + handled_inserted_nodes.append(node) + + # moves known citation node to input and completes citations and references for this node + elif (node.group > 0) and (node.doi_url in inserted_nodes): + node_references = create_global_lists_cit(nodes, edges, node, 1, new_search_depth, "Reference", test_var) + add_citations(nodes, edges, node_references, 1, new_search_depth, "Reference", test_var) + old_max_citations = find_furthermost_citations(node, old_search_height, "Citation") + add_citations(nodes, edges, old_max_citations, old_search_height, new_search_height, "Citation", test_var) + node.group = 0 + handled_inserted_nodes.append(node) -def complete_changed_group_nodes(new_doi_list, search_depth_max, search_height_max, test_var): + return(handled_inserted_nodes) + + +def connect_old_and_new_input(input_nodes_list, input_edges_list, inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var = False): ''' - work in progress + :param input_nodes_list: list of nodes which are processed for new construction call + :type input_nodes_list: List[Publication] + + :param input_edges_list: list of links between nodes from input_nodes_list. + :type input_edges_list: List[List[String,String]] + + :param inserted_nodes: list of nodes which are inserted to new input array + :type inserted_nodes: List[String] + + :param old_search_depth: depth to search for references from old construction call + :type old_search_depth: int + + :param old_search_height: height to search for citations from old construction call + :type old_search_height: int + + :param new_search_depth: depth to search for references from new construction call + :type new_search_depth: int + + :param new_search_height: height to search for citations from new construction call + :type new_search_height: int + + :param test_var: variable to differenciate between test and url call + :type test_var: boolean + + completes the references and citations for nodes which were known in non input group ''' - changed_group_node_citations = [] - changed_group_node_references = [] + global nodes, edges + nodes = input_nodes_list + edges = input_edges_list - for node in nodes: - if (node.group < 0) and (node.doi in new_doi_list): - node.group = "input" - + handled_inserted_nodes = complete_changed_group_nodes(inserted_nodes, old_search_depth, old_search_height, new_search_depth, new_search_height, test_var) - elif (node.group > 0) and (node.doi in new_doi_list): - node.group = "input" + # copy all nodes from inserted_nodes to new node, if node is not in handled_inserted_nodes + not_handled_inserted_nodes = [node for node in inserted_nodes if node not in handled_inserted_nodes] + + # initializes nodes/edges from input and gets a list with publication objects for citations and references returned + #references_obj_list, citations_obj_list = initialize_nodes_list(not_handled_inserted_nodes, new_search_depth, new_search_height, test_var) + + # function calls to begin recursive processing up to max depth/height + #add_citations(nodes, edges, citations_obj_list, 1, new_search_height, "Citation", test_var) + #add_citations(nodes, edges, references_obj_list, 1, new_search_depth, "Reference", test_var) + init_graph_construction(not_handled_inserted_nodes, new_search_depth, new_search_height, test_var = test_var, input_nodes = nodes, input_edges = edges) diff --git a/verarbeitung/update_graph/update_depth.py b/verarbeitung/update_graph/update_depth.py index f87fb58b678ca0d16528713168556550fe5365b9..40849737bc70f7040dfad2510fb1fda03373214c 100644 --- a/verarbeitung/update_graph/update_depth.py +++ b/verarbeitung/update_graph/update_depth.py @@ -133,6 +133,8 @@ def update_depth(obj_input_list, input_edges, new_depth, new_height, test_var): # adds edges between reference group and citation group of known publications complete_inner_edges() + return(old_depth, old_height) + diff --git a/verarbeitung/update_graph/update_graph.py b/verarbeitung/update_graph/update_graph.py index 11a9eda9fb2638fdb4fe0a9560439a297e360612..169e17d166ae6ad905682b2ac6002f6fc0e856f0 100644 --- a/verarbeitung/update_graph/update_graph.py +++ b/verarbeitung/update_graph/update_graph.py @@ -1,4 +1,4 @@ -# -*- coding: utf-8 -*- +1# -*- coding: utf-8 -*- """ Functions to update a graph representing citations between multiple ACS/Nature journals @@ -20,6 +20,7 @@ sys.path.append("../../") from input.publication import Publication from verarbeitung.get_pub_from_input import get_pub +from verarbeitung.construct_new_graph.initialize_graph import init_graph_construction from .Knoten_Vergleich import doi_listen_vergleichen from .delete_nodes_edges import delete_nodes_and_edges from .connect_new_input import connect_old_and_new_input @@ -85,7 +86,6 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes # gets information from previous cunstruction call old_obj_input_list , old_edges_list = input_from_json(json_file) - print(type(old_edges_list[1])) # one global list to save the process of removing unneeded publications and one to save valid edges global processed_list, valid_edges @@ -104,9 +104,9 @@ def update_graph(new_doi_input_list, json_file, search_depth, search_height, tes if (len(deleted_nodes) > 0): processed_list, valid_edges = delete_nodes_and_edges(processed_list, common_nodes, old_edges_list) - update_depth(processed_list, valid_edges, search_depth, search_height, test_var) + old_search_depth, old_search_height = update_depth(processed_list, valid_edges, search_depth, search_height, test_var) if (len(inserted_nodes) > 0): - connect_old_and_new_input(json_file, inserted_nodes, search_depth, search_height, test_var) + connect_old_and_new_input(processed_list, valid_edges, inserted_nodes, old_search_depth, old_search_height, search_depth, search_height, test_var) return(processed_list, valid_edges)