diff --git a/assets/cn_default.js b/assets/cn_default.js
index d4e0d4188046c18d7855d1745c4c0fa1952e02b3..09c3a005c0f8390a4e658505f00c52b8751594ee 100644
--- a/assets/cn_default.js
+++ b/assets/cn_default.js
@@ -325,10 +325,11 @@ function textbox_content(node) {
text_info = "Title:" + '</br>' + node.name +
'</br>' +'</br>'+"Author:"+ '</br>' +authors+'</br>'+'</br>'+"Date:"+'</br>'
+node.year+'</br>'+'</br>'+"Journal:"+'</br>'+node.journal+'</br>'+'</br>'+"DOI:"
- +'</br>'+'<a href="'+node.doi+ '">'+node.doi+'</a>'+'</br>'+'</br>'+"Citations:"
+ +'</br>'+node.doi+'</br>'+'</br>'+"Citations:"
+'</br>'+node.citations;
text_abstract = node.abstract;
document.getElementById('textbox').innerHTML = text_info;
+ document.getElementById('textbox').innerHTML = text_info;
}
/**
diff --git a/assets/cn_timeline.js b/assets/cn_timeline.js
index 9a5199dd2c15f05fd680605fe47462d14c9c0ad7..978e1a5347ff9ee14882ee5db5f7328a5ca53527 100644
--- a/assets/cn_timeline.js
+++ b/assets/cn_timeline.js
@@ -121,7 +121,7 @@ var simulation = d3.forceSimulation()
else {return 75;}
}).strength(1))
.force("charge", d3.forceManyBody().strength(0.001))
- .force("center", d3.forceCenter(width/2-20, height/2+20))
+ .force("center", d3.forceCenter(width/2-20, height/2+40))
.alpha(0.004)
.velocityDecay(0.65)
.on("end", zoom_to);
@@ -205,7 +205,7 @@ function update(links, nodes) {
function updateXAxis(nodes) {
years = [];
for (i = 0; i < nodes.length; i++) {
- years.push(parseInt((nodes[i]["year"]).split(" ")[2]));
+ years.push(parseInt(parseInt(/\d{4}\s*$/.exec(nodes[i]["year"]))));
}
xscale = d3.scaleLinear()
@@ -413,11 +413,11 @@ function display_abstract(a) {
* updates the positions of the links and nodes
*/
function handle_tick() {
- link.attr("x1", function (d) {return xscale(parseInt((d.source.year).split(" ")[2]));})
+ link.attr("x1", function (d) {return xscale(parseInt(/\d{4}\s*$/.exec(d.source.year)));})
.attr("y1", function (d) {return d.source.y;})
- .attr("x2", function (d) {return xscale(parseInt((d.target.year).split(" ")[2]));})
+ .attr("x2", function (d) {return xscale(parseInt(/\d{4}\s*$/.exec(d.target.year)));})
.attr("y2", function (d) {return d.target.y;});
- node.attr("transform", function (d) {return "translate(" + xscale(parseInt((d.year).split(" ")[2])) + ", " + d.y + ")";});
+ node.attr("transform", function (d) {return "translate(" + xscale(parseInt(/\d{4}\s*$/.exec(d.year))) + ", " + d.y + ")";});
}
/**
diff --git a/assets/json_text.json b/assets/json_text.json
index 2effc53e8cc980713aa033b59fcf9b4c644ad1d1..c93bc2d0b3189e89d8d4bcd469256c02b4e4674b 100644
--- a/assets/json_text.json
+++ b/assets/json_text.json
@@ -1,840 +1 @@
-{
- "nodes": [
- {
- "doi": "https://doi.org/10.1021/ci980029a",
- "name": "Prediction of Human Intestinal Absorption of Drug Compounds from Molecular Structure",
- "author": [
- "Matthew D. Wessel",
- "Peter C. Jurs",
- "John W. Tolan",
- "Steven M. Muskal"
- ],
- "year": "June 19, 1998",
- "journal": "J. Chem. Inf. Comput. Sci.",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/ci025620t",
- "name": "Active Learning with Support Vector Machines in the Drug Discovery Process\u2021",
- "author": [
- "Manfred K. Warmuth",
- "Jun Liao",
- "Gunnar R\u00e4tsch",
- "Michael Mathieson",
- "Santosh Putta",
- "Christian Lemmen"
- ],
- "year": "February 12, 2003",
- "journal": "J. Chem. Inf. Comput. Sci.",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.5b00332",
- "name": "Feasibility of Active Machine Learning for Multiclass Compound Classification",
- "author": [
- "Tobias Lang",
- "Florian Flachsenberg",
- "Ulrike von Luxburg",
- "Matthias Rarey"
- ],
- "year": "January 7, 2016",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 31
- },
- {
- "doi": "https://doi.org/10.1021/jm400099d",
- "name": "Rapid Discovery of a Novel Series of Abl Kinase Inhibitors by Application of an Integrated Microfluidic Synthesis and Screening Platform",
- "author": [
- "Bimbisar Desai",
- "Karen Dixon",
- "Elizabeth Farrant",
- "Qixing Feng",
- "Karl R. Gibson",
- "Willem P. van Hoorn",
- "James Mills",
- "Trevor Morgan",
- "David M. Parry",
- "Manoj K. Ramjee",
- "Christopher N. Selway",
- "Gary J. Tarver",
- "Gavin Whitlock",
- "Adrian G. Wright"
- ],
- "year": "February 26, 2013",
- "journal": "J. Med. Chem. ",
- "group": "Reference",
- "depth": 0,
- "citations": 89
- },
- {
- "doi": "https://doi.org/10.1021/ci700085q",
- "name": "Virtual Screening System for Finding Structurally Diverse Hits by Active Learning",
- "author": [
- "Yukiko Fujiwara",
- "Yoshiko Yamashita",
- "Tsutomu Osoda",
- "Minoru Asogawa",
- "Chiaki Fukushima",
- "Masaaki Asao",
- "Hideshi Shimadzu",
- "Kazuya Nakao",
- "Ryo Shimizu"
- ],
- "year": "March 20, 2008",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 23
- },
- {
- "doi": "https://doi.org/10.1021/acscentsci.7b00572",
- "name": "Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules",
- "author": [
- "Rafael G\u00f3mez-Bombarelli",
- "Jennifer N. Wei",
- "David Duvenaud",
- "Jos\u00e9 Miguel Hern\u00e1ndez-Lobato",
- "Benjam\u00edn S\u00e1nchez-Lengeling",
- "Dennis Sheberla",
- "Jorge Aguilera-Iparraguirre",
- "Timothy D. Hirzel",
- "Ryan P. Adams",
- "Al\u00e1n Aspuru-Guzik"
- ],
- "year": "January 12, 2018",
- "journal": "ACS Cent. Sci.",
- "group": "Reference",
- "depth": 0,
- "citations": 98
- },
- {
- "doi": "https://doi.org/10.1021/ci700157b",
- "name": "y-Randomization and Its Variants in QSPR/QSAR",
- "author": [
- "Christoph R\u00fccker",
- "Gerta R\u00fccker",
- "Markus Meringer"
- ],
- "year": "September 20, 2007",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/acscentsci.6b00367",
- "name": "Low Data Drug Discovery with One-Shot Learning",
- "author": [
- "Han Altae-Tran",
- "Bharath Ramsundar",
- "Aneesh S. Pappu",
- "Vijay Pande"
- ],
- "year": "April 3, 2017",
- "journal": "ACS Cent. Sci.",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/ci400737s",
- "name": "QSAR Modeling of Imbalanced High-Throughput Screening Data in PubChem",
- "author": [
- "Alexey V. Zakharov",
- "Megan L. Peach",
- "Markus Sitzmann",
- "Marc C. Nicklaus"
- ],
- "year": "February 13, 2014",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 74
- },
- {
- "doi": "https://doi.org/10.1021/jm0608356",
- "name": "Benchmarking Sets for Molecular Docking",
- "author": [
- "Niu Huang",
- "Brian K. Shoichet",
- "John J. Irwin"
- ],
- "year": "October 26, 2006",
- "journal": "Journal of Medicinal Chemistry",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/ci200528d",
- "name": "Recognizing Pitfalls in Virtual Screening: A Critical Review",
- "author": [
- "Thomas Scior",
- "Andreas Bender",
- "Gary Tresadern",
- "Jos\u00e9 L. Medina-Franco",
- "Karina Mart\u00ednez-Mayorga",
- "Thierry Langer",
- "Karina Cuanalo-Contreras",
- "Dimitris K. Agrafiotis"
- ],
- "year": "March 21, 2012",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/jm025507u",
- "name": "Docking into Knowledge-Based Potential Fields:\u2009 A Comparative Evaluation of DrugScore",
- "author": [
- "Christoph A. Sotriffer",
- "Holger Gohlke",
- "Gerhard Klebe"
- ],
- "year": "April 20, 2002",
- "journal": "Journal of Medicinal Chemistry",
- "group": "Reference",
- "depth": 0,
- "citations": 72
- },
- {
- "doi": "https://doi.org/10.1021/acs.accounts.6b00491",
- "name": "Forging the Basis for Developing Protein\u2013Ligand Interaction Scoring Functions",
- "author": [
- "Zhihai Liu",
- "Minyi Su",
- "Li Han",
- "Jie Liu",
- "Qifan Yang",
- "Yan Li",
- "Renxiao Wang"
- ],
- "year": "February 9, 2017",
- "journal": "Acc. Chem. Res.",
- "group": "Reference",
- "depth": 0,
- "citations": 100
- },
- {
- "doi": "https://doi.org/10.1021/ci400510e",
- "name": "Nonlinear Scoring Functions for Similarity-Based Ligand Docking and Binding Affinity Prediction",
- "author": [
- "Michal Brylinski"
- ],
- "year": "October 30, 2013",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 35
- },
- {
- "doi": "https://doi.org/10.1021/ci2003889",
- "name": "NNScore 2.0: A Neural-Network Receptor\u2013Ligand Scoring Function",
- "author": [
- "Jacob D. Durrant",
- "J. Andrew McCammon"
- ],
- "year": "October 22, 2011",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Reference",
- "depth": 0,
- "citations": 99
- },
- {
- "doi": "https://doi.org/10.1021/acs.analchem.1c03508",
- "name": "Explainable Deep Learning-Assisted Fluorescence Discrimination for Aminoglycoside Antibiotic Identification",
- "author": [
- "Xiaoqing Tan",
- "Yongpeng Liang",
- "Yingying Ye",
- "Zhihao Liu",
- "Jianxin Meng",
- "Fengyu Li"
- ],
- "year": "January 3, 2022",
- "journal": "Anal. Chem.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/jacs.1c08211",
- "name": "Self-Improving Photosensitizer Discovery System via Bayesian Search with First-Principle Simulations",
- "author": [
- "Shidang Xu",
- "Jiali Li",
- "Pengfei Cai",
- "Xiaoli Liu",
- "Bin Liu",
- "Xiaonan Wang",
- "Shengyong Yang"
- ],
- "year": "November 17, 2021",
- "journal": "Journal of the American Chemical Society",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.joc.1c01242",
- "name": "Application of an Electrochemical Microflow Reactor for Cyanosilylation: Machine Learning-Assisted Exploration of Suitable Reaction Conditions for Semi-Large-Scale Synthesis",
- "author": [
- "Eisuke Sato",
- "Mayu Fujii",
- "Hiroki Tanaka",
- "Koichi Mitsudo",
- "Masaru Kondo",
- "Shinobu Takizawa",
- "Hiroaki Sasai",
- "Takeshi Washio",
- "Kazunori Ishikawa",
- "Seiji Suga"
- ],
- "year": "August 6, 2021",
- "journal": "J. Org. Chem.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jmedchem.1c01788",
- "name": "Back to the Medicinal Chemistry Future",
- "author": [
- "Mariateresa Giustiniano",
- "Christian W. Gruber",
- "Caitlin N. Kent",
- "Paul C. Trippier"
- ],
- "year": "November 1, 2021",
- "journal": "Journal of Medicinal Chemistry",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acscentsci.1c00535",
- "name": "The Evolution of Data-Driven Modeling in Organic Chemistry",
- "author": [
- "Wendy L. Williams",
- "Lingyu Zeng",
- "Tobias Gensch",
- "Matthew S. Sigman",
- "Abigail G. Doyle",
- "Eric V. Anslyn"
- ],
- "year": "October 19, 2021",
- "journal": "ACS Cent. Sci.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jpclett.1c02477",
- "name": "Size Doesn\u2019t Matter: Predicting Physico- or Biochemical Properties Based on Dozens of Molecules",
- "author": [
- "Kirill Karpov",
- "Artem Mitrofanov",
- "Vadim Korolev",
- "Valery Tkachenko"
- ],
- "year": "September 16, 2021",
- "journal": "J. Phys. Chem. Lett.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.1c00601",
- "name": "SMINBR: An Integrated Network and Chemoinformatics Tool Specialized for Prediction of Two-Component Crystal Formation",
- "author": [
- "Lulu Zheng",
- "Bin Zhu",
- "Zengrui Wu",
- "Fang Liang",
- "Minghuang Hong",
- "Guixia Liu",
- "Weihua Li",
- "Guobin Ren",
- "Yun Tang"
- ],
- "year": "August 26, 2021",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acssensors.1c01600",
- "name": "Tailored Biosensors for Drug Screening, Efficacy Assessment, and Toxicity Evaluation",
- "author": [
- "Yi Tao",
- "Lin Chen",
- "Meiling Pan",
- "Fei Zhu",
- "Dong Zhu"
- ],
- "year": "September 13, 2021",
- "journal": "ACS Sens.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.chemrev.0c00749",
- "name": "Machine Learning for Electronically Excited States of Molecules",
- "author": [
- "Julia Westermayr",
- "Philipp Marquetand"
- ],
- "year": "November 19, 2020",
- "journal": "Chem. Rev.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.1c00292",
- "name": "True Accuracy of Fast Scoring Functions to Predict High-Throughput Screening Data from Docking Poses: The Simpler the Better",
- "author": [
- "Viet-Khoa Tran-Nguyen",
- "Guillaume Bret",
- "Didier Rognan"
- ],
- "year": "June 10, 2021",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.1c00086",
- "name": "Balancing Data on Deep Learning-Based Proteochemometric Activity Classification",
- "author": [
- "Angela Lopez-del Rio",
- "Sergio Picart-Armada",
- "Alexandre Perera-Lluna"
- ],
- "year": "March 29, 2021",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.0c01143",
- "name": "The Playbooks of Medicinal Chemistry Design Moves",
- "author": [
- "Mahendra Awale",
- "J\u00e9r\u00f4me Hert",
- "Laura Guasch",
- "Sereina Riniker",
- "Christian Kramer"
- ],
- "year": "February 1, 2021",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.0c01046",
- "name": "Machine Learning Enhanced Spectrum Recognition Based on Computer Vision (SRCV) for Intelligent NMR Data Extraction",
- "author": [
- "Wenqiang Jia",
- "Zhuo Yang",
- "Minjian Yang",
- "Liang Cheng",
- "Zengrong Lei",
- "Xiaojian Wang"
- ],
- "year": "November 10, 2020",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acsbiomaterials.0c01459",
- "name": "Satellite-Based Sensor for Environmental Heat-Stress Sweat Creatinine Monitoring: The Remote Artificial Intelligence-Assisted Epidermal Wearable Sensing for Health Evaluation",
- "author": [
- "Surachate Kalasin",
- "Pantawan Sangnuang",
- "Werasak Surareungchai"
- ],
- "year": "December 23, 2020",
- "journal": "ACS Biomater. Sci. Eng.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.0c00565",
- "name": "Adding Stochastic Negative Examples into Machine Learning Improves Molecular Bioactivity Prediction",
- "author": [
- "Elena L. C\u00e1ceres",
- "Nicholas C. Mew",
- "Michael J. Keiser"
- ],
- "year": "November 27, 2020",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.0c01028",
- "name": "Dipole Moment Variation Clears Up Electronic Excitations in the \u03c0-Stacked Complexes of Fluorescent Protein Chromophores",
- "author": [
- "Maria G. Khrenova",
- "Fedor D. Mulashkin",
- "Egor S. Bulavko",
- "Tatiana M. Zakharova",
- "Alexander V. Nemukhin"
- ],
- "year": "November 18, 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": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jpclett.0c02836",
- "name": "COSMO-RS-Based Descriptors for the Machine Learning-Enabled Screening of Nucleotide Analogue Drugs against SARS-CoV-2",
- "author": [
- "Sergey Gusarov",
- "Stanislav R. Stoyanov"
- ],
- "year": "October 26, 2020",
- "journal": "J. Phys. Chem. Lett.",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.0c00155",
- "name": "LIT-PCBA: An Unbiased Data Set for Machine Learning and Virtual Screening",
- "author": [
- "Viet-Khoa Tran-Nguyen",
- "C\u00e9lien Jacquemard",
- "Didier Rognan"
- ],
- "year": "April 13, 2020",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 1
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.9b01212",
- "name": "Predicting Binding from Screening Assays with Transformer Network Embeddings",
- "author": [
- "Paul Morris",
- "Rachel St. Clair",
- "William Edward Hahn",
- "Elan Barenholtz"
- ],
- "year": "June 22, 2020",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jmedchem.9b01989",
- "name": "Drug Research Meets Network Science: Where Are We?",
- "author": [
- "Maurizio Recanatini",
- "Chiara Cabrelle"
- ],
- "year": "April 27, 2020",
- "journal": "Journal of Medicinal Chemistry",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.jmedchem.9b02147",
- "name": "Transfer Learning for Drug Discovery",
- "author": [
- "Chenjing Cai",
- "Shiwei Wang",
- "Youjun Xu",
- "Weilin Zhang",
- "Ke Tang",
- "Qi Ouyang",
- "Luhua Lai",
- "Jianfeng Pei"
- ],
- "year": "July 16, 2020",
- "journal": "Journal of Medicinal Chemistry",
- "group": "Citedby",
- "depth": 1,
- "citations": 1
- },
- {
- "doi": "https://doi.org/10.1021/acs.jcim.9b00909",
- "name": "Database of Nuclear Independent Chemical Shifts (NICS) versus NICSZZ of Polycyclic Aromatic Hydrocarbons (PAHs)",
- "author": [
- "Fernando Alvarez-Ram\u00edrez",
- "Yosadara Ruiz-Morales"
- ],
- "year": "November 12, 2019",
- "journal": "Journal of Chemical Information and Modeling",
- "group": "Citedby",
- "depth": 1,
- "citations": 0
- },
- {
- "doi": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "name": "Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery",
- "author": [
- "Xin Yang",
- "Yifei Wang",
- "Ryan Byrne",
- "Gisbert Schneider",
- "Shengyong Yang"
- ],
- "year": "July 11, 2019",
- "journal": "Chem. Rev.",
- "group": "Input",
- "depth": -1,
- "citations": 99
- },
- {
- "doi": "https://doi.org/10.1021/acs.jpclett.1c03335",
- "name": "Machine Learning Prediction of the Exfoliation Energies of Two-Dimension Materials via Data-Driven Approach",
- "author": [
- "Zhongyu Wan",
- "Quan-De Wang"
- ],
- "year": "November 18, 2021",
- "journal": "J. Phys. Chem. Lett.",
- "group": "Citedby",
- "depth": 0,
- "citations": 0
- }
- ],
- "links": [
- {
- "source": "https://doi.org/10.1021/acs.jpclett.1c03335",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci980029a"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci025620t"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/acs.jcim.5b00332"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/jm400099d"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci700085q"
- },
-
-
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/acscentsci.7b00572"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci700157b"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/acscentsci.6b00367"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci400737s"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/jm0608356"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci200528d"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/jm025507u"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/acs.accounts.6b00491"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci400510e"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.8b00728",
- "target": "https://doi.org/10.1021/ci2003889"
- },
-
-
-
-
- {
- "source": "https://doi.org/10.1021/acs.jcim.5b00332",
- "target": "https://doi.org/10.1021/jm400099d"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.5b00332",
- "target": "https://doi.org/10.1021/ci700085q"
- },
- {
- "source": "https://doi.org/10.1021/acscentsci.7b00572",
- "target": "https://doi.org/10.1021/ci200528d"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.1c00292",
- "target": "https://doi.org/10.1021/acs.jcim.0c00155"
- },
- {
- "source": "https://doi.org/10.1021/acs.jpclett.1c02477",
- "target": "https://doi.org/10.1021/acs.jmedchem.9b02147"
- },
- {
- "source": "https://doi.org/10.1021/acs.analchem.1c03508",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/jacs.1c08211",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.joc.1c01242",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jmedchem.1c01788",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acscentsci.1c00535",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jpclett.1c02477",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.1c00601",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acssensors.1c01600",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.chemrev.0c00749",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.1c00292",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.1c00086",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.0c01143",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.0c01046",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acsbiomaterials.0c01459",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.0c00565",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.0c01028",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jmedchem.0c01332",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jpclett.0c02836",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.0c00155",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.9b01212",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jmedchem.9b01989",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jmedchem.9b02147",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- },
- {
- "source": "https://doi.org/10.1021/acs.jcim.9b00909",
- "target": "https://doi.org/10.1021/acs.chemrev.8b00728"
- }
- ]
-}
\ No newline at end of file
+{"nodes": [{"doi": "https://doi.org/10.1021/ci0496797", "name": "LINGO, an Efficient Holographic Text Based Method To Calculate Biophysical Properties and Intermolecular Similarities", "author": ["David Vidal", "Michael Thormann", "Miquel Pons"], "year": "15.02.2005", "journal": "Journal of Chemical Information and Modeling", "abstract": "SMILES strings are the most compact text based molecular representations. Implicitly they contain the information needed to compute all kinds of molecular structures and, thus, molecular properties derived from these structures. We show that this implicit information can be accessed directly at SMILES string level without the need to apply explicit time-consuming conversion of the SMILES strings into molecular graphs or 3D structures with subsequent 2D or 3D QSPR calculations. Our method is based on the fragmentation of SMILES strings into overlapping substrings of a defined size that we call LINGOs. The integral set of LINGOs derived from a given SMILES string, the LINGO profile, is a hologram of the SMILES representation of the molecule described. LINGO profiles provide input for QSPR models and the calculation of intermolecular similarities at very low computational cost. The octanol/water partition coefficient (LlogP) QSPR model achieved a correlation coefficient R2=0.93, a root-mean-square error RRMS=0.49 log units, a goodness of prediction correlation coefficient Q2=0.89 and a QRMS=0.61 log units. The intrinsic aqueous solubility (LlogS) QSPR model achieved correlation coefficient values of R2=0.91, Q2=0.82, and RRMS=0.60 and QRMS=0.89 log units. Integral Tanimoto coefficients computed from LINGO profiles provided sharp discrimination between random and bioisoster pairs extracted from Accelrys Bioster Database. Average similarities (LINGOsim) were 0.07 for the random pairs and 0.36 for the bioisosteric pairs. ", "group": "Input", "depth": 0, "citations": 100}, {"doi": "https://doi.org/10.1021/acs.jcim.1c00866", "name": "Validation of a Field-Based Ligand Screener Using a Novel Benchmarking Data Set for Assessing 3D-Based Virtual Screening Methods", "author": ["Ilenia Giangreco", "Abhik Mukhopadhyay", "Jason C. Cole"], "year": "18.11.2021", "journal": "Journal of Chemical Information and Modeling", "abstract": "Ligand-based methods play a crucial role in virtual screening when the 3D structure of the target is not available. This study discusses the results of a validation study of the CSD field-based ligand screener using a novel benchmarking data set containing 56 targets. The data set was created starting from the target UniProt IDs in a previously published data set (i.e., the AZ data set), by mining ChEMBL to find known active molecules for these targets and by using DUD-E to generate property-matched decoys of the identified actives. Several experiments were performed to assess the virtual screening performance of the new method. One of its strengths is that it can use an overlay of multiple flexible ligands as a query without the need to run several parallel calculations with one ligand at a time. Here, we discuss how changes to different parameter settings or adoption of different query models can influence the final performance compared to the performance when using the experimentally observed overlay of ligands. We have also generated the enrichment scores based on three external benchmark data sets to enable the comparison with existing methods previously validated using these data sets. Here, we present results for the standard DUD-E data set, the DUD-E+ data set, as well as the DUD_Lib_VS_1.0 data set which was designed for ligand-based virtual screening validation and hence is more suitable for this type of methods.", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jcim.0c01127", "name": "SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning", "author": ["Xinhao Li", "Denis Fourches"], "year": "14.03.2021", "journal": "Journal of Chemical Information and Modeling", "abstract": "Simplified molecular input line entry system (SMILES)-based deep learning models are slowly emerging as an important research topic in cheminformatics. In this study, we introduce SMILES pair encoding (SPE), a data-driven tokenization algorithm. SPE first learns a vocabulary of high-frequency SMILES substrings from a large chemical dataset (e.g., ChEMBL) and then tokenizes SMILES based on the learned vocabulary for the actual training of deep learning models. SPE augments the widely used atom-level tokenization by adding human-readable and chemically explainable SMILES substrings as tokens. Case studies show that SPE can achieve superior performances on both molecular generation and quantitative structure\u2013activity relationship (QSAR) prediction tasks. In particular, the SPE-based generative models outperformed the atom-level tokenization model in the aspects of novelty, diversity, and ability to resemble the training set distribution. The performance of SPE-based QSAR prediction models were evaluated using 24 benchmark datasets where SPE consistently either did match or outperform atom-level and k-mer tokenization. Therefore, SPE could be a promising tokenization method for SMILES-based deep learning models. An open-source Python package SmilesPE was developed to implement this algorithm and is now freely available at https://github.com/XinhaoLi74/SmilesPE.", "group": "Citedby", "depth": 1, "citations": 0}, {"doi": "https://doi.org/10.1021/acs.jcim.9b01210", "name": "LigMate: A Multifeature Integration Algorithm for Ligand-Similarity-Based Virtual Screening", "author": ["Maximilian Grimm", "Yang Liu", "Xiaocong Yang", "Chunya Bu", "Zhixiong Xiao", "Yang Cao"], "year": "16.11.2020", "journal": "Journal of Chemical Information and Modeling", "abstract": "Ligand-similarity-based virtual screening is one of the most applicable computer-aided drug design techniques. The current methodology relies heavily on several descriptors of molecular features, including atoms (zero-dimensional, 0D), the presence or absence of structural features (one-dimensional, 1D), topological descriptors (two-dimensional, 2D), geometry and volume (three-dimensional, 3D), or stereoelectronic and stereodynamic properties (four-dimensional, 4D). These descriptors have been frequently used in virtual screening; however, they are usually used independently without integration, which may hinder effective and precise virtual screening. In this study, we developed a multifeature integration algorithm named LigMate, which employs a Hungarian algorithm-based matching and a machine learning-based nonlinear combination of various descriptors, including the new relevant descriptors focusing on the maximum common substructures (maximum common substructure score, MCSS), the relative distance of atoms from the ligand mass center (intraligand distance score, ILDS), as well as the ring differences (ring score, RS). In the benchmark tests, LigMate achieved an overall enrichment factor of the first percent (EF1) of 36.14 and an area under the curve (AUC) value of 0.81 on the DUD-E data set, as well as an EF1 of 15.44 and an AUC of 0.69 on the maximum unbiased validation (MUV) data set, outperforming the control methods that are based on single descriptors. Thus, our study provides a new framework for multiple feature integration, which can benefit ligand-similarity-based virtual screening. LigMate is freely available for noncommercial users at http://cao.labshare.cn/ligmate/.", "group": "Citedby", "depth": 1, "citations": 2}, {"doi": "https://doi.org/10.1021/acsomega.9b00488", "name": "Stereo-Aware Extension of HOSE Codes", "author": ["Stefan Kuhn", "Sean R. Johnson"], "year": "23.04.2019", "journal": "ACS Omega", "abstract": "Descriptions of molecular environments have many applications in chemoinformatics, including chemical shift prediction. Hierarchically ordered spherical environment (HOSE) codes are the most popular such descriptions. We developed a method to extend these with stereochemistry information. It enables distinguishing atoms which would be considered identical in traditional HOSE codes. The use of our method is demonstrated by chemical shift predictions for molecules in the nmrshiftdb2 database. We give a full specification and an implementation.", "group": "Citedby", "depth": 1, "citations": 7}, {"doi": "https://doi.org/10.1021/acs.jcim.8b00663", "name": "Evaluation of Cross-Validation Strategies in Sequence-Based Binding Prediction Using Deep Learning", "author": ["Angela Lopez-del Rio", "Alfons Nonell-Canals", "David Vidal", "Alexandre Perera-Lluna"], "year": "07.02.2019", "journal": "Journal of Chemical Information and Modeling", "abstract": "Binding prediction between targets and drug-like compounds through deep neural networks has generated promising results in recent years, outperforming traditional machine learning-based methods. However, the generalization capability of these classification models is still an issue to be addressed. In this work, we explored how different cross-validation strategies applied to data from different molecular databases affect to the performance of binding prediction proteochemometrics models. These strategies are (1) random splitting, (2) splitting based on K-means clustering (both of actives and inactives), (3) splitting based on source database, and (4) splitting based both in the clustering and in the source database. These schemas are applied to a deep learning proteochemometrics model and to a simple logistic regression model to be used as baseline. Additionally, two different ways of describing molecules in the model are tested: (1) by their SMILES and (2) by three fingerprints. The classification performance of our deep learning-based proteochemometrics model is comparable to the state of the art. Our results show that the lack of generalization of these models is due to a bias in public molecular databases and that a restrictive cross-validation schema based on compound clustering leads to worse but more robust and credible results. Our results also show better performance when representing molecules by their fingerprints.", "group": "Citedby", "depth": 1, "citations": 9}, {"doi": "https://doi.org/10.1021/acs.jcim.8b00803", "name": "Identifying Structure\u2013Property Relationships through SMILES Syntax Analysis with Self-Attention Mechanism", "author": ["Shuangjia Zheng", "Xin Yan", "Yuedong Yang", "Jun Xu"], "year": "22.01.2019", "journal": "Journal of Chemical Information and Modeling", "abstract": "Recognizing substructures and their relations embedded in a molecular structure representation is a key process for structure\u2013activity or structure\u2013property relationship (SAR/SPR) studies. A molecular structure can be explicitly represented as either a connection table (CT) or linear notation, such as SMILES, which is a language describing the connectivity of atoms in the molecular structure. Conventional SAR/SPR approaches rely on partitioning the CT into a set of predefined substructures as structural descriptors. In this work, we propose a new method to identifying SAR/SPR through linear notation (for example, SMILES) syntax analysis with self-attention mechanism, an interpretable deep learning architecture. The method has been evaluated by predicting chemical properties, toxicology, and bioactivity from experimental data sets. Our results demonstrate that the method yields superior performance compared with state-of-the-art models. Moreover, the method can produce chemically interpretable results, which can be used for a chemist to design and synthesize the activity- or property-improved compounds.", "group": "Citedby", "depth": 1, "citations": 34}, {"doi": "https://doi.org/10.1021/acs.jmedchem.8b00832", "name": "Structure-Based Design of MptpB Inhibitors That Reduce Multidrug-Resistant Mycobacterium tuberculosis Survival and Infection Burden in Vivo", "author": ["Clare F. Vickers", "Ana P. G. Silva", "Ajanta Chakraborty", "Paulina Fernandez", "Natalia Kurepina", "Charis Saville", "Yandi Naranjo", "Miquel Pons", "Laura S. Schnettger", "Maximiliano G. Gutierrez", "Steven Park", "Barry N. Kreiswith", "David S. Perlin", "Eric J. Thomas", "Jennifer S. Cavet", "Lydia Tabernero"], "year": "28.08.2018", "journal": "Journal of Medicinal Chemistry", "abstract": "Mycobacterium tuberculosis protein-tyrosine-phosphatase B (MptpB) is a secreted virulence factor that subverts antimicrobial activity in the host. We report here the structure-based design of selective MptpB inhibitors that reduce survival of multidrug-resistant tuberculosis strains in macrophages and enhance killing efficacy by first-line antibiotics. Monotherapy with an orally bioavailable MptpB inhibitor reduces infection burden in acute and chronic guinea pig models and improves the overall pathology. Our findings provide a new paradigm for tuberculosis treatment.", "group": "Citedby", "depth": 1, "citations": 18}, {"doi": "https://doi.org/10.1021/acs.jcim.6b00694", "name": "Shallow Representation Learning via Kernel PCA Improves QSAR Modelability", "author": ["Stefano E. Rensi", "Russ B. Altman"], "year": "20.07.2017", "journal": "Journal of Chemical Information and Modeling", "abstract": "Linear models offer a robust, flexible, and computationally efficient set of tools for modeling quantitative structure\u2013activity relationships (QSARs) but have been eclipsed in performance by nonlinear methods. Support vector machines (SVMs) and neural networks are currently among the most popular and accurate QSAR methods because they learn new representations of the data that greatly improve modelability. In this work, we use shallow representation learning to improve the accuracy of L1 regularized logistic regression (LASSO) and meet the performance of Tanimoto SVM. We embedded chemical fingerprints in Euclidean space using Tanimoto (a.k.a. Jaccard) similarity kernel principal component analysis (KPCA) and compared the effects on LASSO and SVM model performance for predicting the binding activities of chemical compounds against 102 virtual screening targets. We observed similar performance and patterns of improvement for LASSO and SVM. We also empirically measured model training and cross-validation times to show that KPCA used in concert with LASSO classification is significantly faster than linear SVM over a wide range of training set sizes. Our work shows that powerful linear QSAR methods can match nonlinear methods and demonstrates a modular approach to nonlinear classification that greatly enhances QSAR model prototyping facility, flexibility, and transferability.", "group": "Citedby", "depth": 1, "citations": 10}, {"doi": "https://doi.org/10.1021/acs.chemrestox.5b00481", "name": "ToxCast EPA in Vitro to in Vivo Challenge: Insight into the Rank-I Model", "author": ["Sergii Novotarskyi", "Ahmed Abdelaziz", "Yurii Sushko", "Robert K\u00f6rner", "Joachim Vogt", "Igor V. Tetko"], "year": "27.04.2016", "journal": "Chem. Res. Toxicol.", "abstract": "The ToxCast EPA challenge was managed by TopCoder in Spring 2014. The goal of the challenge was to develop a model to predict the lowest effect level (LEL) concentration based on in vitro measurements and calculated in silico descriptors. This article summarizes the computational steps used to develop the Rank-I model, which calculated the lowest prediction error for the secret test data set of the challenge. The model was developed using the publicly available Online CHEmical database and Modeling environment (OCHEM), and it is freely available at http://ochem.eu/article/68104. Surprisingly, this model does not use any in vitro measurements. The logic of the decision steps used to develop the model and the reason to skip inclusion of in vitro measurements is described. We also show that inclusion of in vitro assays would not improve the accuracy of the model.", "group": "Citedby", "depth": 1, "citations": 19}, {"doi": "https://doi.org/10.1021/acs.langmuir.5b03074", "name": "Self-Assembled Binary Nanoscale Systems: Multioutput Model with LFER-Covariance Perturbation Theory and an Experimental\u2013Computational Study of NaGDC-DDAB Micelles", "author": ["Paula V. Messina", "Jose Miguel Besada-Porto", "Humberto Gonz\u00e1lez-D\u00edaz", "Juan M. Ruso"], "year": "20.10.2015", "journal": "Langmuir", "abstract": "Studies of the self-aggregation of binary systems are of both theoretical and practical importance. They provide an opportunity to investigate the influence of the molecular structure of the hydrophobe on the nonideality of mixing. On the other hand, linear free energy relationship (LFER) models, such as Hansch\u2019s equations, may be used to predict the properties of chemical compounds such as drugs or surfactants. However, the task becomes more difficult once we want to predict simultaneaously the effect over multiple output properties of binary systems of perturbations under multiple input experimental boundary conditions (bj). As a consequence, we need computational chemistry or chemoinformatics models that may help us to predict different properties of the autoaggregation process of mixed surfactants under multiple conditions. In this work, we have developed the first model that combines perturbation theory (PT) and LFER ideas. The model uses as input covariance PT operators (CPTOs). CPTOs are calculated as the difference between covariance \u0394Cov(i\u03bck) functions before and after multiple perturbations in the binary system. In turn, covariances calculated as the product of two Box\u2013Jenkins operators (BJO) operators. BJOs are used to measure the deviation of the structure of different chemical compounds from a set of molecules measured under a given subset of experimental conditions. The best CPT-LFER model found predicted the effects of 25\u202f000 perturbations over 9 different properties of binary systems. We also reported experimental studies of different experimental properties of the binary system formed by sodium glycodeoxycholate and didodecyldimethylammonium bromide (NaGDC-DDAB). Last, we used our CPT-LFER model to carry out a 1000 data point simulation of the properties of the NaGDC-DDAB system under different conditions not studied experimentally.", "group": "Citedby", "depth": 1, "citations": 8}, {"doi": "https://doi.org/10.1021/ci500150t", "name": "Blocked Inverted Indices for Exact Clustering of Large Chemical Spaces", "author": ["Philipp Thiel", "Lisa Sach-Peltason", "Christian Ottmann", "Oliver Kohlbacher"], "year": "19.08.2014", "journal": "Journal of Chemical Information and Modeling", "abstract": "The calculation of pairwise compound similarities based on fingerprints is one of the fundamental tasks in chemoinformatics. Methods for efficient calculation of compound similarities are of the utmost importance for various applications like similarity searching or library clustering. With the increasing size of public compound databases, exact clustering of these databases is desirable, but often computationally prohibitively expensive. We present an optimized inverted index algorithm for the calculation of all pairwise similarities on 2D fingerprints of a given data set. In contrast to other algorithms, it neither requires GPU computing nor yields a stochastic approximation of the clustering. The algorithm has been designed to work well with multicore architectures and shows excellent parallel speedup. As an application example of this algorithm, we implemented a deterministic clustering application, which has been designed to decompose virtual libraries comprising tens of millions of compounds in a short time on current hardware. Our results show that our implementation achieves more than 400 million Tanimoto similarity calculations per second on a common desktop CPU. Deterministic clustering of the available chemical space thus can be done on modern multicore machines within a few days.", "group": "Citedby", "depth": 1, "citations": 8}, {"doi": "https://doi.org/10.1021/ci500364e", "name": "Applicability Domain Based on Ensemble Learning in Classification and Regression Analyses", "author": ["Hiromasa Kaneko", "Kimito Funatsu"], "year": "13.08.2014", "journal": "Journal of Chemical Information and Modeling", "abstract": "We discuss applicability domains (ADs) based on ensemble learning in classification and regression analyses. In regression analysis, the AD can be appropriately set, although attention needs to be paid to the bias of the predicted values. However, because the AD set in classification analysis is too wide, we propose an AD based on ensemble learning and data density. First, we set a threshold for data density below which the prediction result of new data is not reliable. Then, only for new data with a data density higher than the threshold, we consider the reliability of the prediction result based on ensemble learning. By analyzing data from numerical simulations and quantitative structural relationships, we validate our discussion of ADs in classification and regression analyses and confirm that appropriate ADs can be set using the proposed method.", "group": "Citedby", "depth": 1, "citations": 37}, {"doi": "https://doi.org/10.1021/ed400302u", "name": "Use of Freely Available and Open Source Tools for In Silico Screening in Chemical Biology", "author": ["Gareth W. Price", "Phillip S. Gould", "Andrew Marsh"], "year": "14.02.2014", "journal": "J. Chem. Educ.", "abstract": "Automated computational docking of large libraries of chemical compounds to a protein can aid in pharmaceutical drug design and gives scientists with basic computer experience a tool to help plan wet laboratory investigations when exploring the combination of chemical and pharmacological spaces. The use of open source tools to develop and select ligands for subsequent screening is outlined. A protocol leveraging the power of Open Babel and AutoDock Vina to perform file conversion, minimization, and docking implemented as a Python script is offered.", "group": "Citedby", "depth": 1, "citations": 12}, {"doi": "https://doi.org/10.1021/ci400264f", "name": "SCISSORS: Practical Considerations", "author": ["Steven M. Kearnes", "Imran S. Haque", "Vijay S. Pande"], "year": "01.12.2013", "journal": "Journal of Chemical Information and Modeling", "abstract": "Molecular similarity has been effectively applied to many problems in cheminformatics and computational drug discovery, but modern methods can be prohibitively expensive for large-scale applications. The SCISSORS method rapidly approximates measures of pairwise molecular similarity such as ROCS and LINGO Tanimotos, acting as a filter to quickly reduce the size of a problem. We report an in-depth analysis of SCISSORS performance, including a mapping of the SCISSORS error distribution, benchmarking, and investigation of several algorithmic modifications. We show that SCISSORS can accurately predict multiconformer similarity and suggest a method for estimating optimal SCISSORS parameters in a data set-specific manner. These results are a useful resource for researchers seeking to incorporate SCISSORS into molecular similarity applications.", "group": "Citedby", "depth": 1, "citations": 1}, {"doi": "https://doi.org/10.1021/ci4003766", "name": "Criterion for Evaluating the Predictive Ability of Nonlinear Regression Models without Cross-Validation", "author": ["Hiromasa Kaneko", "Kimito Funatsu"], "year": "23.08.2013", "journal": "Journal of Chemical Information and Modeling", "abstract": "We propose predictive performance criteria for nonlinear regression models without cross-validation. The proposed criteria are the determination coefficient and the root-mean-square error for the midpoints between k-nearest-neighbor data points. These criteria can be used to evaluate predictive ability after the regression models are updated, whereas cross-validation cannot be performed in such a situation. The proposed method is effective and helpful in handling big data when cross-validation cannot be applied. By analyzing data from numerical simulations and quantitative structural relationships, we confirm that the proposed criteria enable the predictive ability of the nonlinear regression models to be appropriately quantified.", "group": "Citedby", "depth": 1, "citations": 16}, {"doi": "https://doi.org/10.1021/ci400206h", "name": "SMIfp (SMILES fingerprint) Chemical Space for Virtual Screening and Visualization of Large Databases of Organic Molecules", "author": ["Julian Schwartz", "Mahendra Awale", "Jean-Louis Reymond"], "year": "11.07.2013", "journal": "Journal of Chemical Information and Modeling", "abstract": "SMIfp (SMILES fingerprint) is defined here as a scalar fingerprint describing organic molecules by counting the occurrences of 34 different symbols in their SMILES strings, which creates a 34-dimensional chemical space. Ligand-based virtual screening using the city-block distance CBDSMIfp as similarity measure provides good AUC values and enrichment factors for recovering series of actives from the directory of useful decoys (DUD-E) and from ZINC. DrugBank, ChEMBL, ZINC, PubChem, GDB-11, GDB-13, and GDB-17 can be searched by CBDSMIfp using an online SMIfp-browser at www.gdb.unibe.ch. Visualization of the SMIfp chemical space was performed by principal component analysis and color-coded maps of the (PC1, PC2)-planes, with interactive access to the molecules enabled by the Java application SMIfp-MAPPLET available from www.gdb.unibe.ch. These maps spread molecules according to their fraction of aromatic atoms, size and polarity. SMIfp provides a new and relevant entry to explore the small molecule chemical space.", "group": "Citedby", "depth": 1, "citations": 41}, {"doi": "https://doi.org/10.1021/ci300463g", "name": "Boosting Virtual Screening Enrichments with Data Fusion: Coalescing Hits from Two-Dimensional Fingerprints, Shape, and Docking", "author": ["G. Madhavi Sastry", "V. S. Sandeep Inakollu", "Woody Sherman"], "year": "19.06.2013", "journal": "Journal of Chemical Information and Modeling", "abstract": "Virtual screening is an effective way to find hits in drug discovery, with approaches ranging from fast information-based similarity methods to more computationally intensive physics-based docking methods. However, the best approach to use for a given project is not clear in advance of the screen. In this work, we show that combining results from multiple methods using a standard score (Z-score) can significantly improve virtual screening enrichments over any of the single screening methods. We show that an augmented Z-score, which considers the best two out of three scores for a given compound, outperforms previously published data fusion algorithms. We use three different virtual screening methods (two-dimensional (2D) fingerprint similarity, shape-based similarity, and docking) and study two different databases (DUD and MDDR). The average enrichment in the top 1% was improved by 9% for DUD and 25% for the MDDR, compared with the top individual method. Improvements of 22% for DUD and 43% for MDDR are seen over the average of the three individual methods. Statistics are presented that show a high significance associated with the findings in this work.", "group": "Citedby", "depth": 1, "citations": 52}, {"doi": "https://doi.org/10.1021/jm2013248", "name": "Oxadiazoles in Medicinal Chemistry", "author": ["Jonas Bostr\u00f6m", "Anders Hogner", "Antonio Llin\u00e0s", "Eric Wellner", "Alleyn T. Plowright"], "year": "19.12.2011", "journal": "Journal of Medicinal Chemistry", "abstract": "Oxadiazoles are five-membered heteroaromatic rings containing two carbons, two nitrogens, and one oxygen atom, and they exist in different regioisomeric forms. Oxadiazoles are frequently occurring motifs in druglike molecules, and they are often used with the intention of being bioisosteric replacements for ester and amide functionalities. The current study presents a systematic comparison of 1,2,4- and 1,3,4-oxadiazole matched pairs in the AstraZeneca compound collection. In virtually all cases, the 1,3,4-oxadiazole isomer shows an order of magnitude lower lipophilicity (log D), as compared to its isomeric partner. Significant differences are also observed with respect to metabolic stability, hERG inhibition, and aqueous solubil ity, favoring the 1,3,4-oxadiazole isomers. The difference in profile between the 1,2,4 and 1,3,4 regioisomers can be rationalized by their intrinsically different charge distributions (e.g., dipole moments). To facilitate the use of these heteroaromatic rings, novel synthetic routes for ready access of a broad spectrum of 1,3,4-oxadiazoles, under mild conditions, are described.", "group": "Citedby", "depth": 1, "citations": 100}, {"doi": "https://doi.org/10.1021/ci200251a", "name": "Error Bounds on the SCISSORS Approximation Method", "author": ["Imran S. Haque", "Vijay S. Pande"], "year": "18.08.2011", "journal": "Journal of Chemical Information and Modeling", "abstract": "The SCISSORS method for approximating chemical similarities has shown excellent empirical performance on a number of real-world chemical data sets but lacks theoretically proven bounds on its worst-case error performance. This paper first proves reductions showing SCISSORS to be equivalent to two previous kernel methods: kernel principal components analysis and the rank-k Nystr\u00f6m approximation of a Gram matrix. These reductions allow the use of generalization bounds on these techniques to show that the expected error in SCISSORS approximations of molecular similarity kernels is bounded in expected pairwise inner product error, in matrix 2-norm and Frobenius norm for full kernel matrix approximations and in root-mean-square deviation for approximated matrices. Finally, we show that the actual performance of SCISSORS is significantly better than these worst-case bounds, indicating that chemical space is well-structured for chemical sampling algorithms.", "group": "Citedby", "depth": 1, "citations": 3}, {"doi": "https://doi.org/10.1021/ci100436p", "name": "FRED Pose Prediction and Virtual Screening Accuracy", "author": ["Mark McGann"], "year": "16.02.2011", "journal": "Journal of Chemical Information and Modeling", "abstract": "Results of a previous docking study are reanalyzed and extended to include results from the docking program FRED and a detailed statistical analysis of both structure reproduction and virtual screening results. FRED is run both in a traditional docking mode and in a hybrid mode that makes use of the structure of a bound ligand in addition to the protein structure to screen molecules. This analysis shows that most docking programs are effective overall but highly inconsistent, tending to do well on one system and poorly on the next. Comparing methods, the difference in mean performance on DUD is found to be statistically significant (95% confidence) 61% of the time when using a global enrichment metric (AUC). Early enrichment metrics are found to have relatively poor statistical power, with 0.5% early enrichment only able to distinguish methods to 95% confidence 14% of the time.", "group": "Citedby", "depth": 1, "citations": 100}, {"doi": "https://doi.org/10.1021/ci100437e", "name": "Using Inverted Indices for Accelerating LINGO Calculations", "author": ["Thomas G. Kristensen", "Jesper Nielsen", "Christian N. S. Pedersen"], "year": "18.02.2011", "journal": "Journal of Chemical Information and Modeling", "abstract": "The ever growing size of chemical databases calls for the development of novel methods for representing and comparing molecules. One such method called LINGO is based on fragmenting the SMILES string representation of molecules. Comparison of molecules can then be performed by calculating the Tanimoto coefficient, which is called LINGOsim when used on LINGO multisets. This paper introduces a verbose representation for storing LINGO multisets, which makes it possible to transform them into sparse fingerprints such that fingerprint data structures and algorithms can be used to accelerate queries. The previous best method for rapidly calculating the LINGOsim similarity matrix required specialized hardware to yield a significant speedup over existing methods. By representing LINGO multisets in the verbose representation and using inverted indices, it is possible to calculate LINGOsim similarity matrices roughly 2.6 times faster than existing methods without relying on specialized hardware.", "group": "Citedby", "depth": 1, "citations": 13}, {"doi": "https://doi.org/10.1021/ci1000136", "name": "SCISSORS: A Linear-Algebraical Technique to Rapidly Approximate Chemical Similarities", "author": ["Imran S. Haque", "Vijay S. Pande"], "year": "28.05.2010", "journal": "Journal of Chemical Information and Modeling", "abstract": "Algorithms for several emerging large-scale problems in cheminformatics have as their rate-limiting step the evaluation of relatively slow chemical similarity measures, such as structural similarity or three-dimensional (3-D) shape comparison. In this article we present SCISSORS, a linear-algebraical technique (related to multidimensional scaling and kernel principal components analysis) to rapidly estimate chemical similarities for several popular measures. We demonstrate that SCISSORS faithfully reflects its source similarity measures for both Tanimoto calculation and rank ordering. After an efficient precalculation step on a database, SCISSORS affords several orders of magnitude of speedup in database screening. SCISSORS furthermore provides an asymptotic speedup for large similarity matrix construction problems, reducing the number of conventional slow similarity evaluations required from quadratic to linear scaling.", "group": "Citedby", "depth": 1, "citations": 9}, {"doi": "https://doi.org/10.1021/ci100011z", "name": "SIML: A Fast SIMD Algorithm for Calculating LINGO Chemical Similarities on GPUs and CPUs", "author": ["Imran S. Haque", "Vijay S. Pande", "W. Patrick Walters"], "year": "10.03.2010", "journal": "Journal of Chemical Information and Modeling", "abstract": "LINGOs are a holographic measure of chemical similarity based on text comparison of SMILES strings. We present a new algorithm for calculating LINGO similarities amenable to parallelization on SIMD architectures (such as GPUs and vector units of modern CPUs). We show that it is nearly 3\u00d7 as fast as existing algorithms on a CPU, and over 80\u00d7 faster than existing methods when run on a GPU.", "group": "Citedby", "depth": 1, "citations": 23}, {"doi": "https://doi.org/10.1021/ci8003418", "name": "Bioisosteric Similarity of Molecules Based on Structural Alignment and Observed Chemical Replacements in Drugs", "author": ["Markus Krier", "Michael C. Hutter"], "year": "29.04.2009", "journal": "Journal of Chemical Information and Modeling", "abstract": "The algorithmic concept used to assess the evolutionary relationship between protein sequences was adopted to the comparison of drug-like compounds. For this purpose, we have developed a method that uses the SMILES representation of the molecules to perform the corresponding pairwise alignment. The necessary exchange matrix was generated in an automated procedure that reflects the frequencies of chemical replacements in pharmaceutical substances. From the resulting alignment, the relationship between two molecules is computed as so-called bioisosteric similarity. This measure was used to perform virtual screening in several publicly available substance databases. We observed that databases containing drug-like compounds throughout showed higher bioisosteric similarities to the query compound than our reference set of confirmed nondrugs. Likewise, most actual drugs within a class show a higher bioisosteric similarity than the large background of other substances. The compounds obtained as highest ranking hits from the lead-like subset of the ZINC library showed distinct differences in comparison with corresponding results from a fingerprint-based similarity search, as well as the FTrees method. In particular the kind of chemical replacements as well as the conservation of substructures strongly reflect the underlying bioisosteric exchanges. Moreover, the bioisosteric similarity was used to assess the chemical diversity of the utilized drug classes and to compute the \u201caverage\u201d molecule within the respective class.", "group": "Citedby", "depth": 1, "citations": 11}, {"doi": "https://doi.org/10.1021/ci800326z", "name": "Comparison of Molecular Fingerprint Methods on the Basis of Biological Profile Data", "author": ["Andreas Steffen", "Thierry Kogej", "Christian Tyrchan", "Ola Engkvist"], "year": "28.01.2009", "journal": "Journal of Chemical Information and Modeling", "abstract": "In this study we evaluated a set of molecular fingerprint methods with respect to their capability to reproduce similarities in the biological activity space. The evaluation presented in this paper is therefore different from many other fingerprint studies, in which the enrichment of active compounds binding to the same target as selected query structures was studied. Conversely, our data set was extracted from the BioPrint database, which contains uniformly derived biological activity profiles of mainly marketed drugs for a range of biological assays relevant for the pharmaceutical industry. We compared calculated molecular fingerprint similarity values between all compound pairs of the data set with the corresponding similarities in the biological activity space and additionally analyzed agreements of generated clusterings. A closer analysis of the compound pairs with a high biological activity similarity revealed that fingerprint methods such as CHEMGPS or TRUST4, which describe global features of a molecule such as physicochemical properties and pharmacophore patterns, might be better suited to describe similarity of biological activity profiles than purely structural fingerprint methods. It is therefore suggested that the usage of these fingerprint methods could increase the probability of finding molecules with a similar biological activity profile but yet a different chemical structure.", "group": "Citedby", "depth": 1, "citations": 43}, {"doi": "https://doi.org/10.1021/ci800020s", "name": "Core Trees and Consensus Fragment Sequences for Molecular Representation and Similarity Analysis", "author": ["Eugen Lounkine", "J\u00fcrgen Bajorath"], "year": "21.05.2008", "journal": "Journal of Chemical Information and Modeling", "abstract": "A new type of molecular representation is introduced that is based on activity class characteristic substructures extracted from random fragment populations. Mapping of characteristic substructures is used to determine atom match rates in active molecules. Comparison of match rates of bonded atoms defines a hierarchical molecular fragmentation scheme. Active compounds are encoded as fragmentation pathways isolated from core trees. These paths are amenable to biological sequence alignment methods in combination with substructure-based scoring functions. From multiple core path alignments, consensus fragment sequences are derived that represent compound activity classes. Consensus fragment sequences weighted by increasing structural specificity can also be used to map molecules and search databases for active compounds.", "group": "Citedby", "depth": 1, "citations": 5}, {"doi": "https://doi.org/10.1021/ci6002152", "name": "Lingos, Finite State Machines, and Fast Similarity Searching", "author": ["J. Andrew Grant", "James A. Haigh", "Barry T. Pickup", "Anthony Nicholls", "Roger A. Sayle"], "year": "08.09.2006", "journal": "Journal of Chemical Information and Modeling", "abstract": "We apply a recently published method of text-based molecular similarity searching (LINGO) to standard data sets for the purpose of quantifying the accuracy of the approach. Our implementation is based on a pattern-matching finite state machine (FSM) which results in fast search times. The accuracy of LINGO is demonstrated to be comparable to that of a path-based fingerprint and offers a simple yet effective method for similarity searching. ", "group": "Citedby", "depth": 1, "citations": 44}, {"doi": "https://doi.org/10.1021/ci050464m", "name": "COSMOsim:\u2009 Bioisosteric Similarity Based on COSMO-RS \u03c3 Profiles", "author": ["Michael Thormann", "Andreas Klamt", "Martin Hornig", "Michael Almstetter"], "year": "01.03.2006", "journal": "Journal of Chemical Information and Modeling", "abstract": "A novel approach for the quantification of drug similarity is proposed, which makes use of the surface polarities, that is, conductor surface polarization charge densities \u03c3, as defined in the quantum chemically based conductor-like screening model for realistic solvation(COSMO-RS). The histogram of these surface polarities, the so-called \u03c3 profiles, have been proven to be the key for the calculation of all kinds of partition and adsorption coefficients and, therefore, of relevant absorption, distribution, metabolism, and excretion parameters such as solubility, pKa, log BB, and many others. They also carry a large part of the information required for the estimation of desolvation and binding processes responsible for receptor binding and enzyme inhibition of drug molecules. Thus, a large degree of similarity with respect to the \u03c3 profiles appears to be a necessary condition for drugs of similar physiological action. Driven by this insight, we propose a \u03c3-profile-based drug similarity measure COSMOsim for the detection of new bioisosteric drug candidates. In several examples, we demonstrate its statistical and pharmaceutical plausibility, its practicability for real drug research projects, and its unique independence from the chemical structure, which enables scaffold hopping in a natural way. ", "group": "Citedby", "depth": 1, "citations": 20}], "links": [{"source": "https://doi.org/10.1021/acs.jcim.1c00866", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.0c01127", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.9b01210", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acsomega.9b00488", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00663", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.8b00803", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jmedchem.8b00832", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.6b00694", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.chemrestox.5b00481", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.langmuir.5b03074", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci500150t", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci500364e", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ed400302u", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci400264f", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci4003766", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci400206h", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci300463g", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/jm2013248", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci200251a", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci100436p", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci100437e", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci1000136", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci100011z", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci8003418", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci800326z", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci800020s", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci6002152", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/ci050464m", "target": "https://doi.org/10.1021/ci0496797"}, {"source": "https://doi.org/10.1021/acs.jcim.0c01127", "target": "https://doi.org/10.1021/acs.jcim.8b00803"}, {"source": "https://doi.org/10.1021/acs.jcim.9b01210", "target": "https://doi.org/10.1021/ci400206h"}, {"source": "https://doi.org/10.1021/ci400264f", "target": "https://doi.org/10.1021/ci200251a"}, {"source": "https://doi.org/10.1021/ci300463g", "target": "https://doi.org/10.1021/ci100436p"}, {"source": "https://doi.org/10.1021/ci500150t", "target": "https://doi.org/10.1021/ci100437e"}, {"source": "https://doi.org/10.1021/ci400206h", "target": "https://doi.org/10.1021/ci100437e"}, {"source": "https://doi.org/10.1021/ci400264f", "target": "https://doi.org/10.1021/ci1000136"}, {"source": "https://doi.org/10.1021/ci200251a", "target": "https://doi.org/10.1021/ci1000136"}, {"source": "https://doi.org/10.1021/ci400264f", "target": "https://doi.org/10.1021/ci100011z"}, {"source": "https://doi.org/10.1021/ci200251a", "target": "https://doi.org/10.1021/ci100011z"}, {"source": "https://doi.org/10.1021/ci100437e", "target": "https://doi.org/10.1021/ci100011z"}, {"source": "https://doi.org/10.1021/ci8003418", "target": "https://doi.org/10.1021/ci800020s"}, {"source": "https://doi.org/10.1021/jm2013248", "target": "https://doi.org/10.1021/ci6002152"}, {"source": "https://doi.org/10.1021/ci100436p", "target": "https://doi.org/10.1021/ci6002152"}, {"source": "https://doi.org/10.1021/ci100437e", "target": "https://doi.org/10.1021/ci6002152"}, {"source": "https://doi.org/10.1021/ci100011z", "target": "https://doi.org/10.1021/ci6002152"}, {"source": "https://doi.org/10.1021/ci800326z", "target": "https://doi.org/10.1021/ci6002152"}]}
\ No newline at end of file
diff --git a/input/get/acs.py b/input/get/acs.py
old mode 100755
new mode 100644