The Role of Balanced Training and Testing Data Sets for Binary Classifiers in Bioinformatics
Events
Loading … Spinner

Mendeley | Further Information

{"title"=>"The Role of Balanced Training and Testing Data Sets for Binary Classifiers in Bioinformatics", "type"=>"journal", "authors"=>[{"first_name"=>"Qiong", "last_name"=>"Wei", "scopus_author_id"=>"36629596500"}, {"first_name"=>"Roland L.", "last_name"=>"Dunbrack", "scopus_author_id"=>"7003392559"}], "year"=>2013, "source"=>"PLoS ONE", "identifiers"=>{"scopus"=>"2-s2.0-84879987629", "sgr"=>"84879987629", "issn"=>"19326203", "doi"=>"10.1371/journal.pone.0067863", "pmid"=>"23874456", "isbn"=>"1932-6203 (Electronic)\\r1932-6203 (Linking)", "pui"=>"369287129"}, "id"=>"af746b23-093f-35d2-a7d3-8d946f450011", "abstract"=>"Training and testing of conventional machine learning models on binary classification problems depend on the proportions of the two outcomes in the relevant data sets. This may be especially important in practical terms when real-world applications of the classifier are either highly imbalanced or occur in unknown proportions. Intuitively, it may seem sensible to train machine learning models on data similar to the target data in terms of proportions of the two binary outcomes. However, we show that this is not the case using the example of prediction of deleterious and neutral phenotypes of human missense mutations in human genome data, for which the proportion of the binary outcome is unknown. Our results indicate that using balanced training data (50% neutral and 50% deleterious) results in the highest balanced accuracy (the average of True Positive Rate and True Negative Rate), Matthews correlation coefficient, and area under ROC curves, no matter what the proportions of the two phenotypes are in the testing data. Besides balancing the data by undersampling the majority class, other techniques in machine learning include oversampling the minority class, interpolating minority-class data points and various penalties for misclassifying the minority class. However, these techniques are not commonly used in either the missense phenotype prediction problem or in the prediction of disordered residues in proteins, where the imbalance problem is substantial. The appropriate approach depends on the amount of available data and the specific problem at hand.", "link"=>"http://www.mendeley.com/research/role-balanced-training-testing-data-sets-binary-classifiers-bioinformatics", "reader_count"=>83, "reader_count_by_academic_status"=>{"Unspecified"=>1, "Professor > Associate Professor"=>4, "Researcher"=>10, "Student > Doctoral Student"=>3, "Student > Ph. D. Student"=>28, "Student > Postgraduate"=>2, "Student > Master"=>15, "Other"=>3, "Student > Bachelor"=>12, "Lecturer > Senior Lecturer"=>1, "Professor"=>4}, "reader_count_by_user_role"=>{"Unspecified"=>1, "Professor > Associate Professor"=>4, "Researcher"=>10, "Student > Doctoral Student"=>3, "Student > Ph. D. Student"=>28, "Student > Postgraduate"=>2, "Student > Master"=>15, "Other"=>3, "Student > Bachelor"=>12, "Lecturer > Senior Lecturer"=>1, "Professor"=>4}, "reader_count_by_subject_area"=>{"Engineering"=>10, "Unspecified"=>3, "Biochemistry, Genetics and Molecular Biology"=>9, "Mathematics"=>5, "Agricultural and Biological Sciences"=>20, "Medicine and Dentistry"=>7, "Physics and Astronomy"=>1, "Chemistry"=>4, "Psychology"=>3, "Computer Science"=>20, "Decision Sciences"=>1}, "reader_count_by_subdiscipline"=>{"Engineering"=>{"Engineering"=>10}, "Medicine and Dentistry"=>{"Medicine and Dentistry"=>7}, "Chemistry"=>{"Chemistry"=>4}, "Decision Sciences"=>{"Decision Sciences"=>1}, "Physics and Astronomy"=>{"Physics and Astronomy"=>1}, "Psychology"=>{"Psychology"=>3}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>20}, "Computer Science"=>{"Computer Science"=>20}, "Biochemistry, Genetics and Molecular Biology"=>{"Biochemistry, Genetics and Molecular Biology"=>9}, "Mathematics"=>{"Mathematics"=>5}, "Unspecified"=>{"Unspecified"=>3}}, "reader_count_by_country"=>{"Netherlands"=>2, "United States"=>4, "United Kingdom"=>1, "Israel"=>1, "France"=>1, "Germany"=>1, "Spain"=>1}, "group_count"=>1}

CrossRef

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84879987629"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84879987629?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84879987629&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84879987629&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/84879987629", "dc:identifier"=>"SCOPUS_ID:84879987629", "eid"=>"2-s2.0-84879987629", "dc:title"=>"The Role of Balanced Training and Testing Data Sets for Binary Classifiers in Bioinformatics", "dc:creator"=>"Wei Q.", "prism:publicationName"=>"PLoS ONE", "prism:eIssn"=>"19326203", "prism:volume"=>"8", "prism:issueIdentifier"=>"7", "prism:pageRange"=>nil, "prism:coverDate"=>"2013-07-09", "prism:coverDisplayDate"=>"9 July 2013", "prism:doi"=>"10.1371/journal.pone.0067863", "citedby-count"=>"93", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"Fox Chase Cancer Center", "affiliation-city"=>"Philadelphia", "affiliation-country"=>"United States"}], "pubmed-id"=>"23874456", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e67863", "source-id"=>"10600153309", "openaccess"=>"1", "openaccessFlag"=>true}

Facebook

  • {"url"=>"http%3A%2F%2Fjournals.plos.org%2Fplosone%2Farticle%3Fid%3D10.1371%252Fjournal.pone.0067863", "share_count"=>0, "like_count"=>0, "comment_count"=>0, "click_count"=>0, "total_count"=>0}

Twitter

Counter

  • {"month"=>"7", "year"=>"2013", "pdf_views"=>"30", "xml_views"=>"6", "html_views"=>"225"}
  • {"month"=>"8", "year"=>"2013", "pdf_views"=>"15", "xml_views"=>"1", "html_views"=>"42"}
  • {"month"=>"9", "year"=>"2013", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"48"}
  • {"month"=>"10", "year"=>"2013", "pdf_views"=>"12", "xml_views"=>"3", "html_views"=>"89"}
  • {"month"=>"11", "year"=>"2013", "pdf_views"=>"14", "xml_views"=>"1", "html_views"=>"83"}
  • {"month"=>"12", "year"=>"2013", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"65"}
  • {"month"=>"1", "year"=>"2014", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"97"}
  • {"month"=>"2", "year"=>"2014", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"121"}
  • {"month"=>"3", "year"=>"2014", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"77"}
  • {"month"=>"4", "year"=>"2014", "pdf_views"=>"14", "xml_views"=>"2", "html_views"=>"92"}
  • {"month"=>"5", "year"=>"2014", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"97"}
  • {"month"=>"6", "year"=>"2014", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"83"}
  • {"month"=>"7", "year"=>"2014", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"105"}
  • {"month"=>"8", "year"=>"2014", "pdf_views"=>"14", "xml_views"=>"2", "html_views"=>"102"}
  • {"month"=>"9", "year"=>"2014", "pdf_views"=>"15", "xml_views"=>"1", "html_views"=>"90"}
  • {"month"=>"10", "year"=>"2014", "pdf_views"=>"12", "xml_views"=>"1", "html_views"=>"165"}
  • {"month"=>"11", "year"=>"2014", "pdf_views"=>"6", "xml_views"=>"1", "html_views"=>"106"}
  • {"month"=>"12", "year"=>"2014", "pdf_views"=>"13", "xml_views"=>"1", "html_views"=>"106"}
  • {"month"=>"1", "year"=>"2015", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"79"}
  • {"month"=>"2", "year"=>"2015", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"60"}
  • {"month"=>"3", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"88"}
  • {"month"=>"4", "year"=>"2015", "pdf_views"=>"22", "xml_views"=>"1", "html_views"=>"84"}
  • {"month"=>"5", "year"=>"2015", "pdf_views"=>"27", "xml_views"=>"0", "html_views"=>"86"}
  • {"month"=>"6", "year"=>"2015", "pdf_views"=>"27", "xml_views"=>"0", "html_views"=>"119"}
  • {"month"=>"7", "year"=>"2015", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"72"}
  • {"month"=>"8", "year"=>"2015", "pdf_views"=>"7", "xml_views"=>"2", "html_views"=>"78"}
  • {"month"=>"9", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"93"}
  • {"month"=>"10", "year"=>"2015", "pdf_views"=>"9", "xml_views"=>"1", "html_views"=>"113"}
  • {"month"=>"11", "year"=>"2015", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"122"}
  • {"month"=>"12", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"166"}
  • {"month"=>"1", "year"=>"2016", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"136"}
  • {"month"=>"2", "year"=>"2016", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"112"}
  • {"month"=>"3", "year"=>"2016", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"148"}
  • {"month"=>"4", "year"=>"2016", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"95"}
  • {"month"=>"5", "year"=>"2016", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"94"}
  • {"month"=>"6", "year"=>"2016", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"59"}
  • {"month"=>"7", "year"=>"2016", "pdf_views"=>"8", "xml_views"=>"0", "html_views"=>"63"}
  • {"month"=>"8", "year"=>"2016", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"75"}
  • {"month"=>"9", "year"=>"2016", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"77"}
  • {"month"=>"10", "year"=>"2016", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"63"}
  • {"month"=>"11", "year"=>"2016", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"66"}
  • {"month"=>"12", "year"=>"2016", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"113"}
  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"127"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"41", "xml_views"=>"0", "html_views"=>"255"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"30", "xml_views"=>"0", "html_views"=>"338"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"21", "xml_views"=>"0", "html_views"=>"203"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"19", "xml_views"=>"0", "html_views"=>"223"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"172"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"21", "xml_views"=>"1", "html_views"=>"147"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"27", "xml_views"=>"2", "html_views"=>"189"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"23", "xml_views"=>"0", "html_views"=>"168"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"13", "xml_views"=>"1", "html_views"=>"172"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"155"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"99"}
  • {"month"=>"1", "year"=>"2018", "pdf_views"=>"22", "xml_views"=>"1", "html_views"=>"101"}
  • {"month"=>"2", "year"=>"2018", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"59"}
  • {"month"=>"3", "year"=>"2018", "pdf_views"=>"9", "xml_views"=>"2", "html_views"=>"53"}
  • {"month"=>"4", "year"=>"2018", "pdf_views"=>"26", "xml_views"=>"0", "html_views"=>"78"}
  • {"month"=>"5", "year"=>"2018", "pdf_views"=>"17", "xml_views"=>"2", "html_views"=>"81"}
  • {"month"=>"6", "year"=>"2018", "pdf_views"=>"28", "xml_views"=>"0", "html_views"=>"48"}
  • {"month"=>"7", "year"=>"2018", "pdf_views"=>"7", "xml_views"=>"6", "html_views"=>"83"}
  • {"month"=>"8", "year"=>"2018", "pdf_views"=>"11", "xml_views"=>"1", "html_views"=>"105"}
  • {"month"=>"9", "year"=>"2018", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"96"}
  • {"month"=>"10", "year"=>"2018", "pdf_views"=>"21", "xml_views"=>"1", "html_views"=>"128"}
  • {"month"=>"11", "year"=>"2018", "pdf_views"=>"30", "xml_views"=>"0", "html_views"=>"124"}
  • {"month"=>"12", "year"=>"2018", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"58"}
  • {"month"=>"1", "year"=>"2019", "pdf_views"=>"28", "xml_views"=>"0", "html_views"=>"88"}
  • {"month"=>"2", "year"=>"2019", "pdf_views"=>"20", "xml_views"=>"0", "html_views"=>"110"}
  • {"month"=>"3", "year"=>"2019", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"101"}
  • {"month"=>"4", "year"=>"2019", "pdf_views"=>"13", "xml_views"=>"1", "html_views"=>"98"}
  • {"month"=>"5", "year"=>"2019", "pdf_views"=>"57", "xml_views"=>"0", "html_views"=>"212"}
  • {"month"=>"6", "year"=>"2019", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"57"}
  • {"month"=>"7", "year"=>"2019", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"57"}
  • {"month"=>"8", "year"=>"2019", "pdf_views"=>"22", "xml_views"=>"0", "html_views"=>"60"}
  • {"month"=>"9", "year"=>"2019", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"68"}
  • {"month"=>"10", "year"=>"2019", "pdf_views"=>"38", "xml_views"=>"1", "html_views"=>"94"}
  • {"month"=>"11", "year"=>"2019", "pdf_views"=>"17", "xml_views"=>"0", "html_views"=>"100"}
  • {"month"=>"12", "year"=>"2019", "pdf_views"=>"17", "xml_views"=>"0", "html_views"=>"81"}
  • {"month"=>"1", "year"=>"2020", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"73"}
  • {"month"=>"2", "year"=>"2020", "pdf_views"=>"15", "xml_views"=>"2", "html_views"=>"76"}
  • {"month"=>"3", "year"=>"2020", "pdf_views"=>"36", "xml_views"=>"2", "html_views"=>"97"}
  • {"month"=>"4", "year"=>"2020", "pdf_views"=>"127", "xml_views"=>"0", "html_views"=>"96"}
  • {"month"=>"5", "year"=>"2020", "pdf_views"=>"112", "xml_views"=>"1", "html_views"=>"106"}
  • {"month"=>"6", "year"=>"2020", "pdf_views"=>"25", "xml_views"=>"1", "html_views"=>"107"}
  • {"month"=>"7", "year"=>"2020", "pdf_views"=>"36", "xml_views"=>"0", "html_views"=>"108"}
  • {"month"=>"8", "year"=>"2020", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"109"}
  • {"month"=>"9", "year"=>"2020", "pdf_views"=>"20", "xml_views"=>"1", "html_views"=>"83"}
  • {"month"=>"10", "year"=>"2020", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"94"}

Figshare

  • {"files"=>["https://ndownloader.figshare.com/files/1114888"], "description"=>"<p>Performance of the models trained by human polymorphism and primate polymorphism.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "trained", "polymorphism", "primate"], "article_id"=>742349, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.t004", "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Performance_of_the_models_trained_by_human_polymorphism_and_primate_polymorphism_/742349", "title"=>"Performance of the models trained by human polymorphism and primate polymorphism.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114887"], "description"=>"<p>(a) ACC, (b) BACC, (c) MCC, and (d) AUC of five SVM models trained on 5 different data sets (train_10, train_30, train_50, train_70, and train_90) tested by 9 different testing data sets, ranging from 10% deleterious (x-axis = 0.1) to 90% deleterious (x-axis = 0.9).</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "auc", "svm", "trained", "sets", "tested", "ranging", "deleterious"], "article_id"=>742348, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.g004", "stats"=>{"downloads"=>5, "page_views"=>27, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_a_ACC_b_BACC_c_MCC_and_d_AUC_of_five_SVM_models_trained_on_5_different_data_sets_train_10_train_30_train_50_train_70_and_train_90_tested_by_9_different_testing_data_sets_ranging_from_10_deleterious_x_axis_8202_8202_0_1_to_90_deleterious_x_axis_8202_8202_/742348", "title"=>"(a) ACC, (b) BACC, (c) MCC, and (d) AUC of five SVM models trained on 5 different data sets (train_10, train_30, train_50, train_70, and train_90) tested by 9 different testing data sets, ranging from 10% deleterious (x-axis = 0.1) to 90% deleterious (x-axis = 0.9).", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114884"], "description"=>"<p>Only those 150 mutations accessible by single-nucleotide changes are shown in color; others are shown in gray. Wildtype residue types are given along the x-axis and mutant residue types are given along the y-axis. Blue squares indicate substitution types that are overrepresented in <i>PrimateMut</i>, while orange squares indicate substitution types that are overrepresented in <i>HumanPoly</i>.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "contributions"], "article_id"=>742345, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.g001", "stats"=>{"downloads"=>1, "page_views"=>4, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_contributions_to_G_for_HumanPoly_and_PrimateMut_/742345", "title"=>"The contributions to G for <i>HumanPoly</i> and <i>PrimateMut</i>.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114892"], "description"=>"a<p>39887 disease mutations from PMD database, 13990 neutral mutations from PMD and 26840 neutral mutations from residues that differed in pairwise alignments of enzymes with experimentally annotated similarity in function and the same EC numbers.</p>b<p>Derived from the Swiss-Prot release 48 (Dec 2005).</p>c<p>Includes only mutations from protein sequence deposited in Swiss-Prot from January to November 2006 (release 51).</p>d<p>The neutral mutations are extracted from LacI.</p>e<p>The neutral mutations are extracted from the evolutionary model.</p>f<p>Structure-based case.</p>g<p>Available at <a href=\"http://gpcr2.biocomp.unibo.it/~emidio/PhD-SNP/OutPhD-SNP08.txt\" target=\"_blank\">http://gpcr2.biocomp.unibo.it/~emidio/PhD-SNP/OutPhD-SNP08.txt</a>.</p>h<p>The data set of SNAP.</p>i<p>3155 damaging alleles annotated in the Uniprot database as causing human Mendelian diseases and affecting protein stability or function, 6321 differences between human proteins and their closely related mammalian homologs, assumed to be nondamaging.</p>j<p>13032 human disease-causing mutations from UniProt and 8946 human nonsynonymous single-nucleotide polymorphisms without annotated involvement in disease.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "deleterious", "mutations", "published"], "article_id"=>742353, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.t001", "stats"=>{"downloads"=>4, "page_views"=>5, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_mutations_and_percentage_of_deleterious_mutations_for_published_methods_/742353", "title"=>"The #mutations and percentage of deleterious mutations for published methods.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114890"], "description"=>"*<p>Data sets are available in Supplemental Material.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "mutations", "g-square"], "article_id"=>742351, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.t002", "stats"=>{"downloads"=>1, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_number_of_proteins_mutations_and_self_G_square_for_each_data_set_/742351", "title"=>"The number of proteins, mutations and self G-square for each data set.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114891"], "description"=>"<p>The G values for different datasets against each other.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "datasets"], "article_id"=>742352, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.t003", "stats"=>{"downloads"=>1, "page_views"=>3, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_G_values_for_different_datasets_against_each_other_/742352", "title"=>"The G values for different datasets against each other.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114889"], "description"=>"<p>Top five predictors tested by CASP9 targets (117 targets).</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "predictors", "tested", "casp9", "targets"], "article_id"=>742350, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.t005", "stats"=>{"downloads"=>3, "page_views"=>6, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Top_five_predictors_tested_by_CASP9_targets_117_targets_/742350", "title"=>"Top five predictors tested by CASP9 targets (117 targets).", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114886"], "description"=>"<p>(a) TPR, (b) NPR, (c) PPV, and (d) NPV of five SVM models trained on 5 different data sets (train_10, train_30, train_50, train_70, and train_90) tested by 9 different testing data sets, ranging from 10% deleterious (x-axis = 0.1) to 90% deleterious (x-axis = 0.9).</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "npv", "svm", "trained", "sets", "tested", "ranging", "deleterious"], "article_id"=>742347, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.g003", "stats"=>{"downloads"=>2, "page_views"=>6, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_a_TPR_b_NPR_c_PPV_and_d_NPV_of_five_SVM_models_trained_on_5_different_data_sets_train_10_train_30_train_50_train_70_and_train_90_tested_by_9_different_testing_data_sets_ranging_from_10_deleterious_x_axis_8202_8202_0_1_to_90_deleterious_x_axis_8202_8202_0/742347", "title"=>"(a) TPR, (b) NPR, (c) PPV, and (d) NPV of five SVM models trained on 5 different data sets (train_10, train_30, train_50, train_70, and train_90) tested by 9 different testing data sets, ranging from 10% deleterious (x-axis = 0.1) to 90% deleterious (x-axis = 0.9).", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114885"], "description"=>"<p>(a) Values for TPR, TNR, PPV, and NPV. (b) Values for MCC, BACC, AUC, and ACC.</p>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "cross-validation", "svm", "trained", "sets", "deleterious", "mutations"], "article_id"=>742346, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863.g002", "stats"=>{"downloads"=>1, "page_views"=>5, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_cross_validation_results_of_five_SVM_models_trained_on_data_sets_that_are_10_30_50_70_and_90_deleterious_mutations_x_axis_8202_8202_0_1_0_3_0_5_0_7_and_0_9_respectively_/742346", "title"=>"The cross-validation results of five SVM models trained on data sets that are 10%, 30%, 50%, 70% and 90% deleterious mutations (x-axis = 0.1, 0.3, 0.5, 0.7 and 0.9 respectively).", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2013-07-09 02:40:30"}
  • {"files"=>["https://ndownloader.figshare.com/files/1114893"], "description"=>"<div><p>Training and testing of conventional machine learning models on binary classification problems depend on the proportions of the two outcomes in the relevant data sets. This may be especially important in practical terms when real-world applications of the classifier are either highly imbalanced or occur in unknown proportions. Intuitively, it may seem sensible to train machine learning models on data similar to the target data in terms of proportions of the two binary outcomes. However, we show that this is not the case using the example of prediction of deleterious and neutral phenotypes of human missense mutations in human genome data, for which the proportion of the binary outcome is unknown. Our results indicate that using balanced training data (50% neutral and 50% deleterious) results in the highest balanced accuracy (the average of True Positive Rate and True Negative Rate), Matthews correlation coefficient, and area under ROC curves, no matter what the proportions of the two phenotypes are in the testing data. Besides balancing the data by undersampling the majority class, other techniques in machine learning include oversampling the minority class, interpolating minority-class data points and various penalties for misclassifying the minority class. However, these techniques are not commonly used in either the missense phenotype prediction problem or in the prediction of disordered residues in proteins, where the imbalance problem is substantial. The appropriate approach depends on the amount of available data and the specific problem at hand.</p></div>", "links"=>[], "tags"=>["Computational biology", "Macromolecular structure analysis", "Macromolecular complex analysis", "genetics", "Genetic mutation", "Mutational hypotheses", "genomics", "Genome analysis tools", "Gene prediction", "Computer modeling", "Computing methods", "Computer inferencing", "information science", "sets", "binary", "classifiers"], "article_id"=>742354, "categories"=>["Information And Computing Sciences", "Biological Sciences", "Sociology"], "users"=>["Qiong Wei", "Roland L. Dunbrack Jr"], "doi"=>"https://dx.doi.org/10.1371/journal.pone.0067863", "stats"=>{"downloads"=>3, "page_views"=>12, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_The_Role_of_Balanced_Training_and_Testing_Data_Sets_for_Binary_Classifiers_in_Bioinformatics_/742354", "title"=>"The Role of Balanced Training and Testing Data Sets for Binary Classifiers in Bioinformatics", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2013-07-09 02:40:30"}

PMC Usage Stats | Further Information

  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2013", "month"=>"7"}
  • {"unique-ip"=>"22", "full-text"=>"23", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2013", "month"=>"8"}
  • {"unique-ip"=>"13", "full-text"=>"12", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"3", "cited-by"=>"0", "year"=>"2013", "month"=>"9"}
  • {"unique-ip"=>"6", "full-text"=>"4", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"10"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"11"}
  • {"unique-ip"=>"8", "full-text"=>"8", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"12"}
  • {"unique-ip"=>"11", "full-text"=>"9", "pdf"=>"2", "abstract"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"1"}
  • {"unique-ip"=>"8", "full-text"=>"9", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"2"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"3"}
  • {"unique-ip"=>"15", "full-text"=>"17", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2014", "month"=>"5"}
  • {"unique-ip"=>"8", "full-text"=>"8", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2014", "month"=>"6"}
  • {"unique-ip"=>"6", "full-text"=>"9", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"4"}
  • {"unique-ip"=>"20", "full-text"=>"20", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"4"}
  • {"unique-ip"=>"25", "full-text"=>"26", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"5"}
  • {"unique-ip"=>"95", "full-text"=>"155", "pdf"=>"10", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2015", "month"=>"6"}
  • {"unique-ip"=>"30", "full-text"=>"30", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"7"}
  • {"unique-ip"=>"20", "full-text"=>"23", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"3"}
  • {"unique-ip"=>"24", "full-text"=>"28", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"2"}
  • {"unique-ip"=>"34", "full-text"=>"37", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"8"}
  • {"unique-ip"=>"51", "full-text"=>"55", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"5", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2015", "month"=>"9"}
  • {"unique-ip"=>"57", "full-text"=>"66", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"10"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"7"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"8"}
  • {"unique-ip"=>"7", "full-text"=>"4", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"9"}
  • {"unique-ip"=>"13", "full-text"=>"8", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"10"}
  • {"unique-ip"=>"54", "full-text"=>"56", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"2"}
  • {"unique-ip"=>"7", "full-text"=>"4", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"11"}
  • {"unique-ip"=>"9", "full-text"=>"10", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"12"}
  • {"unique-ip"=>"20", "full-text"=>"22", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2015", "month"=>"1"}
  • {"unique-ip"=>"58", "full-text"=>"64", "pdf"=>"8", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2015", "month"=>"11"}
  • {"unique-ip"=>"41", "full-text"=>"43", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"12"}
  • {"unique-ip"=>"48", "full-text"=>"57", "pdf"=>"4", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"1"}
  • {"unique-ip"=>"60", "full-text"=>"65", "pdf"=>"6", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"3"}
  • {"unique-ip"=>"49", "full-text"=>"53", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"2", "year"=>"2016", "month"=>"4"}
  • {"unique-ip"=>"47", "full-text"=>"51", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"5"}
  • {"unique-ip"=>"55", "full-text"=>"65", "pdf"=>"8", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"6"}
  • {"unique-ip"=>"45", "full-text"=>"67", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"7"}
  • {"unique-ip"=>"52", "full-text"=>"71", "pdf"=>"4", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"8"}
  • {"unique-ip"=>"73", "full-text"=>"78", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"9"}
  • {"unique-ip"=>"68", "full-text"=>"72", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2016", "month"=>"10"}
  • {"unique-ip"=>"93", "full-text"=>"97", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"11"}
  • {"unique-ip"=>"80", "full-text"=>"85", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"8", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2016", "month"=>"12"}
  • {"unique-ip"=>"65", "full-text"=>"71", "pdf"=>"7", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"2", "year"=>"2017", "month"=>"1"}
  • {"unique-ip"=>"75", "full-text"=>"79", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"104", "full-text"=>"120", "pdf"=>"5", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"65", "full-text"=>"66", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"72", "full-text"=>"86", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"7", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"72", "full-text"=>"89", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"45", "full-text"=>"51", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"87", "full-text"=>"98", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"5", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"105", "full-text"=>"127", "pdf"=>"11", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"142", "full-text"=>"162", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
  • {"unique-ip"=>"148", "full-text"=>"159", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2017", "month"=>"11"}
  • {"unique-ip"=>"154", "full-text"=>"164", "pdf"=>"9", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"7", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"12"}
  • {"unique-ip"=>"184", "full-text"=>"194", "pdf"=>"23", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2018", "month"=>"1"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"2"}
  • {"unique-ip"=>"193", "full-text"=>"201", "pdf"=>"15", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2018", "month"=>"3"}
  • {"unique-ip"=>"93", "full-text"=>"107", "pdf"=>"9", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2019", "month"=>"1"}
  • {"unique-ip"=>"225", "full-text"=>"245", "pdf"=>"11", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"2", "year"=>"2018", "month"=>"4"}
  • {"unique-ip"=>"179", "full-text"=>"190", "pdf"=>"6", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"5"}
  • {"unique-ip"=>"140", "full-text"=>"155", "pdf"=>"13", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"6"}
  • {"unique-ip"=>"106", "full-text"=>"116", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2018", "month"=>"7"}
  • {"unique-ip"=>"183", "full-text"=>"198", "pdf"=>"5", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2018", "month"=>"11"}
  • {"unique-ip"=>"197", "full-text"=>"219", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2018", "month"=>"10"}
  • {"unique-ip"=>"153", "full-text"=>"166", "pdf"=>"21", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"2", "year"=>"2018", "month"=>"8"}
  • {"unique-ip"=>"139", "full-text"=>"164", "pdf"=>"9", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"9"}
  • {"unique-ip"=>"105", "full-text"=>"120", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"4", "cited-by"=>"0", "year"=>"2018", "month"=>"12"}
  • {"unique-ip"=>"88", "full-text"=>"96", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"2"}
  • {"unique-ip"=>"191", "full-text"=>"213", "pdf"=>"10", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2019", "month"=>"3"}
  • {"unique-ip"=>"190", "full-text"=>"216", "pdf"=>"8", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2019", "month"=>"4"}
  • {"unique-ip"=>"140", "full-text"=>"164", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"2", "year"=>"2019", "month"=>"5"}
  • {"unique-ip"=>"82", "full-text"=>"106", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"8"}
  • {"unique-ip"=>"82", "full-text"=>"82", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"9"}
  • {"unique-ip"=>"100", "full-text"=>"115", "pdf"=>"6", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"10"}
  • {"unique-ip"=>"79", "full-text"=>"85", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2019", "month"=>"12"}
  • {"unique-ip"=>"82", "full-text"=>"93", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"1", "year"=>"2020", "month"=>"2"}
  • {"unique-ip"=>"91", "full-text"=>"102", "pdf"=>"11", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"3"}
  • {"unique-ip"=>"103", "full-text"=>"125", "pdf"=>"14", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2020", "month"=>"4"}
  • {"unique-ip"=>"84", "full-text"=>"97", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"5"}
  • {"unique-ip"=>"50", "full-text"=>"57", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2020", "month"=>"6"}
  • {"unique-ip"=>"42", "full-text"=>"53", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"7"}
  • {"unique-ip"=>"53", "full-text"=>"59", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2020", "month"=>"8"}
  • {"unique-ip"=>"55", "full-text"=>"61", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2020", "month"=>"9"}

Relative Metric

{"start_date"=>"2013-01-01T00:00:00Z", "end_date"=>"2013-12-31T00:00:00Z", "subject_areas"=>[{"subject_area"=>"/Biology and life sciences/Genetics", "average_usage"=>[284, 491, 620, 738, 843, 945, 1043, 1137, 1225, 1315, 1400, 1479, 1555]}, {"subject_area"=>"/Biology and life sciences/Neuroscience", "average_usage"=>[261, 444, 554, 655, 748, 834, 923, 1004, 1089, 1170, 1244, 1315, 1380]}, {"subject_area"=>"/Computer and information sciences", "average_usage"=>[297, 488, 616, 724, 828, 939, 1038, 1127, 1223, 1311, 1393, 1479, 1556]}, {"subject_area"=>"/Computer and information sciences/Artificial intelligence", "average_usage"=>[271, 413, 528, 633, 737, 815, 890, 970, 1042, 1119, 1222, 1287, 1315]}]}
Loading … Spinner
There are currently no alerts