A Unified Multitask Architecture for Predicting Local Protein Properties
Publication Date
March 26, 2012
Journal
PLOS ONE
Authors
Yanjun Qi, Merja Oja, Jason Weston & William Stafford Noble
Volume
7
Issue
3
Pages
e32235
DOI
https://dx.plos.org/10.1371/journal.pone.0032235
Publisher URL
http://journals.plos.org/plosone/article?id=10.1371%2Fjournal.pone.0032235
PubMed
http://www.ncbi.nlm.nih.gov/pubmed/22461885
PubMed Central
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3312883
Europe PMC
http://europepmc.org/abstract/MED/22461885
Web of Science
000304118900004
Scopus
84858841519
Mendeley
http://www.mendeley.com/research/unified-multitask-architecture-predicting-local-protein-properties
Events
Loading … Spinner
Mendeley 6625 Apr 05:15 UTC

Mendeley | Further Information

{"title"=>"A unified multitask architecture for predicting local protein properties", "type"=>"journal", "authors"=>[{"first_name"=>"Yanjun", "last_name"=>"Qi", "scopus_author_id"=>"8324721600"}, {"first_name"=>"Merja", "last_name"=>"Oja", "scopus_author_id"=>"6603449946"}, {"first_name"=>"Jason", "last_name"=>"Weston", "scopus_author_id"=>"8865128200"}, {"first_name"=>"William Stafford", "last_name"=>"Noble", "scopus_author_id"=>"7102482003"}], "year"=>2012, "source"=>"PLoS ONE", "identifiers"=>{"scopus"=>"2-s2.0-84858841519", "sgr"=>"84858841519", "issn"=>"19326203", "doi"=>"10.1371/journal.pone.0032235", "pmid"=>"22461885", "isbn"=>"1932-6203 (Electronic)\\n1932-6203 (Linking)", "pui"=>"364505229"}, "id"=>"c0279b98-823e-3c22-a303-20f171d01150", "abstract"=>"A variety of functionally important protein properties, such as secondary structure, transmembrane topology and solvent accessibility, can be encoded as a labeling of amino acids. Indeed, the prediction of such properties from the primary amino acid sequence is one of the core projects of computational biology. Accordingly, a panoply of approaches have been developed for predicting such properties; however, most such approaches focus on solving a single task at a time. Motivated by recent, successful work in natural language processing, we propose to use multitask learning to train a single, joint model that exploits the dependencies among these various labeling tasks. We describe a deep neural network architecture that, given a protein sequence, outputs a host of predicted local properties, including secondary structure, solvent accessibility, transmembrane topology, signal peptides and DNA-binding residues. The network is trained jointly on all these tasks in a supervised fashion, augmented with a novel form of semi-supervised learning in which the model is trained to distinguish between local patterns from natural and synthetic protein sequences. The task-independent architecture of the network obviates the need for task-specific feature engineering. We demonstrate that, for all of the tasks that we considered, our approach leads to statistically significant improvements in performance, relative to a single task neural network approach, and that the resulting model achieves state-of-the-art performance.", "link"=>"http://www.mendeley.com/research/unified-multitask-architecture-predicting-local-protein-properties", "reader_count"=>60, "reader_count_by_academic_status"=>{"Unspecified"=>2, "Professor > Associate Professor"=>5, "Researcher"=>11, "Student > Doctoral Student"=>1, "Student > Ph. D. Student"=>18, "Student > Postgraduate"=>2, "Student > Master"=>11, "Other"=>4, "Student > Bachelor"=>5, "Professor"=>1}, "reader_count_by_user_role"=>{"Unspecified"=>2, "Professor > Associate Professor"=>5, "Researcher"=>11, "Student > Doctoral Student"=>1, "Student > Ph. D. Student"=>18, "Student > Postgraduate"=>2, "Student > Master"=>11, "Other"=>4, "Student > Bachelor"=>5, "Professor"=>1}, "reader_count_by_subject_area"=>{"Engineering"=>8, "Unspecified"=>4, "Biochemistry, Genetics and Molecular Biology"=>9, "Materials Science"=>1, "Mathematics"=>1, "Agricultural and Biological Sciences"=>20, "Medicine and Dentistry"=>2, "Neuroscience"=>1, "Chemistry"=>1, "Computer Science"=>13}, "reader_count_by_subdiscipline"=>{"Engineering"=>{"Engineering"=>8}, "Materials Science"=>{"Materials Science"=>1}, "Medicine and Dentistry"=>{"Medicine and Dentistry"=>2}, "Neuroscience"=>{"Neuroscience"=>1}, "Chemistry"=>{"Chemistry"=>1}, "Agricultural and Biological Sciences"=>{"Agricultural and Biological Sciences"=>20}, "Computer Science"=>{"Computer Science"=>13}, "Biochemistry, Genetics and Molecular Biology"=>{"Biochemistry, Genetics and Molecular Biology"=>9}, "Mathematics"=>{"Mathematics"=>1}, "Unspecified"=>{"Unspecified"=>4}}, "reader_count_by_country"=>{"New Zealand"=>1, "Canada"=>1, "Austria"=>1, "Belgium"=>1, "United States"=>6, "Norway"=>1, "South Africa"=>1, "United Kingdom"=>1, "Israel"=>1, "Spain"=>1}, "group_count"=>6}
Scopus 2919 Jul 08:30 UTC

Scopus | Further Information

{"@_fa"=>"true", "link"=>[{"@_fa"=>"true", "@ref"=>"self", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84858841519"}, {"@_fa"=>"true", "@ref"=>"author-affiliation", "@href"=>"https://api.elsevier.com/content/abstract/scopus_id/84858841519?field=author,affiliation"}, {"@_fa"=>"true", "@ref"=>"scopus", "@href"=>"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84858841519&origin=inward"}, {"@_fa"=>"true", "@ref"=>"scopus-citedby", "@href"=>"https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84858841519&origin=inward"}], "prism:url"=>"https://api.elsevier.com/content/abstract/scopus_id/84858841519", "dc:identifier"=>"SCOPUS_ID:84858841519", "eid"=>"2-s2.0-84858841519", "dc:title"=>"A unified multitask architecture for predicting local protein properties", "dc:creator"=>"Qi Y.", "prism:publicationName"=>"PLoS ONE", "prism:eIssn"=>"19326203", "prism:volume"=>"7", "prism:issueIdentifier"=>"3", "prism:pageRange"=>nil, "prism:coverDate"=>"2012-03-26", "prism:coverDisplayDate"=>"26 March 2012", "prism:doi"=>"10.1371/journal.pone.0032235", "citedby-count"=>"29", "affiliation"=>[{"@_fa"=>"true", "affilname"=>"NEC Laboratories America, Inc.", "affiliation-city"=>"Princeton", "affiliation-country"=>"United States"}], "pubmed-id"=>"22461885", "prism:aggregationType"=>"Journal", "subtype"=>"ar", "subtypeDescription"=>"Article", "article-number"=>"e32235", "source-id"=>"10600153309", "openaccess"=>"1", "openaccessFlag"=>true}
Facebook30 Jul 10:08 UTC

Facebook

  • {"url"=>"http%3A%2F%2Fjournals.plos.org%2Fplosone%2Farticle%3Fid%3D10.1371%252Fjournal.pone.0032235", "share_count"=>0, "like_count"=>0, "comment_count"=>0, "click_count"=>0, "total_count"=>0}
Counter 713722 Jul 00:40 UTC

Counter

  • {"month"=>"3", "year"=>"2012", "pdf_views"=>"21", "xml_views"=>"6", "html_views"=>"296"}
  • {"month"=>"4", "year"=>"2012", "pdf_views"=>"57", "xml_views"=>"17", "html_views"=>"225"}
  • {"month"=>"5", "year"=>"2012", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"103"}
  • {"month"=>"6", "year"=>"2012", "pdf_views"=>"12", "xml_views"=>"2", "html_views"=>"39"}
  • {"month"=>"7", "year"=>"2012", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"48"}
  • {"month"=>"8", "year"=>"2012", "pdf_views"=>"14", "xml_views"=>"4", "html_views"=>"37"}
  • {"month"=>"9", "year"=>"2012", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"35"}
  • {"month"=>"10", "year"=>"2012", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"47"}
  • {"month"=>"11", "year"=>"2012", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"37"}
  • {"month"=>"12", "year"=>"2012", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"1", "year"=>"2013", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"55"}
  • {"month"=>"2", "year"=>"2013", "pdf_views"=>"5", "xml_views"=>"1", "html_views"=>"49"}
  • {"month"=>"3", "year"=>"2013", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"4", "year"=>"2013", "pdf_views"=>"9", "xml_views"=>"2", "html_views"=>"43"}
  • {"month"=>"5", "year"=>"2013", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"33"}
  • {"month"=>"6", "year"=>"2013", "pdf_views"=>"5", "xml_views"=>"1", "html_views"=>"23"}
  • {"month"=>"7", "year"=>"2013", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"8", "year"=>"2013", "pdf_views"=>"4", "xml_views"=>"0", "html_views"=>"30"}
  • {"month"=>"9", "year"=>"2013", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"31"}
  • {"month"=>"10", "year"=>"2013", "pdf_views"=>"7", "xml_views"=>"3", "html_views"=>"29"}
  • {"month"=>"11", "year"=>"2013", "pdf_views"=>"10", "xml_views"=>"2", "html_views"=>"42"}
  • {"month"=>"12", "year"=>"2013", "pdf_views"=>"6", "xml_views"=>"0", "html_views"=>"35"}
  • {"month"=>"1", "year"=>"2014", "pdf_views"=>"11", "xml_views"=>"0", "html_views"=>"55"}
  • {"month"=>"2", "year"=>"2014", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"25"}
  • {"month"=>"3", "year"=>"2014", "pdf_views"=>"7", "xml_views"=>"2", "html_views"=>"33"}
  • {"month"=>"4", "year"=>"2014", "pdf_views"=>"9", "xml_views"=>"1", "html_views"=>"48"}
  • {"month"=>"5", "year"=>"2014", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"63"}
  • {"month"=>"6", "year"=>"2014", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"67"}
  • {"month"=>"7", "year"=>"2014", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"80"}
  • {"month"=>"8", "year"=>"2014", "pdf_views"=>"17", "xml_views"=>"2", "html_views"=>"62"}
  • {"month"=>"9", "year"=>"2014", "pdf_views"=>"12", "xml_views"=>"1", "html_views"=>"93"}
  • {"month"=>"10", "year"=>"2014", "pdf_views"=>"8", "xml_views"=>"1", "html_views"=>"115"}
  • {"month"=>"11", "year"=>"2014", "pdf_views"=>"5", "xml_views"=>"1", "html_views"=>"57"}
  • {"month"=>"12", "year"=>"2014", "pdf_views"=>"14", "xml_views"=>"2", "html_views"=>"70"}
  • {"month"=>"1", "year"=>"2015", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"86"}
  • {"month"=>"2", "year"=>"2015", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"93"}
  • {"month"=>"3", "year"=>"2015", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"93"}
  • {"month"=>"4", "year"=>"2015", "pdf_views"=>"12", "xml_views"=>"1", "html_views"=>"117"}
  • {"month"=>"5", "year"=>"2015", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"98"}
  • {"month"=>"6", "year"=>"2015", "pdf_views"=>"24", "xml_views"=>"0", "html_views"=>"82"}
  • {"month"=>"7", "year"=>"2015", "pdf_views"=>"19", "xml_views"=>"0", "html_views"=>"29"}
  • {"month"=>"8", "year"=>"2015", "pdf_views"=>"9", "xml_views"=>"1", "html_views"=>"39"}
  • {"month"=>"9", "year"=>"2015", "pdf_views"=>"10", "xml_views"=>"0", "html_views"=>"56"}
  • {"month"=>"10", "year"=>"2015", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"69"}
  • {"month"=>"11", "year"=>"2015", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"62"}
  • {"month"=>"12", "year"=>"2015", "pdf_views"=>"1", "xml_views"=>"0", "html_views"=>"70"}
  • {"month"=>"1", "year"=>"2016", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"62"}
  • {"month"=>"2", "year"=>"2016", "pdf_views"=>"3", "xml_views"=>"0", "html_views"=>"28"}
  • {"month"=>"3", "year"=>"2016", "pdf_views"=>"8", "xml_views"=>"0", "html_views"=>"63"}
  • {"month"=>"4", "year"=>"2016", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"67"}
  • {"month"=>"5", "year"=>"2016", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"18"}
  • {"month"=>"6", "year"=>"2016", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"27"}
  • {"month"=>"7", "year"=>"2016", "pdf_views"=>"9", "xml_views"=>"0", "html_views"=>"24"}
  • {"month"=>"8", "year"=>"2016", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"51"}
  • {"month"=>"9", "year"=>"2016", "pdf_views"=>"30", "xml_views"=>"0", "html_views"=>"184"}
  • {"month"=>"10", "year"=>"2016", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"110"}
  • {"month"=>"11", "year"=>"2016", "pdf_views"=>"2", "xml_views"=>"0", "html_views"=>"73"}
  • {"month"=>"12", "year"=>"2016", "pdf_views"=>"6", "xml_views"=>"2", "html_views"=>"99"}
  • {"month"=>"1", "year"=>"2017", "pdf_views"=>"35", "xml_views"=>"1", "html_views"=>"92"}
  • {"month"=>"2", "year"=>"2017", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"98"}
  • {"month"=>"3", "year"=>"2017", "pdf_views"=>"12", "xml_views"=>"0", "html_views"=>"37"}
  • {"month"=>"4", "year"=>"2017", "pdf_views"=>"5", "xml_views"=>"0", "html_views"=>"33"}
  • {"month"=>"5", "year"=>"2017", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"37"}
  • {"month"=>"6", "year"=>"2017", "pdf_views"=>"8", "xml_views"=>"0", "html_views"=>"57"}
  • {"month"=>"7", "year"=>"2017", "pdf_views"=>"8", "xml_views"=>"2", "html_views"=>"45"}
  • {"month"=>"8", "year"=>"2017", "pdf_views"=>"15", "xml_views"=>"1", "html_views"=>"60"}
  • {"month"=>"9", "year"=>"2017", "pdf_views"=>"9", "xml_views"=>"1", "html_views"=>"34"}
  • {"month"=>"10", "year"=>"2017", "pdf_views"=>"52", "xml_views"=>"2", "html_views"=>"42"}
  • {"month"=>"11", "year"=>"2017", "pdf_views"=>"87", "xml_views"=>"0", "html_views"=>"72"}
  • {"month"=>"12", "year"=>"2017", "pdf_views"=>"157", "xml_views"=>"2", "html_views"=>"58"}
  • {"month"=>"1", "year"=>"2018", "pdf_views"=>"430", "xml_views"=>"0", "html_views"=>"52"}
  • {"month"=>"2", "year"=>"2018", "pdf_views"=>"257", "xml_views"=>"0", "html_views"=>"14"}
  • {"month"=>"3", "year"=>"2018", "pdf_views"=>"43", "xml_views"=>"2", "html_views"=>"11"}
  • {"month"=>"4", "year"=>"2018", "pdf_views"=>"28", "xml_views"=>"0", "html_views"=>"6"}
  • {"month"=>"5", "year"=>"2018", "pdf_views"=>"41", "xml_views"=>"0", "html_views"=>"30"}
  • {"month"=>"6", "year"=>"2018", "pdf_views"=>"60", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"7", "year"=>"2018", "pdf_views"=>"75", "xml_views"=>"3", "html_views"=>"30"}
  • {"month"=>"8", "year"=>"2018", "pdf_views"=>"16", "xml_views"=>"1", "html_views"=>"16"}
  • {"month"=>"9", "year"=>"2018", "pdf_views"=>"70", "xml_views"=>"0", "html_views"=>"13"}
  • {"month"=>"10", "year"=>"2018", "pdf_views"=>"16", "xml_views"=>"2", "html_views"=>"17"}
  • {"month"=>"11", "year"=>"2018", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"19"}
  • {"month"=>"12", "year"=>"2018", "pdf_views"=>"18", "xml_views"=>"0", "html_views"=>"24"}
  • {"month"=>"1", "year"=>"2019", "pdf_views"=>"16", "xml_views"=>"0", "html_views"=>"27"}
  • {"month"=>"2", "year"=>"2019", "pdf_views"=>"13", "xml_views"=>"0", "html_views"=>"16"}
  • {"month"=>"3", "year"=>"2019", "pdf_views"=>"15", "xml_views"=>"0", "html_views"=>"20"}
  • {"month"=>"4", "year"=>"2019", "pdf_views"=>"14", "xml_views"=>"0", "html_views"=>"14"}
  • {"month"=>"5", "year"=>"2019", "pdf_views"=>"36", "xml_views"=>"0", "html_views"=>"21"}
  • {"month"=>"6", "year"=>"2019", "pdf_views"=>"26", "xml_views"=>"1", "html_views"=>"21"}
  • {"month"=>"7", "year"=>"2019", "pdf_views"=>"7", "xml_views"=>"0", "html_views"=>"17"}
Figshare09 Jan 06:01 UTC

Figshare

  • {"files"=>["https://ndownloader.figshare.com/files/340293"], "description"=>"<div><p>A variety of functionally important protein properties, such as secondary structure, transmembrane topology and solvent accessibility, can be encoded as a labeling of amino acids. Indeed, the prediction of such properties from the primary amino acid sequence is one of the core projects of computational biology. Accordingly, a panoply of approaches have been developed for predicting such properties; however, most such approaches focus on solving a single task at a time. Motivated by recent, successful work in natural language processing, we propose to use <em>multitask learning</em> to train a single, joint model that exploits the dependencies among these various labeling tasks. We describe a deep neural network architecture that, given a protein sequence, outputs a host of predicted local properties, including secondary structure, solvent accessibility, transmembrane topology, signal peptides and DNA-binding residues. The network is trained jointly on all these tasks in a supervised fashion, augmented with a novel form of semi-supervised learning in which the model is trained to distinguish between local patterns from natural and synthetic protein sequences. The task-independent architecture of the network obviates the need for task-specific feature engineering. We demonstrate that, for all of the tasks that we considered, our approach leads to statistically significant improvements in performance, relative to a single task neural network approach, and that the resulting model achieves state-of-the-art performance.</p> </div>", "links"=>[], "tags"=>["unified", "multitask", "predicting", "properties"], "article_id"=>127267, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/A_Unified_Multitask_Architecture_for_Predicting_Local_Protein_Properties/127267", "title"=>"A Unified Multitask Architecture for Predicting Local Protein Properties", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2012-03-26 02:01:07"}
  • {"files"=>["https://ndownloader.figshare.com/files/663068"], "description"=>"<p>Given an input amino acid sequence, the neural network outputs a posterior distribution over the class labels for that amino acid. This general deep network architecture is suitable for all of our prediction tasks. The network is characterized by three parts: (1) an amino acid feature extraction layer, (2) a sequential feature extraction layer, and (3) a series of classical neural network layers. The first layer consists a PSI-BLAST feature module and an amino acid embedding module. With a sliding window input (here ), the amino acid embedding module outputs a series of real valued vectors . Similarly, the PSI-BLAST module derives 20-dimensional PSI-BLAST feature vectors corresponding to the amino acids. These vectors are then concatenated in the sequential extraction layer of the network. Finally, the derived vector is fed into the classical neural network layers. The final softmax layer allows us to interpret the outputs as probabilities for each class.</p>", "links"=>[], "tags"=>["neural"], "article_id"=>333554, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.g001"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Deep_neural_network_architecture_/333554", "title"=>"Deep neural network architecture.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2012-03-26 00:59:14"}
  • {"files"=>["https://ndownloader.figshare.com/files/663131"], "description"=>"<p>In this figure, two related tasks are trained simultaneously using the network the architecture from <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0032235#pone-0032235-g001\" target=\"_blank\">Figure 1</a>. Here only the very last layers of the network are task specific.</p>", "links"=>[], "tags"=>["sharing", "neural"], "article_id"=>333621, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.g002"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Multitask_learning_with_weight_sharing_between_multiple_deep_neural_networks_/333621", "title"=>"Multitask learning with weight sharing between multiple deep neural networks.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2012-03-26 01:00:21"}
  • {"files"=>["https://ndownloader.figshare.com/files/663217"], "description"=>"<p>The “natural protein” auxiliary task aiming to model the local patterns of amino acids that naturally occur in protein sequences. Using local windows in the unlabeled protein sequences as positive examples and randomly modified windows as negative examples, the network learns the feature representations for each amino acid. In contrast to the network illustrated in <a href=\"http://www.plosone.org/article/info:doi/10.1371/journal.pone.0032235#pone-0032235-g001\" target=\"_blank\">Figure 1</a>, the network contains only the amino acid embedding module in the first layer of the network. The learned embedding is encoded into the real valued parameter matrix of the amino acid feature extraction layer.</p>", "links"=>[], "tags"=>["auxiliary"], "article_id"=>333702, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.g003"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Network_architecture_for_training_the_8220_natural_protein_8221_auxiliary_task_/333702", "title"=>"Network architecture for training the “natural protein” auxiliary task.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2012-03-26 01:01:42"}
  • {"files"=>["https://ndownloader.figshare.com/files/663278"], "description"=>"<p>The figure shows an approximation of a 15-dimensional embedding of amino acids, learned by a neural network trained on the natural protein task. The projection to 2D is accomplished via principal component analysis.</p>", "links"=>[], "tags"=>["learned", "amino"], "article_id"=>333767, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.g004"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_A_learned_amino_acid_embedding_/333767", "title"=>"A learned amino acid embedding.", "pos_in_sequence"=>0, "defined_type"=>1, "published_date"=>"2012-03-26 01:02:47"}
  • {"files"=>["https://ndownloader.figshare.com/files/663319"], "description"=>"<p>For each data set, we list the number of protein sequences, the number of amino acids, the number of cross validation folds, and the proportion of amino acids assigned to each label.</p>", "links"=>[], "tags"=>["Computational biology", "Biochemistry"], "article_id"=>333813, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.t001"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Summary_of_data_sets_/333813", "title"=>"Summary of data sets.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2012-03-26 01:03:33"}
  • {"files"=>["https://ndownloader.figshare.com/files/663361"], "description"=>"<p>The table lists, for each prediction task, the per-residue percent accuracy achieved via single-task training of the neural network with just the PSI-BLAST features (“Single”), single-task training that includes the amino acid embedding (“Embed”), multitask training just using the PSI-BLAST features (“Multi”), multitask training including the amino acid embedding (“Multi-Emb”), multitask training of one task along with the natural protein task (“NP”), multitask training without the PSI-BLAST embedding module but initializing the amino acid embedding by using the natural protein task (“NP only”), multitask training including the natural protein task (“All3”), “All3” with Viterbi post-processing (“All3+Vit”) and a previously reported method (“Previous”). Each row corresponds to a single task. The -value column indicates whether the difference between “Single” and “All3+Vit” is significant, according to a Z-test. The “CV” column is computed based on the accuracies separately for each cross-validation fold. It counts the percentage of CV folds in which the “All3+Vit” method outperforms the “Single” method. Rows labeled “(prot)” or “(seg)” report the protein- or segment-level accuracy, rather than residue-level accuracy. For the “NP” setting, the “*” in the “Embedding?” row indicates that this network uses the pre-trained embedding layer from the natural protein task.</p>", "links"=>[], "tags"=>["strategies", "percent"], "article_id"=>333851, "categories"=>["Biological Sciences", "Biochemistry"], "users"=>["Yanjun Qi", "Merja Oja", "Jason Weston", "William Stafford Noble"], "doi"=>["https://dx.doi.org/10.1371/journal.pone.0032235.t002"], "stats"=>{"downloads"=>0, "page_views"=>0, "likes"=>0}, "figshare_url"=>"https://figshare.com/articles/_Comparison_of_learning_strategies_based_on_percent_accuracy_/333851", "title"=>"Comparison of learning strategies based on percent accuracy.", "pos_in_sequence"=>0, "defined_type"=>3, "published_date"=>"2012-03-26 01:04:11"}
PMC Usage Stats 51517 Jul 15:04 UTC

PMC Usage Stats | Further Information

  • {"scanned-page-browse"=>"0", "month"=>"3", "cited-by"=>"0", "abstract"=>"0", "full-text"=>"1", "unique-ip"=>"1", "pdf"=>"0", "year"=>"2012", "figure"=>"0", "scanned-summary"=>"0", "supp-data"=>"0"}
  • {"month"=>"4", "scanned-page-browse"=>"0", "cited-by"=>"0", "abstract"=>"1", "full-text"=>"16", "year"=>"2012", "pdf"=>"7", "unique-ip"=>"19", "figure"=>"8", "scanned-summary"=>"0", "supp-data"=>"0"}
  • {"scanned-page-browse"=>"0", "month"=>"5", "cited-by"=>"0", "abstract"=>"1", "full-text"=>"6", "unique-ip"=>"6", "pdf"=>"0", "year"=>"2012", "figure"=>"0", "scanned-summary"=>"0", "supp-data"=>"0"}
  • {"month"=>"6", "scanned-page-browse"=>"0", "cited-by"=>"0", "abstract"=>"1", "full-text"=>"14", "year"=>"2012", "pdf"=>"3", "unique-ip"=>"12", "figure"=>"0", "scanned-summary"=>"0", "supp-data"=>"0"}
  • {"unique-ip"=>"12", "full-text"=>"11", "pdf"=>"4", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"5", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2012", "month"=>"7"}
  • {"unique-ip"=>"11", "full-text"=>"12", "pdf"=>"5", "abstract"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2012", "month"=>"8"}
  • {"unique-ip"=>"5", "full-text"=>"6", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2012", "month"=>"9"}
  • {"unique-ip"=>"14", "full-text"=>"12", "pdf"=>"5", "abstract"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2012", "month"=>"10"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2012", "month"=>"12"}
  • {"unique-ip"=>"8", "full-text"=>"8", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"1"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"4", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"2"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"4"}
  • {"unique-ip"=>"8", "full-text"=>"8", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2012", "month"=>"11"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"5"}
  • {"unique-ip"=>"6", "full-text"=>"4", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"6"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"7"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"8"}
  • {"unique-ip"=>"4", "full-text"=>"4", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"9"}
  • {"unique-ip"=>"3", "full-text"=>"2", "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"=>"3", "full-text"=>"3", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"11"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2013", "month"=>"12"}
  • {"unique-ip"=>"2", "full-text"=>"1", "pdf"=>"1", "abstract"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"1"}
  • {"unique-ip"=>"3", "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"=>"2"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"5"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"4"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"4"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"5"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"6"}
  • {"unique-ip"=>"6", "full-text"=>"5", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"7"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"3"}
  • {"unique-ip"=>"5", "full-text"=>"3", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"2"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"8"}
  • {"unique-ip"=>"6", "full-text"=>"6", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"9"}
  • {"unique-ip"=>"10", "full-text"=>"8", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"10"}
  • {"unique-ip"=>"5", "full-text"=>"4", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"7"}
  • {"unique-ip"=>"7", "full-text"=>"4", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"8"}
  • {"unique-ip"=>"2", "full-text"=>"0", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"9"}
  • {"unique-ip"=>"17", "full-text"=>"10", "pdf"=>"4", "abstract"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"10"}
  • {"unique-ip"=>"6", "full-text"=>"1", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"2"}
  • {"unique-ip"=>"6", "full-text"=>"5", "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"=>"2", "full-text"=>"0", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2014", "month"=>"12"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2015", "month"=>"1"}
  • {"unique-ip"=>"15", "full-text"=>"8", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"9", "supp-data"=>"1", "cited-by"=>"2", "year"=>"2015", "month"=>"11"}
  • {"unique-ip"=>"9", "full-text"=>"2", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2015", "month"=>"12"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2016", "month"=>"1"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"4"}
  • {"unique-ip"=>"4", "full-text"=>"2", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"5"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"6"}
  • {"unique-ip"=>"5", "full-text"=>"5", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"7"}
  • {"unique-ip"=>"8", "full-text"=>"8", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"8"}
  • {"unique-ip"=>"5", "full-text"=>"3", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"9"}
  • {"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"=>"2016", "month"=>"10"}
  • {"unique-ip"=>"2", "full-text"=>"1", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"11"}
  • {"unique-ip"=>"5", "full-text"=>"6", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2016", "month"=>"12"}
  • {"unique-ip"=>"7", "full-text"=>"4", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"1", "year"=>"2017", "month"=>"1"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"2"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"3"}
  • {"unique-ip"=>"1", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"4"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"5"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"6"}
  • {"unique-ip"=>"2", "full-text"=>"1", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"7"}
  • {"unique-ip"=>"3", "full-text"=>"3", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"8"}
  • {"unique-ip"=>"2", "full-text"=>"2", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"9"}
  • {"unique-ip"=>"8", "full-text"=>"6", "pdf"=>"3", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"10"}
  • {"unique-ip"=>"2", "full-text"=>"1", "pdf"=>"0", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2017", "month"=>"12"}
  • {"unique-ip"=>"6", "full-text"=>"6", "pdf"=>"2", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"1"}
  • {"unique-ip"=>"13", "full-text"=>"10", "pdf"=>"1", "abstract"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"3"}
  • {"unique-ip"=>"10", "full-text"=>"8", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"1"}
  • {"unique-ip"=>"10", "full-text"=>"7", "pdf"=>"3", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"4"}
  • {"unique-ip"=>"12", "full-text"=>"9", "pdf"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"5", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"5"}
  • {"unique-ip"=>"15", "full-text"=>"9", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"4", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"6"}
  • {"unique-ip"=>"3", "full-text"=>"4", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"10"}
  • {"unique-ip"=>"4", "full-text"=>"3", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2018", "month"=>"11"}
  • {"unique-ip"=>"25", "full-text"=>"8", "pdf"=>"4", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"7", "supp-data"=>"2", "cited-by"=>"0", "year"=>"2018", "month"=>"7"}
  • {"unique-ip"=>"13", "full-text"=>"13", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"3", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"9"}
  • {"unique-ip"=>"8", "full-text"=>"3", "pdf"=>"7", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"8"}
  • {"unique-ip"=>"9", "full-text"=>"11", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2018", "month"=>"12"}
  • {"unique-ip"=>"4", "full-text"=>"5", "pdf"=>"0", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"1", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"2"}
  • {"unique-ip"=>"3", "full-text"=>"2", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"2", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"3"}
  • {"unique-ip"=>"4", "full-text"=>"2", "pdf"=>"1", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"1", "cited-by"=>"0", "year"=>"2019", "month"=>"4"}
  • {"unique-ip"=>"8", "full-text"=>"7", "pdf"=>"2", "scanned-summary"=>"0", "scanned-page-browse"=>"0", "figure"=>"0", "supp-data"=>"0", "cited-by"=>"0", "year"=>"2019", "month"=>"5"}
Relative Metric 18272505 Apr 17:12 UTC

Relative Metric

{"start_date"=>"2012-01-01T00:00:00Z", "end_date"=>"2012-12-31T00:00:00Z", "subject_areas"=>[{"subject_area"=>"/Biology and life sciences", "average_usage"=>[322, 550, 671, 773, 864, 955, 1048, 1135, 1223, 1308, 1387, 1465, 1534, 1602, 1673, 1744, 1813, 1885, 1955, 2026, 2093, 2160, 2228, 2290, 2349]}, {"subject_area"=>"/Biology and life sciences/Molecular biology", "average_usage"=>[324, 551, 679, 782, 879, 971, 1064, 1154, 1245, 1328, 1406, 1476, 1541, 1617, 1683, 1754, 1818, 1893, 1962, 2025, 2092, 2164, 2227, 2294, 2355]}, {"subject_area"=>"/Computer and information sciences/Neural networks", "average_usage"=>[385, 629, 754, 840, 925, 1006, 1120, 1211, 1283, 1380, 1441, 1509, 1565, 1639, 1703, 1737, 1808, 1859, 1995, 2078, 2148, 2197, 2234, 2286, 2362]}, {"subject_area"=>"/Physical sciences", "average_usage"=>[304, 506, 616, 712, 799, 879, 968, 1052, 1134, 1212, 1284, 1357, 1427, 1494, 1557, 1621, 1689, 1756, 1823, 1883, 1944, 1997, 2056, 2118, 2171]}, {"subject_area"=>"/Social sciences/Psychology", "average_usage"=>[336, 562, 679, 770, 848, 938, 1036, 1125, 1198, 1287, 1364, 1425, 1488, 1556, 1618, 1687, 1756, 1817, 1879, 1943, 2011, 2065, 2118, 2186, 2243]}]}
Loading … Spinner
There are currently no alerts