Datasets
Models
31 lines (31 with data), 11.3 kB
ÇĽ , îsphinx.addnodesöîdocumentöôö)üö}ö(î rawsourceöî öîchildrenö]ö(îdocutils.nodesöîcommentöôö)üö}ö(hî═DeepProg documentation master file, created by sphinx-quickstart on Fri Dec 6 13:53:29 2019. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive.öh]öh îTextöôöî═DeepProg documentation master file, created by sphinx-quickstart on Fri Dec 6 13:53:29 2019. You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive.öůöüö}ö(hhîparentöh ubaî attributesö}ö(îidsö]öîclassesö]öînamesö]öîdupnamesö]öîbackrefsö]öî xml:spaceöîpreserveöuîtagnameöh hhhhîsourceöî(/home/oliver/code/SimDeep/docs/index.rstöîlineöKubh îsectionöôö)üö}ö(hhh]ö(h îtitleöôö)üö}ö(hî$Welcome to DeepProg's documentation!öh]öhî&Welcome to DeepProgÔÇÖs documentation!öůöüö}ö(hh2hh0hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hh+hhh&h'h(Kubh îcompoundöôö)üö}ö(hhh]öh îtoctreeöôö)üö}ö(hhh]öh}ö(h]öh]öh ]öh ]öh!]öhîindexöîentriesö]ö(Nî installationöćöNîusageöćöNîusage_ensembleöćöNîusage_advancedöćöNî case_studyöćöNî usage_tuningöćöNîLICENSEöćöNî api/simdeepöćöeî includefilesö]ö(hQhShUhWhYh[h]h_eîmaxdepthöKîcaptionöNîgloböëîhiddenöëî includehiddenöëînumberedöK î titlesonlyöëî rawentriesö]öuh%hCh&h'h(K hh@ubah}ö(h]öh]öîtoctree-wrapperöah ]öh ]öh!]öuh%h>hh+hhh&h'h(Nubh*)üö}ö(hhh]ö(h/)üö}ö(hî Introductionöh]öhî Introductionöůöüö}ö(hhxhhvhhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hhshhh&h'h(Kubh î paragraphöôö)üö}ö(hX< This package allows to combine multi-omics data for individual samples together with survival. Using autoencoders (default) or any alternative embedding methods, the pipeline creates new set of features and identifies those linked with survival. In a second time, the samples are clustered with different possible strategies to obtain robust subtypes linked to survival. The robustness of the obtained subtypes can then be tested externally on one or multiple validation datasets and/or the *out-of-bags* samples. The omic data used in the original study are RNA-Seq, MiR and Methylation. However, this approach can be extended to any combination of omic data. The current package contains the omic data used in the study and a copy of the model computed. However, it is easy to recreate a new model from scratch using any combination of omic data. The omic data and the survival files should be in tsv (Tabular Separated Values) format and examples are provided. The deep-learning framework to produce the autoencoders uses Keras with either Theano / tensorflow/ CNTK as background.öh]ö(hXŰ This package allows to combine multi-omics data for individual samples together with survival. Using autoencoders (default) or any alternative embedding methods, the pipeline creates new set of features and identifies those linked with survival. In a second time, the samples are clustered with different possible strategies to obtain robust subtypes linked to survival. The robustness of the obtained subtypes can then be tested externally on one or multiple validation datasets and/or the öůöüö}ö(hXŰ This package allows to combine multi-omics data for individual samples together with survival. Using autoencoders (default) or any alternative embedding methods, the pipeline creates new set of features and identifies those linked with survival. In a second time, the samples are clustered with different possible strategies to obtain robust subtypes linked to survival. The robustness of the obtained subtypes can then be tested externally on one or multiple validation datasets and/or the öhhćhhh&Nh(Nubh îemphasisöôö)üö}ö(hî *out-of-bags*öh]öhî out-of-bagsöůöüö}ö(hhhhĹubah}ö(h]öh]öh ]öh ]öh!]öuh%hĆhhćubhXD samples. The omic data used in the original study are RNA-Seq, MiR and Methylation. However, this approach can be extended to any combination of omic data. The current package contains the omic data used in the study and a copy of the model computed. However, it is easy to recreate a new model from scratch using any combination of omic data. The omic data and the survival files should be in tsv (Tabular Separated Values) format and examples are provided. The deep-learning framework to produce the autoencoders uses Keras with either Theano / tensorflow/ CNTK as background.öůöüö}ö(hXD samples. The omic data used in the original study are RNA-Seq, MiR and Methylation. However, this approach can be extended to any combination of omic data. The current package contains the omic data used in the study and a copy of the model computed. However, it is easy to recreate a new model from scratch using any combination of omic data. The omic data and the survival files should be in tsv (Tabular Separated Values) format and examples are provided. The deep-learning framework to produce the autoencoders uses Keras with either Theano / tensorflow/ CNTK as background.öhhćhhh&Nh(Nubeh}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(Khhshhubh îimageöôö)üö}ö(hî .. image:: ./img/workflow.png öh]öh}ö(h]öh]öh ]öh ]öh!]öîuriöî./img/workflow.pngöî candidatesö}öî*öhĚsuh%h¬hhshhh&h'h(K ubeh}ö(h]öî introductionöah]öh ]öî introductionöah ]öh!]öuh%h)hh+hhh&h'h(Kubh*)üö}ö(hhh]ö(h/)üö}ö(hîAccessöh]öhîAccessöůöüö}ö(hh╚hhĂhhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hh├hhh&h'h(K ubhů)üö}ö(hîPThe package is accessible at this link: https://github.com/lanagarmire/DeepProg.öh]ö(hî(The package is accessible at this link: öůöüö}ö(hî(The package is accessible at this link: öhhďhhh&Nh(Nubh î referenceöôö)üö}ö(hî'https://github.com/lanagarmire/DeepProgöh]öhî'https://github.com/lanagarmire/DeepProgöůöüö}ö(hhhh▀ubah}ö(h]öh]öh ]öh ]öh!]öîrefuriöhßuh%hŢhhďubhî.öůöüö}ö(hî.öhhďhhh&Nh(Nubeh}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K!hh├hhubeh}ö(h]öîaccessöah]öh ]öîaccessöah ]öh!]öuh%h)hh+hhh&h'h(K ubh*)üö}ö(hhh]ö(h/)üö}ö(hî Contributeöh]öhî Contributeöůöüö}ö(hj hj hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hj hhh&h'h(K$ubh î bullet_listöôö)üö}ö(hhh]ö(h î list_itemöôö)üö}ö(hî5Issue Tracker: github.com/lanagarmire/DeepProg/issuesöh]öhů)üö}ö(hj h]öhî5Issue Tracker: github.com/lanagarmire/DeepProg/issuesöůöüö}ö(hj hj ubah}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K&hj ubah}ö(h]öh]öh ]öh ]öh!]öuh%j hj hhh&h'h(Nubj )üö}ö(hî-Source Code: github.com/lanagarmire/DeepProg öh]öhů)üö}ö(hî,Source Code: github.com/lanagarmire/DeepProgöh]öhî,Source Code: github.com/lanagarmire/DeepProgöůöüö}ö(hj6 hj4 ubah}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K'hj0 ubah}ö(h]öh]öh ]öh ]öh!]öuh%j hj hhh&h'h(Nubeh}ö(h]öh]öh ]öh ]öh!]öîbulletöî-öuh%j h&h'h(K&hj hhubeh}ö(h]öî contributeöah]öh ]öî contributeöah ]öh!]öuh%h)hh+hhh&h'h(K$ubh*)üö}ö(hhh]ö(h/)üö}ö(hîSupportöh]öhîSupportöůöüö}ö(hj] hj[ hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hjX hhh&h'h(K*ubhů)üö}ö(hîaIf you are having issues, please let us know. You can reach us using the following email address:öh]öhîaIf you are having issues, please let us know. You can reach us using the following email address:öůöüö}ö(hjk hji hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K,hjX hhubhů)üö}ö(hî*Olivier Poirion, Ph.D. o.poirion@gmail.comöh]ö(hîOlivier Poirion, Ph.D. öůöüö}ö(hîOlivier Poirion, Ph.D. öhjw hhh&Nh(NubhŮ)üö}ö(hîo.poirion@gmail.comöh]öhîo.poirion@gmail.comöůöüö}ö(hhhjÇ ubah}ö(h]öh]öh ]öh ]öh!]öîrefuriöîmailto:o.poirion@gmail.comöuh%hŢhjw ubeh}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K/hjX hhubeh}ö(h]öîsupportöah]öh ]öîsupportöah ]öh!]öuh%h)hh+hhh&h'h(K*ubh*)üö}ö(hhh]ö(h/)üö}ö(hîCitationöh]öhîCitationöůöüö}ö(hjú hjí hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hj× hhh&h'h(K3ubhů)üö}ö(hîĐThis package refers to our preprint paper: [Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models](https://www.medrxiv.org/content/10.1101/19010082v1)öh]ö(hî×This package refers to our preprint paper: [Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models](öůöüö}ö(hî×This package refers to our preprint paper: [Multi-omics-based pan-cancer prognosis prediction using an ensemble of deep-learning and machine-learning models](öhj» hhh&Nh(NubhŮ)üö}ö(hî2https://www.medrxiv.org/content/10.1101/19010082v1öh]öhî2https://www.medrxiv.org/content/10.1101/19010082v1öůöüö}ö(hhhjŞ ubah}ö(h]öh]öh ]öh ]öh!]öîrefuriöj║ uh%hŢhj» ubhî)öůöüö}ö(hî)öhj» hhh&Nh(Nubeh}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K5hj× hhubeh}ö(h]öîcitationöah]öh ]öîcitationöah ]öh!]öuh%h)hh+hhh&h'h(K3ubh*)üö}ö(hhh]ö(h/)üö}ö(hîLicenseöh]öhîLicenseöůöüö}ö(hj▀ hjŢ hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%h.hj┌ hhh&h'h(K8ubhů)üö}ö(hî.The project is licensed under the MIT license.öh]öhî.The project is licensed under the MIT license.öůöüö}ö(hjÝ hjŰ hhh&Nh(Nubah}ö(h]öh]öh ]öh ]öh!]öuh%häh&h'h(K:hj┌ hhubeh}ö(h]öîlicenseöah]öh ]öîlicenseöah ]öh!]öuh%h)hh+hhh&h'h(K8ubeh}ö(h]öî#welcome-to-deepprog-s-documentationöah]öh ]öî$welcome to deepprog's documentation!öah ]öh!]öuh%h)hhhhh&h'h(Kubeh}ö(h]öh]öh ]öh ]öh!]öîsourceöh'uh%hîcurrent_sourceöNî current_lineöNîsettingsöîdocutils.frontendöîValuesöôö)üö}ö(h.Nî generatoröNî datestampöNî source_linköNî source_urlöNî toc_backlinksöîentryöîfootnote_backlinksöKî sectnum_xformöKîstrip_commentsöNîstrip_elements_with_classesöNî strip_classesöNî report_levelöKî halt_levelöKîexit_status_levelöKîdebugöNîwarning_streamöNî tracebacköłîinput_encodingöî utf-8-sigöî input_encoding_error_handleröîstrictöîoutput_encodingöîutf-8öî output_encoding_error_handleröj, îerror_encodingöîutf-8öî error_encoding_error_handleröîbackslashreplaceöî language_codeöîenöîrecord_dependenciesöNîconfigöNî id_prefixöhîauto_id_prefixöîidöî dump_settingsöNîdump_internalsöNîdump_transformsöNîdump_pseudo_xmlöNîexpose_internalsöNîstrict_visitoröNî_disable_configöNî_sourceöh'î _destinationöNî _config_filesö]öîpep_referencesöNî pep_base_urlöî https://www.python.org/dev/peps/öîpep_file_url_templateöîpep-%04döîrfc_referencesöNî rfc_base_urlöî https://tools.ietf.org/html/öî tab_widthöKî trim_footnote_reference_spaceöëîfile_insertion_enabledöłî raw_enabledöKîsyntax_highlightöîlongöî smart_quotesöłîsmartquotes_localesö]öî character_level_inline_markupöëîdoctitle_xformöëî docinfo_xformöKîsectsubtitle_xformöëîembed_stylesheetöëîcloak_email_addressesöłîenvöNubîreporteröNîindirect_targetsö]öîsubstitution_defsö}öîsubstitution_namesö}öîrefnamesö}öîrefidsö}öînameidsö}ö(j j h└hŻh■hűjU jR jŤ jś jÎ jď j■ jű uî nametypesö}ö(j Nh└Nh■NjU NjŤ NjÎ Nj■ Nuh}ö(j h+hŻhshűh├jR j jś jX jď j× jű j┌ uî footnote_refsö}öî citation_refsö}öî autofootnotesö]öîautofootnote_refsö]öîsymbol_footnotesö]öîsymbol_footnote_refsö]öî footnotesö]öî citationsö]öîautofootnote_startöKîsymbol_footnote_startöK î id_counteröî collectionsöîCounteröôö}öůöRöîparse_messagesö]öîtransform_messagesö]öî transformeröNî decorationöNhhub.