1 Project qiita @ DbSchema Layout qiita Hint: Schema comments available as mouse-over tooltips. Group_analyses Group_users Group_study Group_vocabularies Group_ontology Group_logging Group_filepaths Foreign Key fk_controlled_vocab_values controlled_vocab_values references controlled_vocab ( controlled_vocab_id ) controlled_vocab_id Foreign Key fk_investigation_study_person investigation references study_person ( contact_person_id -> study_person_id ) contact_person_id Foreign Key fk_investigation_study investigation_study references investigation ( investigation_id ) investigation_id Foreign Key fk_investigation_study_study investigation_study references study ( study_id ) study_id Foreign Key fk_study_experimental_factor study_experimental_factor references study ( study_id ) study_id Foreign Key fk_study_pmid_study study_pmid references study ( study_id ) study_id Foreign Key fk_job_results_filepath job_results_filepath references job ( job_id ) job_id Foreign Key fk_job_results_filepath_0 job_results_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_analysis_job_analysis analysis_job references analysis ( analysis_id ) analysis_id Foreign Key fk_analysis_job_job analysis_job references job ( job_id ) job_id Foreign Key fk_analysis_chain analysis_chain references analysis ( parent_id -> analysis_id ) parent_id Foreign Key fk_analysis_chain_0 analysis_chain references analysis ( child_id -> analysis_id ) child_id Foreign Key fk_column_controlled_vocabularies column_controlled_vocabularies references mixs_field_description ( column_name ) column_name Foreign Key fk_column_controlled_vocab2 column_controlled_vocabularies references controlled_vocab ( controlled_vocab_id ) controlled_vocab_id Foreign Key fk_analysis_users_analysis analysis_users references analysis ( analysis_id ) analysis_id Foreign Key fk_analysis_users_user analysis_users references qiita_user ( email ) email Foreign Key fk_study_preprocessed_data_0 study_preprocessed_data references preprocessed_data ( preprocessed_data_id ) preprocessed_data_id Foreign Key fk_study_users_study study_users references study ( study_id ) study_id Foreign Key fk_study_users_user study_users references qiita_user ( email ) email Foreign Key fk_study_mapping_columns_study study_sample_columns references study ( study_id ) study_id Foreign Key fk_study_raw_data_study study_raw_data references study ( study_id ) study_id Foreign Key fk_study_raw_data_raw_data study_raw_data references raw_data ( raw_data_id ) raw_data_id Foreign Key fk_processed_data_filepath processed_filepath references processed_data ( processed_data_id ) processed_data_id Foreign Key fk_processed_data_filepath_0 processed_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_logging_severity logging references severity ( severity_id ) severity_id Foreign Key fk_study_processed_data_0 study_processed_data references processed_data ( processed_data_id ) processed_data_id Foreign Key fk_command_data_type command_data_type references command ( command_id ) command_id Foreign Key fk_command_data_type_0 command_data_type references data_type ( data_type_id ) data_type_id Foreign Key fk_preprocessed_filepath preprocessed_filepath references preprocessed_data ( preprocessed_data_id ) preprocessed_data_id Foreign Key fk_preprocessed_filepath_0 preprocessed_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_analysis_filepath analysis_filepath references analysis ( analysis_id ) analysis_id Foreign Key fk_analysis_filepath_0 analysis_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_analysis_filepath_1 analysis_filepath references data_type ( data_type_id ) data_type_id Foreign Key fk_analysis_workflow analysis_workflow references analysis ( analysis_id ) analysis_id Foreign Key fk_column_ontology column_ontology references mixs_field_description ( column_name ) column_name Foreign Key fk_analysis_user analysis references qiita_user ( email ) email Foreign Key fk_analysis_analysis_status analysis references analysis_status ( analysis_status_id ) analysis_status_id Foreign Key fk_processed_params_uclust processed_params_uclust references reference ( reference_id ) reference_id Foreign Key fk_processed_params_sortmerna processed_params_sortmerna references reference ( reference_id ) reference_id Foreign Key fk_preprocessed_processed_data preprocessed_processed_data references preprocessed_data ( preprocessed_data_id ) preprocessed_data_id Foreign Key fk_preprocessed_processed_data_0 preprocessed_processed_data references processed_data ( processed_data_id ) processed_data_id Foreign Key fk_study_user study references qiita_user ( email ) email Foreign Key fk_study_study_status study references study_status ( study_status_id ) study_status_id Foreign Key fk_study_study_emp_person study references study_person ( emp_person_id -> study_person_id ) emp_person_id Foreign Key fk_study_study_lab_person study references study_person ( lab_person_id -> study_person_id ) lab_person_id Foreign Key fk_study_study_pi_person study references study_person ( principal_investigator_id -> study_person_id ) principal_investigator_id Foreign Key fk_study_timeseries_type study references timeseries_type ( timeseries_type_id ) timeseries_type_id Foreign Key fk_study study references portal_type ( portal_type_id ) portal_type_id Foreign Key fk_user_user_level qiita_user references user_level ( user_level_id ) user_level_id Foreign Key fk_prep_columns_prep_template prep_columns references prep_template ( prep_template_id ) prep_template_id Foreign Key fk_raw_filepath raw_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_raw_filepath_0 raw_filepath references raw_data ( raw_data_id ) raw_data_id Foreign Key fk_prep_template_data_type prep_template references data_type ( data_type_id ) data_type_id Foreign Key fk_prep_template_raw_data prep_template references raw_data ( raw_data_id ) raw_data_id Foreign Key fk_raw_data_filetype raw_data references filetype ( filetype_id ) filetype_id Foreign Key fk_preprocessed_data preprocessed_data references data_type ( data_type_id ) data_type_id Foreign Key fk_processed_data processed_data references data_type ( data_type_id ) data_type_id Foreign Key fk_job_function job references command ( command_id ) command_id Foreign Key fk_job_job_status_id job references job_status ( job_status_id ) job_status_id Foreign Key fk_job_data_type job references data_type ( data_type_id ) data_type_id Foreign Key fk_job job references logging ( log_id -> logging_id ) log_id Foreign Key fk_filepath filepath references filepath_type ( filepath_type_id ) filepath_type_id Foreign Key fk_filepath_0 filepath references checksum_algorithm ( checksum_algorithm_id ) checksum_algorithm_id Foreign Key fk_filepath_data_directory filepath references data_directory ( data_directory_id ) data_directory_id Foreign Key fk_term_ontology term references ontology ( ontology_id ) ontology_id Foreign Key fk_required_prep_info_emp_status common_prep_info references emp_status ( emp_status_id ) emp_status_id Foreign Key fk_common_prep_info common_prep_info references required_sample_info ( sample_id ) sample_id Foreign Key fk_prep_template common_prep_info references prep_template ( prep_template_id ) prep_template_id Foreign Key fk_analysis_sample_analysis analysis_sample references analysis ( analysis_id ) analysis_id Foreign Key fk_analysis_processed_data analysis_sample references processed_data ( processed_data_id ) processed_data_id Foreign Key fk_analysis_sample analysis_sample references required_sample_info ( sample_id ) sample_id Foreign Key fk_study_environmental_package study_environmental_package references study ( study_id ) study_id Foreign Key fk_study_environmental_package_0 study_environmental_package references environmental_package ( environmental_package_name ) environmental_package_name Foreign Key fk_filepath_id prep_template_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_prep_template_id prep_template_filepath references prep_template ( prep_template_id ) prep_template_id Foreign Key fk_required_sample_info required_sample_info references required_sample_info_status ( required_sample_info_status_id ) required_sample_info_status_id Foreign Key fk_required_sample_info_study required_sample_info references study ( study_id ) study_id Foreign Key fk_study_id sample_template_filepath references study ( study_id ) study_id Foreign Key fk_filepath_id sample_template_filepath references filepath ( filepath_id ) filepath_id Foreign Key fk_prep_template_id prep_template_preprocessed_data references prep_template ( prep_template_id ) prep_template_id Foreign Key fk_prep_template_preprocessed_data prep_template_preprocessed_data references preprocessed_data ( preprocessed_data_id ) preprocessed_data_id controlled_vocab_valuesTable qiita.controlled_vocab_values Primary Key ( vocab_value_id ) vocab_value_idvocab_value_id bigserial not null Index ( controlled_vocab_id ) controlled_vocab_idcontrolled_vocab_id bigint not null References controlled_vocab ( controlled_vocab_id ) termterm varchar not null order_byorder_by varchar not null default_itemdefault_item varchar investigationTable qiita.investigation Overarching investigation information.An investigation comprises one or more individual studies. Primary Key ( investigation_id ) investigation_idinvestigation_id bigserial not null Referred by investigation_study ( investigation_id ) namename varchar not null descriptiondescription varchar not null Describes the overarching goal of the investigation Index ( contact_person_id ) contact_person_idcontact_person_id bigint References study_person ( contact_person_id -> study_person_id ) investigation_studyTable qiita.investigation_study Primary Key ( investigation_id, study_id ) Index ( investigation_id ) investigation_idinvestigation_id bigint not null References investigation ( investigation_id ) Primary Key ( investigation_id, study_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) study_experimental_factorTable qiita.study_experimental_factor EFO ontological link of experimental factors to studies Primary Key ( study_id, efo_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, efo_id ) efo_idefo_id bigint not null study_pmidTable qiita.study_pmid Links a study to all PMIDs for papers created from study Primary Key ( study_id, pmid ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, pmid ) pmidpmid varchar not null job_results_filepathTable qiita.job_results_filepath Holds connection between jobs and the result filepaths Primary Key ( job_id, filepath_id ) Index ( job_id ) job_idjob_id bigint not null References job ( job_id ) Primary Key ( job_id, filepath_id ) Index ( filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) analysis_jobTable qiita.analysis_job Holds information for a one-to-many relation of analysis to the jobs in it Primary Key ( analysis_id, job_id ) Index ( analysis_id ) analysis_idanalysis_id bigint not null Id of the analysis References analysis ( analysis_id ) Primary Key ( analysis_id, job_id ) Index ( job_id ) job_idjob_id bigint not null Id for a job that is part of the analysis References job ( job_id ) analysis_chainTable qiita.analysis_chain Keeps track of the chain of analysis edits. Tracks what previous analysis a given analysis came from.If a given analysis is not in child_id, it is the root of the chain. Index ( parent_id ) Primary Key ( parent_id, child_id ) parent_idparent_id bigint not null References analysis ( parent_id -> analysis_id ) Index ( child_id ) Primary Key ( parent_id, child_id ) child_idchild_id bigint not null References analysis ( child_id -> analysis_id ) column_controlled_vocabulariesTable qiita.column_controlled_vocabularies Table relates a column with a controlled vocabulary. Primary Key ( controlled_vocab_id, column_name ) Index ( controlled_vocab_id ) controlled_vocab_idcontrolled_vocab_id bigserial not null References controlled_vocab ( controlled_vocab_id ) Primary Key ( controlled_vocab_id, column_name ) Index ( column_name ) column_namecolumn_name varchar not null References mixs_field_description ( column_name ) mixs_field_descriptionTable qiita.mixs_field_description Primary Key ( column_name ) column_namecolumn_name varchar not null Referred by column_controlled_vocabularies ( column_name ) Referred by column_ontology ( column_name ) data_typedata_type varchar not null desc_or_valuedesc_or_value varchar not null definitiondefinition varchar not null min_lengthmin_length integer activeactive integer not null analysis_usersTable qiita.analysis_users Links analyses to the users they are shared with Primary Key ( analysis_id, email ) Index ( analysis_id ) analysis_idanalysis_id bigint not null References analysis ( analysis_id ) Primary Key ( analysis_id, email ) Index ( email ) emailemail varchar not null References qiita_user ( email ) study_preprocessed_dataTable qiita.study_preprocessed_data Primary Key ( study_id, preprocessed_data_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, preprocessed_data_id ) Index ( preprocessed_data_id ) preprocessed_data_idpreprocessed_data_id bigint not null References preprocessed_data ( preprocessed_data_id ) study_usersTable qiita.study_users Links shared studies to users they are shared with Primary Key ( study_id, email ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, email ) Index ( email ) emailemail varchar not null References qiita_user ( email ) sample_xTable qiita.sample_x data for samples in study x (sample template)x is the study_id from study tableMAKE SURE sample_id IS FK TO sample_id IN required_sample_info TABLE Primary Key ( sample_id ) sample_idsample_id varchar not null descriptiondescription varchar not null other_mapping_columnsother_mapping_columns varchar Represents whatever other columns go with this study study_sample_columnsTable qiita.study_sample_columns Holds information on which metadata columns are available for the study sample template Primary Key ( study_id, column_name, column_type ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, column_name, column_type ) column_namecolumn_name varchar(100) not null Primary Key ( study_id, column_name, column_type ) column_typecolumn_type varchar not null study_raw_dataTable qiita.study_raw_data links study to its raw data Index ( study_id ) Primary Key ( study_id, raw_data_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, raw_data_id ) raw_data_idraw_data_id bigint not null References raw_data ( raw_data_id ) portal_typeTable qiita.portal_type What portals are available to show a study in Primary Key ( portal_type_id ) portal_type_idportal_type_id bigserial not null Referred by study ( portal_type_id ) portalportal varchar not null descriptiondescription varchar not null processed_filepathTable qiita.processed_filepath Primary Key ( processed_data_id, filepath_id ) processed_data_idprocessed_data_id bigint not null References processed_data ( processed_data_id ) Primary Key ( processed_data_id, filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) commandTable qiita.command Available commands for jobs Primary Key ( command_id ) command_idcommand_id bigserial not null Unique identifier for function Referred by command_data_type ( command_id ) Referred by job ( command_id ) namename varchar not null commandcommand varchar not null What command to call to run this function inputinput varchar not null JSON of input options for the command requiredrequired varchar not null JSON of required options for the command optionaloptional varchar not null JSON of optional options for command outputoutput varchar not null JSON of output options for the command loggingTable qiita.logging Primary Key ( logging_id ) logging_idlogging_id bigserial not null Referred by job ( log_id -> logging_id ) timetime timestamp not null Time the error was thrown Index ( severity_id ) severity_idseverity_id integer not null References severity ( severity_id ) msgmsg varchar not null Error message thrown informationinformation varchar Other applicable information (depending on error) study_processed_dataTable qiita.study_processed_data Primary Key ( study_id, processed_data_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, processed_data_id ) Unique Index ( processed_data_id ) processed_data_idprocessed_data_id bigint not null References processed_data ( processed_data_id ) command_data_typeTable qiita.command_data_type Primary Key ( command_id, data_type_id ) Index ( command_id ) command_idcommand_id bigint not null References command ( command_id ) Primary Key ( command_id, data_type_id ) Index ( data_type_id ) data_type_iddata_type_id bigint not null References data_type ( data_type_id ) preprocessed_filepathTable qiita.preprocessed_filepath Primary Key ( preprocessed_data_id, filepath_id ) Index ( preprocessed_data_id ) preprocessed_data_idpreprocessed_data_id bigint not null References preprocessed_data ( preprocessed_data_id ) Primary Key ( preprocessed_data_id, filepath_id ) Index ( filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) analysis_filepathTable qiita.analysis_filepath Stores link between analysis and the data file used for the analysis. Index ( analysis_id ) Primary Key ( analysis_id, filepath_id ) analysis_idanalysis_id bigint not null References analysis ( analysis_id ) Index ( filepath_id ) Primary Key ( analysis_id, filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) Index ( data_type_id ) data_type_iddata_type_id bigint References data_type ( data_type_id ) analysis_workflowTable qiita.analysis_workflow Stores what step in_production analyses are on. Primary Key ( analysis_id ) analysis_idanalysis_id bigint not null References analysis ( analysis_id ) stepstep integer not null column_ontologyTable qiita.column_ontology This table relates a column with an ontology. Primary Key ( column_name, ontology_short_name ) Index ( column_name ) column_namecolumn_name varchar not null References mixs_field_description ( column_name ) Primary Key ( column_name, ontology_short_name ) ontology_short_nameontology_short_name varchar not null bioportal_idbioportal_id integer not null ontology_branch_idontology_branch_id varchar study_personTable qiita.study_person Contact information for the various people involved in a study Primary Key ( study_person_id ) study_person_idstudy_person_id bigserial not null Referred by investigation ( contact_person_id -> study_person_id ) Referred by study ( emp_person_id -> study_person_id ) Referred by study ( lab_person_id -> study_person_id ) Referred by study ( principal_investigator_id -> study_person_id ) Unique Index ( name, affiliation ) namename varchar not null emailemail varchar not null Unique Index ( name, affiliation ) affiliationaffiliation varchar not null The institution with which this person is affiliated addressaddress varchar(100) phonephone varchar analysisTable qiita.analysis hHolds analysis information Primary Key ( analysis_id ) analysis_idanalysis_id bigserial not null Unique identifier for analysis Referred by analysis_chain ( parent_id -> analysis_id ) Referred by analysis_chain ( child_id -> analysis_id ) Referred by analysis_filepath ( analysis_id ) Referred by analysis_job ( analysis_id ) Referred by analysis_sample ( analysis_id ) Referred by analysis_users ( analysis_id ) Referred by analysis_workflow ( analysis_id ) Index ( email ) emailemail varchar not null Email for user who owns the analysis References qiita_user ( email ) namename varchar not null Name of the analysis descriptiondescription varchar not null Index ( analysis_status_id ) analysis_status_idanalysis_status_id bigint not null References analysis_status ( analysis_status_id ) pmidpmid varchar PMID of paper from the analysis timestamptimestamp timestamptz default current_timestamp controlled_vocabTable qiita.controlled_vocab Primary Key ( controlled_vocab_id ) controlled_vocab_idcontrolled_vocab_id bigserial not null Referred by column_controlled_vocabularies ( controlled_vocab_id ) Referred by controlled_vocab_values ( controlled_vocab_id ) controlled_vocabcontrolled_vocab varchar not null ontologyTable qiita.ontology Primary Key ( ontology_id ) ontology_idontology_id bigint not null Referred by term ( ontology_id ) Unique Index ( ontology ) ontologyontology varchar not null fully_loadedfully_loaded bool not null fullnamefullname varchar query_urlquery_url varchar source_urlsource_url varchar definitiondefinition text load_dateload_date date not null preprocessed_sequence_454_paramsTable qiita.preprocessed_sequence_454_params Parameters used for processing sequence data. Primary Key ( preprocessed_params_id ) preprocessed_params_idpreprocessed_params_id bigserial not null trim_lengthtrim_length integer not null preprocessed_spectra_paramsTable qiita.preprocessed_spectra_params Parameters used for processing spectra data. Primary Key ( preprocessed_params_id ) preprocessed_params_idpreprocessed_params_id bigserial not null colcol varchar referenceTable qiita.reference Primary Key ( reference_id ) reference_idreference_id bigserial not null Referred by processed_params_sortmerna ( reference_id ) Referred by processed_params_uclust ( reference_id ) reference_namereference_name varchar not null reference_versionreference_version varchar Index ( sequence_filepath ) sequence_filepathsequence_filepath bigint not null References filepath ( sequence_filepath -> filepath_id ) Index ( taxonomy_filepath ) taxonomy_filepathtaxonomy_filepath bigint References filepath ( taxonomy_filepath -> filepath_id ) Index ( tree_filepath ) tree_filepathtree_filepath bigint References filepath ( tree_filepath -> filepath_id ) processed_params_uclustTable qiita.processed_params_uclust Parameters used for processing data using method uclust Primary Key ( processed_params_id ) processed_params_idprocessed_params_id bigserial not null Index ( reference_id ) reference_idreference_id bigint not null What version of reference or type of reference used References reference ( reference_id ) similaritysimilarity float8 not null default 0.97 enable_rev_strand_matchenable_rev_strand_match bool not null default TRUE suppress_new_clusterssuppress_new_clusters bool not null default TRUE processed_params_sortmernaTable qiita.processed_params_sortmerna Parameters used for processing data using method sortmerna Primary Key ( processed_params_id ) processed_params_idprocessed_params_id bigserial not null Index ( reference_id ) reference_idreference_id bigint not null What version of reference or type of reference used References reference ( reference_id ) evalueevalue float8 not null max_posmax_pos integer not null similaritysimilarity float8 not null coveragecoverage float8 not null threadsthreads integer not null preprocessed_sequence_illumina_paramsTable qiita.preprocessed_sequence_illumina_params Parameters used for processing illumina sequence data. Primary Key ( preprocessed_params_id ) preprocessed_params_idpreprocessed_params_id bigserial not null max_bad_run_lengthmax_bad_run_length integer not null default 3 min_per_read_length_fractionmin_per_read_length_fraction real not null default 0.75 sequence_max_nsequence_max_n integer not null default 0 rev_comp_barcoderev_comp_barcode bool not null default FALSE rev_comp_mapping_barcodesrev_comp_mapping_barcodes bool not null default FALSE rev_comprev_comp bool not null default FALSE phred_quality_thresholdphred_quality_threshold integer not null default 3 barcode_typebarcode_type varchar not null default 'golay_12' max_barcode_errorsmax_barcode_errors real not null default 1.5 preprocessed_processed_dataTable qiita.preprocessed_processed_data Primary Key ( preprocessed_data_id, processed_data_id ) Index ( preprocessed_data_id ) preprocessed_data_idpreprocessed_data_id bigint not null References preprocessed_data ( preprocessed_data_id ) Primary Key ( preprocessed_data_id, processed_data_id ) Index ( processed_data_id ) processed_data_idprocessed_data_id bigint not null References processed_data ( processed_data_id ) studyTable qiita.study Primary Key ( study_id ) study_idstudy_id bigserial not null Unique name for study Referred by investigation_study ( study_id ) Referred by required_sample_info ( study_id ) Referred by study_environmental_package ( study_id ) Referred by study_experimental_factor ( study_id ) Referred by study_pmid ( study_id ) Referred by study_preprocessed_data ( study_id ) Referred by study_processed_data ( study_id ) Referred by study_raw_data ( study_id ) Referred by study_sample_columns ( study_id ) Referred by study_users ( study_id ) Referred by sample_template_filepath ( study_id ) Referred by sample_template_filepath ( study_id ) Referred by sample_template_filepath ( study_id ) Index ( email ) emailemail varchar not null Email of study owner References qiita_user ( email ) Index ( study_status_id ) study_status_idstudy_status_id bigint not null References study_status ( study_status_id ) Index ( emp_person_id ) emp_person_idemp_person_id bigint References study_person ( emp_person_id -> study_person_id ) first_contactfirst_contact timestamp not null default current_timestamp fundingfunding varchar Index ( timeseries_type_id ) timeseries_type_idtimeseries_type_id bigint not null What type of timeseries this study is (or is not) Controlled Vocabulary References timeseries_type ( timeseries_type_id ) Index ( lab_person_id ) lab_person_idlab_person_id bigint References study_person ( lab_person_id -> study_person_id ) metadata_completemetadata_complete bool not null mixs_compliantmixs_compliant bool not null most_recent_contactmost_recent_contact timestamp number_samples_collectednumber_samples_collected integer number_samples_promisednumber_samples_promised integer Index ( portal_type_id ) portal_type_idportal_type_id bigint not null References portal_type ( portal_type_id ) Index ( principal_investigator_id ) principal_investigator_idprincipal_investigator_id bigint not null References study_person ( principal_investigator_id -> study_person_id ) reprocessreprocess bool not null spatial_seriesspatial_series bool Unique Index ( study_title ) study_titlestudy_title varchar not null study_aliasstudy_alias varchar not null study_descriptionstudy_description text not null study_abstractstudy_abstract text not null vamps_idvamps_id varchar qiita_userTable qiita.qiita_user Holds all user information Primary Key ( email ) emailemail varchar not null Referred by analysis ( email ) Referred by analysis_users ( email ) Referred by study ( email ) Referred by study_users ( email ) Index ( user_level_id ) user_level_iduser_level_id integer not null default 5 user level References user_level ( user_level_id ) passwordpassword varchar not null namename varchar affiliationaffiliation varchar addressaddress varchar phonephone varchar user_verify_codeuser_verify_code varchar Code for initial user email verification pass_reset_codepass_reset_code varchar Randomly generated code for password reset pass_reset_timestamppass_reset_timestamp timestamp Time the reset code was generated prep_yTable qiita.prep_y Information on how raw data y was prepared (prep template)Linked by y being raw_data_id from raw data table. Primary Key ( sample_id ) sample_idsample_id varchar not null datadata bigint STUFFFFF prep_columnsTable qiita.prep_columns Primary Key ( prep_template_id, column_name, column_type ) Index ( prep_template_id ) prep_template_idprep_template_id bigint not null References prep_template ( prep_template_id ) Primary Key ( prep_template_id, column_name, column_type ) column_namecolumn_name varchar not null Primary Key ( prep_template_id, column_name, column_type ) column_typecolumn_type varchar not null raw_filepathTable qiita.raw_filepath Primary Key ( raw_data_id, filepath_id ) Index ( raw_data_id ) raw_data_idraw_data_id bigint not null References raw_data ( raw_data_id ) Primary Key ( raw_data_id, filepath_id ) Index ( filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) emp_statusTable qiita.emp_status All possible statuses for projects relating to EMP. Whether they are part of, processed in accordance to, or not part of EMP. Primary Key ( emp_status_id ) emp_status_idemp_status_id bigserial not null Referred by common_prep_info ( emp_status_id ) Unique Index ( emp_status ) emp_statusemp_status varchar not null required_sample_info_statusTable qiita.required_sample_info_status Primary Key ( required_sample_info_status_id ) required_sample_info_status_idrequired_sample_info_status_id bigserial not null Referred by required_sample_info ( required_sample_info_status_id ) Unique Index ( status ) statusstatus varchar study_statusTable qiita.study_status Primary Key ( study_status_id ) study_status_idstudy_status_id bigserial not null Referred by study ( study_status_id ) Unique Index ( status ) statusstatus varchar not null descriptiondescription varchar not null filetypeTable qiita.filetype Type of file (FASTA, FASTQ, SPECTRA, etc) Primary Key ( filetype_id ) filetype_idfiletype_id bigserial not null Referred by raw_data ( filetype_id ) Unique Index ( type ) typetype varchar not null filepath_typeTable qiita.filepath_type Primary Key ( filepath_type_id ) filepath_type_idfilepath_type_id bigserial not null Referred by filepath ( filepath_type_id ) Unique Index ( filepath_type ) filepath_typefilepath_type varchar checksum_algorithmTable qiita.checksum_algorithm Primary Key ( checksum_algorithm_id ) checksum_algorithm_idchecksum_algorithm_id bigserial not null Referred by filepath ( checksum_algorithm_id ) Unique Index ( name ) namename varchar not null data_typeTable qiita.data_type Primary Key ( data_type_id ) data_type_iddata_type_id bigserial not null Referred by analysis_filepath ( data_type_id ) Referred by command_data_type ( data_type_id ) Referred by job ( data_type_id ) Referred by prep_template ( data_type_id ) Referred by preprocessed_data ( data_type_id ) Referred by processed_data ( data_type_id ) Unique Index ( data_type ) data_typedata_type varchar not null Data type (16S, metabolome, etc) the job will use user_levelTable qiita.user_level Holds available user levels Primary Key ( user_level_id ) user_level_iduser_level_id serial not null Referred by qiita_user ( user_level_id ) Unique Index ( name ) namename varchar not null One of the user levels (admin, user, guest, etc) descriptiondescription text not null analysis_statusTable qiita.analysis_status Primary Key ( analysis_status_id ) analysis_status_idanalysis_status_id bigserial not null Referred by analysis ( analysis_status_id ) Unique Index ( status ) statusstatus varchar not null job_statusTable qiita.job_status Primary Key ( job_status_id ) job_status_idjob_status_id bigserial not null Referred by job ( job_status_id ) Unique Index ( status ) statusstatus varchar not null severityTable qiita.severity Primary Key ( severity_id ) severity_idseverity_id serial not null Referred by logging ( severity_id ) Unique Index ( severity ) severityseverity varchar not null prep_templateTable qiita.prep_template Primary Key ( prep_template_id ) prep_template_idprep_template_id bigserial not null Referred by common_prep_info ( prep_template_id ) Referred by prep_columns ( prep_template_id ) Referred by prep_template_preprocessed_data ( prep_template_id ) Referred by prep_template_filepath ( prep_template_id ) Referred by prep_template_filepath ( prep_template_id ) Index ( data_type_id ) data_type_iddata_type_id bigint not null References data_type ( data_type_id ) Index ( raw_data_id ) raw_data_idraw_data_id bigint not null References raw_data ( raw_data_id ) preprocessing_statuspreprocessing_status varchar not null default 'not_preprocessed' investigation_typeinvestigation_type varchar The investigation type (e.g., one of the values from EBI's set of known types) raw_dataTable qiita.raw_data Unique Index ( raw_data_id ) Primary Key ( raw_data_id ) raw_data_idraw_data_id bigserial not null Referred by prep_template ( raw_data_id ) Referred by raw_filepath ( raw_data_id ) Referred by study_raw_data ( raw_data_id ) Index ( filetype_id ) filetype_idfiletype_id bigint not null References filetype ( filetype_id ) link_filepaths_statuslink_filepaths_status varchar not null default 'idle' preprocessed_dataTable qiita.preprocessed_data Primary Key ( preprocessed_data_id ) preprocessed_data_idpreprocessed_data_id bigserial not null Referred by prep_template_preprocessed_data ( preprocessed_data_id ) Referred by preprocessed_filepath ( preprocessed_data_id ) Referred by preprocessed_processed_data ( preprocessed_data_id ) Referred by study_preprocessed_data ( preprocessed_data_id ) preprocessed_params_tablepreprocessed_params_table varchar not null Name of table holding the params preprocessed_params_idpreprocessed_params_id bigint not null submitted_to_insdc_statussubmitted_to_insdc_status varchar not null default 'not submitted' ebi_submission_accessionebi_submission_accession varchar ebi_study_accessionebi_study_accession varchar Index ( data_type_id ) data_type_iddata_type_id bigint not null References data_type ( data_type_id ) link_filepaths_statuslink_filepaths_status varchar not null default 'idle' processed_dataTable qiita.processed_data Primary Key ( processed_data_id ) processed_data_idprocessed_data_id bigserial not null Referred by analysis_sample ( processed_data_id ) Referred by preprocessed_processed_data ( processed_data_id ) Referred by processed_filepath ( processed_data_id ) Referred by study_processed_data ( processed_data_id ) processed_params_tableprocessed_params_table varchar not null Name of table holding processing params processed_params_idprocessed_params_id bigint not null Link to a table with the parameters used to generate processed data processed_dateprocessed_date timestamp not null Index ( data_type_id ) data_type_iddata_type_id bigint not null References data_type ( data_type_id ) link_filepaths_statuslink_filepaths_status varchar not null default 'idle' jobTable qiita.job Primary Key ( job_id ) job_idjob_id bigserial not null Unique identifier for job Referred by analysis_job ( job_id ) Referred by job_results_filepath ( job_id ) Index ( data_type_id ) data_type_iddata_type_id bigint not null What datatype (16s, metabolome, etc) job is run on. References data_type ( data_type_id ) Index ( job_status_id ) job_status_idjob_status_id bigint not null References job_status ( job_status_id ) Index ( command_id ) command_idcommand_id bigint not null The Qiime or other function being run (alpha diversity, etc) References command ( command_id ) optionsoptions varchar Holds all options set for the job as a json string Index ( log_id ) log_idlog_id bigint Reference to error if status is error References logging ( log_id -> logging_id ) filepathTable qiita.filepath Primary Key ( filepath_id ) filepath_idfilepath_id bigserial not null Referred by analysis_filepath ( filepath_id ) Referred by job_results_filepath ( filepath_id ) Referred by preprocessed_filepath ( filepath_id ) Referred by processed_filepath ( filepath_id ) Referred by raw_filepath ( filepath_id ) Referred by reference ( sequence_filepath -> filepath_id ) Referred by reference ( taxonomy_filepath -> filepath_id ) Referred by reference ( tree_filepath -> filepath_id ) Referred by prep_template_filepath ( filepath_id ) Referred by prep_template_filepath ( filepath_id ) Referred by prep_template_filepath ( filepath_id ) Referred by sample_template_filepath ( filepath_id ) Referred by sample_template_filepath ( filepath_id ) filepathfilepath varchar not null Index ( filepath_type_id ) filepath_type_idfilepath_type_id bigint not null References filepath_type ( filepath_type_id ) checksumchecksum varchar not null checksum_algorithm_idchecksum_algorithm_id bigint not null References checksum_algorithm ( checksum_algorithm_id ) Index ( data_directory_id ) data_directory_iddata_directory_id bigserial References data_directory ( data_directory_id ) data_directoryTable qiita.data_directory Primary Key ( data_directory_id ) data_directory_iddata_directory_id bigserial not null Referred by filepath ( data_directory_id ) data_typedata_type varchar not null mountpointmountpoint varchar not null subdirectorysubdirectory varchar not null activeactive bool not null termTable qiita.term Primary Key ( term_id ) term_idterm_id bigserial not null Index ( ontology_id ) ontology_idontology_id bigint not null References ontology ( ontology_id ) old_term_idold_term_id bigint default NULL Identifier used in the old system, we are keeping this for consistency termterm varchar not null identifieridentifier varchar definitiondefinition varchar namespacenamespace varchar is_obsoleteis_obsolete bool default 'false' is_root_termis_root_term bool is_leafis_leaf bool user_defineduser_defined bool not null default False Whether or not this term was defined by a user common_prep_infoTable qiita.common_prep_info Primary Key ( prep_template_id, sample_id ) Index ( prep_template_id ) prep_template_idprep_template_id bigint not null The prep template identifier References prep_template ( prep_template_id ) Index ( sample_id ) Index ( sample_id ) Primary Key ( prep_template_id, sample_id ) sample_idsample_id varchar not null References required_sample_info ( sample_id ) center_namecenter_name varchar center_project_namecenter_project_name varchar Index ( emp_status_id ) emp_status_idemp_status_id bigint not null References emp_status ( emp_status_id ) analysis_sampleTable qiita.analysis_sample Index ( analysis_id ) analysis_idanalysis_id bigint not null References analysis ( analysis_id ) Index ( processed_data_id ) processed_data_idprocessed_data_id bigint not null References processed_data ( processed_data_id ) Index ( sample_id ) sample_idsample_id varchar not null References required_sample_info ( sample_id ) environmental_packageTable qiita.environmental_package Primary Key ( environmental_package_name ) environmental_package_nameenvironmental_package_name varchar not null The name of the environmental package Referred by study_environmental_package ( environmental_package_name ) metadata_tablemetadata_table varchar not null Contains the name of the table that contains the pre-defined metadata columns for the environmental package study_environmental_packageTable qiita.study_environmental_package Holds the 1 to many relationship between the study and the environmental_package Primary Key ( study_id, environmental_package_name ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, environmental_package_name ) Index ( environmental_package_name ) environmental_package_nameenvironmental_package_name varchar not null References environmental_package ( environmental_package_name ) timeseries_typeTable qiita.timeseries_type Primary Key ( timeseries_type_id ) timeseries_type_idtimeseries_type_id bigserial not null Referred by study ( timeseries_type_id ) Unique Index ( timeseries_type, intervention_type ) timeseries_typetimeseries_type varchar not null Unique Index ( timeseries_type, intervention_type ) intervention_typeintervention_type varchar not null default 'None' prep_template_filepathTable qiita.prep_template_filepath Primary Key ( prep_template_id, filepath_id ) Index ( prep_template_id ) prep_template_idprep_template_id bigint not null References prep_template ( prep_template_id ) Primary Key ( prep_template_id, filepath_id ) Index ( filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) required_sample_infoTable qiita.required_sample_info Required info for each sample. One row is one sample. Primary Key ( sample_id ) sample_idsample_id varchar not null Referred by analysis_sample ( sample_id ) Referred by common_prep_info ( sample_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) physical_locationphysical_location varchar not null Where the sample itself is stored has_physical_specimenhas_physical_specimen bool not null Whether we have the full speciment or just DNA has_extracted_datahas_extracted_data bool not null sample_typesample_type varchar not null Controlled vocabulary of sample types Index ( required_sample_info_status_id ) required_sample_info_status_idrequired_sample_info_status_id bigint not null What step of the pipeline the samples are in References required_sample_info_status ( required_sample_info_status_id ) collection_timestampcollection_timestamp timestamp not null host_subject_idhost_subject_id varchar not null descriptiondescription varchar not null latitudelatitude float8 not null Latitude of the collection site longitudelongitude float8 not null Longitude of the collection site sample_template_filepathTable qiita.sample_template_filepath Primary Key ( study_id, filepath_id ) Index ( study_id ) study_idstudy_id bigint not null References study ( study_id ) Primary Key ( study_id, filepath_id ) Index ( filepath_id ) filepath_idfilepath_id bigint not null References filepath ( filepath_id ) prep_template_preprocessed_dataTable qiita.prep_template_preprocessed_data Primary Key ( prep_template_id, preprocessed_data_id ) Index ( prep_template_id ) prep_template_idprep_template_id bigint not null References prep_template ( prep_template_id ) Primary Key ( prep_template_id, preprocessed_data_id ) Index ( preprocessed_data_id ) preprocessed_data_idpreprocessed_data_id bigint not null References preprocessed_data ( preprocessed_data_id )

Table controlled_vocab_values
* vocab_value_id bigserial
* controlled_vocab_id bigint
* term varchar
* order_by varchar
  default_item varchar
Indexes
Pkpk_controlled_vocab_values ON vocab_value_id
 idx_controlled_vocab_values ON controlled_vocab_id
Foreign Keys
 fk_controlled_vocab_values ( controlled_vocab_id ) ref controlled_vocab (controlled_vocab_id)


Table investigation
Overarching investigation information.An investigation comprises one or more individual studies.
* investigation_id bigserial
* name varchar
* description varchar Describes the overarching goal of the investigation
  contact_person_id bigint
Indexes
Pkpk_investigation ON investigation_id
 idx_investigation ON contact_person_id
Foreign Keys
 fk_investigation_study_person ( contact_person_id ) ref study_person (study_person_id)


Table investigation_study
* investigation_id bigint
* study_id bigint
Indexes
Pkidx_investigation_study ON investigation_id, study_id
 idx_investigation_study_investigation ON investigation_id
 idx_investigation_study_study ON study_id
Foreign Keys
 fk_investigation_study ( investigation_id ) ref investigation (investigation_id)
 fk_investigation_study_study ( study_id ) ref study (study_id)


Table study_experimental_factor
EFO ontological link of experimental factors to studies
* study_id bigint
* efo_id bigint
Indexes
Pkidx_study_experimental_factor ON study_id, efo_id
 idx_study_experimental_factor_0 ON study_id
Foreign Keys
 fk_study_experimental_factor ( study_id ) ref study (study_id)


Table study_pmid
Links a study to all PMIDs for papers created from study
* study_id bigint
* pmid varchar
Indexes
Pkidx_study_pmid ON study_id, pmid
 idx_study_pmid_0 ON study_id
Foreign Keys
 fk_study_pmid_study ( study_id ) ref study (study_id)


Table job_results_filepath
Holds connection between jobs and the result filepaths
* job_id bigint
* filepath_id bigint
Indexes
Pkidx_job_results_filepath ON job_id, filepath_id
 idx_job_results_filepath_0 ON job_id
 idx_job_results_filepath_1 ON filepath_id
Foreign Keys
 fk_job_results_filepath ( job_id ) ref job (job_id)
 fk_job_results_filepath_0 ( filepath_id ) ref filepath (filepath_id)


Table analysis_job
Holds information for a one-to-many relation of analysis to the jobs in it
* analysis_id bigint Id of the analysis
* job_id bigint Id for a job that is part of the analysis
Indexes
Pkidx_analysis_jobs ON analysis_id, job_id
 idx_analysis_job ON analysis_id
 idx_analysis_job_0 ON job_id
Foreign Keys
 fk_analysis_job_analysis ( analysis_id ) ref analysis (analysis_id)
 fk_analysis_job_job ( job_id ) ref job (job_id)


Table analysis_chain
Keeps track of the chain of analysis edits. Tracks what previous analysis a given analysis came from.If a given analysis is not in child_id, it is the root of the chain.
* parent_id bigint
* child_id bigint
Indexes
 idx_analysis_chain ON parent_id
 idx_analysis_chain_0 ON child_id
Pkidx_analysis_chain_1 ON parent_id, child_id
Foreign Keys
 fk_analysis_chain ( parent_id ) ref analysis (analysis_id)
 fk_analysis_chain_0 ( child_id ) ref analysis (analysis_id)


Table column_controlled_vocabularies
Table relates a column with a controlled vocabulary.
* controlled_vocab_id bigserial
* column_name varchar
Indexes
Pkidx_column_controlled_vocabularies ON controlled_vocab_id, column_name
 idx_column_controlled_vocabularies_0 ON column_name
 idx_column_controlled_vocabularies_1 ON controlled_vocab_id
Foreign Keys
 fk_column_controlled_vocabularies ( column_name ) ref mixs_field_description (column_name)
 fk_column_controlled_vocab2 ( controlled_vocab_id ) ref controlled_vocab (controlled_vocab_id)


Table mixs_field_description
* column_name varchar
* data_type varchar
* desc_or_value varchar
* definition varchar
  min_length integer
* active integer
Indexes
Pkpk_mixs_field_description ON column_name


Table analysis_users
Links analyses to the users they are shared with
* analysis_id bigint
* email varchar
Indexes
Pkidx_analysis_users ON analysis_id, email
 idx_analysis_users_analysis ON analysis_id
 idx_analysis_users_email ON email
Foreign Keys
 fk_analysis_users_analysis ( analysis_id ) ref analysis (analysis_id)
 fk_analysis_users_user ( email ) ref qiita_user (email)


Table study_preprocessed_data
* study_id bigint
* preprocessed_data_id bigint
Indexes
Pkidx_study_preprocessed_data ON study_id, preprocessed_data_id
 idx_study_preprocessed_data_0 ON study_id
 idx_study_preprocessed_data_1 ON preprocessed_data_id
Foreign Keys
 fk_study_preprocessed_data ( study_id ) ref study (study_id)
 fk_study_preprocessed_data_0 ( preprocessed_data_id ) ref preprocessed_data (preprocessed_data_id)


Table study_users
Links shared studies to users they are shared with
* study_id bigint
* email varchar
Indexes
Pkidx_study_users ON study_id, email
 idx_study_users_0 ON study_id
 idx_study_users_1 ON email
Foreign Keys
 fk_study_users_study ( study_id ) ref study (study_id)
 fk_study_users_user ( email ) ref qiita_user (email)


Table sample_x
data for samples in study x (sample template)x is the study_id from study tableMAKE SURE sample_id IS FK TO sample_id IN required_sample_info TABLE
* sample_id varchar
* description varchar
  other_mapping_columns varchar Represents whatever other columns go with this study
Indexes
Pkpk_study_x_y ON sample_id


Table study_sample_columns
Holds information on which metadata columns are available for the study sample template
* study_id bigint
* column_name varchar( 100 )
* column_type varchar
Indexes
Pkidx_study_mapping_columns ON study_id, column_name, column_type
 idx_study_mapping_columns_study_id ON study_id
Foreign Keys
 fk_study_mapping_columns_study ( study_id ) ref study (study_id)


Table study_raw_data
links study to its raw data
* study_id bigint
* raw_data_id bigint
Indexes
 idx_study_raw_data ON study_id
Pkidx_study_raw_data_0 ON study_id, raw_data_id
Foreign Keys
 fk_study_raw_data_study ( study_id ) ref study (study_id)
 fk_study_raw_data_raw_data ( raw_data_id ) ref raw_data (raw_data_id)


Table portal_type
What portals are available to show a study in
* portal_type_id bigserial
* portal varchar
* description varchar
Indexes
Pkpk_portal_type ON portal_type_id


Table processed_filepath
* processed_data_id bigint
* filepath_id bigint
Indexes
Pkidx_processed_filepath ON processed_data_id, filepath_id
Foreign Keys
 fk_processed_data_filepath ( processed_data_id ) ref processed_data (processed_data_id)
 fk_processed_data_filepath_0 ( filepath_id ) ref filepath (filepath_id)


Table command
Available commands for jobs
* command_id bigserial Unique identifier for function
* name varchar
* command varchar What command to call to run this function
* input varchar JSON of input options for the command
* required varchar JSON of required options for the command
* optional varchar JSON of optional options for command
* output varchar JSON of output options for the command
Indexes
Pkpk_command ON command_id


Table logging
* logging_id bigserial
* time timestamp Time the error was thrown
* severity_id integer
* msg varchar Error message thrown
  information varchar Other applicable information (depending on error)
Indexes
 idx_logging_0 ON severity_id
Pkpk_logging ON logging_id
Foreign Keys
 fk_logging_severity ( severity_id ) ref severity (severity_id)


Table study_processed_data
* study_id bigint
* processed_data_id bigint
Indexes
Pkidx_study_processed_data ON study_id, processed_data_id
 idx_study_processed_data_0 ON study_id
Upk_study_processed_data ON processed_data_id
Foreign Keys
 fk_study_processed_data ( study_id ) ref study (study_id)
 fk_study_processed_data_0 ( processed_data_id ) ref processed_data (processed_data_id)


Table command_data_type
* command_id bigint
* data_type_id bigint
Indexes
Pkidx_command_data_type ON command_id, data_type_id
 idx_command_data_type_0 ON command_id
 idx_command_data_type_1 ON data_type_id
Foreign Keys
 fk_command_data_type ( command_id ) ref command (command_id)
 fk_command_data_type_0 ( data_type_id ) ref data_type (data_type_id)


Table preprocessed_filepath
* preprocessed_data_id bigint
* filepath_id bigint
Indexes
Pkidx_preprocessed_filepath ON preprocessed_data_id, filepath_id
 idx_preprocessed_filepath_0 ON preprocessed_data_id
 idx_preprocessed_filepath_1 ON filepath_id
Foreign Keys
 fk_preprocessed_filepath ( preprocessed_data_id ) ref preprocessed_data (preprocessed_data_id)
 fk_preprocessed_filepath_0 ( filepath_id ) ref filepath (filepath_id)


Table analysis_filepath
Stores link between analysis and the data file used for the analysis.
* analysis_id bigint
* filepath_id bigint
  data_type_id bigint
Indexes
 idx_analysis_filepath ON analysis_id
 idx_analysis_filepath_0 ON filepath_id
Pkidx_analysis_filepath_1 ON analysis_id, filepath_id
 idx_analysis_filepath_2 ON data_type_id
Foreign Keys
 fk_analysis_filepath ( analysis_id ) ref analysis (analysis_id)
 fk_analysis_filepath_0 ( filepath_id ) ref filepath (filepath_id)
 fk_analysis_filepath_1 ( data_type_id ) ref data_type (data_type_id)


Table analysis_workflow
Stores what step in_production analyses are on.
* analysis_id bigint
* step integer
Indexes
Pkpk_analysis_workflow ON analysis_id
Foreign Keys
 fk_analysis_workflow ( analysis_id ) ref analysis (analysis_id)


Table column_ontology
This table relates a column with an ontology.
* column_name varchar
* ontology_short_name varchar
* bioportal_id integer
  ontology_branch_id varchar
Indexes
Pkidx_column_ontology ON column_name, ontology_short_name
 idx_column_ontology_0 ON column_name
Foreign Keys
 fk_column_ontology ( column_name ) ref mixs_field_description (column_name)


Table study_person
Contact information for the various people involved in a study
* study_person_id bigserial
* name varchar
* email varchar
* affiliation varchar The institution with which this person is affiliated
  address varchar( 100 )
  phone varchar
Indexes
Pkpk_study_person ON study_person_id
Uidx_study_person ON name, affiliation


Table analysis
hHolds analysis information
* analysis_id bigserial Unique identifier for analysis
* email varchar Email for user who owns the analysis
* name varchar Name of the analysis
* description varchar
* analysis_status_id bigint
  pmid varchar PMID of paper from the analysis
  timestamp timestamptz DEFO current_timestamp
Indexes
Pkpk_analysis ON analysis_id
 idx_analysis_email ON email
 idx_analysis_status_id ON analysis_status_id
Foreign Keys
 fk_analysis_user ( email ) ref qiita_user (email)
 fk_analysis_analysis_status ( analysis_status_id ) ref analysis_status (analysis_status_id)


Table controlled_vocab
* controlled_vocab_id bigserial
* controlled_vocab varchar
Indexes
Pkpk_controlled_vocabularies ON controlled_vocab_id


Table ontology
* ontology_id bigint
* ontology varchar
* fully_loaded bool
  fullname varchar
  query_url varchar
  source_url varchar
  definition text
* load_date date
Indexes
Pkpk_ontology ON ontology_id
Uidx_ontology ON ontology


Table preprocessed_sequence_454_params
Parameters used for processing sequence data.
* preprocessed_params_id bigserial
* trim_length integer
Indexes
Pkpk_preprocessed_sequence_454_params ON preprocessed_params_id


Table preprocessed_spectra_params
Parameters used for processing spectra data.
* preprocessed_params_id bigserial
  col varchar
Indexes
Pkpk_preprocessed_spectra_params ON preprocessed_params_id


Table reference
* reference_id bigserial
* reference_name varchar
  reference_version varchar
* sequence_filepath bigint
  taxonomy_filepath bigint
  tree_filepath bigint
Indexes
Pkpk_reference ON reference_id
 idx_reference ON sequence_filepath
 idx_reference_0 ON taxonomy_filepath
 idx_reference_1 ON tree_filepath
Foreign Keys
 fk_reference_sequence_filepath ( sequence_filepath ) ref filepath (filepath_id)
 fk_reference_taxonomy_filepath ( taxonomy_filepath ) ref filepath (filepath_id)
 fk_reference_tree_filepath ( tree_filepath ) ref filepath (filepath_id)


Table processed_params_uclust
Parameters used for processing data using method uclust
* processed_params_id bigserial
* reference_id bigint What version of reference or type of reference used
* similarity float8 DEFO 0.97
* enable_rev_strand_match bool DEFO TRUE
* suppress_new_clusters bool DEFO TRUE
Indexes
Pkpk_processed_params_uclust ON processed_params_id
 idx_processed_params_uclust ON reference_id
Foreign Keys
 fk_processed_params_uclust ( reference_id ) ref reference (reference_id)


Table processed_params_sortmerna
Parameters used for processing data using method sortmerna
* processed_params_id bigserial
* reference_id bigint What version of reference or type of reference used
* evalue float8
* max_pos integer
* similarity float8
* coverage float8
* threads integer
Indexes
Pkpk_processed_params_sortmerna ON processed_params_id
 idx_processed_params_sortmerna ON reference_id
Foreign Keys
 fk_processed_params_sortmerna ( reference_id ) ref reference (reference_id)


Table preprocessed_sequence_illumina_params
Parameters used for processing illumina sequence data.
* preprocessed_params_id bigserial
* max_bad_run_length integer DEFO 3
* min_per_read_length_fraction real DEFO 0.75
* sequence_max_n integer DEFO 0
* rev_comp_barcode bool DEFO FALSE
* rev_comp_mapping_barcodes bool DEFO FALSE
* rev_comp bool DEFO FALSE
* phred_quality_threshold integer DEFO 3
* barcode_type varchar DEFO 'golay_12'
* max_barcode_errors real DEFO 1.5
Indexes
Pkpk_preprocessed_sequence_illumina_params ON preprocessed_params_id


Table preprocessed_processed_data
* preprocessed_data_id bigint
* processed_data_id bigint
Indexes
Pkidx_preprocessed_processed_data ON preprocessed_data_id, processed_data_id
 idx_preprocessed_processed_data_0 ON preprocessed_data_id
 idx_preprocessed_processed_data_1 ON processed_data_id
Foreign Keys
 fk_preprocessed_processed_data ( preprocessed_data_id ) ref preprocessed_data (preprocessed_data_id)
 fk_preprocessed_processed_data_0 ( processed_data_id ) ref processed_data (processed_data_id)


Table study
* study_id bigserial Unique name for study
* email varchar Email of study owner
* study_status_id bigint
  emp_person_id bigint
* first_contact timestamp DEFO current_timestamp
  funding varchar
* timeseries_type_id bigint What type of timeseries this study is (or is not) Controlled Vocabulary
  lab_person_id bigint
* metadata_complete bool
* mixs_compliant bool
  most_recent_contact timestamp
  number_samples_collected integer
  number_samples_promised integer
* portal_type_id bigint
* principal_investigator_id bigint
* reprocess bool
  spatial_series bool
* study_title varchar
* study_alias varchar
* study_description text
* study_abstract text
  vamps_id varchar
Indexes
Pkpk_study ON study_id
 idx_study ON email
 idx_study_0 ON study_status_id
 idx_study_1 ON emp_person_id
 idx_study_2 ON lab_person_id
 idx_study_3 ON principal_investigator_id
 idx_study_4 ON timeseries_type_id
 idx_study_5 ON portal_type_id
Uunique_study_title ON study_title
Foreign Keys
 fk_study_user ( email ) ref qiita_user (email)
 fk_study_study_status ( study_status_id ) ref study_status (study_status_id)
 fk_study_study_emp_person ( emp_person_id ) ref study_person (study_person_id)
 fk_study_study_lab_person ( lab_person_id ) ref study_person (study_person_id)
 fk_study_study_pi_person ( principal_investigator_id ) ref study_person (study_person_id)
 fk_study_timeseries_type ( timeseries_type_id ) ref timeseries_type (timeseries_type_id)
 fk_study ( portal_type_id ) ref portal_type (portal_type_id)


Table qiita_user
Holds all user information
* email varchar
* user_level_id integer DEFO 5 user level
* password varchar
  name varchar
  affiliation varchar
  address varchar
  phone varchar
  user_verify_code varchar Code for initial user email verification
  pass_reset_code varchar Randomly generated code for password reset
  pass_reset_timestamp timestamp Time the reset code was generated
Indexes
Pkpk_user ON email
 idx_user ON user_level_id
Foreign Keys
 fk_user_user_level ( user_level_id ) ref user_level (user_level_id)


Table prep_y
Information on how raw data y was prepared (prep template)Linked by y being raw_data_id from raw data table.
* sample_id varchar
  data bigint STUFFFFF
Indexes
Pkpk_prep_y ON sample_id


Table prep_columns
* prep_template_id bigint
* column_name varchar
* column_type varchar
Indexes
Pkidx_prep_columns_0 ON prep_template_id, column_name, column_type
 idx_prep_columns_1 ON prep_template_id
Foreign Keys
 fk_prep_columns_prep_template ( prep_template_id ) ref prep_template (prep_template_id)


Table raw_filepath
* raw_data_id bigint
* filepath_id bigint
Indexes
Pkidx_raw_filepath ON raw_data_id, filepath_id
 idx_raw_filepath_0 ON filepath_id
 idx_raw_filepath_1 ON raw_data_id
Foreign Keys
 fk_raw_filepath ( filepath_id ) ref filepath (filepath_id)
 fk_raw_filepath_0 ( raw_data_id ) ref raw_data (raw_data_id)


Table emp_status
All possible statuses for projects relating to EMP. Whether they are part of, processed in accordance to, or not part of EMP.
* emp_status_id bigserial
* emp_status varchar
Indexes
Pkpk_emp_status ON emp_status_id
Uidx_emp_status ON emp_status


Table required_sample_info_status
* required_sample_info_status_id bigserial
  status varchar
Indexes
Pkpk_sample_status ON required_sample_info_status_id
Uidx_required_sample_info_status ON status


Table study_status
* study_status_id bigserial
* status varchar
* description varchar
Indexes
Pkpk_study_status ON study_status_id
Uidx_study_status ON status


Table filetype
Type of file (FASTA, FASTQ, SPECTRA, etc)
* filetype_id bigserial
* type varchar
Indexes
Pkpk_filetype ON filetype_id
Uidx_filetype ON type


Table filepath_type
* filepath_type_id bigserial
  filepath_type varchar
Indexes
Pkpk_filepath_type ON filepath_type_id
Uidx_filepath_type ON filepath_type


Table checksum_algorithm
* checksum_algorithm_id bigserial
* name varchar
Indexes
Pkpk_checksum_algorithm ON checksum_algorithm_id
Uidx_checksum_algorithm ON name


Table data_type
* data_type_id bigserial
* data_type varchar Data type (16S, metabolome, etc) the job will use
Indexes
Pkpk_data_type ON data_type_id
Uidx_data_type ON data_type


Table user_level
Holds available user levels
* user_level_id serial
* name varchar One of the user levels (admin, user, guest, etc)
* description text
Indexes
Pkpk_user_level ON user_level_id
Uidx_user_level ON name


Table analysis_status
* analysis_status_id bigserial
* status varchar
Indexes
Pkpk_analysis_status ON analysis_status_id
Uidx_analysis_status ON status


Table job_status
* job_status_id bigserial
* status varchar
Indexes
Pkpk_job_status ON job_status_id
Uidx_job_status_0 ON status


Table severity
* severity_id serial
* severity varchar
Indexes
Pkpk_severity ON severity_id
Uidx_severity ON severity


Table prep_template
* prep_template_id bigserial
* data_type_id bigint
* raw_data_id bigint
* preprocessing_status varchar DEFO 'not_preprocessed'
  investigation_type varchar The investigation type (e.g., one of the values from EBI's set of known types)
Indexes
Pkpk_prep_template ON prep_template_id
 idx_prep_template ON data_type_id
 idx_prep_template_0 ON raw_data_id
Foreign Keys
 fk_prep_template_data_type ( data_type_id ) ref data_type (data_type_id)
 fk_prep_template_raw_data ( raw_data_id ) ref raw_data (raw_data_id)


Table raw_data
* raw_data_id bigserial
* filetype_id bigint
* link_filepaths_status varchar DEFO 'idle'
Indexes
Upk_raw_data ON raw_data_id
 idx_raw_data ON filetype_id
Pkpk_raw_data_0 ON raw_data_id
Foreign Keys
 fk_raw_data_filetype ( filetype_id ) ref filetype (filetype_id)


Table preprocessed_data
* preprocessed_data_id bigserial
* preprocessed_params_table varchar Name of table holding the params
* preprocessed_params_id bigint
* submitted_to_insdc_status varchar DEFO 'not submitted'
  ebi_submission_accession varchar
  ebi_study_accession varchar
* data_type_id bigint
* link_filepaths_status varchar DEFO 'idle'
Indexes
Pkpk_preprocessed_data ON preprocessed_data_id
 idx_preprocessed_data ON data_type_id
Foreign Keys
 fk_preprocessed_data ( data_type_id ) ref data_type (data_type_id)


Table processed_data
* processed_data_id bigserial
* processed_params_table varchar Name of table holding processing params
* processed_params_id bigint Link to a table with the parameters used to generate processed data
* processed_date timestamp
* data_type_id bigint
* link_filepaths_status varchar DEFO 'idle'
Indexes
Pkpk_processed_data ON processed_data_id
 idx_processed_data ON data_type_id
Foreign Keys
 fk_processed_data ( data_type_id ) ref data_type (data_type_id)


Table job
* job_id bigserial Unique identifier for job
* data_type_id bigint What datatype (16s, metabolome, etc) job is run on.
* job_status_id bigint
* command_id bigint The Qiime or other function being run (alpha diversity, etc)
  options varchar Holds all options set for the job as a json string
  log_id bigint Reference to error if status is error
Indexes
Pkpk_job ON job_id
 idx_job_command ON command_id
 idx_job_status ON job_status_id
 idx_job_type ON data_type_id
 idx_job ON log_id
Foreign Keys
 fk_job_function ( command_id ) ref command (command_id)
 fk_job_job_status_id ( job_status_id ) ref job_status (job_status_id)
 fk_job_data_type ( data_type_id ) ref data_type (data_type_id)
 fk_job ( log_id ) ref logging (logging_id)


Table filepath
* filepath_id bigserial
* filepath varchar
* filepath_type_id bigint
* checksum varchar
* checksum_algorithm_id bigint
  data_directory_id bigserial
Indexes
Pkpk_filepath ON filepath_id
 idx_filepath ON filepath_type_id
 idx_filepath_0 ON data_directory_id
Foreign Keys
 fk_filepath ( filepath_type_id ) ref filepath_type (filepath_type_id)
 fk_filepath_0 ( checksum_algorithm_id ) ref checksum_algorithm (checksum_algorithm_id)
 fk_filepath_data_directory ( data_directory_id ) ref data_directory (data_directory_id)


Table data_directory
* data_directory_id bigserial
* data_type varchar
* mountpoint varchar
* subdirectory varchar
* active bool
Indexes
Pkpk_data_directory ON data_directory_id


Table term
* term_id bigserial
* ontology_id bigint
  old_term_id bigint DEFO NULL Identifier used in the old system, we are keeping this for consistency
* term varchar
  identifier varchar
  definition varchar
  namespace varchar
  is_obsolete bool DEFO 'false'
  is_root_term bool
  is_leaf bool
* user_defined bool DEFO False Whether or not this term was defined by a user
Indexes
Pkpk_term ON term_id
 idx_term ON ontology_id
Foreign Keys
 fk_term_ontology ( ontology_id ) ref ontology (ontology_id)


Table common_prep_info
* prep_template_id bigint The prep template identifier
* sample_id varchar
  center_name varchar
  center_project_name varchar
* emp_status_id bigint
Indexes
 idx_required_prep_info_0 ON emp_status_id
 idx_required_prep_info_2 ON sample_id
 idx_common_prep_info_0 ON sample_id
Pkidx_common_prep_info ON prep_template_id, sample_id
 idx_common_prep_info_1 ON prep_template_id
Foreign Keys
 fk_required_prep_info_emp_status ( emp_status_id ) ref emp_status (emp_status_id)
 fk_common_prep_info ( sample_id ) ref required_sample_info (sample_id)
 fk_prep_template ( prep_template_id ) ref prep_template (prep_template_id)


Table analysis_sample
* analysis_id bigint
* processed_data_id bigint
* sample_id varchar
Indexes
 idx_analysis_sample ON analysis_id
 idx_analysis_sample_0 ON processed_data_id
 idx_analysis_sample_1 ON sample_id
Foreign Keys
 fk_analysis_sample_analysis ( analysis_id ) ref analysis (analysis_id)
 fk_analysis_processed_data ( processed_data_id ) ref processed_data (processed_data_id)
 fk_analysis_sample ( sample_id ) ref required_sample_info (sample_id)


Table environmental_package
* environmental_package_name varchar The name of the environmental package
* metadata_table varchar Contains the name of the table that contains the pre-defined metadata columns for the environmental package
Indexes
Pkpk_environmental_package ON environmental_package_name


Table study_environmental_package
Holds the 1 to many relationship between the study and the environmental_package
* study_id bigint
* environmental_package_name varchar
Indexes
Pkpk_study_environmental_package ON study_id, environmental_package_name
 idx_study_environmental_package ON study_id
 idx_study_environmental_package_0 ON environmental_package_name
Foreign Keys
 fk_study_environmental_package ( study_id ) ref study (study_id)
 fk_study_environmental_package_0 ( environmental_package_name ) ref environmental_package (environmental_package_name)


Table timeseries_type
* timeseries_type_id bigserial
* timeseries_type varchar
* intervention_type varchar DEFO 'None'
Indexes
Pkpk_timeseries_type ON timeseries_type_id
Uidx_timeseries_type ON timeseries_type, intervention_type


Table prep_template_filepath
* prep_template_id bigint
* filepath_id bigint
Indexes
Pkidx_prep_template_filepath ON prep_template_id, filepath_id
 idx_prep_template_filepath ON filepath_id
 idx_prep_template_filepath ON prep_template_id
Foreign Keys
 fk_filepath_id ( filepath_id ) ref filepath (filepath_id)
 fk_prep_template_id ( prep_template_id ) ref prep_template (prep_template_id)


Table required_sample_info
Required info for each sample. One row is one sample.
* sample_id varchar
* study_id bigint
* physical_location varchar Where the sample itself is stored
* has_physical_specimen bool Whether we have the full speciment or just DNA
* has_extracted_data bool
* sample_type varchar Controlled vocabulary of sample types
* required_sample_info_status_id bigint What step of the pipeline the samples are in
* collection_timestamp timestamp
* host_subject_id varchar
* description varchar
* latitude float8 Latitude of the collection site
* longitude float8 Longitude of the collection site
Indexes
 idx_required_sample_info_0 ON required_sample_info_status_id
 idx_required_sample_info ON study_id
Pkidx_required_sample_info_1 ON sample_id
Foreign Keys
 fk_required_sample_info ( required_sample_info_status_id ) ref required_sample_info_status (required_sample_info_status_id)
 fk_required_sample_info_study ( study_id ) ref study (study_id)


Table sample_template_filepath
* study_id bigint
* filepath_id bigint
Indexes
Pkidx_sample_template_filepath ON study_id, filepath_id
 idx_sample_template_filepath_0 ON study_id
 idx_sample_template_filepath_1 ON filepath_id
Foreign Keys
 fk_study_id ( study_id ) ref study (study_id)
 fk_filepath_id ( filepath_id ) ref filepath (filepath_id)


Table prep_template_preprocessed_data
* prep_template_id bigint
* preprocessed_data_id bigint
Indexes
Pkidx_prep_template_preprocessed_data ON prep_template_id, preprocessed_data_id
 idx_prep_template_preprocessed_data_0 ON prep_template_id
 idx_prep_template_preprocessed_data_1 ON preprocessed_data_id
Foreign Keys
 fk_prep_template_id ( prep_template_id ) ref prep_template (prep_template_id)
 fk_prep_template_preprocessed_data ( preprocessed_data_id ) ref preprocessed_data (preprocessed_data_id)