Mercurial > repos > iuc > pysradb_search
changeset 0:1005ffbccd86 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/pysradb commit 95f13fef86ee81a617814a386cb371e94cf45577
| author | iuc |
|---|---|
| date | Fri, 11 Nov 2022 07:35:39 +0000 |
| parents | |
| children | f63cf0adfd87 |
| files | macros.xml pysradb.xml test-data/test_01.tabular test-data/test_01_histogram1.jpg test-data/test_01_histogram2.jpg test-data/test_01_histogram3.jpg test-data/test_01_stats.txt test-data/test_02.tabular test-data/test_02_stats.txt test-data/test_03.tabular test-data/test_03.txt test-data/test_04.tabular test-data/test_04.txt test-data/test_05.tabular test-data/test_05_stats.txt test-data/test_06.tabular test-data/test_06_stats.txt |
| diffstat | 17 files changed, 1049 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,32 @@ +<macros> + <token name="@TOOL_VERSION@">1.4.2</token> + <token name="@SUFFIX_VERSION@">0</token> + <xml name="bio_tools"> + <xrefs> + <xref type="bio.tools">pysradb</xref> + </xrefs> + </xml> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">pysradb</requirement> + <requirement type="package" version="3.6.2">matplotlib</requirement> + <requirement type="package" version="7.1.0_52">imagemagick</requirement> + <requirement type="package" version="5.1.0">gawk</requirement> + </requirements> + </xml> + <xml name="instrument_macro"> + <param name="instrument" type="select" optional="true" label="Instrument" help="Scientific instrument used to automate the DNA sequencing process. You can find more information about the different instruments in the help section."> + <yield/> + </param> + </xml> + <xml name="source_macro"> + <param argument="--source" type="select" label="Library source" help="Type of source material that is being sequenced"> + <yield/> + </param> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.12688/f1000research.18676.1</citation> + </citations> + </xml> +</macros>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/pysradb.xml Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,520 @@ +<tool id='pysradb_search' name='pysradb search' version='@TOOL_VERSION@+galaxy@SUFFIX_VERSION@' profile='20.01'> + <description>sequence metadata from SRA/ENA</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="bio_tools"/> + <expand macro='requirements' /> + <command detect_errors='exit_code'><![CDATA[ + pysradb search + --db $database + #if $conditional_platform.instrument + --query '${conditional_platform.instrument} ${query}' + #else + --query '${query}' + #end if + #if $conditional_mode.source + --source '${conditional_mode.source}' + #end if + #if $conditional_mode.selector == 'false' + --organism '${conditional_mode.organism}' + #end if + #if $conditional_platform.platform == 'illumina' + #if $conditional_platform.layout + --layout $conditional_platform.layout + #end if + #end if + --platform '$conditional_platform.platform' + #if $selection + --selection '${selection}' + #end if + --source $conditional_mode.source + #if $strategy + --strategy '${strategy}' + #end if + + ## Optional fields + --max $output_options.max + #if $advanced.mbases + --mbases $advanced.mbases + #end if + #if $advanced.accession + --accession '${advanced.accession}' + #end if + #if $advanced.publication_date + --publication-date '${advanced.publication_date}' + #end if + --verbosity $output_options.verbosity + #if 'stats' in $output_options.output_files + --stats + #end if + #if 'graphs' in $output_options.output_files + --graphs 'daterange selection basecount' + #end if + --saveto 'output.tsv' + #if 'stats' in $output_options.output_files + > stats.txt + #if $output_options.verbosity == '2' or $output_options.verbosity == '3' + && echo ' Sequencing instrument:' >> stats.txt + #if $database == 'sra' + && gawk -F '\t' '{print $11}' 'output.tsv' | tail -n +2 | sort | uniq -c | gawk '{ print " ", $0 }' >> stats.txt + #else + && gawk -F '\t' '{print $12}' 'output.tsv' | tail -n +2 | sort | uniq -c | gawk '{ print " ", $0 }' >> stats.txt + #end if + #end if + && echo $'\n Query keyworkds: ${query}\n' >> stats.txt + #end if + #if 'graphs' in $output_options.output_files + && convert 'search_plots/Histogram*.svg' -set filename:fn '%[basename]' 'search_plots/%[filename:fn].jpg' + && mv 'search_plots/Histogram of Base Count'*.jpg 'search_plots/histogram_base_count.jpg' + && mv 'search_plots/Histogram of Library'*jpg 'search_plots/histogram_library.jpg' + && mv 'search_plots/Histogram of Publication'*.jpg 'search_plots/histogram_publication.jpg' + #end if + ]]></command> + <inputs> + <param name="database" type="select" label="Database to query" + help="Sequence Read Archive (SRA) data, is the largest publicly available repository of high throughput sequencing data. The European Nucleotide + Archive (ENA) provides a comprehensive record of nucleotide sequencing information."> + <option value="sra">SRA: Sequence Read Archive</option> + <option value="ena">ENA: European Nucleotide Archive</option> + </param> + <param argument="--query" type="text" value="" + label="Query keywords" help="Multiple keywords should be separated by spaces. Example: colorectal cancer"> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"> + <add value="_" /> + <add value="-" /> + <add value=" " /> + </valid> + </sanitizer> + <validator type="regex">[0-9a-zA-Z_ -]+</validator> + </param> + <conditional name="conditional_mode"> + <param name="selector" type="select" label="Genetic material recovered directly from environmental or clinical samples" help="Enable this option if you are interested in metagenomic data. Default: disabled"> + <option value="false" selected="true">Disabled</option> + <option value="true">Enabled</option> + </param> + <when value="false"> + <expand macro="source_macro"> + <option value="genomic">Genomic</option> + <option value="transcriptomic">Transcriptomic</option> + <option value="genomic single cell">Genomic single cell</option> + <option value="transcriptomic single cell">Transcriptomic single cell</option> + <option value="viral rna">Viral RNA</option> + <option value="synthetic">Synthetic</option> + <option value="other">Other</option> + </expand> + <param argument="--organism" type="text" value="Homo sapiens" label="Scientific name of the sample organism" help="The scientific name of a species that is set by binomial nomenclature entails two parts: generic name (or genus name) and specific name"> + <sanitizer invalid_char=""> + <valid initial="string.letters"> + <add value=" " /> + </valid> + </sanitizer> + <validator type="regex" message="This field is compulsory. Please only use letters or whitespace">[a-zA-Z ]+</validator> + </param> + </when> + <when value="true"> + <expand macro="source_macro"> + <option value="metagenomic">Metagenomic</option> + <option value="metatranscriptomic">Metatranscriptomic</option> + </expand> + </when> + </conditional> + <conditional name="conditional_platform"> + <param argument="--platform" type="select" label="Platform" help="Sequencing platform used for generating the reads"> + <option value="illumina">Illumina</option> + <option value="oxford nanopore">Oxford Nanopore</option> + <option value="pacbio smrt">PacBio SMRT</option> + </param> + <when value="illumina"> + <expand macro="instrument_macro" > + <option value="NovaSeq 6000">NovaSeq 6000</option> + <option value="HiSeq X Ten">HiSeq X Ten</option> + <option value="NextSeq 2000">NextSeq 2000</option> + <option value="NextSeq 550">NextSeq 550</option> + <option value="NextSeq 500">NextSeq 500</option> + <option value="HiSeq 4000">HiSeq 4000</option> + <option value="HiSeq 3000">HiSeq 3000</option> + <option value="HiSeq 2500">HiSeq 2500</option> + <option value="HiSeq 2000">HiSeq 2000</option> + <option value="MiSeq">MiSeq</option> + <option value="Genome Analyzer IIx">Genome Analyzer IIx</option> + <option value="Genome Analyzer">Genome Analyzer</option> + </expand> + <param argument="--layout" type="select" optional="true" label="Library layout" help="Paired-end reads improve the ability to identify the relative positions of various reads in the + genome, making it much more effective than single-end reading in resolving structural rearrangements such as gene insertions, deletions, or inversions. Note: Only available for the Illumina platform"> + <option value="single">Single reads</option> + <option value="paired">Paired reads</option> + </param> + </when> + <when value="pacbio smrt"> + <expand macro="instrument_macro"> + <option value="PacBio RS">PacBio RS</option> + <option value="PacBio RS II">PacBio RS II </option> + <option value="Sequel">Sequel</option> + <option value="Sequel II">Sequel II</option> + + </expand> + </when> + <when value="oxford nanopore"> + <expand macro="instrument_macro" > + <option value="MinION">MinION</option> + <option value="PromethION">PromethION</option> + <option value="GridION">GridION</option> + </expand> + </when> + </conditional> + + <param argument="--strategy" type="select" optional="true" label="Library preparation strategy" help="Sequencing technique intended for the library"> + <option value="amplicon">Amplicon</option> + <option value="atac seq">ATAC-seq</option> + <option value="bisulfite seq">Bisulfite-seq</option> + <option value="chia pet">Chromatin interaction analysis with paired-end tag (ChIA-PET)</option> + <option value="chip">ChIP</option> + <option value="chip seq">ChIP-seq</option> + <option value="cts">Coding transcriptome sequencing (CTS)</option> + <option value="dnase hypersensitivity">DNase-seq</option> + <option value="est">EST</option> + <option value="faire seq">FAIRE-seq</option> + <option value="fl cdna">FL-cDNA</option> + <option value="gbs">Genotyping-by-sequencing (GBS)</option> + <option value="hi c">Hi-C</option> + <option value="medip seq">Methylated DNA immunoprecipitation sequencing (MeDIP-Seq)</option> + <option value="mbd seq">Methyl-binding domain sequencing (MBD-seq)</option> + <option value="mnase seq">Micrococcal nuclease sequencing (MNase-seq)</option> + <option value="mirna seq">miRNA-seq</option> + <option value="mre seq">Methylation sensitive restriction enzyme sequencing (MRE-seq)</option> + <option value="ncrna seq">ncRNA-seq</option> + <option value="other">Other</option> + <option value="poolclone">POOLCLONE</option> + <option value="rad seq">Restriction site-associated DNA sequencing (RAD-seq)</option> + <option value="rip seq">RNA immunoprecipitation sequencing (RIP-seq)</option> + <option value="rna seq">RNA-seq</option> + <option value="selex">Systematic evolution of ligands by exponential enrichment (SELEX)</option> + <option value="synthetic long read">Synthetic long-read sequencing</option> + <option value="target capture">Target capture sequencing (TCS)</option> + <option value="tn seq">Tn-seq</option> + <option value="wcs">Whole chromosome shotgun (WCS)</option> + <option value="wga">Whole genome amplification (WGA)</option> + <option value="wgs">Whole genome sequencing (WGS) </option> + <option value="wxs">Whole exome sequencing (WXS)</option> + </param> + <param argument="--selection" type="select" optional="true" label="Library selection" help="Method used to select and/or enrich the material being sequenced"> + <option value="5 methylcytidine antibody">5-methylcytidine antibody</option> + <option value="cage">CAGE</option> + <option value="cdna">cDNA</option> + <option value="chip">ChIP</option> + <option value="chip seq">ChIP-seq</option> + <option value="dnase">DNAse</option> + <option value="hmpr">Hypomethylated partial restriction (HMPR)</option> + <option value="hybrid selection">Hybrid selection</option> + <option value="inverse rrna">Inverse RNA</option> + <option value="mbd2 protein methyl cpg binding domain">Methylated DNA binding domain protein 2 (MBD2)</option> + <option value="mda">Multiple displacement amplification (MDA)</option> + <option value="mf">Mechanical fragmentation (MF)</option> + <option value="mnase">Micrococcal nuclease (MNase)</option> + <option value="msII">MSII</option> + <option value="oligo dt">Oligo(dT)</option> + <option value="padlock proves capture method">Padlock probe capture</option> + <option value="pcr">PCR</option> + <option value="polya">PolyA</option> + <option value="race">Rapid amplification of cDNA ends (RACE)</option> + <option value="random">Random</option> + <option value="random pcr">Random PCR</option> + <option value="reduced representation">Reduced representation</option> + <option value="repeat fractionation">Repeat fractionation</option> + <option value="restriction digest">Restriction digest</option> + <option value="rt pcr">RT-PCR</option> + <option value="size fractionation">Size fractionation</option> + </param> + <section name="advanced" title="Advanced options"> + <param argument="--accession" type="text" value="" optional="true" label="Accession number" help="Relevant study/experiment/sample/run accession number"> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"/> + </sanitizer> + <validator type="regex">[0-9a-zA-Z]+</validator> + </param> + <param argument="--mbases" type="integer" min="0" value="" optional="true" + label="Sample size" help="Size of the sample rounded to the nearest megabase" /> + <param argument="--publication-date" type="text" value="" optional="true" + label="Publication date" help="Publication date of the run in the format dd-mm-yyyy. + If a date range is desired, enter the start date, followed by end date, separated by a colon ':'. + Example: 01-01-2010:31-12-2010"> + <sanitizer invalid_char=""> + <valid initial="string.digits"> + <add value=":" /> + <add value="-" /> + </valid> + </sanitizer> + <validator type="regex">[0-9:-]+</validator> + </param> + </section> + <section name="output_options" title="Output options"> + <param argument="--verbosity" type="select" label="Level of search result details" help="Default: 2"> + <option value="0">0: run accession only</option> + <option value="1">1: run accession and experiment title</option> + <option value="2" selected="true">2: accession numbers, titles and sequencing information</option> + <option value="3">3: all available metadata</option> + </param> + <param argument="--max" type="integer" min="1" max="10000" value="100" label="Maximum number of entries" + help="Note: If the maximum number set is large, querying the SRA database will take significantly longer due to API limits" /> + <param name="output_files" type="select" multiple="true" display="checkboxes" label="Additional output files"> + <option value="stats" selected="true">Statistics for the search query (--stats)</option> + <option value="graphs">Generates graphs to illustrate the search result (--graphs)</option> + </param> + </section> + </inputs> + <outputs> + <data name="metadata_file" from_work_dir="output.tsv" format="tsv" label="${tool.name} on ${on_string}: metadata"/> + <collection name="graphs_collection" type="list" label="${tool.name} on ${on_string}: search plots"> + <discover_datasets pattern="(?P<name>.+)\.jpg" format="jpg" directory="search_plots" /> + <filter>'graphs' in output_options['output_files']</filter> + </collection> + <data name="stats" from_work_dir="stats.txt" format="txt" label="${tool.name} on ${on_string}: stats"> + <filter>'stats' in output_options['output_files']</filter> + </data> + </outputs> + <tests> + <!-- Test 01: default options --> + <test expect_num_outputs="3"> + <param name="database" value="sra"/> + <param name="query" value="cancer"/> + <conditional name="conditional_mode"> + <param name="selector" value="false"/> + <param name="organism" value="Homo sapiens"/> + <param name="source" value="transcriptomic"/> + </conditional> + <section name="output_options"> + <param name="max" value="100"/> + <param name="output_files" value="stats,graphs"/> + </section> + <output name="metadata_file" file="test_01.tabular" ftype="tsv"/> + <output name="stats" file="test_01_stats.txt" ftype="txt"/> + <output_collection name="graphs_collection" type="list" count="3"> + <element name="histogram_base_count" file="test_01_histogram1.jpg" ftype="jpg" compare='sim_size'/> + <element name="histogram_library" file="test_01_histogram2.jpg" ftype="jpg" compare='sim_size'/> + <element name="histogram_publication" file="test_01_histogram3.jpg" ftype="jpg" compare='sim_size'/> + </output_collection> + </test> + <!-- Test 02: Specific search options--> + <test expect_num_outputs="2"> + <param name="database" value="sra"/> + <param name="query" value="colorectal cancer"/> + <conditional name="conditional_platform"> + <param name="platform" value="illumina"/> + <param name="instrument" value="NovaSeq 6000"/> + </conditional> + <param name="strategy" value="wga"/> + <param name="selection" value="pcr"/> + <conditional name="conditional_mode"> + <param name="selector" value="false"/> + <param name="source" value="genomic single cell"/> + <param name="organism" value="Homo sapiens"/> + </conditional> + <section name="advanced"> + <param name="publication_date" value="01-11-2022"/> + <param name="accession" value="SRX18108950"/> + <param name="verbosity" value="3"/> + </section> + <output name="metadata_file" file="test_02.tabular" ftype="tsv"/> + <output name="stats" file="test_02_stats.txt" ftype="txt"/> + </test> + <!-- Test 03: ENA database and verbosity 1--> + <test expect_num_outputs="2"> + <param name="database" value="ena"/> + <param name="query" value="cancer"/> + <param name="strategy" value="wxs"/> + <param name="selection" value="random"/> + <section name="output_options"> + <param name="verbosity" value="1"/> + <param name="max" value="50"/> + </section> + <conditional name="conditional_mode"> + <param name="selector" value="false"/> + <param name="source" value="genomic"/> + <param name="organism" value="homo sapiens"/> + </conditional> + <output name="metadata_file" file="test_03.tabular" ftype="tsv"/> + <output name="stats" file="test_03.txt" ftype="txt"/> + </test> + <!-- Test 04: Test metatranscriptome query --> + <test expect_num_outputs="2"> + <param name="database" value="sra"/> + <param name="query" value="escherichia"/> + <section name="advanced"> + <param name="mbases" value="100"/> + </section> + <conditional name="conditional_mode"> + <param name="selector" value="true"/> + <param name="source" value="metagenomic"/> + </conditional> + <output name="metadata_file" file="test_04.tabular" ftype="tsv"/> + <output name="stats" file="test_04.txt" ftype="txt"/> + </test> + <!-- Test 05: Test nanopore data --> + <test expect_num_outputs="2"> + <param name="database" value="sra"/> + <param name="query" value="cancer"/> + <conditional name="conditional_platform"> + <param name="platform" value="oxford nanopore"/> + <param name="instrument" value="MinION"/> + </conditional> + <param name="strategy" value="rna seq"/> + <param name="selection" value="cdna"/> + <conditional name="conditional_mode"> + <param name="selector" value="false"/> + <param name="source" value="transcriptomic"/> + <param name="organism" value="Homo sapiens"/> + </conditional> + <output name="metadata_file" file="test_05.tabular" ftype="tsv"/> + <output name="stats" file="test_05_stats.txt" ftype="txt"/> + </test> + <!-- Test 06: Different specie --> + <test expect_num_outputs="2"> + <param name="database" value="sra"/> + <param name="query" value="stress"/> + <conditional name="conditional_platform"> + <param name="platform" value="illumina"/> + <param name="instrument" value="NextSeq 500"/> + </conditional> + <param name="strategy" value="rna seq"/> + <param name="selection" value="random"/> + <conditional name="conditional_mode"> + <param name="selector" value="false"/> + <param name="source" value="transcriptomic"/> + <param name="organism" value="Arabidopsis thaliana"/> + </conditional> + <section name="output_options"> + <param name="verbosity" value="3"/> + <param name="max" value="20"/> + </section> + <output name="metadata_file" file="test_06.tabular" ftype="tsv"/> + <output name="stats" file="test_06_stats.txt" ftype="txt"/> + </test> + </tests> + <help><![CDATA[ +.. class:: infomark + +**Purpose** + +pysradb allows to retrieve metadata, such as run accession numbers, from SRA and ENA based on multiple criteria: + +- Database: SRA or ENA +- Query keywords +- Accession number: a relevant study/experiment/sample/run accession number +- Organism: scientific name of the sample organism +- Library layout: paired or single-end reads +- Sample size: rounded to the nearest megabase +- Publication date +- Sequencing platform: Illumina, Nanopore or PacBio +- Library selection: method used to select and/or enrich the material being sequenced +- Library source: Type of source material that is being sequenced +- Library preparation strategy: sequencing technique intended for the library + +------ + +.. class:: infomark + +**Outputs** + +pysradb generates three different output types: + +- Raw metadata file +- Statistics for the search query +- Graphs to illustrate the search results + +------ + +.. class:: infomark + +**Sequencing instruments** + +**Comparisons between HiSeq instruments** + +HiSeq 3000/4000 provides some improvements with respect the previous model HiSeq 2500: + +- HiSeq 3000/4000 genere up to 1.5 Tb and 5 Tb reads per run. +- HiSeq 3000/4000 use patterned flow cell technology originally developed for HiSeq X platforms. +- HiSeq 3000/4000 run 3 times faster and yield 65% more reads per lane. +- HiSeq 3000/4000 patterned flow cells contain billions of nanowells at fixed, known positions on the flow cell. The structured organization enables clustering at higher densities compared to non-pattern HiSeq designs. + +However, the HiSeq 3000/4000 also have some also some limitations with respect to HiSeq 2500: + +- HiSeq 3000/4000 are not recommended for low complexity sequencing. Applications such as non-unique amplicons, 16S, are currently not recommended. +- Libraries with low complexity within the first 25 bases of a read are not expected to produce high quality data. +- Library size restrictions. Libraries that are too long can result in polyclonal clusters that span more than 1 well, these will not pass filter. Smaller libraries will preferentially amplify with Illumina's new kinetic exclusion amplification so tight library distributions ranging from 300-500 bp are recommended. +- Very low tolerance for adapter dimers. Even as little as 1% adapter dimer can take up ~6% of sequencing reads, 10% contamination will take up 84% of reads. Illumina recommends you keep adapter contamination below 0.5% of your entire library. +- Higher duplication rates as compared to HiSeq 2500. +- Low quality read 2 (entire HiSeq 3000 install base is affected). + +HiSeq 3000/4000 support DNA-seq, RNA-seq , ChIP-Seq, mate-pair, small RNA and exome library preparation. Any library preparation where there is enough sequence diversity is currently supported. Amplicon, 16S and applications with low sequencing diversity are currently not supported on the HiSeq 3000 / 4000. + +HiSeq 2500 is considered the most reliable model according to different sources. + +**What type of read quality is expected from the HiSeq 3000/4000 ?** + +- 2 x 50bp ≥85% bases > Q30 +- 2 x 75bp ≥80% bases > Q30 +- 2 x 150bp ≥75% of bases >Q30 + +**What is the difference between MiSeq and HiSeq?** + +HiSeq and MiSeq platforms are among the most widely used platform to study microbial communities. But the two platforms differ in the length and amount of reads. +MiSeq can run 600 cycles to produce 200 million 300 bp reads, on the other hand, HiSeq 2500 can run 500 cycles to produce 120 million 250 bp. + +**What are the differences between HiSeq and NovaSeq?** + +The Illumina NovaSeq provides a massive upgrade in sequencing throughput compared to the HiSeq 4000. There are more stringent library requirements and requires a +larger sample size. Due to the vast amount of data produced by the NovaSeq and the known issue of index swapping, unique dual-indexed libraries are required. + +**What are the characteristics of HiSeq X instruments?** + +- HiSeq X is recommended for whole genome sequencing only (including whole bisulfite sequencing). This means that it is not adequate for RNA-seq, exome, ChIP-seq or small RNA-seq applications. +- Plant and animal samples can be sequenced on the HiSeq X. +- Expect coverate is over 30x or approximately 375 million reads per lane by loading one sample per lane. +- Hiseq X Ten generates utilize 2x150 base pair read configurations and has slightly better GC coverage than the HiSeq 2500. + +**What are the differences between MiSeq and Nextseq?** + +The NextSeq Series of systems delivers the power of high-throughput sequencing with the simplicity of a desktop sequencer. NextSeq instruments represent an improvement when compared with Miseq, despite generating sorter reads (150bp, compared to MiSeq 250bp). NextSeq is recommended in +the following applications & methods: + +- Exome & large panel sequencing (enrichment-based) +- Single-cell profiling (scRNA-Seq, scDNA-Seq, oligo tagging assays) +- Transcriptome sequencing (total RNA-Seq, mRNA-Seq, gene expression profiling) +- Methylation sequencing +- Metagenomic profiling (shotgun metagenomics, metatranscriptomics) +- Cell-free sequencing & liquid biopsy analysis + +Regarding the maximum number of reads per ran, MiSeq can generate 25 million, vs 400 million generated by the Nextseq 550 instrument. MiSeq recommended for sequencing samples of low diversity. + +**What are the differences between HiSeq and NextSeq?** + +The main technical difference between HiSeq and NextSeq will be the number of dyes each machines use. HiSeq uses traditional color coding with four different dyes, while NextSeq uses two dyes. This does not give any practical differences in terms of the data quality, but the trend in illumina sequencers are more into the direction of reducing the number of dyes. + +**What is the difference between Nextseq and NovaSeq?** + +The NovaSeq 6000 system offers deep and broad coverage and is recommended for large whole-genome sequencing (human, plant, animal) projects. It generates 250 bp reads, +with 20 billion maximum reads per run. NovaSeq 6000 instruments have not application based restrictions. + +**Illumina maximum read-length summary** + +- MiSeq: between 300 and 600 bp +- NextSeq: 300 bp +- HiSeq 2500: between 250 and 500 bp (depending of the sofware) +- HiSeq 4000: 150 bp +- HiSeq X: 150 bp + +**Nanopore models - single-molecule ultra-long-read sequencing** + +Nanopore sequencing provides the longest read lengths, from 500 bp to the current record of 2.3 Mb, with 10-30-kb genomic libraries being common. Even after error correction, sequencing error rates of corrected nanopore reads (1.5-9%) are still higher than those of corrected PacBio reads (<1%). + +**PacBio SMRT instruments - single-molecule long-read low-error rate sequencing** + +PacBio Sequel II CLR sequencing represents a major advancement in sequencing throughput over previous PacBio platforms with the production of more sequencing data and longer reads versus RS II and the Sequel I. +The PacBio HiFi sequencing method yields highly accurate long-read sequencing datasets with read lengths averaging 10-25 kb and accuracies greater than 99.5%. + + + ]]> </help> + <expand macro="citations" /> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_01.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,101 @@ +study_accession experiment_accession experiment_title sample_taxon_id sample_scientific_name experiment_library_strategy experiment_library_source experiment_library_selection sample_accession sample_alias experiment_instrument_model pool_member_spots run_1_size run_1_accession run_1_total_spots run_1_total_bases +SRP406950 SRX18219478 J17-72p-3 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716255 J17-72p-3 Illumina NovaSeq 6000 21865805 2011682291 SRR22242707 21865805 6559741500 +SRP406950 SRX18219477 J17-72p-2 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716254 J17-72p-2 Illumina NovaSeq 6000 19102337 1762557173 SRR22242708 19102337 5730701100 +SRP406950 SRX18219476 J17-72p-1 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716253 J17-72p-1 Illumina NovaSeq 6000 20134870 1863354901 SRR22242709 20134870 6040461000 +SRP406950 SRX18219475 hep3b-72p-3 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716252 hep3b-72p-3 Illumina NovaSeq 6000 20032029 1887623947 SRR22242710 20032029 6009608700 +SRP406950 SRX18219474 hep3b-72p-2 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716251 hep3b-72p-2 Illumina NovaSeq 6000 18954951 1743547228 SRR22242711 18954951 5686485300 +SRP406950 SRX18219473 hep3b-72p-1 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716250 hep3b-72p-1 Illumina NovaSeq 6000 19553325 1800573666 SRR22242712 19553325 5865997500 +SRP406950 SRX18219472 hep3b-vec-3 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716249 hep3b-vec-3 Illumina NovaSeq 6000 19039145 1749393677 SRR22242713 19039145 5711743500 +SRP406950 SRX18219471 hep3b-vec-2 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716248 hep3b-vec-2 Illumina NovaSeq 6000 19819809 1821641085 SRR22242714 19819809 5945942700 +SRP406950 SRX18219470 hep3b-vec-1 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15716247 hep3b-vec-1 Illumina NovaSeq 6000 29311538 2787642513 SRR22242715 29311538 8793461400 +SRP406776 SRX18202826 GSM6720851: HepG2 cells, f-RCP+660 nm [B 3]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699868 GSM6720851 Illumina HiSeq 2500 22452313 2016448266 SRR22225215 22452313 6347800899 +SRP406776 SRX18202825 GSM6720850: HepG2 cells, f-RCP+660 nm [B 2]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699867 GSM6720850 Illumina HiSeq 2500 23301966 2101800167 SRR22225216 23301966 6618465928 +SRP406776 SRX18202824 GSM6720849: HepG2 cells, f-RCP+660 nm [B 1]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699866 GSM6720849 Illumina HiSeq 2500 23150509 2101691173 SRR22225217 23150509 6613318643 +SRP406776 SRX18202823 GSM6720848: HepG2 cells, RCP+660 nm [A 3]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699865 GSM6720848 Illumina HiSeq 2500 23012674 2084577587 SRR22225218 23012674 6543146264 +SRP406776 SRX18202822 GSM6720847: HepG2 cells, RCP+660 nm [A 2]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699864 GSM6720847 Illumina HiSeq 2500 21058391 1876834984 SRR22225219 21058391 5941999670 +SRP406776 SRX18202821 GSM6720846: HepG2 cells, RCP+660 nm [A 1]; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15699863 GSM6720846 Illumina HiSeq 2500 23091493 2082180756 SRR22225220 23091493 6587272891 +SRP406643 SRX18193585 GSM6718890: PC3_NC3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691692 GSM6718890 Illumina NovaSeq 6000 23459231 2048517451 SRR22215651 23459231 6634962611 +SRP406643 SRX18193584 GSM6718889: PC3_NC2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691691 GSM6718889 Illumina NovaSeq 6000 23447723 2043917226 SRR22215652 23447723 6632304770 +SRP406643 SRX18193583 GSM6718888: PC3_NC1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691690 GSM6718888 Illumina NovaSeq 6000 24333381 2134599968 SRR22215653 24333381 6885056225 +SRP406643 SRX18193582 GSM6718887: DU145_R3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691689 GSM6718887 Illumina NovaSeq 6000 24414110 2129635530 SRR22215654 24414110 6902065985 +SRP406643 SRX18193581 GSM6718886: DU145_R2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691688 GSM6718886 Illumina NovaSeq 6000 24206817 2139012987 SRR22215655 24206817 6854276087 +SRP406643 SRX18193580 GSM6718885: DU145_R1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691687 GSM6718885 Illumina NovaSeq 6000 24759866 2201510118 SRR22215656 24759866 7015759429 +SRP406643 SRX18193579 GSM6718884: DU145_NC3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691686 GSM6718884 Illumina NovaSeq 6000 23413490 2052300610 SRR22215657 23413490 6622496209 +SRP406643 SRX18193578 GSM6718883: DU145_NC2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691685 GSM6718883 Illumina NovaSeq 6000 23098910 2017150275 SRR22215658 23098910 6533106894 +SRP406643 SRX18193577 GSM6718893: PC3_R3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691684 GSM6718893 Illumina NovaSeq 6000 25275572 2231454551 SRR22215659 25275572 7158981428 +SRP406643 SRX18193576 GSM6718892: PC3_R2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691683 GSM6718892 Illumina NovaSeq 6000 23324148 2038273567 SRR22215660 23324148 6600455016 +SRP406643 SRX18193575 GSM6718891: PC3_R1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691682 GSM6718891 Illumina NovaSeq 6000 24343398 2154463398 SRR22215661 24343398 6897255997 +SRP406643 SRX18193574 GSM6718882: DU145_NC1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15691681 GSM6718882 Illumina NovaSeq 6000 23499672 2054821041 SRR22215662 23499672 6647491555 +SRP405996 SRX18142633 RNA-Seq of GPD1-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644089 GPD1-3 Illumina NovaSeq 6000 20925798 1914833857 SRR22163747 20925798 6207163796 +SRP405996 SRX18142632 RNA-Seq of GPD1-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644088 GPD1-2 Illumina NovaSeq 6000 23860665 2188219511 SRR22163748 23860665 7100176962 +SRP405996 SRX18142631 RNA-Seq of GPD1-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644087 GPD1-1 Illumina NovaSeq 6000 21427274 1956307538 SRR22163749 21427274 6382445460 +SRP405996 SRX18142630 RNA-Seq of GPD1-mut-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644086 K120A-3 Illumina NovaSeq 6000 23974893 2199388419 SRR22163750 23974893 7142011070 +SRP405996 SRX18142629 RNA-Seq of GPD1-mut-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644085 K120A-2 Illumina NovaSeq 6000 34212538 3102446211 SRR22163751 34212538 10168388248 +SRP405996 SRX18142628 RNA-Seq of GPD1-mut-OE 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644084 K120A-1 Illumina NovaSeq 6000 22781183 2056285283 SRR22163752 22781183 6764866900 +SRP405996 SRX18142627 RNA-Seq of 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644083 Con-3 Illumina NovaSeq 6000 23325722 2097939888 SRR22163753 23325722 6941714338 +SRP405996 SRX18142626 RNA-Seq of 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644082 Con-2 Illumina NovaSeq 6000 22103936 2020280158 SRR22163754 22103936 6574686904 +SRP405996 SRX18142625 RNA-Seq of 5637 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR SRS15644081 Con-1 Illumina NovaSeq 6000 22883975 2079148433 SRR22163755 22883975 6800103580 +SRP405518 SRX18093653 GSM6700937: RC77 T/E; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15618824 GSM6700937 Illumina HiSeq 2500 113241775 14027009073 SRR22113916 113241775 34199016050 +SRP405518 SRX18093652 GSM6700936: MDA PCa 2b; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15596651 GSM6700936 Illumina HiSeq 2500 92541233 11725686132 SRR22113917 92541233 27503968067 +ERP131546 ERX6235633 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286434 SAMEA9563694 Illumina HiSeq 2500 ERR6609153 +ERP131546 ERX6235632 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286433 SAMEA9563693 Illumina HiSeq 2500 ERR6609152 +ERP131546 ERX6235631 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286432 SAMEA9563692 Illumina HiSeq 2500 ERR6609151 +ERP131546 ERX6235630 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286431 SAMEA9563691 Illumina HiSeq 2500 ERR6609150 +ERP131546 ERX6235629 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286430 SAMEA9563690 Illumina HiSeq 2500 ERR6609149 +ERP131546 ERX6235628 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286429 SAMEA9563689 Illumina HiSeq 2500 ERR6609148 +ERP131546 ERX6235627 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286428 SAMEA9563688 Illumina HiSeq 2500 ERR6609147 +ERP131546 ERX6235626 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286427 SAMEA9563687 Illumina HiSeq 2500 ERR6609146 +ERP131546 ERX6235625 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286426 SAMEA9563686 Illumina HiSeq 2500 ERR6609145 +ERP131546 ERX6235624 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286425 SAMEA9563685 Illumina HiSeq 2500 ERR6609144 +ERP131546 ERX6235623 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286424 SAMEA9563684 Illumina HiSeq 2500 ERR6609143 +ERP131546 ERX6235622 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286423 SAMEA9563683 Illumina HiSeq 2500 ERR6609142 +ERP131546 ERX6235621 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286422 SAMEA9563682 Illumina HiSeq 2500 ERR6609141 +ERP131546 ERX6235620 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286421 SAMEA9563681 Illumina HiSeq 2500 ERR6609140 +ERP131546 ERX6235619 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286420 SAMEA9563680 Illumina HiSeq 2500 ERR6609139 +ERP131546 ERX6235618 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286419 SAMEA9563679 Illumina HiSeq 2500 ERR6609138 +ERP131546 ERX6235617 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286418 SAMEA9563678 Illumina HiSeq 2500 ERR6609137 +ERP131546 ERX6235616 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286417 SAMEA9563677 Illumina HiSeq 2500 ERR6609136 +ERP131546 ERX6235615 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286416 SAMEA9563676 Illumina HiSeq 2500 ERR6609135 +ERP131546 ERX6235614 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286415 SAMEA9563675 Illumina HiSeq 2500 ERR6609134 +ERP131546 ERX6235613 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286414 SAMEA9563674 Illumina HiSeq 2500 ERR6609133 +ERP131546 ERX6235612 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286413 SAMEA9563673 Illumina HiSeq 2500 ERR6609132 +ERP131546 ERX6235611 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286412 SAMEA9563672 Illumina HiSeq 2500 ERR6609131 +ERP131546 ERX6235610 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286411 SAMEA9563671 Illumina HiSeq 2500 ERR6609130 +ERP131546 ERX6235609 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286410 SAMEA9563670 Illumina HiSeq 2500 ERR6609129 +ERP131546 ERX6235608 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286409 SAMEA9563669 Illumina HiSeq 2500 ERR6609128 +ERP131546 ERX6235607 Illumina HiSeq 2500 sequencing 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC PCR ERS7286408 SAMEA9563667 Illumina HiSeq 2500 ERR6609127 +SRP405359 SRX18082254 GSM6697086: Patient61; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586208 GSM6697086 Illumina HiSeq 4000 31947164 4047815431 SRR22102209 31947164 9648043528 +SRP405359 SRX18082253 GSM6697085: Patient60; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586207 GSM6697085 Illumina HiSeq 4000 38555712 4842551626 SRR22102210 38555712 11643825024 +SRP405359 SRX18082252 GSM6697084: Patient59; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586206 GSM6697084 Illumina HiSeq 4000 42085416 5272334669 SRR22102211 42085416 12709795632 +SRP405359 SRX18082251 GSM6697083: Patient58; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586205 GSM6697083 Illumina HiSeq 4000 34410281 4332064189 SRR22102212 34410281 10391904862 +SRP405359 SRX18082250 GSM6697082: Patient57; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586204 GSM6697082 Illumina HiSeq 4000 44202589 5772115042 SRR22102213 44202589 13349181878 +SRP405359 SRX18082249 GSM6697081: Patient56; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586203 GSM6697081 Illumina HiSeq 4000 56761858 7188373175 SRR22102214 56761858 17142081116 +SRP405359 SRX18082248 GSM6697080: Patient55; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586202 GSM6697080 Illumina HiSeq 4000 43007557 5497362360 SRR22102215 43007557 12988282214 +SRP405359 SRX18082247 GSM6697079: Patient54; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586201 GSM6697079 Illumina HiSeq 4000 28729299 3849047462 SRR22102216 28729299 8676248298 +SRP405359 SRX18082246 GSM6697078: Patient53; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586200 GSM6697078 Illumina HiSeq 4000 27758639 3690700827 SRR22102217 27758639 8383108978 +SRP405359 SRX18082245 GSM6697077: Patient52; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586199 GSM6697077 Illumina HiSeq 4000 31064684 3939177209 SRR22102218 31064684 9381534568 +SRP405359 SRX18082244 GSM6697076: Patient51; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586198 GSM6697076 Illumina HiSeq 4000 31505467 3987918246 SRR22102219 31505467 9514651034 +SRP405359 SRX18082243 GSM6697075: Patient50; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586197 GSM6697075 Illumina HiSeq 4000 34426584 4334042951 SRR22102220 34426584 10396828368 +SRP405359 SRX18082242 GSM6697074: Patient49; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586196 GSM6697074 Illumina HiSeq 4000 26673393 3340287227 SRR22102221 26673393 8055364686 +SRP405359 SRX18082241 GSM6697073: Patient48; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586195 GSM6697073 Illumina HiSeq 4000 30867031 3993026607 SRR22102222 30867031 9321843362 +SRP405359 SRX18082240 GSM6697072: Patient47; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586194 GSM6697072 Illumina HiSeq 4000 35322031 4433071306 SRR22102223 35322031 10667253362 +SRP405359 SRX18082239 GSM6697071: Patient46; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586193 GSM6697071 Illumina HiSeq 4000 33009330 4158400585 SRR22102224 33009330 9968817660 +SRP405359 SRX18082238 GSM6697070: Patient45; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586192 GSM6697070 Illumina HiSeq 4000 28983658 3897067912 SRR22102225 28983658 8753064716 +SRP405359 SRX18082237 GSM6697069: Patient44; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586191 GSM6697069 Illumina HiSeq 4000 40190178 5163897011 SRR22102226 40190178 12137433756 +SRP405359 SRX18082236 GSM6697068: Patient43; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586190 GSM6697068 Illumina HiSeq 4000 35262046 4493047289 SRR22102227 35262046 10649137892 +SRP405359 SRX18082235 GSM6697067: Patient42; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586189 GSM6697067 Illumina HiSeq 4000 40585471 5143646051 SRR22102228 40585471 12256812242 +SRP405359 SRX18082234 GSM6697066: Patient41; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586188 GSM6697066 Illumina HiSeq 4000 33942412 4490395870 SRR22102229 33942412 10250608424 +SRP405359 SRX18082233 GSM6697065: Patient40; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586187 GSM6697065 Illumina HiSeq 4000 32781382 4058331783 SRR22102230 32781382 9899977364 +SRP405359 SRX18082232 GSM6697064: Patient39; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586186 GSM6697064 Illumina HiSeq 4000 40942797 5093355659 SRR22102231 40942797 12364724694 +SRP405359 SRX18082231 GSM6697063: Patient38; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586185 GSM6697063 Illumina HiSeq 4000 38192324 4768475078 SRR22102232 38192324 11534081848 +SRP405359 SRX18082230 GSM6697062: Patient37; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586184 GSM6697062 Illumina HiSeq 4000 36365508 4568980294 SRR22102233 36365508 10982383416 +SRP405359 SRX18082229 GSM6697061: Patient36; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586183 GSM6697061 Illumina HiSeq 4000 30158877 3917819621 SRR22102234 30158877 9107980854 +SRP405359 SRX18082228 GSM6697060: Patient35; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586182 GSM6697060 Illumina HiSeq 4000 34297360 4265438881 SRR22102235 34297360 10357802720 +SRP405359 SRX18082227 GSM6697059: Patient34; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586181 GSM6697059 Illumina HiSeq 4000 37925806 4699958650 SRR22102236 37925806 11453593412 +SRP405359 SRX18082226 GSM6697058: Patient33; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586180 GSM6697058 Illumina HiSeq 4000 33308463 4383553950 SRR22102237 33308463 10059155826 +SRP405359 SRX18082225 GSM6697057: Patient32; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586179 GSM6697057 Illumina HiSeq 4000 34658814 4360066537 SRR22102238 34658814 10466961828 +SRP405359 SRX18082224 GSM6697056: Patient31; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586178 GSM6697056 Illumina HiSeq 4000 16274738 2021803534 SRR22102239 16274738 4914970876 +SRP405359 SRX18082223 GSM6697055: Patient30; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586177 GSM6697055 Illumina HiSeq 4000 39401509 4920729499 SRR22102240 39401509 11899255718 +SRP405359 SRX18082222 GSM6697054: Patient29; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586176 GSM6697054 Illumina HiSeq 4000 39659987 5262172617 SRR22102241 39659987 11977316074 +SRP405359 SRX18082221 GSM6697053: Patient28; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586175 GSM6697053 Illumina HiSeq 4000 32460742 4035027222 SRR22102242 32460742 9803144084 +SRP405359 SRX18082220 GSM6697052: Patient27; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS15586174 GSM6697052 Illumina HiSeq 4000 39137332 4888152280 SRR22102243 39137332 11819474264
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_01_stats.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,41 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 7 + Number of unique experiments: 100 + Number of unique runs: 100 + Number of unique samples: 100 + Mean base count of samples: 9247829385.671 + Median base count of samples: 8383108978.000 + Sample base count standard deviation: 4445810003.504 + Date range: + 2022-11: 100 + + Organisms: + Homo sapiens: 100 + + Platform: + ILLUMINA: 100 + + Library strategy: + RNA-Seq: 100 + + Library source: + TRANSCRIPTOMIC: 100 + + Library selection: + PCR: 36 + cDNA: 64 + + Library layout: + PAIRED: 73 + SINGLE: 27 + + + Sequencing instrument: + 35 Illumina HiSeq 2500 + 35 Illumina HiSeq 4000 + 30 Illumina NovaSeq 6000 + + Query keyworkds: cancer +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_02.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,2 @@ +study_accession experiment_accession experiment_title sample_taxon_id sample_scientific_name experiment_library_strategy experiment_library_source experiment_library_selection sample_accession sample_alias experiment_instrument_model pool_member_spots run_1_size run_1_accession run_1_total_spots run_1_total_bases +SRP405661 SRX18108950 Whole-genome amplification using Ampli1 of CRC28-TP-Lgr5-7 followed by whole-genome sequencing 9606 Homo sapiens WGA GENOMIC SINGLE CELL PCR SRS15611831 SC44-TP-Lgr5-7 Illumina NovaSeq 6000 85324861 8311782177 SRR22129228 85324861 25768108022
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_02_stats.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,37 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 1 + Number of unique experiments: 1 + Number of unique runs: 1 + Number of unique samples: 1 + Mean base count of samples: 25768108022.000 + Median base count of samples: 25768108022.000 + Sample base count standard deviation: nan + Date range: + 2022-11: 1 + + Organisms: + Homo sapiens: 1 + + Platform: + ILLUMINA: 1 + + Library strategy: + WGA: 1 + + Library source: + GENOMIC SINGLE CELL: 1 + + Library selection: + PCR: 1 + + Library layout: + PAIRED: 1 + + + Sequencing instrument: + 1 Illumina NovaSeq 6000 + + Query keyworkds: colorectal cancer +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_03.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,51 @@ +run_accession description +DRR013000 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013001 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013002 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013003 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013004 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013005 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013006 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013007 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013008 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013009 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013010 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013011 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013012 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013013 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +DRR013014 Illumina Genome Analyzer IIx sequencing; Mutation profiles in inflamed gastric epithelium with Helicobacter pylori infection during the development of gastric cancer. +ERR166302 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166303 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166304 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166305 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166306 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166307 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166308 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166309 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166310 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166311 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166312 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166313 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166314 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166315 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166316 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166317 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166318 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166319 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166320 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166321 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166322 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166323 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166324 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166325 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166326 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166327 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166328 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166329 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166330 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166331 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166332 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166333 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166334 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166335 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles. +ERR166336 Illumina Genome Analyzer II paired end sequencing; Whole exome sequencing suggests much of non BRCA1/BRCA2 familial breast cancer is due to moderate and low penetrance susceptibility alleles.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_03.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,36 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 2 + Number of unique experiments: 50 + Number of unique runs: 50 + Number of unique samples: 33 + Mean base count of samples: 4578793656.560 + Median base count of samples: 4764134876.000 + Sample base count standard deviation: 734903723.447 + Date range: + 2013-08: 35 + 2014-12: 15 + + Organisms: + Homo sapiens: 50 + + Platform: + ILLUMINA: 50 + + Library strategy: + WXS: 50 + + Library source: + GENOMIC: 50 + + Library selection: + RANDOM: 50 + + Library layout: + PAIRED: 50 + + + + Query keyworkds: cancer +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_04.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,17 @@ +study_accession experiment_accession experiment_title sample_taxon_id sample_scientific_name experiment_library_strategy experiment_library_source experiment_library_selection sample_accession sample_alias experiment_instrument_model pool_member_spots run_1_size run_1_accession run_1_total_spots run_1_total_bases +ERP124756 ERX4648078 Illumina HiSeq 4000 paired end sequencing 749906 gut metagenome AMPLICON METAGENOMIC PCR ERS5259723 SAMEA7503087 Illumina HiSeq 4000 173663 56058305 ERR4778259 173663 99683370 +ERP124756 ERX4648028 Illumina HiSeq 4000 paired end sequencing 749906 gut metagenome AMPLICON METAGENOMIC PCR ERS5259673 SAMEA7503037 Illumina HiSeq 4000 173099 53076773 ERR4778209 173099 99532489 +ERP124756 ERX4648027 Illumina HiSeq 4000 paired end sequencing 749906 gut metagenome AMPLICON METAGENOMIC PCR ERS5259672 SAMEA7503036 Illumina HiSeq 4000 173338 52865525 ERR4778208 173338 99669968 +SRP341852 SRX12665402 16S sequencing of interdigital skin swab from sheep 1338477 skin metagenome AMPLICON METAGENOMIC PCR SRS10618044 Sheep skin microbiome Illumina MiSeq 166958 64367895 SRR16387857 166958 100324236 +SRP117119 SRX11222252 16s sequencing of stool 408170 human gut metagenome AMPLICON METAGENOMIC PCR SRS9254173 UMB23_10.1 HiSeq X Ten 286384 65801055 SRR14907840 286384 100234400 +DRP007056 DRX162766 Illumina MiSeq sequencing of SAMD00164285 527639 wastewater metagenome AMPLICON METAGENOMIC PCR DRS174917 SAMD00164285 Illumina MiSeq 336318 46757340 DRR172154 336318 100373320 +SRP276298 SRX8896576 16S_rRNA_metagenome_blood_chickens 256318 metagenome AMPLICON METAGENOMIC PCR SRS7155476 81_buffy coat_14dpi Illumina MiSeq 166389 55327914 SRR12398266 166389 99833400 +SRP276298 SRX8896560 16S_rRNA_metagenome_blood_chickens 256318 metagenome AMPLICON METAGENOMIC PCR SRS7155460 45_buffy coat_7dpi Illumina MiSeq 165929 57268691 SRR12398282 165929 99557400 +ERP112563 ERX2987278 Illumina MiSeq sequencing; qiita_ptid_5663:12056.4499LW0042 870726 food metagenome OTHER METAGENOMIC PCR ERS2958743 SAMEA5151002 Illumina MiSeq 339262 53039991 ERR2984706 339262 100082290 +ERP114115 ERX3224980 Illumina MiSeq paired end sequencing 1510822 pig gut metagenome AMPLICON METAGENOMIC PCR ERS3201120 SAMEA5394763 Illumina MiSeq 165654 68047601 ERR3197204 165654 99532834 +SRP192618 SRX5687626 Whole Population Sequencing of Escherchia Coli Cultures Evolved to Withstand Starvation 562 Escherichia coli WGA METAGENOMIC RANDOM SRS4627531 SampleM2_T700_P116 NextSeq 500 330161 41707500 SRR8901618 330161 99708622 +SRP184350 SRX5345728 16SrRNS gene amplicon by Illumina miseq: Humpback whale blow 1850221 respiratory tract metagenome AMPLICON METAGENOMIC PCR SRS4337512 37_S47_L001 Illumina MiSeq 182446 52474806 SRR8543521 182446 99871728 +SRP184350 SRX5345692 16SrRNS gene amplicon by Illumina miseq: Humpback whale blow 1850221 respiratory tract metagenome AMPLICON METAGENOMIC PCR SRS4337478 45_S31_L001 Illumina MiSeq 188922 51993718 SRR8543557 188922 100140147 +SRP184350 SRX5345678 16SrRNS gene amplicon by Illumina miseq: Humpback whale blow 1850221 respiratory tract metagenome AMPLICON METAGENOMIC PCR SRS4337464 23_S30_L001 Illumina MiSeq 185157 52670220 SRR8543571 185157 100079103 +SRP168493 SRX5027285 DNA-Seq of diel tents 561 Escherichia WGS METAGENOMIC unspecified SRS4058709 VostokTent3Time12S67 Illumina MiSeq 545114 69214545 SRR8208050 545114 99804019 +SRP117119 SRX3169990 408170 human gut metagenome AMPLICON METAGENOMIC PCR SRS2500000 UMB07_09 Illumina MiSeq 284791 64753277 SRR6018546 284791 99676850
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_04.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,65 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 10 + Number of unique experiments: 16 + Number of unique runs: 16 + Number of unique samples: 16 + Mean base count of samples: 99881511.000 + Median base count of samples: 99818709.500 + Sample base count standard deviation: 285342.123 + Date range: + 2017-09: 1 + 2018-12: 1 + 2019-04: 3 + 2019-05: 1 + 2019-11: 1 + 2020-04: 1 + 2020-10: 2 + 2021-03: 1 + 2021-06: 1 + 2021-10: 1 + 2022-05: 3 + + Organisms: + Escherichia: 1 + Escherichia coli: 1 + food metagenome: 1 + gut metagenome: 3 + human gut metagenome: 2 + metagenome: 2 + pig gut metagenome: 1 + respiratory tract metagenome: 3 + skin metagenome: 1 + wastewater metagenome: 1 + + Platform: + ILLUMINA: 16 + + Library strategy: + AMPLICON: 13 + OTHER: 1 + WGA: 1 + WGS: 1 + + Library source: + METAGENOMIC: 16 + + Library selection: + PCR: 14 + RANDOM: 1 + unspecified: 1 + + Library layout: + PAIRED: 13 + SINGLE: 3 + + + Sequencing instrument: + 1 HiSeq X Ten + 3 Illumina HiSeq 4000 + 11 Illumina MiSeq + 1 NextSeq 500 + + Query keyworkds: escherichia +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_05.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,44 @@ +study_accession experiment_accession experiment_title sample_taxon_id sample_scientific_name experiment_library_strategy experiment_library_source experiment_library_selection sample_accession sample_alias experiment_instrument_model pool_member_spots run_1_size run_1_accession run_1_total_spots run_1_total_bases +SRP364041 SRX14464490 GSM5953857: MHCC97H_RNC-nanopore; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS12267183 GSM5953857 MinION 1079264 948584405 SRR18327309 1079264 1033957555 +SRP362338 SRX14360489 GSM5931556: SUP-M2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS12174011 GSM5931556 MinION 2037577 798137655 SRR18213996 2037577 924315795 +SRP362338 SRX14360488 GSM5931555: COST; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS12174010 GSM5931555 MinION 899727 338675907 SRR18213997 899727 392469322 +SRP362338 SRX14360487 GSM5931554: Karpas; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS12174009 GSM5931554 MinION 1734198 629115600 SRR18213998 1734198 726162043 +SRP362338 SRX14360486 GSM5931553: SU-DHL-1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS12174008 GSM5931553 MinION 1473477 647839329 SRR18213999 1473477 752499298 +SRP344552 SRX12970590 GSM5671082: Drug3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911457 GSM5671082 MinION 3595302 4029747451 SRR16770676 3595302 4470158434 +SRP344552 SRX12970589 GSM5671081: Drug2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911454 GSM5671081 MinION 4697490 5001236478 SRR16770675 4697490 5548374559 +SRP344552 SRX12970588 GSM5671080: Drug1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911453 GSM5671080 MinION 5082186 5461712070 SRR16770674 5082186 6059224616 +SRP344552 SRX12970587 GSM5671079: Con3; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911456 GSM5671079 MinION 3938013 4457987427 SRR16770673 3938013 4946233812 +SRP344552 SRX12970586 GSM5671078: Con2; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911455 GSM5671078 MinION 6211419 6541587648 SRR16770672 6211419 7258960045 +SRP344552 SRX12970585 GSM5671077: Con1; Homo sapiens; RNA-Seq 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS10911452 GSM5671077 MinION 4391012 5030059285 SRR16770671 4391012 5584530949 +SRP327036 SRX11355633 The cDNA reads of HT-1376 treated with IFN beta generated by Nanopore GridION long-read sequencer 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS9402525 HT1376_IFNB GridION 4131387 4053455556 SRR15045003 4131387 4462607152 +SRP327036 SRX11355632 The cDNA reads of HT-1376 generated by Nanopore GridION long-read sequencer 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS9402523 HT1376_mock GridION 5248704 4711063243 SRR15045004 5248704 5213662036 +SRP327036 SRX11355631 The cDNA reads of A549 treated with IFN beta generated by Nanopore GridION long-read sequencer 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS9402524 A549_IFNB GridION 4068179 4137656943 SRR15045005 4068179 4562233232 +SRP327036 SRX11355630 The cDNA reads of A549 generated by Nanopore GridION long-read sequencer 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS9402522 A549_mock GridION 5439422 5712690623 SRR15045006 5439422 6304165733 +DRP006784 DRX218802 MinION sequencing of SAMD00226213 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165690 SAMD00226213 MinION 3366513 2119221526 DRR228538 3366513 2773299827 +DRP006784 DRX218801 MinION sequencing of SAMD00226212 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165689 SAMD00226212 MinION 3306271 2339482009 DRR228537 3306271 3050184097 +DRP006784 DRX218800 MinION sequencing of SAMD00226211 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165688 SAMD00226211 MinION 3164764 2330757868 DRR228536 3164764 3065025046 +DRP006784 DRX218799 MinION sequencing of SAMD00226210 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165687 SAMD00226210 MinION 2527678 1876736359 DRR228535 2527678 2468871702 +DRP006784 DRX218798 MinION sequencing of SAMD00226209 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165686 SAMD00226209 MinION 4021818 4405996086 DRR228534 4021818 5482507325 +DRP006784 DRX218797 MinION sequencing of SAMD00226208 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165685 SAMD00226208 MinION 3525069 4791720545 DRR228533 3525069 6090073534 +DRP006784 DRX218796 MinION sequencing of SAMD00226207 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165684 SAMD00226207 MinION 3782177 5013672301 DRR228532 3782177 6130029268 +DRP006784 DRX218795 MinION sequencing of SAMD00226206 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165683 SAMD00226206 MinION 3796960 5722906607 DRR228531 3796960 7162516555 +DRP006784 DRX218794 MinION sequencing of SAMD00226205 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165682 SAMD00226205 MinION 3910088 4834546257 DRR228530 3910088 5957220765 +DRP006784 DRX218793 MinION sequencing of SAMD00226204 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165681 SAMD00226204 MinION 3734261 4600135570 DRR228529 3734261 5711643212 +DRP006784 DRX218792 MinION sequencing of SAMD00226203 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165680 SAMD00226203 MinION 3694667 4894141426 DRR228528 3694667 6101767665 +DRP006784 DRX218791 MinION sequencing of SAMD00226202 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165679 SAMD00226202 MinION 3248921 4589391538 DRR228527 3248921 5623410669 +DRP006784 DRX218790 MinION sequencing of SAMD00226201 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165678 SAMD00226201 MinION 4333762 5077321032 DRR228526 4333762 6303451503 +DRP006784 DRX218789 MinION sequencing of SAMD00226200 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165677 SAMD00226200 MinION 4264033 5807197866 DRR228525 4264033 7288691756 +DRP006784 DRX218788 MinION sequencing of SAMD00226199 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165676 SAMD00226199 MinION 3941718 5874313289 DRR228524 3941718 7452048411 +DRP006784 DRX218787 MinION sequencing of SAMD00226198 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165675 SAMD00226198 MinION 3778281 5002152144 DRR228523 3778281 6388850159 +DRP006784 DRX218786 MinION sequencing of SAMD00226197 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165674 SAMD00226197 MinION 4472949 5299905442 DRR228522 4472949 6535575850 +DRP006784 DRX218785 MinION sequencing of SAMD00226196 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165673 SAMD00226196 MinION 2319979 2725613781 DRR228521 2319979 3333376869 +DRP006784 DRX218784 MinION sequencing of SAMD00226195 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165672 SAMD00226195 MinION 4076481 5395052714 DRR228520 4076481 6750854750 +DRP006784 DRX218783 MinION sequencing of SAMD00226194 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165671 SAMD00226194 MinION 4427220 6549721894 DRR228519 4427220 8248195300 +DRP006784 DRX218782 MinION sequencing of SAMD00226193 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165670 SAMD00226193 MinION 2864884 4504239069 DRR228518 2864884 5773222991 +DRP006784 DRX218781 MinION sequencing of SAMD00226192 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165669 SAMD00226192 MinION 994111 1272105387 DRR228517 994111 1451773725 +DRP006784 DRX218780 MinION sequencing of SAMD00226191 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS165668 SAMD00226191 MinION 3799001 4636674066 DRR228516 3799001 5670567152 +SRP254471 SRX9103576 RNA seqencing of A375 cell line sensitive to BRAF inhibitor 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS6395584 A375 S MinION SRR12620695 +SRP254471 SRX9103575 RNA seqencing of A375 cell line resistant to BRAF inhibitor 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA SRS6395583 A375 R MinION SRR12620696 +DRP005565 DRX165666 MinION sequencing of SAMD00169379 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS138540 SAMD00169379 MinION 3164290 3676429048 DRR175098 3164290 4533271547 +DRP005565 DRX165665 MinION sequencing of SAMD00169378 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS138539 SAMD00169378 MinION 2863544 3853899018 DRR175097 2863544 4944525742 +DRP005565 DRX165664 MinION sequencing of SAMD00169377 9606 Homo sapiens RNA-Seq TRANSCRIPTOMIC cDNA DRS138538 SAMD00169377 MinION 3765322 4395067967 DRR175096 3765322 5403685814
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_05_stats.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,44 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 7 + Number of unique experiments: 43 + Number of unique runs: 43 + Number of unique samples: 43 + Mean base count of samples: 4827663312.561 + Median base count of samples: 5548374559.000 + Sample base count standard deviation: 2091645973.144 + Date range: + 2020-05: 3 + 2020-12: 23 + 2021-11: 6 + 2022-04: 2 + 2022-05: 4 + 2022-06: 1 + 2022-08: 4 + + Organisms: + Homo sapiens: 43 + + Platform: + OXFORD_NANOPORE: 43 + + Library strategy: + RNA-Seq: 43 + + Library source: + TRANSCRIPTOMIC: 43 + + Library selection: + cDNA: 43 + + Library layout: + SINGLE: 43 + + + Sequencing instrument: + 4 GridION + 39 MinION + + Query keyworkds: cancer +
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_06.tabular Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,21 @@ +study_accession experiment_accession experiment_title sample_taxon_id sample_scientific_name experiment_library_strategy experiment_library_source experiment_library_selection sample_accession sample_alias experiment_instrument_model pool_member_spots run_1_size run_1_accession run_1_total_spots run_1_total_bases experiment_alias experiment_base_coord experiment_center_name experiment_external_id experiment_library_construction_protocol experiment_library_name experiment_platform experiment_read_class experiment_read_index experiment_read_type experiment_sample_descriptor_accession experiment_sample_descriptor_refcenter experiment_sample_descriptor_refname experiment_spot_length library_layout pool_external_id pool_member_accession pool_member_bases pool_member_member_name pool_member_organism pool_member_sample_name pool_member_sample_title pool_member_tax_id run_1_alias run_1_base_A_count run_1_base_C_count run_1_base_G_count run_1_base_N_count run_1_base_T_count run_1_center_name run_1_cloudfile_1_filetype run_1_cloudfile_1_location run_1_cloudfile_1_provider run_1_cloudfile_2_filetype run_1_cloudfile_2_location run_1_cloudfile_2_provider run_1_cluster_name run_1_database_1 run_1_has_taxanalysis run_1_is_public run_1_load_done run_1_published run_1_srafile_1_alternative_1_access_type run_1_srafile_1_alternative_1_free_egress run_1_srafile_1_alternative_1_org run_1_srafile_1_alternative_1_url run_1_srafile_1_alternative_2_access_type run_1_srafile_1_alternative_2_free_egress run_1_srafile_1_alternative_2_org run_1_srafile_1_alternative_2_url run_1_srafile_1_alternative_3_access_type run_1_srafile_1_alternative_3_free_egress run_1_srafile_1_alternative_3_org run_1_srafile_1_alternative_3_url run_1_srafile_1_cluster run_1_srafile_1_date run_1_srafile_1_filename run_1_srafile_1_md5 run_1_srafile_1_semantic_name run_1_srafile_1_size run_1_srafile_1_sratoolkit run_1_srafile_1_supertype run_1_srafile_1_url run_1_static_data_available run_1_total_base_count run_1_total_base_cs_native run_set_bases run_set_bytes run_set_runs run_set_spots sample_attributes_1_tag sample_attributes_1_value sample_attributes_2_tag sample_attributes_2_value sample_attributes_3_tag sample_attributes_3_value sample_attributes_4_tag sample_attributes_4_value sample_attributes_5_tag sample_attributes_5_value sample_attributes_6_tag sample_attributes_6_value sample_description sample_external_id_1 sample_external_id_1_namespace sample_title study_alias study_center_name study_center_project_name study_external_id_1 study_external_id_1_namespace study_study_abstract study_study_title study_study_type_existing_study_type submission_accession submission_alias submission_center_name submission_lab_name +DRP008863 DRX234163 NextSeq 500 sequencing of SAMD00246673 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250781 SAMD00246673 NextSeq 500 10077080 321156005 DRR244366 10077080 841466642 DRX234163 1 CHUBU SAMD00246673 TruSeq RNA library prep kit v2 myb_Salt_r3 ILLUMINA Application Read 0 Forward DRS250781 CHUBU DRS250781 86 SINGLE SAMD00246673 DRS250781 841466642 Arabidopsis thaliana SAMD00246673 myb3r135_7DAG_24h salt treatment 3702 DRR244366 217241699 205753833 200326567 2134 218142409 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""10077080"" /><Elements count=""841466642"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244366/DRR244366 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244366/DRR244366.1 public 2022-08-10 12:33:09 DRR244366 e53a7eb58a9113079018a4305e449613 run 321157826 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244366/DRR244366 1 841466642 false 841466642 321156005 1 10077080 sample_name myb3r135_salt24h age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246673 BioSample myb3r135_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234162 NextSeq 500 sequencing of SAMD00246672 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250780 SAMD00246672 NextSeq 500 12707941 417558824 DRR244365 12707941 1061050593 DRX234162 1 CHUBU SAMD00246672 TruSeq RNA library prep kit v2 myb_Cont_r3 ILLUMINA Application Read 0 Forward DRS250780 CHUBU DRS250780 86 SINGLE SAMD00246672 DRS250780 1061050593 Arabidopsis thaliana SAMD00246672 myb3r135_7DAG_24h control treatment 3702 DRR244365 272077671 262904885 253228390 4518 272835129 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""12707941"" /><Elements count=""1061050593"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244365/DRR244365 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244365/DRR244365 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244365/DRR244365.1 public 2022-08-10 12:33:30 DRR244365 322190ad0855f3a4a4060ff3d1a41f5a run 417560652 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244365/DRR244365 1 1061050593 false 1061050593 417558824 1 12707941 sample_name myb3r135_mock age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment mock ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246672 BioSample myb3r135_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234161 NextSeq 500 sequencing of SAMD00246671 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250779 SAMD00246671 NextSeq 500 10833863 353509516 DRR244364 10833863 904596684 DRX234161 1 CHUBU SAMD00246671 TruSeq RNA library prep kit v2 Col_Salt_r3 ILLUMINA Application Read 0 Forward DRS250779 CHUBU DRS250779 86 SINGLE SAMD00246671 DRS250779 904596684 Arabidopsis thaliana SAMD00246671 Col_7DAG_24h salt treatment 3702 DRR244364 232350490 223066154 214906934 3709 234269397 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""10833863"" /><Elements count=""904596684"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244364/DRR244364 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244364/DRR244364 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244364/DRR244364.1 public 2022-08-10 12:34:37 DRR244364 2dca09477e6e5ca21d0edb28096b342b run 353511343 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244364/DRR244364 1 904596684 false 904596684 353509516 1 10833863 sample_name Col_salt24h age 8 day old genotype wild type tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia Wild type Col seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246671 BioSample Col_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234160 NextSeq 500 sequencing of SAMD00246670 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250778 SAMD00246670 NextSeq 500 15198010 496240398 DRR244363 15198010 1269137186 DRX234160 1 CHUBU SAMD00246670 TruSeq RNA library prep kit v2 Col_Cont_r3 ILLUMINA Application Read 0 Forward DRS250778 CHUBU DRS250778 86 SINGLE SAMD00246670 DRS250778 1269137186 Arabidopsis thaliana SAMD00246670 Col_7DAG_24h control treatment 3702 DRR244363 319500778 318763054 309759268 5446 321108640 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""15198010"" /><Elements count=""1269137186"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244363/DRR244363 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244363/DRR244363 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244363/DRR244363.1 public 2022-08-10 12:34:15 DRR244363 62954dc65f8f20d1091d4e493f636ee7 run 496242221 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244363/DRR244363 1 1269137186 false 1269137186 496240398 1 15198010 sample_name Col_mock age 8 day old genotype wild type tissue_type whole seedling treatment mock ecotype Columbia Wild type Col seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246670 BioSample Col_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234155 NextSeq 500 sequencing of SAMD00246673 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250781 SAMD00246673 NextSeq 500 8316950 266221232 DRR244358 8316950 694366365 DRX234155 1 CHUBU SAMD00246673 TruSeq RNA library prep kit v2 myb_Salt_r2 ILLUMINA Application Read 0 Forward DRS250781 CHUBU DRS250781 86 SINGLE SAMD00246673 DRS250781 694366365 Arabidopsis thaliana SAMD00246673 myb3r135_7DAG_24h salt treatment 3702 DRR244358 178628363 169140625 166285876 1730 180309771 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""8316950"" /><Elements count=""694366365"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244358/DRR244358 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244358/DRR244358 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244358/DRR244358.1 public 2022-08-10 12:33:52 DRR244358 144b6585d95d517844b5f2227e724f49 run 266223052 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244358/DRR244358 1 694366365 false 694366365 266221232 1 8316950 sample_name myb3r135_salt24h age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246673 BioSample myb3r135_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234154 NextSeq 500 sequencing of SAMD00246672 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250780 SAMD00246672 NextSeq 500 9237421 304819387 DRR244357 9237421 771273641 DRX234154 1 CHUBU SAMD00246672 TruSeq RNA library prep kit v2 myb_Cont_r2 ILLUMINA Application Read 0 Forward DRS250780 CHUBU DRS250780 86 SINGLE SAMD00246672 DRS250780 771273641 Arabidopsis thaliana SAMD00246672 myb3r135_7DAG_24h control treatment 3702 DRR244357 196991668 190316147 186820462 3267 197142097 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""9237421"" /><Elements count=""771273641"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244357/DRR244357 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244357/DRR244357.1 public 2022-08-10 12:33:32 DRR244357 d75cdc1c24e24453c00df2eee6e33832 run 304821209 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244357/DRR244357 1 771273641 false 771273641 304819387 1 9237421 sample_name myb3r135_mock age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment mock ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246672 BioSample myb3r135_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234153 NextSeq 500 sequencing of SAMD00246671 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250779 SAMD00246671 NextSeq 500 11552257 378668250 DRR244356 11552257 964591478 DRX234153 1 CHUBU SAMD00246671 TruSeq RNA library prep kit v2 Col_Salt_r2 ILLUMINA Application Read 0 Forward DRS250779 CHUBU DRS250779 86 SINGLE SAMD00246671 DRS250779 964591478 Arabidopsis thaliana SAMD00246671 Col_7DAG_24h salt treatment 3702 DRR244356 246840721 238746807 231296067 4233 247703650 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""11552257"" /><Elements count=""964591478"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244356/DRR244356 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244356/DRR244356 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244356/DRR244356.1 public 2022-08-10 12:34:43 DRR244356 57bbcf263b0d81399b206a6e3f010175 run 378670075 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244356/DRR244356 1 964591478 false 964591478 378668250 1 11552257 sample_name Col_salt24h age 8 day old genotype wild type tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia Wild type Col seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246671 BioSample Col_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234152 NextSeq 500 sequencing of SAMD00246670 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250778 SAMD00246670 NextSeq 500 12100266 394434917 DRR244355 12100266 1010182169 DRX234152 1 CHUBU SAMD00246670 TruSeq RNA library prep kit v2 Col_Cont_r2 ILLUMINA Application Read 0 Forward DRS250778 CHUBU DRS250778 86 SINGLE SAMD00246670 DRS250778 1010182169 Arabidopsis thaliana SAMD00246670 Col_7DAG_24h control treatment 3702 DRR244355 261049089 247945899 239968991 4319 261213871 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""12100266"" /><Elements count=""1010182169"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244355/DRR244355 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244355/DRR244355 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244355/DRR244355.1 public 2022-08-10 12:34:17 DRR244355 5c7510fdd468ef678734557b15e783dc run 394436735 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244355/DRR244355 1 1010182169 false 1010182169 394434917 1 12100266 sample_name Col_mock age 8 day old genotype wild type tissue_type whole seedling treatment mock ecotype Columbia Wild type Col seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246670 BioSample Col_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234147 NextSeq 500 sequencing of SAMD00246673 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250781 SAMD00246673 NextSeq 500 10997702 351845201 DRR244350 10997702 918306581 DRX234147 1 CHUBU SAMD00246673 TruSeq RNA library prep kit v2 myb_Salt_r1 ILLUMINA Application Read 0 Forward DRS250781 CHUBU DRS250781 86 SINGLE SAMD00246673 DRS250781 918306581 Arabidopsis thaliana SAMD00246673 myb3r135_7DAG_24h salt treatment 3702 DRR244350 236270140 225720983 218070765 2310 238242383 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""10997702"" /><Elements count=""918306581"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244350/DRR244350 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244350/DRR244350 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244350/DRR244350.1 public 2022-08-10 12:33:19 DRR244350 c90cca7fc022c2934d07262d4bf690bd run 351847021 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244350/DRR244350 1 918306581 false 918306581 351845201 1 10997702 sample_name myb3r135_salt24h age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246673 BioSample myb3r135_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234146 NextSeq 500 sequencing of SAMD00246672 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250780 SAMD00246672 NextSeq 500 12921662 427189150 DRR244349 12921662 1078936294 DRX234146 1 CHUBU SAMD00246672 TruSeq RNA library prep kit v2 myb_Cont_r1 ILLUMINA Application Read 0 Forward DRS250780 CHUBU DRS250780 86 SINGLE SAMD00246672 DRS250780 1078936294 Arabidopsis thaliana SAMD00246672 myb3r135_7DAG_24h control treatment 3702 DRR244349 278515666 265806252 254431285 4443 280178648 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""12921662"" /><Elements count=""1078936294"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244349/DRR244349 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244349/DRR244349 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244349/DRR244349.1 public 2022-08-10 12:33:53 DRR244349 ec73564e4e4766c2540b267cd27f010d run 427190973 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244349/DRR244349 1 1078936294 false 1078936294 427189150 1 12921662 sample_name myb3r135_mock age 8 day old genotype myb3r1 myb3r3 myb3r3 triple mutant tissue_type whole seedling treatment mock ecotype Columbia myb3r1 myb3r3 myb3r5 seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246672 BioSample myb3r135_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234145 NextSeq 500 sequencing of SAMD00246671 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250779 SAMD00246671 NextSeq 500 12585531 415962802 DRR244348 12585531 1051121271 DRX234145 1 CHUBU SAMD00246671 TruSeq RNA library prep kit v2 Col_Salt_r1 ILLUMINA Application Read 0 Forward DRS250779 CHUBU DRS250779 86 SINGLE SAMD00246671 DRS250779 1051121271 Arabidopsis thaliana SAMD00246671 Col_7DAG_24h salt treatment 3702 DRR244348 262635693 266188310 257327118 4369 264965781 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""12585531"" /><Elements count=""1051121271"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244348/DRR244348 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244348/DRR244348 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244348/DRR244348.1 public 2022-08-10 12:34:44 DRR244348 659efbf7f61872ac6efc1a5cf8bde88f run 415964627 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244348/DRR244348 1 1051121271 false 1051121271 415962802 1 12585531 sample_name Col_salt24h age 8 day old genotype wild type tissue_type whole seedling treatment 150 mM NaCl for 24 hours ecotype Columbia Wild type Col seedlings were treated with 150 mM NaCl for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246671 BioSample Col_7DAG_24h salt treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008863 DRX234144 NextSeq 500 sequencing of SAMD00246670 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS250778 SAMD00246670 NextSeq 500 12814785 418969197 DRR244347 12814785 1070030618 DRX234144 1 CHUBU SAMD00246670 TruSeq RNA library prep kit v2 Col_Cont_r1 ILLUMINA Application Read 0 Forward DRS250778 CHUBU DRS250778 86 SINGLE SAMD00246670 DRS250778 1070030618 Arabidopsis thaliana SAMD00246670 Col_7DAG_24h control treatment 3702 DRR244347 276562745 262362352 253056511 5393 278043617 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""12814785"" /><Elements count=""1070030618"" /></Statistics></Table></Database>" 1 true true 2022-08-10 12:31:34 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244347/DRR244347 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244347/DRR244347 gcp identity gs.US GCP gs://sra-pub-run-2/sra/DRR244347/DRR244347.1 public 2022-08-10 12:34:53 DRR244347 2404780abb312680ae9bfcc4bb7c6b02 run 418971020 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR244347/DRR244347 1 1070030618 false 1070030618 418969197 1 12814785 sample_name Col_mock age 8 day old genotype wild type tissue_type whole seedling treatment mock ecotype Columbia Wild type Col seedlings were mock-treated for 24 hours after grwon for 7 days on half-strength MS medium containing 2% sucrose under continuous light condition SAMD00246670 BioSample Col_7DAG_24h control treatment DRP008863 CHUBU Arabidopsis thaliana PRJDB10553 BioProject Three MYB3R proteins, MYB3R1, MYB3R3 and MYB3R5, are responsible for transcriptional repression of G2/M-specific genes to maintain their proper expression levels during cell cycle and plant development. Importantly, MYB3R repressors were found to be required for active growth repression under salt stress conditions. To understand the mechanisms of the MYB3R-mediated growth repression under salt stress, transcriptome analysis was performed for Arabidopsis seedlings treated with high concentration of NaCl continuously or transiently. Roles of MYB3R repressors for gene expression changes under salt stress Other DRA010790 DRA010790 CHUBU Chubu University +DRP008429 DRX218758 NextSeq 500 sequencing of SAMD00227985 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235491 SAMD00227985 NextSeq 500 11647755 416563035 DRR228494 11647755 1001706915 DRX218758 1 CHUBU SAMD00227985 NEBNext Ultra DNA Library Prep Kit for Illumina WT_12_3 ILLUMINA Application Read 0 Forward DRS235491 CHUBU DRS235491 86 SINGLE SAMD00227985 DRS235491 1001706915 Arabidopsis thaliana SAMD00227985 WT_12 3702 DRR228494 263477176 240385788 238894690 2782 258946479 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""11647755"" /><Elements count=""1001706915"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:14 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228494/DRR228494 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228494/DRR228494 gcp identity gs.US GCP gs://sra-pub-run-9/DRR228494/DRR228494.1 public 2022-04-12 12:22:24 DRR228494 df1c218fb5016da9e2b40e598afa27c1 run 416564858 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228494/DRR228494 1 1001706915 false 1001706915 416563035 1 11647755 sample_name WT_12 age 14-day-old cold_stress_hours 12 collection_date 2019-06-24 genotype wild type tissue_type whole seedlings WT (Col-0) plants under the cold stress conditions for 12 hour from ZT2 SAMD00227985 BioSample WT_12 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218757 NextSeq 500 sequencing of SAMD00227984 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235490 SAMD00227984 NextSeq 500 11660980 393314912 DRR228493 11660980 1002844280 DRX218757 1 CHUBU SAMD00227984 NEBNext Ultra DNA Library Prep Kit for Illumina WT_3_3 ILLUMINA Application Read 0 Forward DRS235490 CHUBU DRS235490 86 SINGLE SAMD00227984 DRS235490 1002844280 Arabidopsis thaliana SAMD00227984 WT_3 3702 DRR228493 276494020 229709012 226372617 3566 270265065 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""11660980"" /><Elements count=""1002844280"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:14 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228493/DRR228493 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228493/DRR228493 gcp identity gs.US GCP gs://sra-pub-run-12/DRR228493/DRR228493.1 public 2022-04-12 12:21:46 DRR228493 7026f03462bd4be539d8b883238a201d run 393316143 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228493/DRR228493 1 1002844280 false 1002844280 393314912 1 11660980 sample_name WT_3 age 14-day-old cold_stress_hours 3 collection_date 2019-06-24 genotype wild type tissue_type whole seedlings WT (Col-0) plants under the cold stress conditions for 3 hour from ZT2 SAMD00227984 BioSample WT_3 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218756 NextSeq 500 sequencing of SAMD00227983 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235489 SAMD00227983 NextSeq 500 13273886 446774784 DRR228492 13273886 1141554196 DRX218756 1 CHUBU SAMD00227983 NEBNext Ultra DNA Library Prep Kit for Illumina WT_0_3 ILLUMINA Application Read 0 Forward DRS235489 CHUBU DRS235489 86 SINGLE SAMD00227983 DRS235489 1141554196 Arabidopsis thaliana SAMD00227983 WT_0 3702 DRR228492 314772649 261248885 257960596 4002 307568064 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""13273886"" /><Elements count=""1141554196"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:14 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228492/DRR228492 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228492/DRR228492 gcp identity gs.US GCP gs://sra-pub-run-2/DRR228492/DRR228492.1 public 2022-04-12 12:22:55 DRR228492 353f78b468cdcdd42e512acf1f421059 run 446776014 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228492/DRR228492 1 1141554196 false 1141554196 446774784 1 13273886 sample_name WT_0 age 14-day-old cold_stress_hours 0 collection_date 2019-06-24 genotype wild type tissue_type whole seedlings WT (Col-0) plants under the normal growth conditions at 2 hour after dawn (ZT2) SAMD00227983 BioSample WT_0 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218755 NextSeq 500 sequencing of SAMD00227982 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235488 SAMD00227982 NextSeq 500 8875819 320965496 DRR228491 8875819 763320418 DRX218755 1 CHUBU SAMD00227982 NEBNext Ultra DNA Library Prep Kit for Illumina r48_12_3 ILLUMINA Application Read 0 Forward DRS235488 CHUBU DRS235488 86 SINGLE SAMD00227982 DRS235488 763320418 Arabidopsis thaliana SAMD00227982 rve48_12 3702 DRR228491 210592983 174401463 173312581 1974 205011417 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""8875819"" /><Elements count=""763320418"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:14 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228491/DRR228491 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228491/DRR228491 gcp identity gs.US GCP gs://sra-pub-run-3/DRR228491/DRR228491.1 public 2022-04-12 12:21:09 DRR228491 73aeb463276c206aa41f12add4dac462 run 320967316 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228491/DRR228491 1 763320418 false 763320418 320965496 1 8875819 sample_name r48_12 age 14-day-old cold_stress_hours 12 collection_date 2019-06-24 genotype rve4 rve8 tissue_type whole seedlings rve4 rve8 mutant plants under the cold stress conditions for 12 hour from ZT2 SAMD00227982 BioSample rve48_12 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218754 NextSeq 500 sequencing of SAMD00227981 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235487 SAMD00227981 NextSeq 500 15165885 502400983 DRR228490 15165885 1304266110 DRX218754 1 CHUBU SAMD00227981 NEBNext Ultra DNA Library Prep Kit for Illumina r48_3_3 ILLUMINA Application Read 0 Forward DRS235487 CHUBU DRS235487 86 SINGLE SAMD00227981 DRS235487 1304266110 Arabidopsis thaliana SAMD00227981 rve48_3 3702 DRR228490 359176604 297760568 295069565 4766 352254607 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""15165885"" /><Elements count=""1304266110"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:14 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228490/DRR228490 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228490/DRR228490 gcp identity gs.US GCP gs://sra-pub-run-3/DRR228490/DRR228490.1 public 2022-04-12 12:21:14 DRR228490 8d53cbdb5ca069810a1e4c2af83b9c3c run 502402216 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228490/DRR228490 1 1304266110 false 1304266110 502400983 1 15165885 sample_name r48_3 age 14-day-old cold_stress_hours 3 collection_date 2019-06-24 genotype rve4 rve8 tissue_type whole seedlings rve4 rve8 mutant plants under the cold stress conditions for 3 hour from ZT2 SAMD00227981 BioSample rve48_3 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218753 NextSeq 500 sequencing of SAMD00227980 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235486 SAMD00227980 NextSeq 500 15187212 501850106 DRR228489 15187212 1306100232 DRX218753 1 CHUBU SAMD00227980 NEBNext Ultra DNA Library Prep Kit for Illumina r48_0_3 ILLUMINA Application Read 0 Forward DRS235486 CHUBU DRS235486 86 SINGLE SAMD00227980 DRS235486 1306100232 Arabidopsis thaliana SAMD00227980 rve48_0 3702 DRR228489 358607812 298955729 297427715 4774 351104202 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""15187212"" /><Elements count=""1306100232"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:24:40 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228489/DRR228489 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228489/DRR228489 gcp identity gs.US GCP gs://sra-pub-run-5/DRR228489/DRR228489.1 public 2022-04-12 12:22:11 DRR228489 660d223a0a0a89d1c8c21dec834162fe run 501851337 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228489/DRR228489 1 1306100232 false 1306100232 501850106 1 15187212 sample_name r48_0 age 14-day-old cold_stress_hours 0 collection_date 2019-06-24 genotype rve4 rve8 tissue_type whole seedlings rve4 rve8 mutant plants under the normal growth conditions at 2 hour after dawn (ZT2) SAMD00227980 BioSample rve48_0 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218752 NextSeq 500 sequencing of SAMD00227979 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235485 SAMD00227979 NextSeq 500 13006006 464544238 DRR228488 13006006 1118516489 DRX218752 1 CHUBU SAMD00227979 NEBNext Ultra DNA Library Prep Kit for Illumina Clr48_12_3 ILLUMINA Application Read 0 Forward DRS235485 CHUBU DRS235485 86 SINGLE SAMD00227979 DRS235485 1118516489 Arabidopsis thaliana SAMD00227979 quad_12 3702 DRR228488 291308300 271620363 269869779 3179 285714868 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""13006006"" /><Elements count=""1118516489"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:13 anonymous worldwide NCBI https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228488/DRR228488 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228488/DRR228488 gcp identity gs.US GCP gs://sra-pub-run-10/DRR228488/DRR228488.1 public 2022-04-12 12:22:16 DRR228488 c4535e1ae353ca7b702c218f5dee501a run 464546063 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228488/DRR228488 1 1118516489 false 1118516489 464544238 1 13006006 sample_name Clr48_12 age 14-day-old cold_stress_hours 12 collection_date 2019-06-24 genotype cca1 lhy rve4 rve8 tissue_type whole seedlings cca1 lhy rve4 rve8 mutant plants under the cold stress conditions for 12 hour from ZT2 SAMD00227979 BioSample quad_12 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University +DRP008429 DRX218751 NextSeq 500 sequencing of SAMD00227978 3702 Arabidopsis thaliana RNA-Seq TRANSCRIPTOMIC RANDOM DRS235484 SAMD00227978 NextSeq 500 11941593 416101311 DRR228487 11941593 1003093742 DRX218751 1 CHUBU SAMD00227978 NEBNext Ultra DNA Library Prep Kit for Illumina Clr48_3_3 ILLUMINA Application Read 0 Forward DRS235484 CHUBU DRS235484 86 SINGLE SAMD00227978 DRS235484 1003093742 Arabidopsis thaliana SAMD00227978 quad_3 3702 DRR228487 274672358 229405455 229040046 3169 269972714 CHUBU run gs.US gs run s3.us-east-1 s3 public "<Database><Table name=""SEQUENCE""><Statistics source=""meta""><Rows count=""11941593"" /><Elements count=""1003093742"" /></Statistics></Table></Database>" 1 true true 2022-04-12 12:22:13 anonymous worldwide AWS https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228487/DRR228487 gcp identity gs.US GCP gs://sra-pub-run-7/DRR228487/DRR228487.1 public 2022-04-12 12:22:39 DRR228487 00d3b8388e7320bd796e17ebb0d6e993 run 416103140 1 Primary ETL https://sra-pub-run-odp.s3.amazonaws.com/sra/DRR228487/DRR228487 1 1003093742 false 1003093742 416101311 1 11941593 sample_name Clr48_3 age 14-day-old cold_stress_hours 3 collection_date 2019-06-24 genotype cca1 lhy rve4 rve8 tissue_type whole seedlings cca1 lhy rve4 rve8 mutant plants under the cold stress conditions for 3 hour from ZT2 SAMD00227978 BioSample quad_3 DRP008429 CHUBU Arabidopsis thaliana PRJDB9852 BioProject It was reported that CCA1 and LHY positively regulated the gene expression of DREB1A and DREB1C. In addition, we revealed that RVE4 and RVE8 directly activated the cold-inducible DREB1A expression. The cca1 lhy double mutant, rve4 rve8 double mutant (rve48), and cca1 lhy rve4 rve8 quadruple mutant (quad) plants were sensitive to the freezing stress. In order to comprehensively analyze downstream genes of RVE4/RVE8 and CCA1/LHY in the cold response, we conducted RNA sequence analyses. We used 14-day-old whole seedlings of wild type (Col-0), cca1 lhy, rve48 and quad mutant plants grown on GM agar plates under the normal growth conditions at ZT2 (2 h after dawn) and the cold stress conditions treated at 4°C for 3 h and 12 h. We have three biological replicates for this analysis. RNAseq analyses of the multiple mutant plants of CCA1/LHY and RVE4/RVE8 under cold stresses Transcriptome Analysis DRA010211 DRA010211 CHUBU Chubu University
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/test_06_stats.txt Fri Nov 11 07:35:39 2022 +0000 @@ -0,0 +1,38 @@ + + Statistics for the search query: + ================================= + Number of unique studies: 2 + Number of unique experiments: 20 + Number of unique runs: 20 + Number of unique samples: 12 + Mean base count of samples: 1013823095.200 + Median base count of samples: 1006637955.500 + Sample base count standard deviation: 170213388.613 + Date range: + 2022-04: 8 + 2022-08: 12 + + Organisms: + Arabidopsis thaliana: 20 + + Platform: + ILLUMINA: 20 + + Library strategy: + RNA-Seq: 20 + + Library source: + TRANSCRIPTOMIC: 20 + + Library selection: + RANDOM: 20 + + Library layout: + SINGLE: 20 + + + Sequencing instrument: + 20 NextSeq 500 + + Query keyworkds: stress +