IsoSeq Clustering (Refine + Cluster)
Clustering: DBA K7-50pM (individual)
Type
CWL
Status
succeeded
Engine
cwltool
Duration
0.2 h
Source Data
Pipeline
PacBio CCS (Subreads → HiFi)
IsoSeq Clustering (Refine + Cluster)
Run #82
(this run)
succeeded
1 sources
IsoSeq Annotation (Map + Collapse + SQANTI3)
Functional Annotation (TransDecoder + Pfam + SwissProt)
Combined From
- #77 — PacBio CCS (Subreads → HiFi) succeeded
Workflow
IsoSeq Clustering (Refine + Cluster)
#cwl
Software Tools
| Tool | Version | URL |
|---|---|---|
| cwltool | - | https://github.com/common-workflow-language/cwltool |
Results Summary
Input CCS Reads
167,774
FLNC Reads
164,772
Mean FLNC Length
0 nt
HQ Isoforms
0
LQ Isoforms
0
Clustering Ratio
0.0
FLNC / HQ isoforms
Mean FL Support
6.9
reads per isoform
Total FL Reads
112,079
Output Files
Provenance
| Execution | Expression quantification summary |
| Completed | 2026-03-04T12:46:43+00:00 |
RO-Crate 1.1
Workflow RO-Crate 1.0
FAIR
This analysis is packaged as a Research Object Crate
with machine-readable provenance and FAIR metadata.
RO-Crate Metadata (JSON-LD)
Show/hide raw JSON-LD
{
"@context": "https://w3id.org/ro/crate/1.1/context",
"@graph": [
{
"@id": "ro-crate-metadata.json",
"@type": "CreativeWork",
"about": {
"@id": "./"
},
"conformsTo": [
{
"@id": "https://w3id.org/ro/crate/1.1"
},
{
"@id": "https://w3id.org/workflowhub/workflow-ro-crate/1.0"
}
]
},
{
"@id": "./",
"@type": "Dataset",
"name": "IsoSeq Clustering (Refine + Cluster) \u2014 Run #82",
"description": "Generic IsoSeq3 clustering pipeline. Merges demultiplexed BAMs, runs primer removal + polyA filtering (refine), then clusters into HQ/LQ isoform consensus sequences. Compatible with Sequel I CCS (use_qvs=false) and Sequel II/IIe HiFi data.",
"datePublished": "2026-03-04",
"license": {
"@id": "https://creativecommons.org/licenses/by/4.0/"
},
"mainEntity": {
"@id": "isoseq_clustering.cwl"
},
"hasPart": [
{
"@id": "isoseq_clustering.cwl"
},
{
"@id": "job.yml"
},
{
"@id": "clustered.hq.bam"
},
{
"@id": "clustered.lq.bam"
},
{
"@id": "clustered.cluster_report.csv"
},
{
"@id": "clustered.cluster"
},
{
"@id": "flnc.filter_summary.report.json"
},
{
"@id": "flnc.bam"
},
{
"@id": "clustered.hq.bam.pbi"
},
{
"@id": "demux_primers.lima.summary"
},
{
"@id": "flnc.bam.pbi"
},
{
"@id": "clustered.lq.bam.pbi"
},
{
"@id": "results_summary.json"
},
{
"@id": "summary_extractor.py"
}
],
"mentions": [
{
"@id": "#execution"
},
{
"@id": "#summary-extraction"
}
]
},
{
"@id": "isoseq_clustering.cwl",
"@type": [
"File",
"SoftwareSourceCode",
"ComputationalWorkflow"
],
"name": "IsoSeq Clustering (Refine + Cluster)",
"description": "#cwl",
"programmingLanguage": {
"@id": "Generic IsoSeq3 clustering pipeline. Merges demultiplexed BAMs, runs primer removal + polyA filtering (refine), then clusters into HQ/LQ isoform consensus sequences. Compatible with Sequel I CCS (use_qvs=false) and Sequel II/IIe HiFi data."
},
"contentSize": "2.9 KB",
"sha256": "3cd8cfcc8caaf0fb4a964a16fc02edffbddb048e0c46b8c633c8fd3abf7efa08"
},
{
"@id": "#cwl",
"@type": "ComputerLanguage",
"name": "Common Workflow Language",
"url": {
"@id": "https://www.commonwl.org/"
},
"version": "1.2"
},
{
"@id": "#cwltool",
"@type": "SoftwareApplication",
"name": "cwltool",
"url": {
"@id": "https://github.com/common-workflow-language/cwltool"
}
},
{
"@id": "job.yml",
"@type": "File",
"name": "job.yml",
"description": "CWL job input parameters",
"encodingFormat": "text/yaml",
"contentSize": "278 B",
"sha256": "69e2f2ff5a33dfdc0d9c554e2f8615a1e32618f9cc212758c9e3b82d6c3d3436"
},
{
"@id": "clustered.hq.bam",
"@type": "File",
"name": "clustered.hq.bam",
"encodingFormat": "application/octet-stream",
"contentSize": "13.9 MB",
"sha256": "e49d0b287795526ea61900234d5196c312712fe00066ac34dc61d2e077b1509d"
},
{
"@id": "clustered.lq.bam",
"@type": "File",
"name": "clustered.lq.bam",
"encodingFormat": "application/octet-stream",
"contentSize": "627 B",
"sha256": "aac4621266275d925395adac4b2454a125e0c9ea3373fb37448d8d646d53b1c3"
},
{
"@id": "clustered.cluster_report.csv",
"@type": "File",
"name": "clustered.cluster_report.csv",
"encodingFormat": "text/csv",
"contentSize": "5.7 MB",
"sha256": "34479939ca91c7636ff684f5a82caeba3b47d870003b75198be045315ac97efc"
},
{
"@id": "clustered.cluster",
"@type": "File",
"name": "clustered.cluster",
"encodingFormat": "application/octet-stream",
"contentSize": "7.3 MB",
"sha256": "f0fb2dc205f3949a25f24802398ce52ce4ffe840b89c4056c43b9a0d842f457c"
},
{
"@id": "flnc.filter_summary.report.json",
"@type": "File",
"name": "flnc.filter_summary.report.json",
"encodingFormat": "application/json",
"contentSize": "819 B",
"sha256": "1ab7091f55e3c6c1e03f784eb909e3ee1efb9757d9b792a7f3990f93d8d486c0"
},
{
"@id": "flnc.bam",
"@type": "File",
"name": "flnc.bam",
"encodingFormat": "application/octet-stream",
"contentSize": "376.9 MB",
"sha256": "5c4d24c36d51a9b23012a4112ec702db7a8ab133f76f1d2d899b6f2b6031f6ba"
},
{
"@id": "clustered.hq.bam.pbi",
"@type": "File",
"name": "clustered.hq.bam.pbi",
"encodingFormat": "application/octet-stream",
"contentSize": "91.6 KB",
"sha256": "9fc0b1e4d4b263e2ca812c23b92b9e557eccc46b94e883dbb1625c62017caf92"
},
{
"@id": "demux_primers.lima.summary",
"@type": "File",
"name": "demux_primers.lima.summary",
"encodingFormat": "application/octet-stream",
"contentSize": "917 B",
"sha256": "4e43242dfa8e82c8eb7a84bc86d16fb3cb6890c36ce042122f1f6b7c7fa81c38"
},
{
"@id": "flnc.bam.pbi",
"@type": "File",
"name": "flnc.bam.pbi",
"encodingFormat": "application/octet-stream",
"contentSize": "1.7 MB",
"sha256": "65f2ed9cf61c9544c47fc4a773a389c394107b5dba4574e9598281f71c627f52"
},
{
"@id": "clustered.lq.bam.pbi",
"@type": "File",
"name": "clustered.lq.bam.pbi",
"encodingFormat": "application/octet-stream",
"contentSize": "65 B",
"sha256": "0898b440b5d691c4384b9cadaf7b007cfb06b947826234896416987b491df3ad"
},
{
"@id": "#execution",
"@type": "CreateAction",
"name": "IsoSeq Clustering (Refine + Cluster) execution",
"instrument": {
"@id": "isoseq_clustering.cwl"
},
"startTime": "2026-03-04T22:32:28+00:00",
"endTime": "2026-03-04T12:46:28+00:00",
"object": [
{
"@id": "job.yml"
}
],
"result": [
{
"@id": "clustered.hq.bam"
},
{
"@id": "clustered.lq.bam"
},
{
"@id": "clustered.cluster_report.csv"
},
{
"@id": "clustered.cluster"
},
{
"@id": "flnc.filter_summary.report.json"
},
{
"@id": "flnc.bam"
},
{
"@id": "clustered.hq.bam.pbi"
},
{
"@id": "demux_primers.lima.summary"
},
{
"@id": "flnc.bam.pbi"
},
{
"@id": "clustered.lq.bam.pbi"
}
]
},
{
"@id": "results_summary.json",
"@type": "File",
"name": "results_summary.json",
"description": "Derived summary statistics from pipeline outputs (CPM >= 1, uniquely mapped reads)",
"encodingFormat": "application/json",
"contentSize": "277 B",
"sha256": "4a3001e70ed7f867da3269d0edbebd400b3c1e278876182eff4c9f44eb64d7b9"
},
{
"@id": "summary_extractor.py",
"@type": [
"File",
"SoftwareSourceCode"
],
"name": "Summary extraction script",
"description": "Python script that computed results_summary.json from pipeline outputs",
"programmingLanguage": {
"@id": "#python3"
}
},
{
"@id": "#python3",
"@type": "ComputerLanguage",
"name": "Python",
"url": {
"@id": "https://www.python.org/"
},
"version": "3"
},
{
"@id": "#summary-extraction",
"@type": "CreateAction",
"name": "Expression quantification summary",
"instrument": {
"@id": "summary_extractor.py"
},
"endTime": "2026-03-04T12:46:43+00:00",
"object": [
{
"@id": "OUT.read_assignments.tsv.gz"
},
{
"@id": "OUT.gene_counts.tsv"
},
{
"@id": "OUT.transcript_counts.tsv"
},
{
"@id": "OUT.extended_annotation.gtf"
},
{
"@id": "OUT.transcript_models.gtf"
}
],
"result": [
{
"@id": "results_summary.json"
}
]
}
]
}