Merge pull request #18 from AlexsLemonade/jashapiro/alevin-benchmark

Initial alevin benchmarking result
AlexsLemonade · Sep 9, 2020 · d85b6b5 · d85b6b5
2 parents 0ba7895 + 7a321cf
commit d85b6b5
Show file tree

Hide file tree

Showing 5 changed files with 2,156 additions and 0 deletions.
diff --git a/workflows/alevin-quant/alevin-benchmark-indexes.nf b/workflows/alevin-quant/alevin-benchmark-indexes.nf
@@ -0,0 +1,72 @@
+#!/usr/bin/env nextflow
+nextflow.enable.dsl=2
+
+// run parameters
+params.sample_dir = 's3://ccdl-scpca-data/raw/green_adam'
+params.sample_ids = "834,905_3" //comma separated list to be parsed into a list
+params.outdir = 's3://nextflow-ccdl-results/scpca-benchmark/alevin-quant'
+
+process alevin{
+  container 'quay.io/biocontainers/salmon:1.3.0--hf69c8f4_0'
+  cpus 8
+  // try dynamic memory (28.GB so 2x will fit in r4.2xlarge)
+  memory { 28.GB * task.attempt}
+  errorStrategy { task.exitStatus in 137..140 ? 'retry' : 'terminate' }
+  maxRetries 1
+  tag "${sample_id}-${index_id}"
+  publishDir "${params.outdir}"
+  input:
+    tuple val(sample_id), path(read1), path(read2), val(index_id), path(index), path(tx2gene)
+  output:
+    path "${sample_id}-${index_id}"
+  script:
+    """
+    salmon alevin \
+      -l ISR \
+      --chromium \
+      -1 ${read1} \
+      -2 ${read2} \
+      -i ${index} \
+      --tgMap ${tx2gene} \
+      -o ${sample_id}-${index_id} \
+      -p ${task.cpus} \
+      --dumpFeatures \
+    """
+}
+
+workflow{
+  sample_ids = params.sample_ids?.tokenize(',') ?: []
+  ch_reads = Channel.fromList(sample_ids)
+    // create tuple of [sample_id, [Read1 files], [Read2 files]]
+    .map{ id -> tuple("$id",
+                      file("${params.sample_dir}/${id}/*_R1_*.fastq.gz"),
+                      file("${params.sample_dir}/${id}/*_R2_*.fastq.gz"),
+                      )}
+  ch_indexes = Channel.fromList([
+    ['cdna_k31_no_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/cdna_k31',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['cdna_k23_no_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/cdna_k23',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['txome_k31_no_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/txome_k31',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['txome_k23_no_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/txome_k23',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['cdna_k31_full_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/cdna_k31_full_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['txome_k31_full_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/salmon_index/txome_k31_full_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/ensembl-100/annotation/Homo_sapiens.ensembl.100.tx2gene.tsv'],
+    ['cdna_k31_partial_sa',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/refgenomes-hg38/salmon_partial_sa_index',
+     's3://nextflow-ccdl-data/reference/homo_sapiens/refgenomes-hg38/annotation/Homo_sapiens.ensembl.97.tx2gene.tsv'],
+  ])
+  ch_testset = ch_reads.combine(ch_indexes)
+
+  // run Alevin
+  alevin(ch_testset)
+}
diff --git a/workflows/alevin-quant/alevin-benchmark_2020-08-31.html b/workflows/alevin-quant/alevin-benchmark_2020-08-31.html
diff --git a/workflows/alevin-quant/alevin-benchmark_2020-09-08.html b/workflows/alevin-quant/alevin-benchmark_2020-09-08.html
diff --git a/workflows/alevin-quant/trace_2020-08-31.txt b/workflows/alevin-quant/trace_2020-08-31.txt
@@ -0,0 +1,13 @@
+task_id	hash	native_id	name	status	exit	submit	duration	realtime	%cpu	peak_rss	peak_vmem	rchar	wchar
+7	2a/19fe3a	090ebaa5-66e2-48f4-8959-beea91bc23f7	alevin (905_3-cdna_k31_no_sa)	COMPLETED	0	2020-08-31 20:43:48.958	59m 30s	33m 1s	529.4%	1.9 GB	3 GB	28.4 GB	58.3 MB
+9	a8/0a2a33	91899763-c8dd-4e55-9662-1b4215a2cefc	alevin (905_3-txome_k31_no_sa)	COMPLETED	0	2020-08-31 20:43:49.094	1h 29s	34m 19s	535.4%	2.2 GB	3 GB	28.6 GB	59.3 MB
+12	83/708fcd	2b86c8b5-7469-47ec-bef5-f72939bdd699	alevin (905_3-cdna_k31_full_sa)	COMPLETED	0	2020-08-31 20:43:49.239	1h 5m 51s	37m 59s	528.9%	18 GB	21.5 GB	44.3 GB	58.2 MB
+11	02/7fbd19	f766e8e5-ab4d-4a15-8624-7ffb3fa0b47a	alevin (905_3-cdna_k31_partial_sa)	COMPLETED	0	2020-08-31 20:43:49.217	1h 8m 21s	42m 54s	551.5%	2.3 GB	3.4 GB	28.7 GB	58.3 MB
+8	6d/289107	cb4c2738-05cd-4ea5-abda-fb5ddc30fb78	alevin (905_3-cdna_k23_no_sa)	COMPLETED	0	2020-08-31 20:43:48.905	1h 13m 31s	48m 55s	557.8%	2.1 GB	3.1 GB	28.4 GB	58.3 MB
+1	68/9634ca	c0e7c168-179a-4cdb-9ac4-2d81bf94b92b	alevin (834-cdna_k31_no_sa)	COMPLETED	0	2020-08-31 20:43:48.712	1h 14m 20s	1h 4m 57s	564.3%	3 GB	4.2 GB	30.6 GB	68.1 MB
+10	4b/088f05	5819be1a-a843-407f-a378-6531101524f2	alevin (905_3-txome_k23_no_sa)	COMPLETED	0	2020-08-31 20:43:49.215	1h 14m 20s	50m 31s	557.6%	2.4 GB	3.4 GB	28.6 GB	59.3 MB
+4	9f/d04d76	47802779-1c74-491f-8565-35472f2d4956	alevin (834-txome_k31_no_sa)	COMPLETED	0	2020-08-31 20:43:48.747	1h 32m 42s	1h 10m 18s	565.2%	3.4 GB	4.4 GB	30.8 GB	70.5 MB
+6	e3/e71cf9	2a27a3a6-ef4a-4317-a4c4-db396f693d2c	alevin (834-cdna_k31_full_sa)	COMPLETED	0	2020-08-31 20:43:48.793	1h 39m 11s	1h 13m 36s	571.3%	19.1 GB	22.6 GB	46.5 GB	67.4 MB
+5	17/3adaca	72b2bcc5-50ab-4124-82e6-90e20e3de94a	alevin (834-cdna_k31_partial_sa)	COMPLETED	0	2020-08-31 20:43:48.763	1h 47m 2s	1h 33m 33s	579.3%	3.4 GB	4.7 GB	30.9 GB	67.9 MB
+2	8a/7e105e	6b1a6262-f0ee-4167-ab1d-50b41c120b6e	alevin (834-cdna_k23_no_sa)	COMPLETED	0	2020-08-31 20:43:48.700	1h 55m 33s	1h 40m 12s	581.0%	3.2 GB	4.6 GB	30.6 GB	68.1 MB
+3	70/d5ef01	3a8978af-c569-4e57-814f-e8b0e3cb0fb4	alevin (834-txome_k23_no_sa)	COMPLETED	0	2020-08-31 20:43:48.704	1h 59m 42s	1h 48m 22s	581.9%	3.7 GB	4.8 GB	30.8 GB	70.5 MB
diff --git a/workflows/alevin-quant/trace_2020-09-08.txt b/workflows/alevin-quant/trace_2020-09-08.txt
@@ -0,0 +1,15 @@
+task_id	hash	native_id	name	status	exit	submit	duration	realtime	%cpu	peak_rss	peak_vmem	rchar	wchar
+8	d3/042daa	259bbc02-3968-4c6f-9f2c-87268d918cde	alevin (905_3-cdna_k31_no_sa)	COMPLETED	0	2020-09-08 09:37:15.527	37m 8s	31m 52s	531.1%	1.9 GB	3 GB	28.4 GB	58.3 MB
+10	39/a3e171	e62ed318-8c84-48f3-bc7d-9e018fe20953	alevin (905_3-txome_k31_no_sa)	COMPLETED	0	2020-09-08 09:37:15.647	39m 19s	34m 9s	531.7%	2.2 GB	3 GB	28.6 GB	59.3 MB
+12	5e/c7a87a	01ce0572-5e46-4c56-a33a-2f7bc3a36780	alevin (905_3-cdna_k31_full_sa)	COMPLETED	0	2020-09-08 09:37:15.827	46m 58s	39m 9s	524.9%	18 GB	21.5 GB	44.3 GB	58.2 MB
+13	5d/f7d2d8	f161ff12-90ea-4c26-847d-6e48e9efba7d	alevin (905_3-txome_k31_full_sa)	COMPLETED	0	2020-09-08 09:37:15.909	47m 38s	39m 13s	522.4%	18.1 GB	26.5 GB	44.4 GB	59.1 MB
+14	8a/8bdfec	11347032-537f-44a1-a562-074d16a2d0d9	alevin (905_3-cdna_k31_partial_sa)	COMPLETED	0	2020-09-08 09:37:16.074	47m 57s	42m 50s	546.5%	2.3 GB	3.4 GB	28.7 GB	58.3 MB
+11	56/bfb031	2b3fa360-b13f-4f2b-8964-132459a7da40	alevin (905_3-txome_k23_no_sa)	COMPLETED	0	2020-09-08 09:37:16.004	54m 39s	49m 35s	557.1%	2.4 GB	3.3 GB	28.6 GB	59.3 MB
+9	16/de4c48	782ac556-f1eb-4366-86e1-fd6d25a4ecaf	alevin (905_3-cdna_k23_no_sa)	COMPLETED	0	2020-09-08 09:37:15.575	55m 28s	50m 38s	559.4%	2.1 GB	3.1 GB	28.4 GB	58.3 MB
+1	82/0fe1a3	8d3730a2-db8a-49f5-9adf-5dd42aebb0f8	alevin (834-cdna_k31_no_sa)	COMPLETED	0	2020-09-08 09:37:15.314	1h 7m 59s	1h 2m 54s	565.5%	3 GB	4.2 GB	30.6 GB	68.1 MB
+3	3c/fa499d	0908c414-958e-4c6b-a9ea-e45e939547e0	alevin (834-txome_k31_no_sa)	COMPLETED	0	2020-09-08 09:37:15.348	1h 21m 40s	1h 16m 18s	571.5%	3.4 GB	4.5 GB	30.8 GB	70.5 MB
+5	be/add80a	fd34fd1e-a93d-4e0c-9ff8-c54fdc7d1540	alevin (834-cdna_k31_full_sa)	COMPLETED	0	2020-09-08 09:37:15.377	1h 21m 59s	1h 13m 15s	573.2%	19.1 GB	22.6 GB	46.5 GB	67.5 MB
+6	7c/9cf52c	805b310d-2ade-46f4-b711-fc355047758c	alevin (834-txome_k31_full_sa)	COMPLETED	0	2020-09-08 09:37:15.355	1h 24m 10s	1h 15m 34s	572.9%	19.3 GB	27.9 GB	46.6 GB	69.5 MB
+7	bd/3f4fe2	94129596-23d7-42ae-9587-72ac57acf9f8	alevin (834-cdna_k31_partial_sa)	COMPLETED	0	2020-09-08 09:37:15.387	1h 34m 49s	1h 29m 28s	576.2%	3.4 GB	4.7 GB	30.9 GB	67.9 MB
+4	2e/c863fd	4933f10e-2ef5-409a-878f-2137acca8f14	alevin (834-txome_k23_no_sa)	COMPLETED	0	2020-09-08 09:37:15.345	1h 47m 40s	1h 42m 12s	581.3%	3.7 GB	4.9 GB	30.8 GB	70.5 MB
+2	d7/2c7eb7	4ba9aeff-6eae-4b26-bb71-5b48d0457e0e	alevin (834-cdna_k23_no_sa)	COMPLETED	0	2020-09-08 09:37:15.336	1h 51m 1s	1h 45m 54s	580.7%	3.2 GB	4.6 GB	30.6 GB	68.1 MB