Upgrade simpleaf to 0.19.0 (#7405)

* update simpleaf index * done updating simpleaf modules. testing * tests passed * remove sshash from index test * remove sshash from index test * update snapshot and clean meta.yml * rewrite version.json * rewrite version.json * update version md5 * update version md5 * update version md5 * remove salmon from versions.json * remove md5sum checks * restructure simpleaf quant output * add quant_dir in stub * fix link * last try of md5sum test * remove md5 related tests * remove md5 related tests * rewrote index and quant to be more generalized * set meta[count_type] as raw or filter * linting * update simpleaf modules tags * update simpleaf modules tags * add filtered to simpleaf quant meta * make read id the default in simpleaf quant * update simpleaf tests * update simpleaf tests * update simpleaf tests and passed * update simpleaf tests and passed * test --update * upgrade to simpleaf 0.19.0 * make lint happy * write h5ad by default * update to 0.19.1 --------- Co-authored-by: dongzehe <[email protected]> Co-authored-by: Gregor Sturm <[email protected]> Co-authored-by: Dongze He <[email protected]>
nf-core · Feb 4, 2025 · 094299f · 094299f
1 parent 83fb0b4
commit 094299f
Show file tree

Hide file tree

Showing 9 changed files with 187 additions and 64 deletions.
diff --git a/modules/nf-core/simpleaf/index/environment.yml b/modules/nf-core/simpleaf/index/environment.yml
@@ -6,6 +6,6 @@ channels:
 
 dependencies:
   - bioconda::alevin-fry=0.11.1
-  - bioconda::piscem=0.11.0
+  - bioconda::piscem=0.12.2
   - bioconda::salmon=1.10.3
-  - bioconda::simpleaf=0.18.4
+  - bioconda::simpleaf=0.19.1
diff --git a/modules/nf-core/simpleaf/index/main.nf b/modules/nf-core/simpleaf/index/main.nf
@@ -5,12 +5,14 @@ process SIMPLEAF_INDEX {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/simpleaf:0.18.4--ha6fb395_1':
-        'biocontainers/simpleaf:0.18.4--ha6fb395_1' }"
+        'https://depot.galaxyproject.org/singularity/simpleaf:0.19.1--ha6fb395_0':
+        'biocontainers/simpleaf:0.19.1--ha6fb395_0' }"
 
     input:
     tuple val(meta),  path(genome_fasta), path(genome_gtf)
     tuple val(meta2), path(transcript_fasta)
+    tuple val(meta3), path(probe_csv)
+    tuple val(meta4), path(feature_csv)
 
     output:
     tuple val(meta), path("${prefix}/index")                    , emit: index
@@ -23,10 +25,9 @@ process SIMPLEAF_INDEX {
 
     script:
     def args = task.ext.args ?: ''
-    def seq_inputs = input_args(genome_fasta, genome_gtf, transcript_fasta)//, probes_csv, features_csv)
+    (meta, seq_inputs) = input_args(genome_fasta, genome_gtf, transcript_fasta, probe_csv, feature_csv, meta, meta2, meta3, meta4)
 
     // Output meta needs to correspond to the input used
-    meta = (transcript_fasta) ? meta2 : meta
     prefix = task.ext.prefix ?: "${meta.id}"
     """
     # export required var
@@ -56,8 +57,8 @@ process SIMPLEAF_INDEX {
     """
 
     stub:
-    def args = task.ext.args ?: ''
-    prefix = task.ext.prefix ?: (meta.id ? "${meta.id}" : "${meta2.id}")
+    meta = meta ? meta : [id: 'stub']
+    prefix = task.ext.prefix ?: "${meta.id}"
 
     """
     mkdir -p ${prefix}/index
@@ -78,19 +79,22 @@ process SIMPLEAF_INDEX {
     """
 }
 
-def input_args(genome_fasta, genome_gtf, transcript_fasta) { //, probes_csv, features_csv) {
-    // if (probe_csv) {
-    //     args = "--probe_csv ${probe_csv}"
-    // } else if (feature_csv) {
-    //     args = "--feature_csv ${feature_csv}"
-    // } else
-    if (transcript_fasta) {
-        return "--ref-seq ${transcript_fasta}"
+def input_args(genome_fasta, genome_gtf, transcript_fasta, probe_csv, feature_csv, meta, meta2, meta3, meta4) {
+    // check if all null
+    if (!genome_fasta && !genome_gtf && !transcript_fasta && !probe_csv && !feature_csv) {
+        error "No valid input provided; please provide either a genome fasta + gtf set or a transcript fasta file."
+    }
+
+    if (feature_csv) {
+        return [meta4, "--feature-csv ${feature_csv}"]
+    } else if (probe_csv) {
+        return [meta3, "--probe-csv ${probe_csv}"]
+    } else if (transcript_fasta) {
+        return [meta2, "--ref-seq ${transcript_fasta}"]
     } else if (genome_fasta && genome_gtf) {
-        return "--fasta ${genome_fasta} --gtf ${genome_gtf}"
+        return [meta, "--fasta ${genome_fasta} --gtf ${genome_gtf}"]
     } else {
-        error "No valid input provided; please provide either a genome fasta + gtf set or a transcript fasta file. ${genome_fasta} ${genome_gtf} ${transcript_fasta}"
-        // error "No valid input provided; please provide one of the followings: (i) a genome fasta + gtf set, (ii) a transcript fasta file, (iii) a probes csv file (iv) a features csv file."
+        error "No valid input provided; please provide one of the followings: (i) a genome fasta + gtf set, (ii) a transcript fasta file, (iii) a probes csv file (iv) a features csv file."
     }
 
 }
diff --git a/modules/nf-core/simpleaf/index/meta.yml b/modules/nf-core/simpleaf/index/meta.yml
@@ -20,17 +20,13 @@ input:
     - genome_fasta:
         type: file
         description: |
-          FASTA file containing the genome sequence.
-          It conflicts with transcript_fasta.
-          When transcript_fasta is provided, it must be empty (provided as []).
-          When transcript_fasta is empty, it must be provided together with its corresponding genome_gtf file.
+          FASTA file containing the genome sequence. It must be provided together with the corresponding genome_gtf file.
+          When another input set is provided, it must be empty (provided as []).
     - genome_gtf:
         type: file
         description: |
-          GTF file containing gene annotations.
-          It conflicts with transcript_fasta.
-          When transcript_fasta is provided, it must be empty (provided as []).
-          When transcript_fasta is empty, it must be provided together with its corresponding genome_fasta file.
+          GTF file containing gene annotations. It must be provided together with its corresponding genome_fasta file.
+          When another input set rather than genome_fasta + genome_gtf is provided, it must be empty (provided as []).
   - - meta2:
         type: map
         description: |
@@ -39,8 +35,25 @@ input:
         type: file
         description: |
           FASTA file containing the transcript sequences to build index directly on.
-          It conflicts with genome_gtf and genome_fasta.
-          When genome_gtf and genome_fasta are provided, it must be empty (provided as []).
+          When another input set is provided, it must be empty (provided as []).
+  - - meta3:
+        type: map
+        description: |
+          Groovy Map containing information on probe_csv.
+    - probe_csv:
+        type: file
+        description: |
+          CSV file containing the reference probe sequences to build index directly on.
+          When another input set is provided, it must be empty (provided as []).
+  - - meta4:
+        type: map
+        description: |
+          Groovy Map containing information on feature_csv.
+    - feature_csv:
+        type: file
+        description: |
+          CSV file containing the reference feature barcodes to build index directly on.
+          When another input set is provided, it must be empty (provided as []).
 output:
   - index:
       - meta:

diff --git a/modules/nf-core/simpleaf/index/tests/main.nf.test b/modules/nf-core/simpleaf/index/tests/main.nf.test
@@ -21,6 +21,8 @@ nextflow_process {
 
                 input[0] = Channel.of([ meta, genome_fasta, gtf ])
                 input[1] = Channel.of([[],[]])
+                input[2] = Channel.of([[],[]])
+                input[3] = Channel.of([[],[]])
                 """
             }
         }
@@ -56,6 +58,80 @@ nextflow_process {
 
                 input[0] = Channel.of([[],[],[]])
                 input[1] = Channel.of([ meta, transcriptome_fasta ])
+                input[2] = Channel.of([[],[]])
+                input[3] = Channel.of([[],[]])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx_cfish.json").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.ctab").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.ectab").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.json").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.refinfo").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.sshash").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/simpleaf_index.json").exists() }
+                // { assert snapshot(
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx.ctab"),
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx.json"),
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx_cfish.json"),
+                //     process.out.versions)
+                //     .match() }
+            )
+        }
+    }
+
+    test("Homo sapiens - probe index - direct - probe csv") {
+        when {
+            process {
+                """
+                probe_csv = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/spaceranger/human-brain-cancer-11-mm-capture-area-ffpe-2-standard_v2_ffpe_cytassist/CytAssist_11mm_FFPE_Human_Glioblastoma_probe_set.csv', checkIfExists: true)
+                meta = [ 'id': 'CytAssist_11mm_FFPE_Human_Glioblastoma_probe_set']
+
+                input[0] = Channel.of([[],[],[]])
+                input[1] = Channel.of([[],[]])
+                input[2] = Channel.of([ meta, probe_csv ])
+                input[3] = Channel.of([[],[]])
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.versions).match() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx_cfish.json").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.ctab").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.ectab").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.json").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.refinfo").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/piscem_idx.sshash").exists() },
+                { assert file("${process.out.index.get(0).get(1)}/simpleaf_index.json").exists() }
+                // { assert snapshot(
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx.ctab"),
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx.json"),
+                //     path("${process.out.index.get(0).get(1)}/piscem_idx_cfish.json"),
+                //     process.out.versions)
+                //     .match() }
+            )
+        }
+    }
+
+    test("Homo sapiens - feature index - direct - feature csv") {
+        when {
+            process {
+                """
+                feature_csv = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc/sc5p_v2_hs_PBMC_10k_multi_5gex_5fb_b_t_feature_ref.csv', checkIfExists: true)
+                meta = [ 'id': 'sc5p_v2_hs_PBMC_10k_multi_5gex_5fb_b_t_feature_ref']
+
+                input[0] = Channel.of([[],[],[]])
+                input[1] = Channel.of([[],[]])
+                input[2] = Channel.of([[],[]])
+                input[3] = Channel.of([ meta, feature_csv ])
                 """
             }
         }
@@ -90,7 +166,9 @@ nextflow_process {
                 meta = [ 'id': 'human_transcriptome']
 
                 input[0] = Channel.of([[],[],[]])
-                input[1] = Channel.of([ meta, transcriptome_fasta ])
+                input[1] = Channel.of([ [], [] ])
+                input[2] = Channel.of([ [], [] ])
+                input[3] = Channel.of([ [], [] ])
                 """
             }
         }

diff --git a/modules/nf-core/simpleaf/index/tests/main.nf.test.snap b/modules/nf-core/simpleaf/index/tests/main.nf.test.snap
@@ -1,24 +1,48 @@
 {
+    "Homo sapiens - probe index - direct - probe csv": {
+        "content": [
+            [
+                "versions.yml:md5,d2fa3ef3c792f5bd01cf4e05866caceb"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.3"
+        },
+        "timestamp": "2025-02-04T20:19:57.286321286"
+    },
     "Homo sapiens - transcriptome index - direct - transcriptome fasta": {
         "content": [
             [
-                "versions.yml:md5,bd96efe900339c637533c40b37fa5cfc"
+                "versions.yml:md5,d2fa3ef3c792f5bd01cf4e05866caceb"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.2",
+            "nextflow": "24.10.3"
+        },
+        "timestamp": "2025-02-04T20:15:47.68048376"
+    },
+    "Homo sapiens - feature index - direct - feature csv": {
+        "content": [
+            [
+                "versions.yml:md5,d2fa3ef3c792f5bd01cf4e05866caceb"
             ]
         ],
         "meta": {
             "nf-test": "0.9.2",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-01-23T00:40:55.088252924"
+        "timestamp": "2025-02-04T20:20:04.705227496"
     },
     "Homo sapiens - transcriptome index - direct - transcriptome fasta - stub": {
         "content": [
             {
                 "0": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         [
                             "piscem_idx.ectab:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "piscem_idx.sshash:md5,d41d8cd98f00b204e9800998ecf8427e",
@@ -28,9 +52,9 @@
                 ],
                 "1": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         [
                             "roers_ref.fa:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "t2g_3col.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
@@ -39,20 +63,20 @@
                 ],
                 "2": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         "t2g_3col.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "3": [
-                    "versions.yml:md5,78f7da1109cf98d7b9107222704848e1"
+                    "versions.yml:md5,70c02c3b43e257fa1abb47cb6879f6b7"
                 ],
                 "index": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         [
                             "piscem_idx.ectab:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "piscem_idx.sshash:md5,d41d8cd98f00b204e9800998ecf8427e",
@@ -62,9 +86,9 @@
                 ],
                 "ref": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         [
                             "roers_ref.fa:md5,d41d8cd98f00b204e9800998ecf8427e",
                             "t2g_3col.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
@@ -73,33 +97,33 @@
                 ],
                 "t2g": [
                     [
-                        [
-
-                        ],
+                        {
+                            "id": "stub"
+                        },
                         "t2g_3col.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,78f7da1109cf98d7b9107222704848e1"
+                    "versions.yml:md5,70c02c3b43e257fa1abb47cb6879f6b7"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.9.2",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-01-23T02:08:51.588975264"
+        "timestamp": "2025-02-04T20:20:12.01549861"
     },
     "Homo sapiens - genome index - expanded - fasta + gtf": {
         "content": [
             [
-                "versions.yml:md5,bd96efe900339c637533c40b37fa5cfc"
+                "versions.yml:md5,d2fa3ef3c792f5bd01cf4e05866caceb"
             ]
         ],
         "meta": {
             "nf-test": "0.9.2",
             "nextflow": "24.10.3"
         },
-        "timestamp": "2025-01-23T00:40:41.692166586"
+        "timestamp": "2025-02-04T20:15:30.566784151"
     }
 }
diff --git a/modules/nf-core/simpleaf/quant/environment.yml b/modules/nf-core/simpleaf/quant/environment.yml
@@ -6,6 +6,6 @@ channels:
 
 dependencies:
   - bioconda::alevin-fry=0.11.1
-  - bioconda::piscem=0.11.0
+  - bioconda::piscem=0.12.2
   - bioconda::salmon=1.10.3
-  - bioconda::simpleaf=0.18.4
+  - bioconda::simpleaf=0.19.1