Miniprot p2

README.md

@@ -22,11 +22,48 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
 
 The version 1 pipeline will be made up of the following steps:
 
+- INPUT_READ
+
+  - The reading of the input yaml and conversion into channels for the sub-workflows.
+
+
 - GENERATE_GENOME
-  Generate .genome for the input genome.
+
+  - Generate .genome for the input genome.
+  - Uses SAMTOOLS FAIDX.
+
 
 - GENERATE_ALIGNMENT
-  Generate .as files from BLAST alignment results of input genome against set datasets.
+
+  - Peptides will run pep_alignment.nf
+    - Uses Miniprot.
+
+  - CDNA, RNA and CDS will run through nuc_alignment.nf
+    - Uses Minimap2.
+
+
+- INSILICO DIGEST
+
+  - Generates a map of enzymatic digests using 3 Bionano enzymes
+  - Uses Bionano software.
+
+
+- SELFCOMP
+
+  - Identifies regions of self-complementary sequence
+  - Uses Mummer.
+
+- SYNTENY
+
+  - Generates syntenic alignments between other high quality genomes.
+  - Uses Minimap2.
+
+
+- ANCESTRAL ELEMENT ANALYSIS
+  - Lepidopteran Element Analysis
+    - Uses BUSCO and custom python scripts to parse ancestral lep genes
+  - This will eventually have a number of clade specific sub-workflows.
+
 
 ## Quick Start
 
@@ -52,7 +89,12 @@ The version 1 pipeline will be made up of the following steps:
    <!-- TODO nf-core: Update the example "typical command" below used to run the pipeline -->
 
    ```console
-   nextflow run nf-core/treeval --input samplesheet.csv --outdir <OUTDIR> --genome GRCh37 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute>
+   nextflow run main.nf  -profile singularity --input treeval.yaml
+   ```
+
+   LSF specific run
+   ```console
+   echo "nextflow run main.nf  -profile singularity --input treeval.yaml" | bsub -Is -tty -e error -o out -n 10 -q normal -M10000 -R'select[mem>10000] rusage[mem=10000] span[hosts=1]'
    ```
 
 ## Documentation
@@ -61,11 +103,14 @@ The nf-core/treeval pipeline comes with documentation about the pipeline [usage]
 
 ## Credits
 
-nf-core/treeval was originally written by Damon-Lee Pointon, Yumi Sims and William Eagles.
+nf-core/treeval was originally written by Damon-Lee Pointon (@DLBPointon), Yumi Sims (@yumisims) and William Eagles (@weaglesBio).
 
 We thank the following people for their extensive assistance in the development of this pipeline:
 
-<!-- TODO nf-core: If applicable, make list of people who have also contributed -->
+@muffato
+@gq1
+@ksenia-krasheninnikova
+@priyanka-surana
 
 ## Contributions and Support
 
@@ -75,10 +120,29 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
 <!-- If you use  nf-core/treeval for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
 
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+### Tools
+
+BedTools
+
+Bionano CMAP
+
+BUSCO
+
+Minimap2
+
+Miniprot
+
+Mummer
+
+Python3
+
+Samtools
+
+TABIX
+
+UCSC
 
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 

assets/treeval_test.yaml

@@ -1,4 +1,5 @@
 assembly:
+  sizeClass: '' # S if {genome => 4Gb} else L
   level: scaffold
   sample_id: nxOscDoli1
   classT: nematode
@@ -17,3 +18,5 @@ self_comp:
 synteny:
   synteny_genome_path: "/nfs/team135/dp24/treeval_testdata/synteny_data"
 outdir: "NEEDS TESTING"
+intron:
+  size: "50k"

conf/base.config

@@ -18,13 +18,25 @@ process {
     maxRetries    = 1
     maxErrors     = '-1'
 
+    withName:SAMTOOLS_MERGE {
+        memory = { check_max( 50.GB     * task.attempt, 'memory') }
+    }
+
+    // 20GB * (task attempt * 2) = 40GB, 80GB, 120GB
+    withName:MUMMER {
+        cpus    = { check_max( 12        * task.attempt, 'cpus'                      ) }
+        memory  = { check_max( 20.GB     * Math.ceil( task.attempt * 2 ), 'memory'   ) }
+        time    = { check_max( 2.h       * task.attempt, 'time'                      ) }
+    }
+
     // Process-specific resource requirements
     // NOTE - Please try and re-use the labels below as much as possible.
     //        These labels are used and recognised by default in DSL2 files hosted on nf-core/modules.
     //        If possible, it would be nice to keep the same label naming convention when
     //        adding in your local modules too.
     // TODO nf-core: Customise requirements for specific processes.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
+
     withLabel:process_low {
         cpus   = { check_max( 2     * task.attempt, 'cpus'    ) }
         memory = { check_max( 12.GB * task.attempt, 'memory'  ) }

conf/modules.config

@@ -26,20 +26,12 @@ process {
         ]
     }
 
-    withName: FILTER_BLAST {
-        ext.args    = 90.00
+    withName: MINIPROT_ALIGN {
+        ext.args    = "-u --gff -j 1"
     }
 
-    withName: BLAST_MAKEBLASTDB {
-        ext.args    = '-dbtype nucl'
-    }
-
-    withName: BLAST_TBLASTN {
-        ext.args    = '-outfmt 6 -task tblastn -evalue 0.001 -qcov_hsp_perc 60 -max_target_seqs 1'
-    }
-
-    withName: BLAST_BLASTN {
-        ext.args    = '-outfmt 6 -task blastn -evalue 0.001'
+    withName: '.*:.*:.*:NUC_ALIGNMENTS:BEDTOOLS_BAMTOBED' {
+        ext.args        = "-bed12"
     }
 
     withName: '.*:.*:INSILICO_DIGEST:UCSC_BEDTOBIGBED' {
@@ -53,16 +45,21 @@ process {
     }
 
     withName: '.*:.*:SELFCOMP:UCSC_BEDTOBIGBED' {
-        ext.args   = { " -type=bed3+6 -extraIndex=name,qStart,qEnd" }
-        ext.prefix = { "${meta.id}" }
+        ext.args    = { " -type=bed3+6 -extraIndex=name,qStart,qEnd" }
+        ext.prefix  = { "${meta.id}" }
+    }
+
+    withName: '.*:.*:SYNTENY:MINIMAP2_ALIGN' {
+        ext.args    = '-t 8 -x asm10'
+        ext.prefix  = { "${meta.id}_synteny_${reference.getName().tokenize('.')[0]}" }
     }
 
-    withName: MINIMAP2_ALIGN {
-        ext.args = '-t 8 -x asm10'
-        ext.prefix = { "${meta.id}_synteny_${reference.getName().tokenize('.')[0]}" }
+    withName: '.*:.*:.*:NUC_ALIGNMENTS:MINIMAP2_ALIGN' {
+        ext.args    = "-ax splice"
+        ext.prefix  = { "${meta.id}_alignment_${reference.getName().tokenize('.')[0]}" }
     }
 
     withName : MUMMER {
         ext.args = "-n -b -c -L -l 400"
     }
-}
+}

modules.json

@@ -18,17 +18,32 @@
             "minimap2/align": {
                 "git_sha": "1a5a9e7b4009dcf34e6867dd1a5a1d9a718b027b"
             },
+            "mummer": {
+                "git_sha": "233fa70811a03a4cecb2ece483b5c8396e2cee1d"
+            },
+            "nf-core/bedtools/sort": {
+                "git_sha": "4bb1d4e362a38642e877afe41aaf58ded9e56c86"
+            },
+            "nf-core/samtools/merge": {
+                "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+            },
+            "nf-core/tabix/bgziptabix": {
+                "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
+            },
             "samtools/faidx": {
                 "git_sha": "3eb99152cedbb7280258858e5df08478a4670696"
             },
             "ucsc/bedtobigbed": {
                 "git_sha": "90aef30f432332bdf0ce9f4b9004aa5d5c4960bb"
-            },
-            "mummer": {
-                "git_sha": "233fa70811a03a4cecb2ece483b5c8396e2cee1d"
             }
         },
         "sanger-tol/nf-core-modules": {
+            "": {
+                "git_sha": "5f56c87e361ae0a90b1e54f574ab48c58988f5f7"
+            },
+            "bedtools/bamtobed": {
+                "git_sha": "90aef30f432332bdf0ce9f4b9004aa5d5c4960bb"
+            },
             "blast/tblastn": {
                 "git_sha": "a6effa038df6248bad2329c6ab104c5ae9d556c5"
             },
@@ -41,6 +56,12 @@
             "makecmap/renamecmapids": {
                 "git_sha": "461204ac9e8bae621a24a493db3ec9f8274b7757"
             },
+            "miniprot/align": {
+                "git_sha": "f7c0161a1375840fca96f1bab27d3e9a8d423b06"
+            },
+            "miniprot/index": {
+                "git_sha": "5f56c87e361ae0a90b1e54f574ab48c58988f5f7"
+            },
             "selfcomp/mapids": {
                 "git_sha": "6f5a750a30268d30ab55ad2ae6e8af48b0d29d1b"
             },

modules/local/bedtools_bed_sort.nf

@@ -0,0 +1,32 @@
+process BEDTOOLS_BED_SORT {
+    tag "${meta.id}"
+    label "process_medium"
+
+    def version = '2.30.0--hc088bd4_0'
+
+    if (params.enable_conda) {
+        exit 1, "Conda environments cannot be used when using the chunkfasta process. Please use docker or singularity containers."
+    }
+    container "quay.io/repository/biocontainers/bedtools:${version}"
+
+    input:
+    tuple val( meta ), path( merged_bam )
+
+    output:
+    tuple val( meta ), file( "*.bed" ), emit: sorted_bed
+    path "versions.yml",                emit: versions
+
+    script:
+    """
+    bamToBed \\
+        -i $merged_bam \\
+        -bed12 | \\
+        bedtools sort \\
+        -i > $meta.id/.sorted.bed
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        BEDTOOLS_BED_SORT: $version
+    END_VERSIONS
+    """
+}

modules/local/chunkfasta.nf

@@ -1,5 +1,6 @@
 process CHUNKFASTA {
     tag "${meta.id}"
+    label "process_medium"
 
     if (params.enable_conda) {
         exit 1, "Conda environments cannot be used when using the chunkfasta process. Please use docker or singularity containers."

modules/local/concat_gff.nf

@@ -0,0 +1,15 @@
+process CONCAT_GFF {
+    tag "${meta.id} - ${meta.type}"
+    label "process_medium"
+
+    input:
+    tuple val(meta), file(input_files)
+
+    output:
+    tuple val(meta), file ("${meta.id}-${meta.type}-all.gff"),     emit: concat_gff
+
+    script:
+    """
+    cat $input_files > $meta.id-$meta.type-all.gff
+    """
+}

modules/local/csv_generator.nf

@@ -1,6 +1,6 @@
 process CSV_GENERATOR {
     tag "${ch_org}"
-    label 'process_small'
+    label 'process_low'
 
     input:
     val ch_org

modules/local/filter_blast.nf

@@ -1,6 +1,6 @@
 process FILTER_BLAST {
     tag "${meta.id} - ${meta.type}"
-    label "process_small"
+    label "process_low"
 
     def version = '0.004-c1'
 

modules/local/generate_genome_file.nf

@@ -1,6 +1,6 @@
 process GENERATE_GENOME_FILE {
     tag "${meta.id}"
-    label "process_small"
+    label "process_low"
 
     input:
     tuple val( meta ), path( fai )

modules/local/get_synteny_genomes.nf

@@ -1,6 +1,6 @@
     process GET_SYNTENY_GENOMES {
         tag "${assembly_classT}"
-        label "process_small"
+        label "process_low"
 
         input:
         val ( synteny_path )

modules/local/merge_bam.nf

@@ -0,0 +1,17 @@
+process MERGE_BAM {
+    tag " ${meta.id} "
+    label "process_medium"
+
+    container ""
+
+    script:
+    """
+    samtools merge merged.bam *.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}": 
+        MERGE_BAM: $version
+    END_VERSIONS
+    """
+
+}

modules/local/minimap_samtools.nf

@@ -0,0 +1,29 @@
+process MINIMAP_SAMTOOLS {
+    tag "${meta.id}"
+    label "process_medium"
+
+    def version = '2.22_1.12'
+
+    container "niemasd/minimap2_samtools:${version}"
+
+    input:
+    tuple val( ref_meta ), file( ref )
+    tuple val( meta ), file( nuc_file )
+
+    output:
+    tuple val( meta ), file( "${nuc_file}.bam" ),     emit: partial_alignment
+    path "versions.yml",                              emit: versions
+
+    script:
+    def intron_size = task.ext.args ?: '50k'
+    """
+    minimap2 -ax splice $ref $nuc_file -G $intron_size | samtools view -Sb -T $ref - > ${nuc_file}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        MINIMAP_SAMTOOLS: $version
+    END_VERSIONS
+    """
+}
+
+//USE THE OFFICIAL MINIMAP MODULE