Add hifiasm assembler

.github/workflows/test_pr_lreads_docker_ont_hifi.bkp

@@ -0,0 +1,37 @@
+name: Testing long-reads HIFI / docker (ONT) from PR
+on:
+  pull_request:
+    branches: [ master, dev ]
+    types: [ opened, synchronize, reopened ]
+
+jobs:
+  run_nextflow:
+    name: Run pipeline for the upcoming PR
+    runs-on: ubuntu-latest
+
+    steps:
+
+      - name: Check out pipeline code
+        uses: actions/checkout@v2
+
+      - name: Install Nextflow
+        env:
+          CAPSULE_LOG: none
+        run: |
+          wget -qO- get.nextflow.io | bash
+          sudo mv nextflow /usr/local/bin/
+
+      - name: Clean environment
+        run: |
+          sudo rm -rf /usr/local/lib/android # will release about 10 GB if you don't need Android
+          sudo rm -rf /usr/share/dotnet # will release about 20GB if you don't need .NET
+
+      - name: Run tests for long-reads (ont)
+        run: |
+          nextflow run main.nf -profile docker,test,lreads,ont_hifi --max_memory '6.GB' --max_cpus 4
+          rm -r work .nextflow*
+
+      - name: View results
+        run: |
+          sudo apt-get install -y tree
+          tree lreads_test_ont_hifi

Dockerfile

@@ -17,8 +17,8 @@ RUN medaka --help
 
 # fix permissions
 USER root
-RUN mkdir -p $CONDA_PREFIX/envs/mpgap-3.2/lib/python3.8/site-packages/medaka && \
-      chmod -R 777 $CONDA_PREFIX/envs/mpgap-3.2/lib/python3.8/site-packages/medaka
+RUN mkdir -p $CONDA_PREFIX/envs/mpgap-3.2/lib/python3.9/site-packages/medaka && \
+      chmod -R 777 $CONDA_PREFIX/envs/mpgap-3.2/lib/python3.9/site-packages/medaka
 
 # pre-download BUSCO bacteria database
 RUN mkdir -p /opt/busco_db/ && \

README.md

@@ -36,7 +36,7 @@ This pipeline wraps up the following software:
 
 || **Source** |
 |:- | :- |
-| **Assemblers** | [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta), [wtdbg2](https://github.com/ruanjue/wtdbg2), [Haslr](https://github.com/vpc-ccg/haslr), [Unicycler](https://github.com/rrwick/Unicycler), [Spades](https://github.com/ablab/spades), [Shovill](https://github.com/tseemann/shovill), [Megahit](https://github.com/voutcn/megahit) |
+| **Assemblers** | [Hifiasm](https://github.com/chhylp123/hifiasm), [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta), [wtdbg2](https://github.com/ruanjue/wtdbg2), [Haslr](https://github.com/vpc-ccg/haslr), [Unicycler](https://github.com/rrwick/Unicycler), [Spades](https://github.com/ablab/spades), [Shovill](https://github.com/tseemann/shovill), [Megahit](https://github.com/voutcn/megahit) |
 | **Polishers** | [Nanopolish](https://github.com/jts/nanopolish), [Medaka](https://github.com/nanoporetech/medaka), [gcpp](https://github.com/PacificBiosciences/gcpp), [Polypolish](https://github.com/rrwick/Polypolish) and [Pilon](https://github.com/broadinstitute/pilon) |
 | **Quality check** | [Quast](https://github.com/ablab/quast), [BUSCO](https://busco.ezlab.org/busco_userguide.html) and [MultiQC](https://multiqc.info/) |
 

assets/lreads_test_ont_hifi.yml

@@ -0,0 +1,4 @@
+samplesheet:
+  - id: ont_only_hifi
+    nanopore:  https://github.com/fmalmeida/test_datasets/raw/main/SRR27467590.fq.gz
+    genome_size: 4m

conf/defaults.config

@@ -143,10 +143,12 @@ params {
   skip_shasta = false                         // Nanopore longreads only assemblies
   shasta_additional_parameters = null         // Must be given as shown in shasta manual. E.g. " --Reads.minReadLength 5000 "
 
+  skip_hifiasm = false                        // Longreads only assemblies
+  hifiasm_additional_parameters = null        // Must be given as shown in Hifiasm manual. E.g. " --ul ul.fq.gz "
+
   skip_pilon = false                          // Skip pilon polisher when performing hybrid assembly strategy 2
   skip_polypolish = false                     // Skip polypolisher polisher when performing hybrid assembly strategy 2
 
-
             /*
              * Resources controlling parameters
              * 
@@ -174,4 +176,4 @@ params {
   max_cpus                   = 10
   max_time                   = '40.h'
 
-}
+}

conf/docker.config

@@ -6,6 +6,6 @@ docker.runOptions       = '-u \$(id -u):\$(id -g)'
 fixOwnership            = true
 process {
     withName:  '.*' {
-        container = "fmalmeida/mpgap@sha256:f640835dad87d98ded0582271aafaebe609f9196618f52a46ac10d991a0fce27"
+        container = "fmalmeida/mpgap@sha256:28223374b5500b09ae467064d825b44d086c99f1ade6afa80dbf8fd0053d760e"
     }
 }

conf/singularity.config

@@ -5,6 +5,6 @@ singularity.enabled     = true
 singularity.autoMounts  = true
 process {
     withName: '.*' {
-        container = "docker://fmalmeida/mpgap@sha256:f640835dad87d98ded0582271aafaebe609f9196618f52a46ac10d991a0fce27"
+        container = "docker://fmalmeida/mpgap@sha256:28223374b5500b09ae467064d825b44d086c99f1ade6afa80dbf8fd0053d760e"
     }
-}
+}

conf/test.config

@@ -9,7 +9,7 @@ profiles {
         params {
             input      = "$baseDir/assets/illumina_test.yml"
             output     = "sreads_test"
-            tracedir   = "sreads_test/pipeline_info"
+            tracedir   = "${params.output}/pipeline_info"
             max_memory = 6.GB
             max_cpus   = 2
             max_time   = '6.h'
@@ -30,16 +30,26 @@ profiles {
 
             ont {
                 params {
-                    input      = "$baseDir/assets/lreads_test_ont.yml"
-                    output     = "lreads_test_ont"
-                    tracedir   = "lreads_test_ont/pipeline_info"
+                    input        = "$baseDir/assets/lreads_test_ont.yml"
+                    output       = "lreads_test_ont"
+                    tracedir     = "${params.output}/pipeline_info"
+                    skip_hifiasm = true
+                }
+            }
+            ont_hifi {
+                params {
+                    input      = "$baseDir/assets/lreads_test_ont_hifi.yml"
+                    output     = "lreads_test_ont_hifi"
+                    tracedir   = "${params.output}/pipeline_info"
+                    high_quality_longreads = true
                 }
             }
             pacbio {
                 params {
-                    input      = "$baseDir/assets/lreads_test_pacbio.yml"
-                    output     = "lreads_test_pacbio"
-                    tracedir   = "lreads_test_pacbio/pipeline_info"
+                    input        = "$baseDir/assets/lreads_test_pacbio.yml"
+                    output       = "lreads_test_pacbio"
+                    tracedir     = "${params.output}/pipeline_info"
+                    skip_hifiasm = true
                 }
             }
 
@@ -60,16 +70,18 @@ profiles {
 
             ont {
                 params {
-                    input      = "$baseDir/assets/hybrid_test_ont.yml"
-                    output     = "hybrid_test_ont"
-                    tracedir   = "hybrid_test_ont/pipeline_info"
+                    input        = "$baseDir/assets/hybrid_test_ont.yml"
+                    output       = "hybrid_test_ont"
+                    tracedir     = "${params.output}/pipeline_info"
+                    skip_hifiasm = true
                 }
             }
             pacbio {
                 params {
-                    input      = "$baseDir/assets/hybrid_test_pacbio.yml"
-                    output     = "hybrid_test_pacbio"
-                    tracedir   = "hybrid_test_pacbio/pipeline_info"
+                    input        = "$baseDir/assets/hybrid_test_pacbio.yml"
+                    output       = "hybrid_test_pacbio"
+                    tracedir     = "${params.output}/pipeline_info"
+                    skip_hifiasm = true
                 }
             }
 

docs/index.md

@@ -23,7 +23,7 @@ The pipeline wraps up the following tools and analyses:
 
 | Software | Analysis |
 | :------- | :------- |
-|  [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Unicycler](https://github.com/rrwick/Unicycler), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta) and [wtdbg2](https://github.com/ruanjue/wtdbg2) | Long reads assembly |
+|  [Hifiasm](https://github.com/chhylp123/hifiasm), [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Unicycler](https://github.com/rrwick/Unicycler), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta) and [wtdbg2](https://github.com/ruanjue/wtdbg2) | Long reads assembly |
 | [Haslr](https://github.com/vpc-ccg/haslr), [Unicycler](https://github.com/rrwick/Unicycler) and [SPAdes](https://github.com/ablab/spades) | Hybrid assembly |
 | [Shovill](https://github.com/tseemann/shovill), [Unicycler](https://github.com/rrwick/Unicycler), [Megahit](https://github.com/voutcn/megahit) and [SPAdes](https://github.com/ablab/spades) | Short reads assembly |
 | [Nanopolish](https://github.com/jts/nanopolish), [Medaka](https://github.com/nanoporetech/medaka), [gcpp](https://github.com/PacificBiosciences/gcpp), [Polypolish](https://github.com/rrwick/Polypolish) and [Pilon](https://github.com/broadinstitute/pilon) | Assembly polishing |

docs/manual.md

@@ -42,6 +42,7 @@ The pipeline is capable of assembling Illumina, ONT and Pacbio reads in three ma
     + Raven
     + Shasta
     + wtdbg2
+    + hifiasm
 
 3. **Hybrid assemblies (using both short and long reads)**
     + Unicycler
@@ -162,6 +163,8 @@ However, they can also be set in a sample-specific manner. If a sample has a val
 | `--shasta_additional_parameters`              | :material-close: | False | Passes additional parameters for Raven assembler. E.g. `" --Assembly.detangleMethod 1 "`. Must be given as shown in Shasta's manual |
 | `--skip_wtdbg2`              | :material-close: | False | Skip the execution of wtdbg2 |
 | `--wtdbg2_additional_parameters`              | :material-close: | False | Passes additional parameters for wtdbg2 assembler. E.g. `" -k 250 "`. Must be given as shown in wtdbg2's manual. Remember, the script called for wtdbg2 is `wtdbg2.pl` thus you must give the parameters used by it |
+| `--skip_hifiasm`              | :material-close: | False | Skip the execution of hifiasm |
+| `--hifiasm_additional_parameters`              | :material-close: | False | Passes additional parameters for hifiasm assembler. E.g. `" --ul ul.fq.gz "`. Must be given as shown in hifiasm's manual |
 | `--skip_unicycler`              | :material-close: | False | Skip the execution of Unicycler |
 | `--unicycler_additional_parameters`              | :material-close: | False | Passes additional parameters for Unicycler assembler. E.g. `" --mode conservative --no_correct "`. Must be given as shown in Unicycler's manual |
 | `--skip_spades`              | :material-close: | False | Skip the execution of SPAdes |

docs/non_bacteria.md

@@ -38,6 +38,7 @@ nextflow run fmalmeida/mpgap \
     --skip_unicycler \
     --flye_additional_parameters ' --keep-haplotypes ' \
     --quast_additional_parameters ' --eukaryote ' \
+    --skip_hifiasm \
     --max_cpus 20 \
     --max_memory '40.GB'
 ```

environment.yml

@@ -55,7 +55,7 @@ dependencies:
 - bioconda::csvtk=0.23.0
 - bioconda::wtdbg=2.5
 - bioconda::medaka=1.11.1
-
+- bioconda::hifiasm=0.19.8
 # for medaka > 1.4
 - bioconda::samtools>=1.11
 - bioconda::tabix>=1.11

markdown/CHANGELOG.md

@@ -10,11 +10,12 @@ The tracking for changes started in v2.
 * Increase default `--max_memory` value to 20.GB.
 * Add a directory called `final_assemblies` in the main output directory holding all the assemblies generated in the pipeline execution.
 * Updated documentation as discussed in [[#58](https://github.com/fmalmeida/MpGAP/issues/58)] and [[#57](https://github.com/fmalmeida/MpGAP/issues/57)].
-* [[#61](https://github.com/fmalmeida/MpGAP/issues/61)] - Add a simple parameter to adjust how many cpus and how much memory should the assembly jobs request in the first attempt to avoid lack of resources errors.
 * [[#50](https://github.com/fmalmeida/MpGAP/issues/50)]
   * Parameters `--skip_pilon` and `--skip_polypolish` added to the pipeline
   * MultiQC report was fixed and enhanced
   * Docker image was also modified to download BUSCO standalone and pipeline perform the BUSCO standalone run instead of via quast.
+* [[#53](https://github.com/fmalmeida/MpGAP/issues/53)] - Include hifiasm assembler in the pipeline. Long reads only and hybrid strategy 2.
+* [[#61](https://github.com/fmalmeida/MpGAP/issues/61)] - Add a simple parameter to adjust how many cpus and how much memory should the assembly jobs request in the first attempt to avoid lack of resources errors.
 * [[#66](https://github.com/fmalmeida/MpGAP/issues/66)] - Include an automated generation of a samplesheet for bacannot pipeline.
 
 ## v3.1.4 -- [2022-Sep-03]

markdown/list_of_tools.md

@@ -4,6 +4,6 @@ These are the tools that wrapped inside mpgap. **Cite** the tools whenever you u
 
 || **Source** |
 |:- | :- |
-| **Assemblers** | [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta), [wtdbg2](https://github.com/ruanjue/wtdbg2), [Haslr](https://github.com/vpc-ccg/haslr), [Unicycler](https://github.com/rrwick/Unicycler), [Spades](https://github.com/ablab/spades), [Shovill](https://github.com/tseemann/shovill) |
+| **Assemblers** | [Hifiasm](https://github.com/chhylp123/hifiasm), [Canu](https://github.com/marbl/canu), [Flye](https://github.com/fenderglass/Flye), [Raven](https://github.com/lbcb-sci/raven), [Shasta](https://github.com/chanzuckerberg/shasta), [wtdbg2](https://github.com/ruanjue/wtdbg2), [Haslr](https://github.com/vpc-ccg/haslr), [Unicycler](https://github.com/rrwick/Unicycler), [Spades](https://github.com/ablab/spades), [Shovill](https://github.com/tseemann/shovill) |
 | **Polishers** | [Nanopolish](https://github.com/jts/nanopolish), [Medaka](https://github.com/nanoporetech/medaka), [gcpp](https://github.com/PacificBiosciences/gcpp), [Polypolish](https://github.com/rrwick/Polypolish) and [Pilon](https://github.com/broadinstitute/pilon) |
 | **Quality check** | [Quast](https://github.com/ablab/quast), [BUSCO](https://busco.ezlab.org/busco_userguide.html) and [MultiQC](https://multiqc.info/) |

nextflow_schema.json

@@ -243,6 +243,13 @@
                     "hidden": true,
                     "fa_icon": "fas fa-ban"
                 },
+                "skip_hifiasm": {
+                    "type": "boolean",
+                    "description": "Skip Hifiasm assembler",
+                    "help_text": "Hifiasm is a long reads only assembler. Can be use for hybrid assemblies in strategy 2.",
+                    "hidden": true,
+                    "fa_icon": "fas fa-ban"
+                },
                 "skip_pilon": {
                     "type": "boolean",
                     "description": "Skip pilon polisher",
@@ -340,6 +347,13 @@
                     "help_text": "Must be given as shown in shasta manual. E.g. \" --Reads.minReadLength 5000 \", inside quotes and separated by spaces",
                     "hidden": true,
                     "fa_icon": "fas fa-quote-left"
+                },
+                "hifiasm_additional_parameters": {
+                    "type": "string",
+                    "description": "Hifiasm additional parameters",
+                    "help_text": "Must be giveen as shown in hifiasm manual. E.g. \" --ul ul.fq.gz \", inside quotes and separated by spaces",
+                    "hidden": true,
+                    "fa_icon": "fas fa-quote-left"
                 }
             },
             "fa_icon": "fas fa-list-ul"
@@ -463,4 +477,4 @@
             "$ref": "#/definitions/institutional_config_options"
         }
     ]
-}
+}