Update to version 1.4.2

changelog.md

@@ -1,9 +1,24 @@
 # Changelog
 
-## Changes in upcoming release (`dev` branch) 
+## 1.4.2
 
+### New components
 
-## 1.4.0
+- `Bwa`: align short paired-end sequencing reads to long reference sequences
+- `MarkDuplicates`: Identifies duplicate reads
+- `BaseRecalibrator`: Detects systematic errors in base quality scores
+- `Haplotypecaller`: Call germline SNPs and indels via local re-assembly of haplotypes
+
+- `Seroba`: Serotyping of *Streptococcus pneumoniae* sequencing data (FastQ)
+- `Concoct`: Clustering metagenomic assembled comtigs with coverage and composition
+- `MetaBAT2`: A robust statistical framework for reconstructing genomes from metagenomic data
+
+### Minor/Other changes
+
+- added manifest information to the `nextflow.config` file to allow for remote execution
+- Added checks for the DAG's dot files in the compile_reports component
+
+## 1.4.1
 
 ### New features
 

docs/dev/create_process.rst

@@ -28,7 +28,7 @@ substitute key variables in the process, such as input/output channels.
 An example created as a ``my_process.nf`` file is as follows::
 
     some_channel_{{ pid }} = Channel.value(params.param1{{ param_id}})
-    other_channel_{{ pid }} = Chanel.fromPath(params.param2{{ param_id}})
+    other_channel_{{ pid }} = Channel.fromPath(params.param2{{ param_id}})
 
     process myProcess_{{ pid }} {
 
@@ -795,4 +795,4 @@ template::
     <main input> from {{ input_channel }}
 
 
-.. _jinja2: http://jinja.pocoo.org/docs/2.10/
+.. _jinja2: http://jinja.pocoo.org/docs/2.10/

docs/getting_started/installation.rst

@@ -63,7 +63,6 @@ setup.py::
 
     git clone https://github.com/assemblerflow/flowcraft.git
     cd flowcraft
-    git submodule update --init --recursive
     python3 setup.py install
 
 

flowcraft/__init__.py

@@ -1,6 +1,6 @@
 
-__version__ = "1.4.1"
-__build__ = "02032019"
+__version__ = "1.4.2"
+__build__ = "18062019"
 __author__ = "Diogo N. Silva, Tiago F. Jesus, Ines Mendes, Bruno Ribeiro-Goncalves"
 __copyright__ = "Diogo N. Silva"
 __license__ = "GPL3"

flowcraft/flowcraft.py

@@ -279,10 +279,6 @@ def copy_project(path):
     # Copy bin scripts
     copy_tree(join(repo_dir, "bin"), join(target_dir, "bin"))
 
-    # Copy default config file
-    shutil.copy(join(repo_dir, "nextflow.config"),
-                join(target_dir, "nextflow.config"))
-
     # Copy static profiles file
     shutil.copy(join(repo_dir, "profiles.config"),
                 join(target_dir, "profiles.config"))

flowcraft/generator/components/assembly.py

@@ -114,7 +114,7 @@ def __init__(self, **kwargs):
             "cpus": 4,
             "memory": "{ 5.GB * task.attempt }",
             "container": "flowcraft/spades",
-            "version": "3.12.0-1",
+            "version": "3.13.0-1",
             "scratch": "true"
         }}
 

flowcraft/generator/components/mapping.py

@@ -108,3 +108,141 @@ def __init__(self, **kwargs):
         self.status_channels = [
             "retrieve_mapped"
         ]
+
+
+class Bwa(Process):
+    """Bwa to align short paired-end sequencing reads to long reference sequences
+
+        This process is set with:
+
+            - ``input_type``: fastq
+            - ``output_type``: bam
+            - ``ptype``: mapping
+
+        """
+
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "fastq"
+        self.output_type = "bam"
+
+        self.params = {
+            "bwaIndex": {
+                "default": "'s3://ngi-igenomes/igenomes/Homo_sapiens/GATK/GRCh37/Sequence/BWAIndex/human_g1k_v37_decoy.fasta'",
+                "description": "Specifies the reference indexes to be provided "
+                               "to bwa."
+            }
+        }
+
+        self.directives = {
+            "bwa": {
+                "container": "flowcraft/bwa_samtools",
+                "version": "0.7.17-1",
+                "memory": "{5.Gb*task.attempt}",
+                "cpus": 4
+            }
+        }
+
+        self.status_channels = [
+            "bwa",
+        ]
+
+
+class MarkDuplicates(Process):
+    """Identifies duplicate reads.
+
+        This process is set with:
+
+            - ``input_type``: bam
+            - ``output_type``: bam
+            - ``ptype``: mapping
+
+        """
+
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "bam"
+        self.output_type = "bam"
+
+        self.compiler["multiqc"] = ["markDupMultiQC"]
+
+        self.directives = {
+            "mark_duplicates": {
+                "container": "broadinstitute/gatk",
+                "memory": "{5.Gb*task.attempt}",
+                "cpus": 4
+            }
+        }
+
+        self.status_channels = [
+            "mark_duplicates"
+        ]
+
+
+class BaseRecalibrator(Process):
+    """Detects systematic errors in base quality scores
+
+        This process is set with:
+
+            - ``input_type``: bam
+            - ``output_type``: bam
+            - ``ptype``: mapping
+
+        """
+
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "bam"
+        self.output_type = "bam"
+
+        self.params = {
+            "reference": {
+                "default": "null",
+                "description": "Specifies the name of the FASTA reference genome and index files to be provided "
+                               "to BaseRecalibrator."
+            },
+            "dbsnp": {
+                "default": "null",
+                "description": "Specifies the dbSNP VCF file to be provided "
+                               "to BaseRecalibrator."
+            },
+            "dbsnpIdx": {
+                "default": "null",
+                "description": "Specifies the dbSNP VCF index file to be provided "
+                               "to BaseRecalibrator."
+            },
+            "goldenIndel": {
+                "default": "null",
+                "description": "Specifies the Gold standard INDELs VCF file to be provided "
+                               "to BaseRecalibrator."
+            },
+            "goldenIndelIdx": {
+                "default": "null",
+                "description": "Specifies the Gold standard INDELs VCF index file to be provided "
+                               "to BaseRecalibrator."
+            }
+        }
+
+        self.directives = {
+            "base_recalibrator": {
+                "container": "broadinstitute/gatk",
+                "memory": "{5.Gb*task.attempt}",
+                "cpus": 4
+            },
+            "apply_bqsr": {
+                "container": "broadinstitute/gatk",
+                "memory": "{5.Gb*task.attempt}",
+                "cpus": 4
+            }
+        }
+
+        self.status_channels = [
+            "base_recalibrator",
+            "apply_bqsr"
+        ]

flowcraft/generator/components/metagenomics.py

@@ -5,6 +5,74 @@
     from flowcraft.generator.process import Process
 
 
+class Concoct(Process):
+    """
+    CONCOCT process template interface for the
+    taxonomic independent binning of metagenomic
+    assemblies.
+
+    This process is set with:
+        - ``input_type``: assembly
+        - ``output_type``: assembly
+        - ``ptype``: post_assembly
+
+        It contains one **secondary channel link end**:
+
+            - ``MAIN_fq`` (alias: ``_MAIN_assembly``): Receives the FastQ files
+            from the last process with ``fastq`` output type.
+    """
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "fasta"
+        self.output_type = "fasta"
+
+        self.link_end.append({"link": "__fastq", "alias": "_LAST_fastq"})
+
+        self.params = {
+            "clusters": {
+                "default": 400,
+                "description": "Maximum number of clusters for VGMM. Default: 400"
+            },
+            "lengthThreshold": {
+                "default": 1000,
+                "description": "Contigs shorter than this value will not be included. Default: 1000."
+            },
+            "readLength": {
+                "default": 100,
+                "description": "Specify read length for coverage."
+                               "Default: 0.9"
+            },
+            "iterations": {
+                "default": 500,
+                "description": "Number of iterations for the VBGMM. Default: 500"
+            },
+            "clearInput": {
+                "default": "false",
+                "description":
+                    "Permanently removes temporary input files. This option "
+                    "is only useful to remove temporary files in large "
+                    "workflows and prevents nextflow's resume functionality. "
+                    "Use with caution."
+            }
+        }
+
+        self.directives = {
+            "concoct": {
+                "container": "flowcraft/concoct",
+                "version": "1.0.0-1",
+                "cpus": 4,
+                "memory": "{ 5.GB * task.attempt }"
+            }
+        }
+
+        self.status_channels = [
+            "concoct",
+            "report_concoct"
+        ]
+
+
 class Kraken(Process):
     """kraken process template interface
 
@@ -41,6 +109,7 @@ def __init__(self, **kwargs):
             "kraken"
         ]
 
+
 class Kraken2(Process):
     """kraken2 process template interface
 
@@ -212,6 +281,66 @@ def __init__(self, **kwargs):
         ]
 
 
+class Metabat2(Process):
+    """
+    MetaBat2 process template interface for the
+    taxonomic independent binning of metagenomic
+    assemblies.
+
+    This process is set with:
+        - ``input_type``: assembly
+        - ``output_type``: assembly
+        - ``ptype``: post_assembly
+
+    It contains one **dependency process**:
+
+        - ``assembly_mapping``: Requires the BAM file generated by the
+        assembly mapping process
+
+    """
+    def __init__(self, **kwargs):
+
+        super().__init__(**kwargs)
+
+        self.input_type = "fasta"
+        self.output_type = "fasta"
+
+        self.dependencies = ["assembly_mapping"]
+
+        self.params = {
+            "maxPercentage": {
+                "default": 95,
+                "description": "Percentage of 'good' contigs considered for binning decided by connection. Default: 95."
+            },
+            "minContig": {
+                "default": 2500,
+                "description": "Minimum size of a contig for binning (should be >=1500). Default: 2500."
+            },
+            "clearInput": {
+                "default": "false",
+                "description":
+                    "Permanently removes temporary input files. This option "
+                    "is only useful to remove temporary files in large "
+                    "workflows and prevents nextflow's resume functionality. "
+                    "Use with caution."
+            }
+        }
+
+        self.directives = {
+            "metabat2": {
+                "container": "flowcraft/metabat",
+                "version": "2.13-1",
+                "cpus": 4,
+                "memory": "{ 5.GB * task.attempt }"
+            }
+        }
+
+        self.status_channels = [
+            "metabat2",
+            "report_metabat2"
+        ]
+
+
 class Metaspades(Process):
     """Metaspades process template interface
 
@@ -349,6 +478,7 @@ def __init__(self, **kwargs):
             "report_remove_host"
         ]
 
+
 class Metaprob(Process):
     """MetaProb to bin metagenomic reads interface
 
@@ -431,4 +561,3 @@ def __init__(self, **kwargs):
         self.status_channels = [
             "split_assembly"
         ]
-

flowcraft/generator/components/phylogeny.py

@@ -34,6 +34,10 @@ def __init__(self, **kwargs):
             "bootstrap": {
                 "default": "500",
                 "description": "Specify the number of alternative runs on distinct starting trees"
+            },
+            "simpleLabel": {
+                "default": "true",
+                "description": "Simplify the labels in the newick tree (for interactive report only)"
             }
         }