Update README (#38)

* Bump version, update kraken db

* Add details on additional analyses & outputs

Author: dfornika

README.md

@@ -11,7 +11,9 @@ A generic pipeline that can be run routinely on all Illumina sequence runs, rega
 
 * Parse run-level QC statistics from the 'InterOp' directory and write to `.csv` and `.json` format.
 * [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/): sample-level sequence quality metrics
-* [Kraken2](https://github.com/DerrickWood/kraken2) + [Bracken](https://github.com/jenniferlu717/Bracken): Taxonomic classification
+* [`mash`](https://github.com/marbl/Mash): Estimate genome size and depth of coverage
+* [`seqtk fqchk`](https://github.com/lh3/seqtk): Measure average sequence quality score, percent of bases above Q30 and GC content.
+* [`kraken2`](https://github.com/DerrickWood/kraken2) + [`bracken`](https://github.com/jenniferlu717/Bracken): Taxonomic classification
 of reads. Estimation of relative abundances of taxonomic groups (genus, species) in each sample.
 * [MultiQC](https://github.com/ewels/MultiQC): Collect several QC metrics into a single interactive HTML report.
 
@@ -22,6 +24,9 @@ nextflow run BCCDC-PHL/routine-sequence-qc \
   [--instrument_type nextseq] \
   [--kraken2_db /path/to/kraken2_db] \
   [--bracken_db /path/to/bracken_db] \
+  [--seqtk_fqchk_threshold <threshold>] \
+  [--mash_sketch_kmer_size <kmer_size>] \
+  [--mash_sketch_minimum_copies <copies>] \
   --run_dir <your illumina run directory> \
   --outdir <output directory>
 ```
@@ -33,6 +38,8 @@ nextflow run BCCDC-PHL/routine-sequence-qc \
 ├── abundance_top_n
 │   ├── top_3_abundances_genus.csv
 │   └── top_5_abundances_species.csv
+├── basic_qc_stats
+│   └── basic_qc_stats.csv
 ├── bracken
 │   ├── <sample_id>_Genus_bracken_abundances.tsv
 │   ├── <sample_id>_Genus_bracken.txt
@@ -45,13 +52,24 @@ nextflow run BCCDC-PHL/routine-sequence-qc \
 │   ├── ...
 ├── interop_summary
 │   ├── interop_index-summary.csv
-│   └── interop_summary.csv
+│   ├── interop_summary.csv
+│   └── interop_summary.json
 ├── kraken2
 │   ├── <sample_id>_kraken2.txt
 │   ├── ...
+├── mash_sketch
+│   ├── <sample_id>_R1_mash_sketch.txt
+├── mash_sketch_summary
+│   └── mash_sketch_summary.csv
 ├── multiqc
 │   ├── multiqc_data
 │   └── multiqc_report.html
 └── parse_sample_sheet
-    └── sample_sheet.json
+│   └── sample_sheet.json
+├── pipeline_complete.json
+├── seqtk_fqchk
+│   ├── <sample_id>_seqtk_fqchk_all_positions.csv
+│   ├── <sample_id>_seqtk_fqchk_by_position.csv
+└── seqtk_fqchk_summary
+    └── seqtk_fqchk_summary.csv
 ```

nextflow.config

@@ -1,6 +1,6 @@
 params {
-  kraken2_db = "/data/ref_databases/kraken2/2020-12-02_standard"
-  bracken_db = "/data/ref_databases/bracken/2020-12-02_standard"
+  kraken2_db = "/data/ref_databases/kraken2/2021-05-17_standard"
+  bracken_db = "/data/ref_databases/bracken/2021-05-17_standard"
   instrument_type = "miseq"
   seqtk_fqchk_threshold = 30
   mash_sketch_kmer_size = 21
@@ -28,10 +28,10 @@ process {
 
 
 manifest {
-  author = 'Dan Fornika'
+  author = 'Dan Fornika, Nima Farzaneh'
   description = 'Routine Sequence QC'
   mainScript = 'main.nf'
   nextflowVersion = '>=20.01.0'
-  version = '0.2.3'
+  version = '0.3.0'
 }