new branch to make config for uncharged libs

config/config-uncharged.yml

@@ -0,0 +1,39 @@
+# new config for running uncharged nanopore tRNA-seq libraries (to be edited)
+
+# either a path to a basecalling model to use with dorado or a model selection name to specify model to download and use
+base_calling_model: "resources/models/[email protected]"
+
+# either FAST5 or POD5, if FAST5 then these files will be converted to pod5 before rebasecalling
+input_format: "POD5"
+
+# path to fasta file to use for bwa alignment.
+# a BWA index will be built if it does not exist for this fasta file
+fasta: "resources/ref/sacCer3-mature-tRNAs-dual-adapt-v2.fa"
+
+# If a kmer table if provided then the pipeline will use get_signal_metrics.py to extract metrics using remora
+# from: https://github.com/nanoporetech/kmer_models/tree/master/rna004
+remora_kmer_table: "resources/kmers/9mer_levels_v1.txt"
+
+# read classification model - remora trained model to classify charged vs uncharged reads
+remora_cca_classifier: "resources/models/cca_classifier.pt"
+
+# additional options for particular commands
+opts:
+    # additional options for dorado basecalling e.g
+    dorado: " --emit-moves "
+
+    # additional options for bwa alignment
+    # based on Novoa lab optimising bwa for tRNA alignment
+    # the -h 20 option is used to increase the number of secondary alignments reported in the XA tag
+    bwa: " -W 13 -k 6 -T 20 -x ont2d"
+
+    # requires positive strand alignment
+    # requires at least 1 5' adapter base
+    # requires 1 3' adapter base in the discriminating adapter region between charged and uncharged (v2 adapters).
+    bam_filter: "-5 24 -3 23 -s"
+
+    #requires positive strand alignment and excludes non-primary alignments
+    coverage: "--filterRNAstrand 'reverse' --samFlagExclude 256"
+
+    # pass additional options to get_signal_metrics.py script which uses Remora to calculate metrics
+    remora: ""