fix: added missing dependencies and improved docs (#450)

* Added mising dependencies and improved docs

* Reformat

* Small tweaks

* Improved description

bio/mapdamage2/environment.yaml

@@ -4,3 +4,5 @@ channels:
   - defaults
 dependencies:
   - mapdamage2 =2.2
+  - python >=3.9
+  - pysam >=0.17

bio/mapdamage2/meta.yaml

@@ -1,4 +1,30 @@
 name: mapDamage2
-description: tracking and quantifying damage patterns in ancient DNA sequences. For more information about MapDamage2 see `MapDamage2 documentation <https://ginolhac.github.io/mapDamage/>`_.
+description: mapDamage2 is a computational framework written in Python and R, which tracks and quantifies DNA damage patterns among ancient DNA sequencing reads generated by Next-Generation Sequencing platforms.
 authors:
   - Filipe G. Vieira
+input:
+  - reference genome
+  - SAM/BAM/CRAM alignemnt
+output:
+  - Runtime_log.txt: log file with a summary of command lines used and timestamps.
+  # If plotting
+  - Fragmisincorporation_plot.pdf, a pdf file that displays both fragmentation and misincorporation patterns.
+  - Length_plot.pdf, a pdf file that displays length distribution of singleton reads per strand and cumulative frequencies of C->T at 5'-end and G->A at 3'-end are also displayed per strand.
+  - misincorporation.txt, contains a table with occurrences for each type of mutations and relative positions from the reads ends.
+  - 5pCtoT_freq.txt, contains frequencies of Cytosine to Thymine mutations per position from the 5'-ends.
+  - 3pGtoA_freq.txt, contains frequencies of Guanine to Adenine mutations per position from the 3'-ends.
+  - dnacomp.txt, contains a table of the reference genome base composition per position, inside reads and adjacent regions.
+  - lgdistribution.txt, contains a table with read length distributions per strand.
+  # If stats output
+  - Stats_out_MCMC_hist.pdf, MCMC histogram for the damage parameters and log likelihood.
+  - Stats_out_MCMC_iter.csv, values for the damage parameters and log likelihood in each MCMC iteration.
+  - Stats_out_MCMC_trace.pdf, a MCMC trace plot for the damage parameters and log likelihood.
+  - Stats_out_MCMC_iter_summ_stat.csv, summary statistics for the damage parameters estimated posterior distributions.
+  - Stats_out_post_pred.pdf, empirical misincorporation frequency and posterior predictive intervals from the fitted model.
+  - Stats_out_MCMC_correct_prob.csv, position specific probability of a C->T and G->A misincorporation is due to damage.
+  - dnacomp_genome.txt, contains the global reference genome base composition (computed by seqtk).
+  # If rescaled BAM output
+  - Rescaled BAM file, where likely post-mortem damaged bases have downscaled quality scores.
+notes: |
+  * The `extra` param allows for additional program arguments.
+  * For more information see, https://ginolhac.github.io/mapDamage/

bio/mapdamage2/test/Snakefile

@@ -11,11 +11,11 @@ rule mapdamage2:
         len="results/{sample}/Length_plot.pdf",
         lg_dist="results/{sample}/lgdistribution.txt",
         misincorp="results/{sample}/misincorporation.txt",
-#        rescaled_bam="results/{sample}.rescaled.bam", # uncomment if you want the rescaled BAM file
+    #   rescaled_bam="results/{sample}.rescaled.bam", # uncomment if you want the rescaled BAM file
     params:
-        extra="--no-stats"  # optional parameters for mapdamage2 (except -i, -r, -d, --rescale)
+        extra="--no-stats",  # optional parameters for mapdamage2 (except -i, -r, -d, --rescale)
     log:
-        "logs/{sample}/mapdamage2.log"
+        "logs/{sample}/mapdamage2.log",
     threads: 1  # MapDamage2 is not threaded
     wrapper:
         "master/bio/mapdamage2"