command line documentation

rename the file name to be consistent wit the out file file sufflix

pgr-bin/src/bin/pgr-fetch-seqs.rs

@@ -11,17 +11,22 @@ use std::path::Path;
 #[clap(author, version)]
 #[clap(about = "list or fetch sequences from a pgr database", long_about = None)]
 struct CmdOptions {
+    /// the prefix to a PGR-TK sequence database
     pgr_db_prefix: String,
 
+    /// using the frg format for the sequence database (default to the AGC backend databse if not specified)
     #[clap(long, default_value_t = false)]
     frg_file: bool,
 
+    /// the regions file path
     #[clap(short, long, default_value=None)]
     region_file: Option<String>,
 
+    /// output file name
     #[clap(short, long, default_value=None)]
     output_file: Option<String>,
 
+    /// list all sequence source, contig names in the database
     #[clap(long, default_value_t = false)]
     list: bool,
 }

pgr-bin/src/bin/pgr-make-fragdb.rs → pgr-bin/src/bin/pgr-make-frgdb.rs

@@ -9,11 +9,11 @@ use std::io::{BufRead, BufReader};
 use std::path::Path;
 
 #[derive(Parser, Debug)]
-#[clap(name = "pgr-mdb")]
+#[clap(name = "pgr-make-frgdb")]
 #[clap(author, version)]
-#[clap(about = "create pgr fragment minimizer db", long_about = None)]
+#[clap(about = "create PGR-TK fragment minimizer database with frg format backend", long_about = None)]
 struct CmdOptions {
-    // file contains the paths to the fastx files to load
+    /// the path to the file contains the paths to the fastx files to load
     filepath: String,
     prefix: String,
     /// minimizer window size

pgr-bin/src/bin/pgr-pbundle-bed2sorted.rs

@@ -10,7 +10,9 @@ use std::{fs::File, path};
 #[clap(author, version)]
 #[clap(about = "sort the contig by bunldes", long_about = None)]
 struct CmdOptions {
+    /// the path to the pricipal bundle bed file
     bed_file_path: String,
+    /// the prefix of the output file
     output_prefix: String,
 }
 

pgr-bin/src/bin/pgr-pbundle-bed2svg.rs

@@ -11,28 +11,41 @@ use svg::Document;
 #[clap(author, version)]
 #[clap(about = "generate SVG from a principal bundle bed file", long_about = None)]
 struct CmdOptions {
+    /// the path to the pricipal bundle bed file
     bed_file_path: String,
+    /// the prefix of the output file
     output_prefix: String,
+    /// the prefix of the dendrogram file generated by pgr-pbundle-bed2dist
     #[clap(long)]
     ddg_file: Option<String>,
+    /// the path the annotation files 
     #[clap(long)]
     annotations: Option<String>,
+    /// the path the annotation track file 
     #[clap(long)]
     annotation_region_bedfile: Option<String>,
+    /// the track range in base pair count
     #[clap(long, default_value_t = 100000)]
     track_range: usize,
+    /// the track tick interval
     #[clap(long, default_value_t = 10000)]
     track_tick_interval: usize,
+    /// the track panel size in pixel
     #[clap(long, default_value_t = 1600)]
     track_panel_width: usize,
+    /// the left padding in pixel
     #[clap(long)]
     left_padding: Option<usize>,
+    /// the stroke boundary width
     #[clap(long, default_value_t = 0.5)]
     stroke_width: f32,
+    /// the stroke with for the annotation track
     #[clap(long, default_value_t = 2.5)]
     annotation_region_stroke_width: f32,
+    /// the anotation panel width
     #[clap(long, default_value_t = 500.0)]
     annotation_panel_width: f32,
+    /// the factor to increase the bounder width for highlighting repeatitive bundles
     #[clap(long, default_value_t = 1.0)]
     highlight_repeats: f32,
 }

pgr-bin/src/bin/pgr-pbundle-decomp.rs

@@ -15,24 +15,35 @@ use std::{
 #[clap(author, version)]
 #[clap(about = "take a fasta file and output the principal bundle decomposition though MAP Graph", long_about = None)]
 struct CmdOptions {
+    /// the path to the input fasta file
     fastx_path: String,
+    /// the prefix of the output files
     output_prefix: String,
+    /// the path to the file that contains a list of contig name to be analyzed
     #[clap(long, short, default_value = None)]
     include: Option<String>,
+    /// the SHIMMER parameter w
     #[clap(short, default_value_t = 48)]
     w: u32,
+    /// the SHIMMER parameter k
     #[clap(short, default_value_t = 56)]
     k: u32,
+    /// the SHIMMER parameter r
     #[clap(short, default_value_t = 4)]
     r: u32,
+    /// the SHIMMER parameter minimum span length
     #[clap(long, default_value_t = 12)]
     min_span: u32,
+    /// minimum coverage to be included in principal bundles
     #[clap(long, default_value_t = 0)]
     min_cov: usize,
+    /// the minimum branch length to be included in the principal bundles
     #[clap(long, default_value_t = 8)]
     min_branch_size: usize,
+    /// the minimum local project bundle size to includes 
     #[clap(long, default_value_t = 2500)]
     bundle_length_cutoff: usize,
+    /// merge two bundles with the same id with the specified length
     #[clap(long, default_value_t = 10000)]
     bundle_merge_distance: usize,
 }

pgr-bin/src/bin/pgr-query.rs

@@ -12,28 +12,38 @@ use std::path::Path;
 #[clap(author, version)]
 #[clap(about = "query a pgr pangenome database and ouput the hits", long_about = None)]
 struct CmdOptions {
+    /// the prefix to a PGR-TK sequence database
     pgr_db_prefix: String,
+    /// the path to the query fasta file
     query_fastx_path: String,
+    /// the prefix of the output file 
     output_prfix: String,
 
+    /// using the frg format for the sequence database (default to the AGC backend databse if not specified)
     #[clap(long, default_value_t = false)]
     frg_file: bool,
 
+    /// the gap penality factor for sparse alignments in the SHIMMER space
     #[clap(long, short, default_value_t = 0.025)]
     gap_penality_factor: f32,
 
+    /// merge hits with the specified distance
     #[clap(long, short, default_value_t = 100000)]
     merge_range_tol: usize,
 
+    /// the max count of SHIMMER used for the sparse alignemnt 
     #[clap(long, default_value_t = 128)]
     max_count: u32,
 
+    /// the max count of SHIMMER in the query sequences used for the sparse alignemnt 
     #[clap(long, default_value_t = 128)]
     max_query_count: u32,
 
+    /// the max count of SHIMMER in the targets sequences used for the sparse alignemnt 
     #[clap(long, default_value_t = 128)]
     max_target_count: u32,
 
+    /// the span of the chain for building the sparse alignment directed acyclic graph 
     #[clap(long, default_value_t = 8)]
     max_aln_chain_span: u32,
 }