new param wfmash_hg_filter_ani_diff

conf/modules.config

@@ -113,6 +113,7 @@ process {
                 "-H ${params.wfmash_mash_kmer_thres}",
                 "${wfmash_sparse_map_cmd}",
                 params.wfmash_temp_dir         ? "-B ${wfmash_temp_dir}"             : "",
+                "-2 ${params.wfmash_hg_filter_ani_diff}",
             ].join(" ").trim()
         }
         publishDir = [
@@ -137,6 +138,7 @@ process {
                 "${wfmash_sparse_map_cmd}",
                 params.wfmash_temp_dir         ? "-B ${wfmash_temp_dir}"             : "",
                 "-m",
+                "-2 ${params.wfmash_hg_filter_ani_diff}",
             ].join(" ").trim()
         }
         publishDir = [
@@ -161,6 +163,7 @@ process {
                 "${wfmash_sparse_map_cmd}",
                 params.wfmash_temp_dir         ? "-B ${wfmash_temp_dir}"             : "",
                 "-m",
+                "-2 ${params.wfmash_hg_filter_ani_diff}",
             ].join(" ").trim()
         }
         publishDir = [
@@ -194,6 +197,7 @@ process {
                 "${wfmash_sparse_map_cmd}",
                 params.wfmash_temp_dir         ? "-B ${wfmash_temp_dir}"             : "",
                 "--invert-filtering",
+                "-2 ${params.wfmash_hg_filter_ani_diff}",
             ].join(" ").trim()
         }
         publishDir = [

nextflow.config

@@ -26,6 +26,7 @@ params {
     wfmash_chunks               = 1
     wfmash_only                 = false
     wfmash_temp_dir             = null
+    wfmash_hg_filter_ani_diff   = 30
 
     // Seqwish options
     seqwish_paf = null

nextflow_schema.json

@@ -54,13 +54,13 @@
             "properties": {
                 "wfmash_map_pct_id": {
                     "type": "number",
-                    "default": 90.0,
+                    "default": 90,
                     "description": "Percent identity in the wfmash mashmap step.",
                     "help_text": "Use `mash dist` or `mash triangle` to explore the typical level of divergence between the sequences in your input (see https://pggb.readthedocs.io/en/latest/rst/tutorials/divergence_estimation.html#divergence-estimation for more information). Convert this to an approximate percent identity and provide it as --wfmash_map_pct_id <PCT>. A list of examples can be found at https://github.com/pangenome/pggb#example-builds-for-diverse-species."
                 },
                 "wfmash_segment_length": {
                     "type": "string",
-                    "default": 5000,
+                    "default": "5000",
                     "description": "Segment length for mapping.",
                     "help_text": "Crucially, --wfmash_segment_length provides a kind of minimum alignment length filter. The `mashmap3` step in `wfmash` will only consider segments of this size. For small pangenome graphs, or where there are few repeats, --wfmash_segment_length can be set low (for example 500 when building a MHC pangenome graph). However, for larger contexts, with repeats, it can be very important to set this high (for instance 50k in the case of human genomes). A long segment length ensures that we represent long collinear regions of the input sequences in the structure of the graph. In general, this should at least be larger than transposons and other common repeats in your pangenome. A list of examples can be found at https://github.com/pangenome/pggb#example-builds-for-diverse-species.",
                     "pattern": "^([1-9]\\d*[kKmMgGtT]?|0)$"
@@ -114,6 +114,10 @@
                 "wfmash_only": {
                     "type": "boolean",
                     "description": "If this parameter is set, only the wfmash alignment step of the pipeline is executed. This option is offered for users who want to run wfmash on a cluster."
+                },
+                "wfmash_hg_filter_ani_diff": {
+                    "type": "integer",
+                    "default": 30
                 }
             }
         },
@@ -131,14 +135,14 @@
                 },
                 "seqwish_transclose_batch": {
                     "type": "string",
-                    "default": 10000000,
+                    "default": "10000000",
                     "description": "Number of base pairs to use for transitive closure batch.",
                     "help_text": "If you run out of memory during the seqwish step, you can lower this value. It will take longer, but it will use less memory.",
                     "pattern": "^([1-9]\\d*[kKmMgGtT]?|0)$"
                 },
                 "seqwish_sparse_factor": {
                     "type": "number",
-                    "default": 0.0,
+                    "default": 0,
                     "description": "Keep this randomly selected fraction of input matches."
                 },
                 "seqwish_temp_dir": {