Module Biokepi_bfx_tools.Samtools (.ml)

module Samtools: sig .. end

module Remove: Biokepi_run_environment.Workflow_utilities.Remove
val sam_to_bam : run_with:Biokepi_run_environment.Machine.t ->
reference_build:string ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< escaped_sample_name : string;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; reference_build : string; sample_name : string;
sorting : [ `Coordinate | `Read_name ] option >
Biokepi_run_environment.Common.KEDSL.workflow_node
val faidx : run_with:Biokepi_run_environment.Machine.t ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val flagstat : run_with:Biokepi_run_environment.Machine.t ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val bgzip : run_with:Biokepi_run_environment.Machine.t ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
string ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val tabix : run_with:Biokepi_run_environment.Machine.t ->
tabular_format:[< `Bed | `Gff | `Psltab | `Sam | `Vcf ] ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val do_on_bam : run_with:Biokepi_run_environment.Machine.t ->
?more_depends_on:Biokepi_run_environment.Common.KEDSL.workflow_edge list ->
name:string ->
?more_requirements:Biokepi_run_environment.Machine.Make_fun.Requirement.t
list ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : 'a; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
product:(< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; .. >
as 'b)
Biokepi_run_environment.Common.KEDSL.product ->
make_command:('a -> string -> string list) ->
'b Biokepi_run_environment.Common.KEDSL.workflow_node
val sort_bam_no_check : run_with:Biokepi_run_environment.Machine.t ->
by:[ `Coordinate | `Read_name ] ->
< escaped_sample_name : string;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; reference_build : string; sample_name : string;
sorting : [ `Coordinate | `Read_name ] option >
Biokepi_run_environment.Common.KEDSL.product
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< escaped_sample_name : string;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; reference_build : string; sample_name : string;
sorting : [ `Coordinate | `Read_name ] option >
Biokepi_run_environment.Common.KEDSL.workflow_node
val sort_bam_if_necessary : run_with:Biokepi_run_environment.Machine.t ->
by:[ `Coordinate | `Read_name ] ->
Biokepi_run_environment.Common.KEDSL.bam_file
Biokepi_run_environment.Common.KEDSL.workflow_node ->
Biokepi_run_environment.Common.KEDSL.bam_file
Biokepi_run_environment.Common.KEDSL.workflow_node
Uses "samtools sort" if the input_bam is not tagged as “sorted as the ~by argument.” If it is indeed already sorted the function returns the input_bam node as is.
val index_to_bai : run_with:Biokepi_run_environment.Machine.t ->
?check_sorted:bool ->
< is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; sorting : [> `Read_name ] option; .. >
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val mpileup : run_with:Biokepi_run_environment.Machine.t ->
?adjust_mapq:int ->
region:[< `Chromosome of string
| `Chromosome_interval of string * int * int
| `Full ] ->
Biokepi_run_environment.Common.KEDSL.bam_file
Biokepi_run_environment.Common.KEDSL.workflow_node ->
< exists : Ketrew_pure.Target.Condition.t;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_bigger_than : int -> Ketrew_pure.Target.Condition.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string >
Biokepi_run_environment.Common.KEDSL.workflow_node
val merge_bams : run_with:Biokepi_run_environment.Machine.t ->
?delete_input_on_success:bool ->
?attach_rg_tag:bool ->
?uncompressed_bam_output:bool ->
?compress_level_one:bool ->
?combine_rg_headers:bool ->
?combine_pg_headers:bool ->
Biokepi_run_environment.Common.KEDSL.bam_file
Biokepi_run_environment.Common.KEDSL.workflow_node list ->
string ->
< escaped_sample_name : string;
host : Biokepi_run_environment.Common.KEDSL.Host.t;
is_done : Biokepi_run_environment.Common.KEDSL.Condition.t option;
path : string; reference_build : string; sample_name : string;
sorting : [ `Coordinate | `Read_name ] option >
Biokepi_run_environment.Common.KEDSL.workflow_node
Merge a list of BAM files.

The BAMs will be sorted, by coordinate, if they are not already.

"samtools merge" fails if the list of bams has only one (or zero) bams, so this functions raises an exception if input_bam_list has lenth < 2.

By default, duplicate @PG and @RG IDs will be automatically uniquified with a random suffix.