From c3a7788dbd3e5881877c3e5bba5ce19eb0b8959c Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 11:30:59 -0500
Subject: [PATCH 01/11] feat: Add _cigar(::Variation) function

Add a function that can convert the information contained in an
Insertion or a Deletion into a CIGAR operator.
---
 src/Variation.jl | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/src/Variation.jl b/src/Variation.jl
index 8af22bd..af9f4df 100644
--- a/src/Variation.jl
+++ b/src/Variation.jl
@@ -120,6 +120,21 @@ function Base.in(v::Variation, var::Haplotype)
     return any(v.edit == edit for edit in var.edits)
 end
 
+"""
+    _cigar(var::Variation{S,T}) where {S,T}
+
+Returns a CIGAR operation for `var`. Only supports insertions and deletions.
+
+See also [`_cigar_between`](@ref)
+"""
+function _cigar(var::Variation{S,T}) where {S,T}
+    mut = mutation(var)
+    mut isa Union{Deletion,Insertion} ||
+        throw(ArgumentError("var must be an Insertion or Deletion"))
+    cigar_letter = mut isa Deletion ? 'D' : 'I'
+    return string(length(mut), cigar_letter)
+end
+
 """
     translate(var::Variation{S,T}, aln::PairwiseAlignment{S,S}) where {S,T}
 

From e84f765357f4ff4fed39260d063f366395561af9 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 11:32:21 -0500
Subject: [PATCH 02/11] feat: Add _cigar_between(::Variation, ::Variation)
 function

Add a function that can calculate the matching bases between two
(non-matching) Variations and return a matching (M) CIGAR operation
---
 src/Variation.jl | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/src/Variation.jl b/src/Variation.jl
index af9f4df..851650a 100644
--- a/src/Variation.jl
+++ b/src/Variation.jl
@@ -135,6 +135,26 @@ function _cigar(var::Variation{S,T}) where {S,T}
     return string(length(mut), cigar_letter)
 end
 
+"""
+    _cigar_between(x::Variation{S,T}, y::Variation{S,T}) where {S,T}
+
+Returns a CIGAR operation for the (assumed) matching bases between `x` and `y`.
+
+See also [`_cigar`](@ref)
+"""
+function _cigar_between(x::Variation{S,T}, y::Variation{S,T}) where {S,T}
+    x == y && return ""
+    match_length = leftposition(y) - rightposition(x)
+    if mutation(y) isa Insertion
+        match_length -= 1
+    end
+    if mutation(y) isa Deletion
+        match_length += 1
+    end
+    match_length > 0 || return ""
+    return "$(match_length)M"
+end
+
 """
     translate(var::Variation{S,T}, aln::PairwiseAlignment{S,S}) where {S,T}
 

From 719a1239927addf4f66bb7b65fe8a83ebe2f1cd4 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 11:34:35 -0500
Subject: [PATCH 03/11] feat: Add cigar(::Haplotype) function

---
 src/Haplotype.jl         | 29 +++++++++++++++++++++++++++++
 src/SequenceVariation.jl |  2 +-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/src/Haplotype.jl b/src/Haplotype.jl
index 6d1274d..f5cf985 100644
--- a/src/Haplotype.jl
+++ b/src/Haplotype.jl
@@ -221,6 +221,35 @@ function reconstruct(h::Haplotype)
     return seq
 end
 
+"""
+    cigar(hap::Haplotype{S,T}) where {S,T}
+
+Constructs a CIGAR string representing the alignment of the sequence of `hap` to its
+reference.
+"""
+function BioAlignments.cigar(hap::Haplotype{S,T}) where {S,T}
+    cigar_string = String[]
+
+    mismatch_vars = filter(var -> !isa(mutation(var), Substitution), variations(hap))
+
+    length(mismatch_vars) > 0 || return "$(length(reference(hap)))M"
+
+    lastvar = first(mismatch_vars)
+
+    leftposition(lastvar) > 1 && push!(cigar_string, "$(leftposition(lastvar))M")
+
+    for var in mismatch_vars
+        push!(cigar_string, _cigar_between(lastvar, var))
+        push!(cigar_string, _cigar(var))
+        lastvar = var
+    end #for
+
+    remaining_bases = length(reference(hap)) - rightposition(lastvar)
+    remaining_bases > 0 && push!(cigar_string, "$(remaining_bases)M")
+
+    return join(cigar_string, "")
+end
+
 """
     translate(hap::Haplotype{S,T}, aln::PairwiseAlignment{S,S}) where {S,T}
 
diff --git a/src/SequenceVariation.jl b/src/SequenceVariation.jl
index 0e8cadd..37b0a42 100644
--- a/src/SequenceVariation.jl
+++ b/src/SequenceVariation.jl
@@ -20,7 +20,7 @@ TODO now:
 * Add tests
 """
 
-using BioAlignments: BioAlignments, PairwiseAlignment, OP_SOFT_CLIP, sequence
+using BioAlignments: BioAlignments, PairwiseAlignment, OP_SOFT_CLIP, cigar, sequence
 using BioGenerics: BioGenerics, leftposition, rightposition
 using BioSequences: BioSequences, BioSequence, NucleotideSeq, LongSequence, isgap
 using BioSymbols: BioSymbol

From 95ef4fdc620c102be07505e5b3f5d3d7bc42bb28 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 11:36:27 -0500
Subject: [PATCH 04/11] test: Add tests for cigar(::Haplotype)

---
 test/runtests.jl | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/test/runtests.jl b/test/runtests.jl
index 18ba9f1..5a5ca1b 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -31,7 +31,8 @@ using BioAlignments:
     pairalign,
     Alignment,
     AlignedSequence,
-    PairwiseAlignment
+    PairwiseAlignment,
+    cigar
 using BioSequences: BioSequence, @dna_str, ungap!
 using BioSymbols: DNA_A
 using SequenceVariation
@@ -127,6 +128,25 @@ end
     @test Variation(seq2, "A3T") < Variation(seq2, "T4A")
 end
 
+@testset "CIGAR" begin
+    reference = dna"TGATGCGTGTAGCAACACTTATAGCG"
+    reference_genotype = Haplotype(
+        reference, Variation{typeof(reference),eltype(reference)}[]
+    )
+    genotype = Haplotype(
+        reference,
+        [
+            Variation(reference, "Δ1-2"),
+            Variation(reference, "10T"),
+            Variation(reference, "Δ17-18"),
+            Variation(reference, "A23C"),
+        ],
+    )
+
+    @test cigar(reference_genotype) == "26M"
+    @test cigar(genotype) == "2D7M1I7M2D8M"
+end
+
 @testset "HaplotypeTranslation" begin
     ref1 = seq2
     ref2 = seq3

From 4817c8016add1e47e88f8eff9782407488d38a90 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 11:50:24 -0500
Subject: [PATCH 05/11] feat: Add alignment(::Haplotype) function

---
 src/Haplotype.jl         | 11 +++++++++++
 src/SequenceVariation.jl | 10 +++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/src/Haplotype.jl b/src/Haplotype.jl
index f5cf985..9164455 100644
--- a/src/Haplotype.jl
+++ b/src/Haplotype.jl
@@ -250,6 +250,17 @@ function BioAlignments.cigar(hap::Haplotype{S,T}) where {S,T}
     return join(cigar_string, "")
 end
 
+"""
+    alignment(hap::Haplotype)
+
+Gets a `PairwiseAlignment` of the mutated sequence of `hap` mapped to its refernce sequence
+"""
+function BioAlignments.alignment(hap::Haplotype)
+    return PairwiseAlignment(
+        AlignedSequence(reconstruct(hap), Alignment(cigar(hap))), reference(hap)
+    )
+end
+
 """
     translate(hap::Haplotype{S,T}, aln::PairwiseAlignment{S,S}) where {S,T}
 
diff --git a/src/SequenceVariation.jl b/src/SequenceVariation.jl
index 37b0a42..e8e7210 100644
--- a/src/SequenceVariation.jl
+++ b/src/SequenceVariation.jl
@@ -20,7 +20,15 @@ TODO now:
 * Add tests
 """
 
-using BioAlignments: BioAlignments, PairwiseAlignment, OP_SOFT_CLIP, cigar, sequence
+using BioAlignments:
+    BioAlignments,
+    Alignment,
+    AlignedSequence,
+    PairwiseAlignment,
+    OP_SOFT_CLIP,
+    alignment,
+    cigar,
+    sequence
 using BioGenerics: BioGenerics, leftposition, rightposition
 using BioSequences: BioSequences, BioSequence, NucleotideSeq, LongSequence, isgap
 using BioSymbols: BioSymbol

From db170730f0069df9141f286f1e10a919dc4545e0 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Tue, 4 Apr 2023 12:32:13 -0500
Subject: [PATCH 06/11] test: Add test for alignment(::Haplotype)

---
 test/runtests.jl | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/test/runtests.jl b/test/runtests.jl
index 5a5ca1b..f9ad9f2 100644
--- a/test/runtests.jl
+++ b/test/runtests.jl
@@ -32,6 +32,7 @@ using BioAlignments:
     Alignment,
     AlignedSequence,
     PairwiseAlignment,
+    alignment,
     cigar
 using BioSequences: BioSequence, @dna_str, ungap!
 using BioSymbols: DNA_A
@@ -147,6 +148,12 @@ end
     @test cigar(genotype) == "2D7M1I7M2D8M"
 end
 
+@testset "HaplotypeAlignment" begin
+    # This test is broken until we get a way to remove sequence info from alignments
+    # See: https://github.com/BioJulia/BioAlignments.jl/issues/90
+    @test_broken alignment(var) == align(seq1, seq2)
+end
+
 @testset "HaplotypeTranslation" begin
     ref1 = seq2
     ref2 = seq3

From 2d16c0b7b68d11bb02a40c23debc2c49aa71f2a9 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Sat, 8 Apr 2023 20:40:17 -0500
Subject: [PATCH 07/11] docs: Rename 'Variants' header to 'Haplotypes'

---
 docs/src/api.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/docs/src/api.md b/docs/src/api.md
index ef8121e..0836254 100644
--- a/docs/src/api.md
+++ b/docs/src/api.md
@@ -15,7 +15,7 @@ Deletion
 Insertion
 ```
 
-## Variants
+## Haplotypes
 
 ```@docs
 Haplotype

From 8458f74053058af5cb389ceb110d537b9794b6a8 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Sat, 8 Apr 2023 20:43:30 -0500
Subject: [PATCH 08/11] docs: Add autodocs for alignment

---
 docs/src/api.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/src/api.md b/docs/src/api.md
index 0836254..f479c15 100644
--- a/docs/src/api.md
+++ b/docs/src/api.md
@@ -22,6 +22,7 @@ Haplotype
 reference(::Haplotype)
 variations
 reconstruct
+BioAlignments.alignment
 translate(::Haplotype{S,T}, ::PairwiseAlignment{S,S}) where {S,T}
 ```
 

From 341faa45e3056fa81085cea46fb3c75ba4e48a67 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Sat, 8 Apr 2023 20:43:50 -0500
Subject: [PATCH 09/11] docs: Add autodocs for cigar

---
 docs/src/api.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/docs/src/api.md b/docs/src/api.md
index f479c15..86277f0 100644
--- a/docs/src/api.md
+++ b/docs/src/api.md
@@ -23,6 +23,7 @@ reference(::Haplotype)
 variations
 reconstruct
 BioAlignments.alignment
+BioAlignment.cigar
 translate(::Haplotype{S,T}, ::PairwiseAlignment{S,S}) where {S,T}
 ```
 

From 6b2bd018e2e6b5cdd1817b886d0fbe868305d1f7 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Sat, 8 Apr 2023 20:44:21 -0500
Subject: [PATCH 10/11] docs: Add examples of alignment getters

---
 docs/src/haplotypes.md | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/docs/src/haplotypes.md b/docs/src/haplotypes.md
index 4694b45..b462dba 100644
--- a/docs/src/haplotypes.md
+++ b/docs/src/haplotypes.md
@@ -39,6 +39,24 @@ human2 == bovine
 human2 == human
 ```
 
+## Alignment reconstruction
+
+Just like [Sequence reconstruction](@ref), alignments can also be reconstructed
+from `Haplotype`s using the extension of the [`BioAlignments.alignment`](@ref)
+function.
+
+```@repl call_variants
+human_alignment = alignment(bos_human_haplotype)
+human_alignment == bos_human_alignment
+```
+
+Alternatively, you can get the information in CIGAR format using the
+extension of the [`BioAlignments.cigar`](@ref) function.
+
+```@repl call_variants
+cigar(bos_human_haplotype)
+```
+
 ## Reference switching
 
 All variations within a haplotype can be mapped to a new reference sequence

From 373e485802031d4b7eb29fae8943f575ae36cabb Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Sat, 8 Apr 2023 20:51:09 -0500
Subject: [PATCH 11/11] chore: Update CHANGELOG

---
 CHANGELOG.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 656a9a3..e7c07f5 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Added
+
+- `alignment` and `cigar` getters for `Haplotype`s ([#39](https://github.com/BioJulia/SequenceVariation.jl/issues/39)/[#42](https://github.com/BioJulia/SequenceVariation.jl/pull/42))
+
 ## [0.2.2] - 2023-01-28
 
 ### Fixed