Merge pull request #27 from camilogarciabotero/decoupling

Decoupling findorfs method
camilogarciabotero · Mar 30, 2024 · 7704d98 · 7704d98
2 parents 01ae7b7 + 92b0e22
commit 7704d98
Show file tree

Hide file tree

Showing 17 changed files with 491 additions and 457 deletions.
diff --git a/.gitignore b/.gitignore
@@ -4,4 +4,5 @@
 /docs/build/
 .travis.yml
 /docs/src/*_cache
-/docs/src/*_files
+/docs/src/*_files
+/test/Manifest.toml
diff --git a/Manifest.toml b/Manifest.toml
@@ -1,20 +1,8 @@
 # This file is machine-generated - editing it directly is not advised
 
-julia_version = "1.10.0"
+julia_version = "1.10.2"
 manifest_format = "2.0"
-project_hash = "4f6774eaeaec568c8cb7a865a84c0c7d9a180727"
-
-[[deps.Automa]]
-deps = ["PrecompileTools", "TranscodingStreams"]
-git-tree-sha1 = "588e0d680ad1d7201d4c6a804dcb1cd9cba79fbb"
-uuid = "67c07d97-cdcb-5c2c-af73-a7f9c32a568b"
-version = "1.0.3"
-
-[[deps.BioGenerics]]
-deps = ["TranscodingStreams"]
-git-tree-sha1 = "7bbc085aebc6faa615740b63756e4986c9e85a70"
-uuid = "47718e42-2ac5-11e9-14af-e5595289c2ea"
-version = "0.1.4"
+project_hash = "0426921543f1f35e1faa99ad2688f4a61508977b"
 
 [[deps.BioSequences]]
 deps = ["BioSymbols", "PrecompileTools", "Random", "Twiddle"]
@@ -32,32 +20,22 @@ version = "5.1.3"
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
 
-[[deps.FASTX]]
-deps = ["Automa", "BioGenerics", "PrecompileTools", "StringViews", "TranscodingStreams"]
-git-tree-sha1 = "bff5d62bf5e1c382a370ac701bcaea9a24115ac6"
-uuid = "c2308a5c-f048-11e8-3e8a-31650f418d12"
-version = "2.1.4"
-weakdeps = ["BioSequences"]
-
-    [deps.FASTX.extensions]
-    BioSequencesExt = "BioSequences"
-
 [[deps.IterTools]]
 git-tree-sha1 = "42d5f897009e7ff2cf88db414a389e5ed1bdd023"
 uuid = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
 version = "1.10.0"
 
 [[deps.PrecompileTools]]
 deps = ["Preferences"]
-git-tree-sha1 = "03b4c25b43cb84cee5c90aa9b5ea0a78fd848d2f"
+git-tree-sha1 = "5aa36f7049a63a1528fe8f7c3f2113413ffd4e1f"
 uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
-version = "1.2.0"
+version = "1.2.1"
 
 [[deps.Preferences]]
 deps = ["TOML"]
-git-tree-sha1 = "00805cd429dcb4870060ff49ef443486c262e38e"
+git-tree-sha1 = "9306f6085165d270f7e3db02af26a400d580f5c6"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
-version = "1.4.1"
+version = "1.4.3"
 
 [[deps.Printf]]
 deps = ["Unicode"]
@@ -71,28 +49,11 @@ uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
 version = "0.7.0"
 
-[[deps.StringViews]]
-git-tree-sha1 = "f7b06677eae2571c888fd686ba88047d8738b0e3"
-uuid = "354b36f9-a18e-4713-926e-db85100087ba"
-version = "1.3.3"
-
 [[deps.TOML]]
 deps = ["Dates"]
 uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
 version = "1.0.3"
 
-[[deps.TranscodingStreams]]
-git-tree-sha1 = "54194d92959d8ebaa8e26227dbe3cdefcdcd594f"
-uuid = "3bb67fe8-82b1-5028-8e26-92a6c54297fa"
-version = "0.10.3"
-
-    [deps.TranscodingStreams.extensions]
-    TestExt = ["Test", "Random"]
-
-    [deps.TranscodingStreams.weakdeps]
-    Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-    Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
-
 [[deps.Twiddle]]
 git-tree-sha1 = "29509c4862bfb5da9e76eb6937125ab93986270a"
 uuid = "7200193e-83a8-5a55-b20d-5d36d44a0795"

diff --git a/Project.toml b/Project.toml
@@ -5,13 +5,11 @@ version = "0.2.0"
 
 [deps]
 BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
-FASTX = "c2308a5c-f048-11e8-3e8a-31650f418d12"
 IterTools = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
 PrecompileTools = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
 
 [compat]
 BioSequences = "3"
-FASTX = "2"
 IterTools = "1.4"
 PrecompileTools = "1"
 julia = "1"

diff --git a/README.md b/README.md
@@ -53,18 +53,18 @@ Now lest us find the ORFs
 findorfs(seq)
 
 12-element Vector{ORF}:
- ORF(29:40, '+', 2)
- ORF(137:145, '+', 2)
- ORF(164:184, '+', 2)
- ORF(173:184, '+', 2)
- ORF(236:241, '+', 2)
- ORF(248:268, '+', 2)
- ORF(362:373, '+', 2)
- ORF(470:496, '+', 2)
- ORF(551:574, '+', 2)
- ORF(569:574, '+', 2)
- ORF(581:601, '+', 2)
- ORF(695:706, '+', 2)
+ ORF(29:40, '+', 2, 0.0)
+ ORF(137:145, '+', 2, 0.0)
+ ORF(164:184, '+', 2, 0.0)
+ ORF(173:184, '+', 2, 0.0)
+ ORF(236:241, '+', 2, 0.0)
+ ORF(248:268, '+', 2, 0.0)
+ ORF(362:373, '+', 2, 0.0)
+ ORF(470:496, '+', 2, 0.0)
+ ORF(551:574, '+', 2, 0.0)
+ ORF(569:574, '+', 2, 0.0)
+ ORF(581:601, '+', 2, 0.0)
+ ORF(695:706, '+', 2, 0.0)
 ```
 
 Two other functions (`get_orfs_dna` and `get_orfs_aa`) are implemented to get the ORFs in DNA and amino acid sequences, respectively. They use the `findorfs` function to first get the ORFs and then get the correspondance array of `BioSequence` objects.

diff --git a/docs/src/simplefinder.md b/docs/src/simplefinder.md
@@ -15,18 +15,18 @@ Now lest us find the ORFs
 findorfs(seq)
 
 12-element Vector{ORF}:
- ORF(29:40, '+', 2)
- ORF(137:145, '+', 2)
- ORF(164:184, '+', 2)
- ORF(173:184, '+', 2)
- ORF(236:241, '+', 2)
- ORF(248:268, '+', 2)
- ORF(362:373, '+', 2)
- ORF(470:496, '+', 2)
- ORF(551:574, '+', 2)
- ORF(569:574, '+', 2)
- ORF(581:601, '+', 2)
- ORF(695:706, '+', 2)
+ ORF(29:40, '+', 2, 0.0)
+ ORF(137:145, '+', 2, 0.0)
+ ORF(164:184, '+', 2, 0.0)
+ ORF(173:184, '+', 2, 0.0)
+ ORF(236:241, '+', 2, 0.0)
+ ORF(248:268, '+', 2, 0.0)
+ ORF(362:373, '+', 2, 0.0)
+ ORF(470:496, '+', 2, 0.0)
+ ORF(551:574, '+', 2, 0.0)
+ ORF(569:574, '+', 2, 0.0)
+ ORF(581:601, '+', 2, 0.0)
+ ORF(695:706, '+', 2, 0.0)
 ```
 
 Two other functions (`get_orfs_dna` and `get_orfs_aa`) are implemented to get the ORFs in DNA and amino acid sequences, respectively. They use the `findorfs` function to first get the ORFs and then get the correspondance array of `BioSequence` objects.

diff --git a/src/GeneFinder.jl b/src/GeneFinder.jl
@@ -20,22 +20,16 @@ using BioSequences:
     ncbi_trans_table,
     translate
 
-using FASTX: FASTAReader, FASTARecord, description, sequence
+# using FASTX: FASTAReader, FASTARecord, description, sequence
 using IterTools: takewhile, iterated
 using PrecompileTools: @setup_workload, @compile_workload
 
+include("algorithms/naivefinder.jl")
 include("types.jl")
-export ORF
-
-include("algorithms/findorfs.jl")
-export locationiterator, findorfs, get_orfs_dna, get_orfs_aa, record_orfs_fna, record_orfs_faa
-
+include("findorfs.jl")
+include("getorfs.jl")
 include("io.jl")
-export write_orfs_fna, write_orfs_faa, write_orfs_bed, write_orfs_gff
-
 include("utils.jl")
-export fasta_to_dna, hasprematurestop
-
 include("extended.jl")
 
 @setup_workload begin
@@ -46,8 +40,6 @@ include("extended.jl")
         # all calls in this block will be precompiled, regardless of whether
         # they belong to your package or not (on Julia 1.8 and higher)
         findorfs(seq)
-        get_orfs_dna(seq)
-        get_orfs_aa(seq)
     end
 end