migrating to Automav1, TranscodingStreams, BioGenerics etc

.github/workflows/UnitTests.yml

@@ -1,34 +1,30 @@
 name: Unit Tests
 
 on:
-  - push
-  - pull_request
+  push:
+      branches:
+        - master
+        - develop
+  pull_request:
 
 jobs:
   test:
-    name: Julia ${{ matrix.julia-version }} - ${{ matrix.os }} - ${{ matrix.julia-arch }} - ${{ github.event_name }}
     runs-on: ${{ matrix.os }}
-    continue-on-error: ${{ matrix.julia-version == 'nightly' }}
+    continue-on-error: ${{ matrix.experimental }}
     strategy:
       fail-fast: false
       matrix:
         julia-version:
-          - '1.0'
-          - '1.5'
-          - '1.6' # LTS
-          - '1'
-        julia-arch: [x64, x86]
-        os: [ubuntu-latest, windows-latest, macOS-latest]
-        exclude:
-          - os: macOS-latest
-            julia-arch: x86
+          - '1.10'
+        os: [ubuntu-latest, macOS-latest, windows-latest]
         experimental: [false]
         include:
+          # Include nightly, but experimental, so it's allowed to fail without
+          # failing CI.
           - julia-version: nightly
-            julia-arch: x64
             os: ubuntu-latest
             experimental: true
-
+            fail_ci_if_error: false
     steps:
       - name: Checkout Repository
         uses: actions/checkout@v2

CHANGELOG.md

@@ -4,9 +4,23 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
-## [Unreleased]
+## [Unreleased] 
 ### Added
 - :arrow_up: Added Project.toml
+- Automa v1 compatibility: Upgraded the Automa dependency to "1", enabling the new Automav1 API.
+- BioGenerics support: Imported metadata functions from BioGenerics to unify VCF/BCF header handling.
+- TranscodingStreams integration: Added using TranscodingStreams for more efficient stream transformations in VCF/BCF readers.
+- New VCF record reader: Introduced `src/vcf/readrecord.jl` to encapsulate record parsing logic.
+
+### Changed
+- Streamlined imports: Limited BioSequences imports, upgraded BGZFStreams and BufferedStreams usage, and replaced BioCore I/O types with BioGenerics abstractions.
+- BCF reader refactoring: Transitioned Reader to subtype BioGenerics.IO.AbstractReader, centralized exception handling, and cleaned up parse logic.
+- VCF header & metainfo: Fixed header parsing and improved metainfo tag/value functions to use BioGenerics APIs.
+- Project.toml targets: Reorganized `[extras]` and `[targets]` sections.
+
+### Removed
+- Deprecated dependencies: Dropped older Automa versions (0.7, 0.8) and obsolete IO imports from BioCore.
+
 
 ## [0.4.0] - 2018-11-22
 ### Added

Project.toml

@@ -1,33 +1,39 @@
 name = "GeneticVariation"
 uuid = "9bc6ac9d-e6b2-5f70-b0a8-242a01662520"
-authors = ["Kenta Sato <bicycle1885@gmail.com>", "Sabrina J. Ward <sabrinajward@protonmail.com>"]
-
-version = "0.4.1"
+authors = ["Kenta Sato <bicycle1885@gmail.com>", "Sabrina J. Ward <sabrinajward@protonmail.com>", "Abhinav Singh <abhinavsns7@gmail.com>"]
+version = "0.5.0"
 
 [deps]
 Automa = "67c07d97-cdcb-5c2c-af73-a7f9c32a568b"
 BGZFStreams = "28d598bf-9b8f-59f1-b38c-5a06b4a0f5e6"
-BioCore = "37cfa864-2cd6-5c12-ad9e-b6597d696c81"
+BioGenerics = "47718e42-2ac5-11e9-14af-e5595289c2ea"
 BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
-BufferedStreams = "e1450e63-4bb3-523b-b2a4-4ffa8c0fd77d"
 Combinatorics = "861a8166-3701-5b0c-9a16-15d98fcdc6aa"
+Indexes = "4ffb77ac-cb80-11e8-1b35-4b78cc642f6d"
 IntervalTrees = "524e6230-43b7-53ae-be76-1e9e4d08d11b"
+MinHash = "4b3c9753-2685-44e9-8a29-365b96c023ed"
+Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
+TranscodingStreams = "3bb67fe8-82b1-5028-8e26-92a6c54297fa"
 Twiddle = "7200193e-83a8-5a55-b20d-5d36d44a0795"
 
 [compat]
-Automa = "0.7, 0.8"
+Automa = "1"
 BGZFStreams = "0.3"
-BioCore = "2.0.5"
-BioSequences = "1"
-BufferedStreams = "1"
-Combinatorics = "0.7"
-IntervalTrees = "1"
-Twiddle = "1.1"
+BioGenerics = "0.1"
+BioSequences = "3.4"
+Combinatorics = "1"
+Indexes = "0.1, 0.2"
+IntervalTrees = "1.1"
+MinHash = "0.2"
+Statistics = "1"
+TranscodingStreams = "0.9"
+Twiddle = "1"
 julia = "1"
 
 [extras]
+FormatSpecimens = "3372ea36-2a1a-11e9-3eb7-996970b6ffbd"
+TOML = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
-YAML = "ddb6d928-2868-570f-bddf-ab3f9cf99eb6"
 
 [targets]
-test = ["Test", "YAML"]
+test = ["Test", "FormatSpecimens", "TOML"]

src/GeneticVariation.jl

@@ -11,22 +11,18 @@ __precompile__()
 module GeneticVariation
 
 export
-    # Site types
-    Conserved,
-    Mutated,
-    #Transition,
-    #Transversion,
-    Segregating,
+    segregating_sites,
+    count_segregating_sites,
 
     # Distances
-    Proportion,
-    Jaccard,
-    MASH,
+    create_sketch, 
+    jaccard, 
+    mash, 
     distance,
     pdistance,
-    mash,
-    jaccard,
-
+    pdistance_mutated,
+    jukes_cantor,
+    kimura_distance,
     # Allele frequencies
     gene_frequencies,
 
@@ -37,36 +33,24 @@ export
     # VCF and BCF
     VCF,
     BCF,
-    header,
-    metainfotag,
-    metainfoval,
-    isfilled,
-    MissingFieldException
+    header
 
+# Import only the necessary symbols from BioSequences v3.
 import BioSequences:
     BioSequences,
     Alphabet,
     AA_Term,
     BioSequence,
-    bp_chunk_count,
-    Certain,
-    Composition,
     DNAAlphabet,
     GeneticCode,
     ispurine,
-    Kmer,
-    Match,
-    Mismatch,
-    MinHashSketch,
-    NucAlphs,
-    Position,
-    RNAAlphabet,
-    Sequence
-
-import BioCore:
-    metainfotag,
-    metainfoval,
-    header
+    RNAAlphabet
+
+# Import metadata functions from BioGenerics
+import BioGenerics: header, metainfotag, metainfoval, isfilled
+using Indexes
+using TranscodingStreams
+#import BioGenerics.Exceptions: MissingFieldException, missingerror
 
 import Combinatorics.permutations
 import IntervalTrees: Interval, IntervalValue
@@ -80,9 +64,9 @@ import Twiddle:
 include("vcf/vcf.jl")
 include("bcf/bcf.jl")
 include("site_counting.jl")
-include("seg_sites.jl")
 include("distances/minhash.jl")
 include("distances/proportion.jl")
+include("distances/evodistances.jl")
 include("allele_freq.jl")
 include("diversity_measures.jl")
 

src/allele_freq.jl

@@ -6,50 +6,23 @@
 # This file is a part of BioJulia.
 # License is MIT: https://github.com/BioJulia/GeneticVariation.jl/blob/master/LICENSE.md
 
-"""
-    gene_frequencies(seqcounts::Composition{T}) where T <: Sequence
-
-Compute gene_frequencies from a `BioSequences.Composition` variable that contains
-unique sequence counts.
-"""
-function gene_frequencies(seqcounts::Composition{T}) where T <: Sequence
-    n = sum(values(seqcounts))
-    frequencies = Dict{T, Float64}()
-    @inbounds for (seq, count) in seqcounts
-        frequencies[seq] = count / n
-    end
-    return frequencies
-end
+using BioSequences 
 
 """
     gene_frequencies(iterable)
 
-Compute the gene frequencies for any iterable with an `eltype` which is a
-concrete subtype of the abstract `Sequence` type.
+Compute allele frequencies from any iterable whose element type is a subtype of BioSequence.
+This function iterates over the input, counts occurrences of unique sequences,
+and then returns a dictionary mapping each sequence to its relative frequency.
+Example:
+    freqs = gene_frequencies(["ATGC", "ATGC", "ATGT"])
 """
 function gene_frequencies(iterable)
-    return _gene_frequencies(iterable, eltype(iterable), Base.IteratorSize(iterable))
-end
-
-# Default for most iterables, throws an error.
-_gene_frequencies(iterable, eltype, is) = error("Iterable not supported.")
-
-# Action to take for a sequence iterable which has no known size.
-function _gene_frequencies(iterable, ::Type{<:Sequence}, is::Base.SizeUnknown)
-    composition = BioSequences.composition(iterable)
-    return gene_frequencies(composition)
-end
-
-# Action to take for a sequence iterable which has a known size.
-# This version computes frequencies directly as n is known in advance.
-# The other method first computes composition, and computes frequencies from
-# that.
-function _gene_frequencies(sequences, ::Type{T}, is::Union{Base.HasLength,Base.HasShape}) where T<:Sequence
-    inc = 1 / length(sequences)
-    frequencies = Dict{T, Float64}()
-    @inbounds for seq in sequences
-        old = get(frequencies, seq, 0.0)
-        frequencies[seq] = old + inc
+    counts = Dict{eltype(iterable),Int}()
+    total = 0
+    for seq in iterable
+        counts[seq] = get(counts, seq, 0) + 1
+        total += 1
     end
-    return frequencies
+    return Dict(k => v / total for (k, v) in counts)
 end

src/bcf/bcf.jl

@@ -8,10 +8,17 @@
 
 module BCF
 
-import BioCore: BioCore, isfilled
+#import BioGenerics: BioGenerics, isfilled
 import GeneticVariation.VCF
 import BGZFStreams
-import BufferedStreams
+import TranscodingStreams
+using BioGenerics
+import BioGenerics: BioGenerics, isfilled
+import BioGenerics.Exceptions: MissingFieldException, missingerror
+
+function parsehex(str)
+    return map(x -> parse(UInt8, x, base=16), split(str, ' '))
+end
 
 include("record.jl")
 include("reader.jl")

src/bcf/reader.jl

@@ -5,8 +5,7 @@
 #
 # This file is a part of BioJulia.
 # License is MIT: https://github.com/BioJulia/GeneticVariation.jl/blob/master/LICENSE
-
-struct Reader{T<:IO} <: BioCore.IO.AbstractReader
+struct Reader{T<:IO} <: BioGenerics.IO.AbstractReader
     version::Tuple{UInt8,UInt8}  # (major, minor)
     header::VCF.Header
     stream::BGZFStreams.BGZFStream{T}
@@ -39,7 +38,7 @@ function Reader(input::IO)
     data = read(stream, l_header)
 
     # parse VCF header
-    vcfreader = VCF.Reader(BufferedStreams.BufferedInputStream(data))
+    vcfreader = VCF.Reader(IOBuffer(data))
 
     return Reader((major, minor), vcfreader.header, stream)
 end
@@ -48,7 +47,7 @@ function Base.eltype(::Type{Reader{T}}) where T
     return Record
 end
 
-function BioCore.IO.stream(reader::Reader)
+function stream(reader::Reader)
     return reader.stream
 end
 
@@ -60,8 +59,11 @@ function header(reader::Reader)
     return reader.header
 end
 
-function BioCore.header(reader::Reader)
-    return header(reader)
+function Base.close(reader::Reader)
+    if reader.stream isa IO
+        close(reader.stream)
+    end
+    return nothing
 end
 
 function Base.read!(reader::Reader, record::Record)
@@ -75,3 +77,4 @@ function Base.read!(reader::Reader, record::Record)
     record.indivlen = indivlen
     return record
 end
+

src/bcf/writer.jl

@@ -6,7 +6,7 @@
 # This file is a part of BioJulia.
 # License is MIT: https://github.com/BioJulia/GeneticVariation.jl/blob/master/LICENSE
 
-struct Writer{T<:IO} <: BioCore.IO.AbstractWriter
+struct Writer{T<:IO} <: BioGenerics.IO.AbstractWriter
     stream::BGZFStreams.BGZFStream{T}
 end
 
@@ -32,7 +32,7 @@ function Writer(output::IO, header::VCF.Header)
     return Writer(stream)
 end
 
-function BioCore.IO.stream(writer::Writer)
+function stream(writer::Writer)
     return writer.stream
 end
 
@@ -43,3 +43,10 @@ function Base.write(writer::Writer, record::Record)
     n += write(writer.stream, record.data)
     return n
 end
+
+function Base.close(writer::Writer)
+    if writer.stream isa IO
+        close(writer.stream)
+    end
+    return nothing
+end