Refine tests and some refactors

Project.toml

@@ -26,6 +26,7 @@ julia = "1"
 
 [extras]
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+Aqua = "4c88cf16-eb10-579e-8560-4a9242c79595"
 
 [targets]
-test = ["Test"]
+test = ["Test", "Aqua"]

README.md

@@ -13,6 +13,7 @@
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](https://github.com/camilogarciabotero/BioMarkovChains.jl/blob/main/LICENSE)
 [![Work in Progress](https://www.repostatus.org/badges/latest/wip.svg)](https://www.repostatus.org/#wip)
 [![Downloads](https://shields.io/endpoint?url=https://pkgs.genieframework.com/api/v1/badge/BioMarkovChains&label=downloads)](https://pkgs.genieframework.com?packages=BioMarkovChains)
+[![Aqua QA](https://raw.githubusercontent.com/JuliaTesting/Aqua.jl/master/badge.svg)](https://github.com/JuliaTesting/Aqua.jl)
 
 </div>
 
@@ -50,7 +51,7 @@ Let find one ORF in a random `LongDNA` :
 using BioSequences, GeneFinder, BioMarkovChains
 
 sequence = randdnaseq(10^3)
-orfdna = getorfdna(sequence, min_len=75)[1]
+orfdna = get_orfs_dna(sequence, min_len=75)[1]
 ```
 
 If we translate it, we get a 69aa sequence:
@@ -71,7 +72,7 @@ BioMarkovChain(orfdna, 2)
 ```
 
 ```
-BioMarkovChain with DNAAlphabet{4}() Alphabet:
+BioMarkovChain of DNAAlphabet{4}():
   - Transition Probability Matrix -> Matrix{Float64}(4 × 4):
    0.2123  0.2731  0.278   0.2366
    0.2017  0.3072  0.2687  0.2224
@@ -94,7 +95,7 @@ ECOLICDS
 ```
 
 ```
-BioMarkovChain with DNAAlphabet{4}() Alphabet:
+BioMarkovChain of DNAAlphabet{4}():
   - Transition Probability Matrix -> Matrix{Float64}(4 × 4):
    0.31    0.224   0.199   0.268
    0.251   0.215   0.313   0.221

docs/src/biomarkovchains.md

@@ -122,7 +122,7 @@ build a transition model (`BioMarkovChain`):
 BioMarkovChain(sequence)
 ```
 
-    BioMarkovChain with DNA Alphabet:
+    BioMarkovChain of DNAAlphabet{4}():
       - Transition Probability Matrix --> Matrix{Float64}(4 × 4):
        0.0     1.0     0.0     0.0
        0.0     0.5     0.2     0.3
@@ -149,7 +149,7 @@ the *n-step transition probability matrix* ``\mathscr{M}^{n} = (\mathscr{m}_{ij}
 BioMarkovChain(sequence, 2)
 ```
 
-    BioMarkovChain with DNA Alphabet:
+    BioMarkovChain of DNAAlphabet{4}():
       - Transition Probability Matrix --> Matrix{Float64}(4 × 4):
        0.0     0.5     0.2     0.3
        0.05    0.475   0.325   0.15

docs/src/index.md

@@ -20,6 +20,9 @@
 <a href="https://github.com/camilogarciabotero/BioMarkovChains.jl/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-MIT-green.svg" alt="License"></a>
 <a href="https://www.repostatus.org/#wip"><img src="https://www.repostatus.org/badges/latest/wip.svg" alt="Work in Progress"></a>
 <a href="https://pkgs.genieframework.com?packages=BioMarkovChains"><img src="https://shields.io/endpoint?url=https://pkgs.genieframework.com/api/v1/badge/BioMarkovChains&label=downloads" alt="Downloads"></a>
+<a href="https://github.com/JuliaTesting/Aqua.jl">
+  <img src="https://raw.githubusercontent.com/JuliaTesting/Aqua.jl/master/badge.svg" alt="Aqua QA">
+</a>
 
 </div>
 

src/extended.jl

@@ -1,7 +1,10 @@
-import Base: show, length, eltype
+import Base: show, length, eltype, size
 # import StatsAPI: fit!
 
-function Base.show(io::IO, model::BioMarkovChain)
+function Base.show(
+    io::IO, 
+    model::BioMarkovChain
+)
     # # Print the type name
     # println(io, "BioMarkovChain:")
 
@@ -10,7 +13,7 @@ function Base.show(io::IO, model::BioMarkovChain)
     alphabet_type = eltype(model)
 
     # Print the type name with inferred alphabet type
-    println(io, "BioMarkovChain with $alphabet_type Alphabet:")
+    println(io, "BioMarkovChain of $alphabet_type:")
 
     # Print the transition probability matrix
     println(io, "  - Transition Probability Matrix -> Matrix{Float64}($(size(model.tpm, 1)) × $(size(model.tpm, 2))):")
@@ -45,11 +48,9 @@ function Base.show(io::IO, model::BioMarkovChain)
     println(io, "   ", "$(model.n)")
 end
 
-Base.length(bmc::BioMarkovChain) = length(bmc.inits)
-
-function Base.eltype(bmc::BioMarkovChain)
-    return bmc.alphabet
-end
+@inline Base.length(bmc::BioMarkovChain) = length(bmc.inits)
+@inline Base.size(bmc::BioMarkovChain) = size(bmc.tpm)
+@inline Base.eltype(bmc::BioMarkovChain) = bmc.alphabet
 
 """
     fit!(bmc::BMC, inits:Vector{Float64}, tpm::Matrix{Float64})

src/models.jl

@@ -38,7 +38,6 @@ const CPGPOS = begin
     BMC(DNAAlphabet{4}(), tpm, inits)
 end
 
-
 const CPGNEG = begin
     tpm = [
         0.300 0.205 0.285 0.210 

src/perronfrobenius.jl

@@ -21,16 +21,23 @@ n = 2
 pf = perronfrobenius(sequence, n)
 ```
 """
-function perronfrobenius(sequence::SeqOrView{A}; n::Int64=1) where A
+function perronfrobenius(
+    sequence::SeqOrView{A};
+    n::Int64=1
+) where {A}
     tpm = transition_probability_matrix(sequence, n)
     return copy(tpm')
 end
 
-function perronfrobenius(bmc::BioMarkovChain)
+function perronfrobenius(
+    bmc::BioMarkovChain
+)
    return copy(bmc.tpm')
 end
 
-function perronfrobenius(tpm::Matrix{Float64})
+function perronfrobenius(
+    tpm::Matrix{Float64}
+)
     return copy(tpm')
 end
 

test/aquatests.jl

@@ -0,0 +1,10 @@
+@testset "Aqua" begin
+
+    Aqua.test_ambiguities(BioMarkovChains)
+    Aqua.test_persistent_tasks(BioMarkovChains)
+    Aqua.test_piracies(BioMarkovChains)
+    Aqua.test_stale_deps(BioMarkovChains)
+    Aqua.test_unbound_args(BioMarkovChains)
+    Aqua.test_undefined_exports(BioMarkovChains)
+
+end

test/oddstests.jl

@@ -0,0 +1,6 @@
+@testset "lorm" begin
+
+    lorm01 = log_odds_ratio_matrix(CPGPOS, CPGNEG, b=2) # Extracted from the Biological Sequence Analysis: probabilistic models of proteins and nucleic acids, Durbin et al. 1998 
+    @test lorm01 == [-0.7369655941662062 0.4185519834550808 0.5798915111737342 -0.8073549220576043; -0.913064363228719 0.3043934355948513 1.8126298640982785 -0.6838158876474414; -0.6232794322722583 0.4626269577971041 0.3315782649210818 -0.7346554334790053; -1.1638248019058943 0.5708084064112958 0.3951379418411391 -0.6820299186813209]
+
+end

test/runtests.jl

@@ -1,23 +1,12 @@
 module BioMarkovChainsTests
 
 using Test
+using Aqua
 using BioMarkovChains
 using BioSequences
 
-@testset "lorm" begin
-
-    lorm01 = log_odds_ratio_matrix(CPGPOS, CPGNEG, b=2) # Extracted from the Biological Sequence Analysis: probabilistic models of proteins and nucleic acids, Durbin et al. 1998 
-    lorm01 == [-0.7369655941662062 0.4185519834550808 0.5798915111737342 -0.8073549220576043; -0.913064363228719 0.3043934355948513 1.8126298640982785 -0.6838158876474414; -0.6232794322722583 0.4626269577971041 0.3315782649210818 -0.7346554334790053; -1.1638248019058943 0.5708084064112958 0.3951379418411391 -0.6820299186813209]
-end
-
-@testset "tpm" begin
-    seq01 = dna"CCTCCCGGACCCTGGGCTCGGGAC"
-    tpm01 = transition_probability_matrix(seq01)
-    @test round.(tpm01, digits = 3) == [0.0 1.0 0.0 0.0; 0.0 0.5 0.2 0.3; 0.25 0.125 0.625 0.0; 0.0 0.667 0.333 0.0]
-
-    seq02 = aa"ACDEFGHIKLMNPQRSTVWY"
-    tpm02 = transition_probability_matrix(seq02)
-    @test round.(tpm02, digits = 3) == [0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0]
-end
+include("tpmtests.jl")
+include("oddstests.jl")
+include("aquatests.jl")
 
 end

test/tpmtests.jl

@@ -0,0 +1,11 @@
+@testset "tpm" begin
+
+    seq01 = dna"CCTCCCGGACCCTGGGCTCGGGAC"
+    tpm01 = transition_probability_matrix(seq01)
+    @test round.(tpm01, digits = 3) == [0.0 1.0 0.0 0.0; 0.0 0.5 0.2 0.3; 0.25 0.125 0.625 0.0; 0.0 0.667 0.333 0.0]
+
+    seq02 = aa"ACDEFGHIKLMNPQRSTVWY"
+    tpm02 = transition_probability_matrix(seq02)
+    @test round.(tpm02, digits = 3) == [0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0; 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0 1.0 0.0 0.0]
+
+end