X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=code_ruby%2Ftest%2Fmaasha%2Ftest_seq.rb;h=171e6b1ae9157205527a0613ef68fe65686bf4e7;hb=d4b9c1bec954d5ff3e6eb2f7dc6c1aaa1f7f810f;hp=93737d44280dbf02d8c029048ada0d2a51816998;hpb=2d1f69b1d1205a9dc4433f243f8787f0f26147e0;p=biopieces.git diff --git a/code_ruby/test/maasha/test_seq.rb b/code_ruby/test/maasha/test_seq.rb index 93737d4..171e6b1 100755 --- a/code_ruby/test/maasha/test_seq.rb +++ b/code_ruby/test/maasha/test_seq.rb @@ -14,6 +14,15 @@ class TestSeq < Test::Unit::TestCase # dna.seq = "A\tT\r\tC\nG " # assert_equal(dna.seq, "ATCG") # end + + def test_Seq_new_bp_returns_correctly + record = {:SEQ_NAME => "test", :SEQ => "ATCG", :SEQ_TYPE => "dna", :SCORES => "hhhh"} + seq = Seq.new_bp(record) + assert_equal("test", seq.seq_name) + assert_equal("ATCG", seq.seq) + assert_equal("dna", seq.type) + assert_equal("hhhh", seq.qual) + end def test_Seq_is_dna_with_no_sequence_type_returns_false assert(@entry.is_dna? == false) @@ -157,6 +166,28 @@ class TestSeq < Test::Unit::TestCase assert_raise(SeqError) { @entry.to_bp } end + def test_Seq_to_fasta_raises_on_missing_seq_name + @entry.seq = 'ATCG' + assert_raise(SeqError) { @entry.to_fasta } + end + + def test_Seq_to_fasta_raises_on_empty_seq_name + @entry.seq_name = '' + @entry.seq = 'ATCG' + assert_raise(SeqError) { @entry.to_fasta } + end + + def test_Seq_to_fasta_raises_on_missing_seq + @entry.seq_name = 'test' + assert_raise(SeqError) { @entry.to_fasta } + end + + def test_Seq_to_fasta_raises_on_empty_seq + @entry.seq_name = 'test' + @entry.seq = '' + assert_raise(SeqError) { @entry.to_fasta } + end + def test_Seq_to_fasta_returns_correct_entry @entry.seq_name = 'test' @entry.seq = 'ATCG' @@ -168,6 +199,13 @@ class TestSeq < Test::Unit::TestCase assert_equal(">test\nAT\nCG\n", entry.to_fasta(2)) end + def test_Seq_to_fastq_returns_correct_entry + @entry.seq_name = 'test' + @entry.seq = 'ATCG' + @entry.qual = 'hhhh' + assert_equal("@test\nATCG\n+\nhhhh\n", @entry.to_fastq) + end + def test_Seq_to_key_with_bad_residue_raises entry = Seq.new("test", "AUCG") assert_raise(SeqError) { entry.to_key } @@ -180,7 +218,7 @@ class TestSeq < Test::Unit::TestCase def test_Seq_reverse_returns_correctly @entry.seq = "ATCG" - assert_equal("GCTA", @entry.reverse) + assert_equal("GCTA", @entry.reverse.seq) end def test_Seq_complement_raises_if_no_sequence @@ -209,13 +247,19 @@ class TestSeq < Test::Unit::TestCase def test_Seq_reverse_complement_for_DNA_is_correct @entry.seq = 'ATCGatcg' @entry.type = 'dna' - assert_equal("cgatCGAT", @entry.reverse_complement) + assert_equal("cgatCGAT", @entry.reverse_complement.seq) end def test_Seq_reverse_complement_for_RNA_is_correct @entry.seq = 'AUCGaucg' @entry.type = 'rna' - assert_equal("cgauCGAU", @entry.reverse_complement) + assert_equal("cgauCGAU", @entry.reverse_complement.seq) + end + + def test_Seq_hamming_distance_returns_correctly + seq1 = Seq.new("test1", "ATCG") + seq2 = Seq.new("test2", "atgg") + assert_equal(1, seq1.hamming_distance(seq2)) end def test_Seq_generate_with_length_lt_1_raises @@ -238,11 +282,6 @@ class TestSeq < Test::Unit::TestCase assert_raise(SeqError) { @entry.subseq(-1, 1) } end - def test_Seq_subseq_with_length_lt_1_raises - @entry.seq = "ATCG" - assert_raise(SeqError) { @entry.subseq(0, 0) } - end - def test_Seq_subseq_with_start_plus_length_gt_seq_raises @entry.seq = "ATCG" assert_raise(SeqError) { @entry.subseq(0, 5) } @@ -279,11 +318,6 @@ class TestSeq < Test::Unit::TestCase assert_raise(SeqError) { @entry.subseq!(-1, 1) } end - def test_Seq_subseq_bang_with_length_lt_1_raises - @entry.seq = "ATCG" - assert_raise(SeqError) { @entry.subseq!(0, 0) } - end - def test_Seq_subseq_bang_with_start_plus_length_gt_seq_raises @entry.seq = "ATCG" assert_raise(SeqError) { @entry.subseq!(0, 5) } @@ -334,6 +368,19 @@ class TestSeq < Test::Unit::TestCase assert_equal("ATCG", @entry.subseq_rand(4).seq) end + def test_Seq_indels_remove_without_qual_returns_correctly + @entry.seq = "A-T.CG~CG" + @entry.qual = nil + assert_equal("ATCGCG", @entry.indels_remove.seq) + end + + def test_Seq_indels_remove_with_qual_returns_correctly + @entry.seq = "A-T.CG~CG" + @entry.qual = "a@b@cd@fg" + assert_equal("ATCGCG", @entry.indels_remove.seq) + assert_equal("abcdfg", @entry.indels_remove.qual) + end + def test_Seq_composition_returns_correctly @entry.seq = "AAAATTTCCG" assert_equal(4, @entry.composition["A"]) @@ -372,7 +419,268 @@ class TestSeq < Test::Unit::TestCase @entry.seq = "--AAAa" assert_equal(25.00, @entry.soft_mask) end -end + def test_Seq_mask_seq_hard_bang_with_nil_seq_raises + @entry.seq = nil + @entry.qual = "" + + assert_raise(SeqError) { @entry.mask_seq_hard!(20) } + end + + def test_Seq_mask_seq_hard_bang_with_nil_qual_raises + @entry.seq = "" + @entry.qual = nil + + assert_raise(SeqError) { @entry.mask_seq_hard!(20) } + end + + def test_Seq_mask_seq_hard_bang_with_bad_cutoff_raises + assert_raise(SeqError) { @entry.mask_seq_hard!(-1) } + assert_raise(SeqError) { @entry.mask_seq_hard!(41) } + end + + def test_Seq_mask_seq_hard_bang_with_OK_cutoff_dont_raise + @entry.seq = "ATCG" + @entry.qual = "RSTU" + + assert_nothing_raised { @entry.mask_seq_hard!(0) } + assert_nothing_raised { @entry.mask_seq_hard!(40) } + end + + def test_Seq_mask_seq_hard_bang_returns_correctly + @entry.seq = "-ATCG" + @entry.qual = "RRSTU" + + assert_equal("-NNCG", @entry.mask_seq_hard!(20).seq) + end + + def test_Seq_mask_seq_soft_bang_with_nil_seq_raises + @entry.seq = nil + @entry.qual = "" + + assert_raise(SeqError) { @entry.mask_seq_soft!(20) } + end + + def test_Seq_mask_seq_soft_bang_with_nil_qual_raises + @entry.seq = "" + @entry.qual = nil + + assert_raise(SeqError) { @entry.mask_seq_soft!(20) } + end + + def test_Seq_mask_seq_soft_bang_with_bad_cutoff_raises + assert_raise(SeqError) { @entry.mask_seq_soft!(-1) } + assert_raise(SeqError) { @entry.mask_seq_soft!(41) } + end + + def test_Seq_mask_seq_soft_bang_with_OK_cutoff_dont_raise + @entry.seq = "ATCG" + @entry.qual = "RSTU" + + assert_nothing_raised { @entry.mask_seq_soft!(0) } + assert_nothing_raised { @entry.mask_seq_soft!(40) } + end + + def test_Seq_mask_seq_soft_bang_returns_correctly + @entry.seq = "-ATCG" + @entry.qual = "RRSTU" + + assert_equal("-atCG", @entry.mask_seq_soft!(20).seq) + end + + # qual score detection + + def test_Seq_qual_base33_returns_correctly + # self.qual.match(/[!-:]/) + @entry.qual = '!"#$%&\'()*+,-./0123456789:' + assert_equal(true, @entry.qual_base33? ) + @entry.qual = 32.chr + assert_equal(false, @entry.qual_base33? ) + @entry.qual = 59.chr + assert_equal(false, @entry.qual_base33? ) + end + + def test_Seq_qual_base64_returns_correctly + # self.qual.match(/[K-h]/) + @entry.qual = 'KLMNOPQRSTUVWXYZ[\]^_`abcdefgh' + assert_equal(true, @entry.qual_base64? ) + @entry.qual = 74.chr + assert_equal(false, @entry.qual_base64? ) + @entry.qual = 105.chr + assert_equal(false, @entry.qual_base64? ) + end + + def test_Seq_qual_valid_with_nil_qual_raises + assert_raise(SeqError) { @entry.qual_valid?("illumina1.8") } + end + + def test_Seq_qual_valid_with_bad_encoding_raises + @entry.qual = "abc" + assert_raise(SeqError) { @entry.qual_valid?("foobar") } + end + + def test_Seq_qual_valid_returns_correctly + tests = [["sanger", 0, 40, 33], + ["454", 0, 40, 64], + ["solexa", -5, 40, 64], + ["illumina13", 0, 40, 64], + ["illumina15", 0, 40, 64], + ["illumina18", 0, 41, 33]] + + tests.each do |test| + @entry.qual = (test[1] + test[-1]).chr + (test[2] + test[-1]).chr + assert_equal(true, @entry.qual_valid?(test[0])) + @entry.qual = (test[1] + test[-1] - 1).chr + assert_equal(false, @entry.qual_valid?(test[0])) + @entry.qual = (test[2] + test[-1] + 1).chr + assert_equal(false, @entry.qual_valid?(test[0])) + end + end + + # convert sanger to ... + + def test_Seq_convert_scores_bang_from_sanger_to_sanger_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('sanger', 'sanger').qual) + end + + def test_Seq_convert_scores_bang_from_sanger_to_solexa_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('sanger', 'solexa').qual) + end + + def test_Seq_convert_scores_bang_from_sanger_to_illumina13_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('sanger', 'illumina13').qual) + end + + def test_Seq_convert_scores_bang_from_sanger_to_illumina15_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('sanger', 'illumina15').qual) + end + + def test_Seq_convert_scores_bang_from_sanger_to_illumina18_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('sanger', 'illumina18').qual) + end + + # convert solexa to ... + + def test_Seq_convert_scores_bang_from_solexa_to_sanger_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('solexa', 'sanger').qual) + end + + def test_Seq_convert_scores_bang_from_solexa_to_solexa_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('solexa', 'solexa').qual) + end + + def test_Seq_convert_scores_bang_from_solexa_to_illumina13_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('solexa', 'illumina13').qual) + end + + def test_Seq_convert_scores_bang_from_solexa_to_illumina15_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('solexa', 'illumina15').qual) + end + + def test_Seq_convert_scores_bang_from_solexa_to_illumina18_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('solexa', 'illumina18').qual) + end + + # convert illumina13 to ... + + def test_Seq_convert_scores_bang_from_illumina13_to_sanger_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('illumina13', 'sanger').qual) + end + + def test_Seq_convert_scores_bang_from_illumina13_to_solexa_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina13', 'solexa').qual) + end + + def test_Seq_convert_scores_bang_from_illumina13_to_illumina13_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina13', 'illumina13').qual) + end + + def test_Seq_convert_scores_bang_from_illumina13_to_illumina15_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina13', 'illumina15').qual) + end + + def test_Seq_convert_scores_bang_from_illumina13_to_illumina18_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('illumina13', 'illumina18').qual) + end + + # convert illumina15 to ... + + def test_Seq_convert_scores_bang_from_illumina15_to_sanger_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('illumina15', 'sanger').qual) + end + + def test_Seq_convert_scores_bang_from_illumina15_to_solexa_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina15', 'solexa').qual) + end + + def test_Seq_convert_scores_bang_from_illumina15_to_illumina13_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina15', 'illumina13').qual) + end + + def test_Seq_convert_scores_bang_from_illumina15_to_illumina15_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina15', 'illumina15').qual) + end + + def test_Seq_convert_scores_bang_from_illumina15_to_illumina18_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal(%q[#$%&'()*], @entry.convert_scores!('illumina15', 'illumina18').qual) + end + + # convert illumina18 to ... + + def test_Seq_convert_scores_bang_from_illumina18_to_sanger_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina18', 'sanger').qual) + end + + def test_Seq_convert_scores_bang_from_illumina18_to_solexa_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('illumina18', 'solexa').qual) + end + + def test_Seq_convert_scores_bang_from_illumina18_to_illumina13_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('illumina18', 'illumina13').qual) + end + + def test_Seq_convert_scores_bang_from_illumina18_to_illumina15_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('abcdefgh', @entry.convert_scores!('illumina18', 'illumina15').qual) + end + + def test_Seq_convert_scores_bang_from_illumina18_to_illumina18_returns_OK + @entry.qual = 'BCDEFGHI' + assert_equal('BCDEFGHI', @entry.convert_scores!('illumina18', 'illumina18').qual) + end + + def test_Seq_scores_mean_without_qual_raises + @entry.qual = nil + assert_raise(SeqError) { @entry.scores_mean } + end + + def test_Seq_scores_mean_returns_correctly + @entry.qual = '@@hh' + assert_equal(20.0, @entry.scores_mean) + end +end __END__