macroape 4.0.2 → 4.1.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (74) hide show
  1. checksums.yaml +4 -4
  2. data/.gitignore +17 -17
  3. data/Gemfile +4 -4
  4. data/LICENSE +22 -22
  5. data/README.md +70 -70
  6. data/Rakefile.rb +49 -49
  7. data/TODO.txt +46 -46
  8. data/benchmark/benchmark_helper.rb +4 -4
  9. data/benchmark/similarity_benchmark.rb +52 -52
  10. data/bin/align_motifs +4 -4
  11. data/bin/eval_alignment +4 -4
  12. data/bin/eval_similarity +4 -4
  13. data/bin/find_pvalue +4 -4
  14. data/bin/find_threshold +4 -4
  15. data/bin/preprocess_collection +4 -4
  16. data/bin/scan_collection +4 -4
  17. data/lib/macroape.rb +14 -11
  18. data/lib/macroape/aligned_pair_intersection.rb +61 -62
  19. data/lib/macroape/cli.rb +191 -188
  20. data/lib/macroape/cli/align_motifs.rb +120 -100
  21. data/lib/macroape/cli/eval_alignment.rb +157 -156
  22. data/lib/macroape/cli/eval_similarity.rb +138 -137
  23. data/lib/macroape/cli/find_pvalue.rb +93 -87
  24. data/lib/macroape/cli/find_threshold.rb +103 -96
  25. data/lib/macroape/cli/preprocess_collection.rb +169 -161
  26. data/lib/macroape/cli/scan_collection.rb +171 -163
  27. data/lib/macroape/collection.rb +29 -0
  28. data/lib/macroape/motif_with_thresholds.rb +18 -0
  29. data/lib/macroape/pwm_compare.rb +39 -44
  30. data/lib/macroape/pwm_compare_aligned.rb +139 -130
  31. data/lib/macroape/{counting.rb → pwm_counting.rb} +175 -121
  32. data/lib/macroape/support/inverf.rb +13 -0
  33. data/lib/macroape/support/partial_sums.rb +17 -0
  34. data/lib/macroape/version.rb +4 -4
  35. data/macroape.gemspec +19 -19
  36. data/spec/count_distribution_spec.rb +112 -109
  37. data/spec/inverf_spec.rb +23 -0
  38. data/spec/partial_sums_spec.rb +28 -0
  39. data/spec/spec_helper.rb +11 -11
  40. data/test/align_motifs_test.rb +42 -43
  41. data/test/data/AHR_si.pwm +10 -10
  42. data/test/data/KLF3_f1.pcm +16 -16
  43. data/test/data/KLF3_f1.pwm +16 -16
  44. data/test/data/KLF4_f2.pcm +11 -11
  45. data/test/data/KLF4_f2.pwm +11 -11
  46. data/test/data/KLF4_f2_scan_results_all.txt +2 -2
  47. data/test/data/KLF4_f2_scan_results_default_cutoff.txt +1 -1
  48. data/test/data/KLF4_f2_scan_results_precise_mode.txt +2 -2
  49. data/test/data/SP1_f1.pcm +12 -12
  50. data/test/data/SP1_f1.pwm +12 -12
  51. data/test/data/SP1_f1_revcomp.pcm +12 -12
  52. data/test/data/SP1_f1_revcomp.pwm +12 -12
  53. data/test/data/medium_motif.pwm +8 -8
  54. data/test/data/short_motif.pwm +7 -7
  55. data/test/data/test_collection.yaml +231 -214
  56. data/test/data/test_collection/GABPA_f1.pwm +14 -14
  57. data/test/data/test_collection/KLF4_f2.pwm +10 -10
  58. data/test/data/test_collection/SP1_f1.pwm +12 -12
  59. data/test/data/test_collection_pcm/GABPA_f1.pcm +14 -14
  60. data/test/data/test_collection_pcm/KLF4_f2.pcm +11 -11
  61. data/test/data/test_collection_pcm/SP1_f1.pcm +12 -12
  62. data/test/data/test_collection_single_file.txt +38 -38
  63. data/test/data/test_collection_single_file_pcm.txt +37 -37
  64. data/test/data/test_collection_weak.yaml +231 -214
  65. data/test/eval_alignment_test.rb +90 -111
  66. data/test/eval_similarity_test.rb +105 -123
  67. data/test/find_pvalue_test.rb +34 -39
  68. data/test/find_threshold_test.rb +87 -91
  69. data/test/preprocess_collection_test.rb +56 -65
  70. data/test/scan_collection_test.rb +42 -48
  71. data/test/test_helper.rb +159 -160
  72. metadata +14 -10
  73. data/test/data/collection_pcm_without_thresholds.yaml +0 -188
  74. data/test/data/collection_without_thresholds.yaml +0 -188
data/test/data/test_collection/GABPA_f1.pwm CHANGED
@@ -1,14 +1,14 @@
1
- GABPA_f1
2
- -0.1106670158341858 0.013801606113892391 0.6054596108973699 -1.3518085041421573
3
- 0.37030668921643345 0.15761121480429963 0.009069314183831202 -0.9888619717703562
4
- 0.47526546359546684 -0.3011678534572083 0.4031522994412777 -1.8638752827041059
5
- -1.5544255540164373 1.1082369687811506 -0.2814091552834454 -5.30708531823271
6
- -0.6362037835776368 1.235338189985594 -3.5801322928552253 -5.717323067092849
7
- -5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575
8
- -5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575
9
- 1.3835219739184708 -5.2341956006430985 -5.852906870733575 -5.852906870733575
10
- 1.3756340514956562 -5.394962755562375 -5.394962755562375 -3.401117964959733
11
- -1.2176198315414444 -3.109079898175411 1.2964067931472216 -5.717323067092849
12
- -1.3716559438167257 -0.2761401935045069 -1.8504445165866068 1.0404320473626856
13
- -0.5440863133031895 -0.48103682561971345 0.907381908447086 -1.1280642594012078
14
- 0.10557340209290218 -0.01814819455289191 0.4381106695354074 -1.0304105539540915
1
+ GABPA_f1
2
+ -0.1106670158341858 0.013801606113892391 0.6054596108973699 -1.3518085041421573
3
+ 0.3703066892164342 0.15761121480430038 0.009069314183831861 -0.9888619717703555
4
+ 0.47526546359546656 -0.30116785345720876 0.40315229944127723 -1.8638752827041063
5
+ -1.5544255540164387 1.1082369687811493 -0.28140915528344673 -5.307085318232711
6
+ -0.6362037835776333 1.2353381899855975 -3.5801322928552217 -5.717323067092845
7
+ -5.852906870733565 -5.852906870733565 1.3841383838057844 -5.852906870733565
8
+ -5.852906870733565 -5.852906870733565 1.3841383838057844 -5.852906870733565
9
+ 1.3835219739184805 -5.234195600643089 -5.852906870733565 -5.852906870733565
10
+ 1.375634051495666 -5.394962755562365 -5.394962755562365 -3.4011179649597234
11
+ -1.2176198315414393 -3.109079898175406 1.2964067931472267 -5.717323067092844
12
+ -1.3716559438167275 -0.2761401935045087 -1.8504445165866086 1.0404320473626838
13
+ -0.5440863133031892 -0.4810368256197133 0.9073819084470863 -1.1280642594012076
14
+ 0.10557340209290259 -0.018148194552891343 0.43811066953540795 -1.0304105539540909
data/test/data/test_collection/KLF4_f2.pwm CHANGED
@@ -1,10 +1,10 @@
1
- 0.30861857265872605 -2.254321000121579 0.13505703522674192 0.3285194224375633
2
- -1.227018967707036 -4.814127713368663 1.3059890687390967 -4.908681463544344
3
- -2.443469374521196 -4.648238485031404 1.3588686548279805 -4.441801801188402
4
- -2.7177827948276123 -3.8073538975356565 1.356272809724262 -3.504104725510225
5
- -0.5563232977367343 0.5340697765121405 -3.61417723090579 0.5270259776377405
6
- -1.8687622060887386 -4.381483976582316 1.337932245336098 -3.815629658877517
7
- -2.045671123823928 -2.384975142213679 0.7198551207724355 0.5449254135616948
8
- -1.373157530374372 -3.0063112097748217 1.285188335493552 -2.5026044231773543
9
- -2.1030513122772208 -1.8941348100402244 1.249265758393991 -1.4284210948906104
10
- -1.3277128628152939 0.8982415633049462 -0.8080773665408135 -0.18161647647456935
1
+ 0.30861857265872605 -2.254321000121579 0.13505703522674192 0.3285194224375633
2
+ -1.2270189677070362 -4.814127713368663 1.3059890687390965 -4.908681463544344
3
+ -2.4434693745211966 -4.648238485031404 1.3588686548279802 -4.441801801188402
4
+ -2.7177827948276128 -3.807353897535657 1.3562728097242616 -3.504104725510225
5
+ -0.5563232977367345 0.5340697765121402 -3.61417723090579 0.5270259776377402
6
+ -1.8687622060887386 -4.381483976582316 1.337932245336098 -3.815629658877517
7
+ -2.0456711238239285 -2.3849751422136793 0.7198551207724353 0.5449254135616943
8
+ -1.3731575303743726 -3.006311209774822 1.2851883354935514 -2.5026044231773548
9
+ -2.103051312277221 -1.8941348100402247 1.249265758393991 -1.4284210948906106
10
+ -1.327712862815294 0.898241563304946 -0.8080773665408136 -0.1816164764745695
data/test/data/test_collection/SP1_f1.pwm CHANGED
@@ -1,12 +1,12 @@
1
- > SP1_f1
2
- -0.24435707885585292 -0.674823404693731 0.8657012535789866 -1.1060188862599287
3
- -1.0631255752097797 -2.111925969423868 1.0960627561110403 -0.6138563775211977
4
- -0.3872276234760535 -2.9739851913218045 1.1807800242010378 -4.338927525031566
5
- -4.563896055436894 -2.9161633002532277 1.3684371349982638 -5.077972423609655
6
- -2.2369752892820083 -3.7196436313301846 1.3510439136452734 -4.889930670508233
7
- -0.07473964149330865 0.944919654762011 -2.6246857648086044 -0.8510983487822436
8
- -1.9643526491643322 -2.978402770880115 1.3113096718240573 -2.324334259499025
9
- -4.0155484139655835 -3.1384268078096667 1.3387488589788057 -2.084673903537648
10
- -0.44509385828355363 -2.2510053061629702 1.1265431574368685 -1.7780413702431372
11
- -1.1896356092245048 -1.2251832285630027 1.1636760063747527 -1.6080243648157353
12
- -0.5166047365590571 0.7641033353626657 -0.2862677570028208 -0.68254820978656
1
+ > SP1_f1
2
+ -0.24435707885585292 -0.674823404693731 0.8657012535789866 -1.1060188862599287
3
+ -1.063125575209786 -2.111925969423874 1.096062756111034 -0.6138563775212038
4
+ -0.38722762347606526 -2.9739851913218165 1.180780024201026 -4.338927525031577
5
+ -4.563896055436912 -2.916163300253245 1.3684371349982463 -5.077972423609672
6
+ -2.2369752892820247 -3.7196436313302015 1.3510439136452568 -4.8899306705082495
7
+ -0.07473964149331284 0.9449196547620068 -2.6246857648086084 -0.8510983487822477
8
+ -1.9643526491643477 -2.9784027708801304 1.3113096718240418 -2.3243342594990404
9
+ -4.015548413965599 -3.138426807809682 1.3387488589787901 -2.0846739035376634
10
+ -0.44509385828356285 -2.2510053061629796 1.1265431574368594 -1.7780413702431463
11
+ -1.1896356092245128 -1.2251832285630104 1.1636760063747449 -1.608024364815743
12
+ -0.5166047365590577 0.7641033353626651 -0.28626775700282125 -0.6825482097865606
data/test/data/test_collection_pcm/GABPA_f1.pcm CHANGED
@@ -1,14 +1,14 @@
1
- GABPA_f1
2
- 615.2572649050138 697.0698715160123 1261.1903440712872 176.43506582414153
3
- 996.4929869323321 805.1878697364007 693.7695793644275 254.5021102832924
4
- 1106.9888035794224 508.19444415177276 1029.8329748714536 104.93632371380718
5
- 143.7121486195701 2086.4279160661263 518.37507049306 1.4374111377025893
6
- 362.9541452731307 2369.473894845734 17.23702397004065 0.2874822275405179
7
- 0.0 0.0 2749.952546316428 0.0
8
- 0.0 0.0 2749.952546316428 0.0
9
- 2748.2567506938462 1.695795622582083 0.0 0.0
10
- 2726.6484322711017 1.1499289101620715 1.1499289101620715 21.00425622500253
11
- 202.05697400573305 28.799402471063658 2518.808687612104 0.2874822275405179
12
- 172.92889618879767 521.1240363384483 106.38197600987633 1949.517637779338
13
- 398.1679460365911 424.20938204069563 1706.4024212088275 221.17279703034018
14
- 764.2587933951809 675.0883944902433 1066.5413633225007 244.06399510852864
1
+ GABPA_f1
2
+ 615.2572649050138 697.0698715160123 1261.1903440712872 176.43506582414153
3
+ 996.4929869323321 805.1878697364007 693.7695793644275 254.5021102832924
4
+ 1106.9888035794224 508.19444415177276 1029.8329748714536 104.93632371380718
5
+ 143.7121486195701 2086.4279160661263 518.37507049306 1.4374111377025893
6
+ 362.9541452731307 2369.473894845734 17.23702397004065 0.2874822275405179
7
+ 0.0 0.0 2749.952546316428 0.0
8
+ 0.0 0.0 2749.952546316428 0.0
9
+ 2748.2567506938462 1.695795622582083 0.0 0.0
10
+ 2726.6484322711017 1.1499289101620715 1.1499289101620715 21.00425622500253
11
+ 202.05697400573305 28.799402471063658 2518.808687612104 0.2874822275405179
12
+ 172.92889618879767 521.1240363384483 106.38197600987633 1949.517637779338
13
+ 398.1679460365911 424.20938204069563 1706.4024212088275 221.17279703034018
14
+ 764.2587933951809 675.0883944902433 1066.5413633225007 244.06399510852864
data/test/data/test_collection_pcm/KLF4_f2.pcm CHANGED
@@ -1,11 +1,11 @@
1
- KLF4_f2
2
- 1233.46088405354 93.18173277811673 1036.6014857092885 1258.2948629970272
3
- 263.979242343185 5.314520555872139 3347.5949971525274 4.650205486388122
4
- 76.7700780003465 6.643150694840173 3529.4896409394937 8.636095903292224
5
- 57.86097393406657 18.102585643439472 3520.3342027139347 25.24120324653207
6
- 518.1947904009378 1545.9062946905135 22.396758181071043 1535.0411222654507
7
- 137.98151691820345 9.300410972776241 3456.320530770924 17.936506876068467
8
- 115.27647661640499 81.51802997128804 1861.9425868567278 1562.801872093553
9
- 227.8095486111286 42.84555258785854 3278.6396005325996 72.244263806387
10
- 108.73384179997886 134.47328134862394 3162.880454846513 215.45138754285665
11
- 238.49636899561344 2225.9561104691043 402.40727964384774 754.6792064294074
1
+ KLF4_f2
2
+ 1233.46088405354 93.18173277811673 1036.6014857092885 1258.2948629970272
3
+ 263.979242343185 5.314520555872139 3347.5949971525274 4.650205486388122
4
+ 76.7700780003465 6.643150694840173 3529.4896409394937 8.636095903292224
5
+ 57.86097393406657 18.102585643439472 3520.3342027139347 25.24120324653207
6
+ 518.1947904009378 1545.9062946905135 22.396758181071043 1535.0411222654507
7
+ 137.98151691820345 9.300410972776241 3456.320530770924 17.936506876068467
8
+ 115.27647661640499 81.51802997128804 1861.9425868567278 1562.801872093553
9
+ 227.8095486111286 42.84555258785854 3278.6396005325996 72.244263806387
10
+ 108.73384179997886 134.47328134862394 3162.880454846513 215.45138754285665
11
+ 238.49636899561344 2225.9561104691043 402.40727964384774 754.6792064294074
data/test/data/test_collection_pcm/SP1_f1.pcm CHANGED
@@ -1,12 +1,12 @@
1
- SP1_f1
2
- 682.6436366358055 443.1455214015781 2075.655346294993 287.211468117951
3
- 299.8883246804867 103.74338315843572 2613.8927022405364 471.1315623708902
4
- 591.4892493324709 42.631827541794564 2845.1654083148564 9.36948726124641
5
- 7.071084742361592 45.29093411231232 3432.8847704374107 3.409183158303573
6
- 91.308984085713 19.1536481364332 3373.656949880137 4.5363903481026
7
- 809.2082973387932 2246.941954176211 61.30766021687515 371.19806071846244
8
- 120.56476435866055 42.4349244403591 3242.1560628684038 83.50022078295852
9
- 13.72524477409959 35.858220519297525 3332.4066864946167 106.66582066236779
10
- 558.1188080161639 90.0084504200356 2694.854973210736 145.67374080342415
11
- 264.0088462230318 254.7175868081866 2796.88087480315 173.0486646159857
12
- 519.46013914282 1874.9349086474765 654.5411208373813 439.7198038226514
1
+ SP1_f1
2
+ 682.6436366358055 443.1455214015781 2075.655346294993 287.211468117951
3
+ 299.8883246804867 103.74338315843572 2613.8927022405364 471.1315623708902
4
+ 591.4892493324709 42.631827541794564 2845.1654083148564 9.36948726124641
5
+ 7.071084742361592 45.29093411231232 3432.8847704374107 3.409183158303573
6
+ 91.308984085713 19.1536481364332 3373.656949880137 4.5363903481026
7
+ 809.2082973387932 2246.941954176211 61.30766021687515 371.19806071846244
8
+ 120.56476435866055 42.4349244403591 3242.1560628684038 83.50022078295852
9
+ 13.72524477409959 35.858220519297525 3332.4066864946167 106.66582066236779
10
+ 558.1188080161639 90.0084504200356 2694.854973210736 145.67374080342415
11
+ 264.0088462230318 254.7175868081866 2796.88087480315 173.0486646159857
12
+ 519.46013914282 1874.9349086474765 654.5411208373813 439.7198038226514
data/test/data/test_collection_single_file.txt CHANGED
@@ -1,38 +1,38 @@
1
- > GABPA_f1
2
- -0.1106670158341858 0.013801606113892391 0.6054596108973699 -1.3518085041421573
3
- 0.37030668921643345 0.15761121480429963 0.009069314183831202 -0.9888619717703562
4
- 0.47526546359546684 -0.3011678534572083 0.4031522994412777 -1.8638752827041059
5
- -1.5544255540164373 1.1082369687811506 -0.2814091552834454 -5.30708531823271
6
- -0.6362037835776368 1.235338189985594 -3.5801322928552253 -5.717323067092849
7
- -5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575
8
- -5.852906870733575 -5.852906870733575 1.3841383838057746 -5.852906870733575
9
- 1.3835219739184708 -5.2341956006430985 -5.852906870733575 -5.852906870733575
10
- 1.3756340514956562 -5.394962755562375 -5.394962755562375 -3.401117964959733
11
- -1.2176198315414444 -3.109079898175411 1.2964067931472216 -5.717323067092849
12
- -1.3716559438167257 -0.2761401935045069 -1.8504445165866068 1.0404320473626856
13
- -0.5440863133031895 -0.48103682561971345 0.907381908447086 -1.1280642594012078
14
- 0.10557340209290218 -0.01814819455289191 0.4381106695354074 -1.0304105539540915
15
-
16
- KLF4_f2
17
- 0.30861857265872605 -2.254321000121579 0.13505703522674192 0.3285194224375633
18
- -1.227018967707036 -4.814127713368663 1.3059890687390967 -4.908681463544344
19
- -2.443469374521196 -4.648238485031404 1.3588686548279805 -4.441801801188402
20
- -2.7177827948276123 -3.8073538975356565 1.356272809724262 -3.504104725510225
21
- -0.5563232977367343 0.5340697765121405 -3.61417723090579 0.5270259776377405
22
- -1.8687622060887386 -4.381483976582316 1.337932245336098 -3.815629658877517
23
- -2.045671123823928 -2.384975142213679 0.7198551207724355 0.5449254135616948
24
- -1.373157530374372 -3.0063112097748217 1.285188335493552 -2.5026044231773543
25
- -2.1030513122772208 -1.8941348100402244 1.249265758393991 -1.4284210948906104
26
- -1.3277128628152939 0.8982415633049462 -0.8080773665408135 -0.18161647647456935
27
- SP1_f1
28
- -0.24435707885585292 -0.674823404693731 0.8657012535789866 -1.1060188862599287
29
- -1.0631255752097797 -2.111925969423868 1.0960627561110403 -0.6138563775211977
30
- -0.3872276234760535 -2.9739851913218045 1.1807800242010378 -4.338927525031566
31
- -4.563896055436894 -2.9161633002532277 1.3684371349982638 -5.077972423609655
32
- -2.2369752892820083 -3.7196436313301846 1.3510439136452734 -4.889930670508233
33
- -0.07473964149330865 0.944919654762011 -2.6246857648086044 -0.8510983487822436
34
- -1.9643526491643322 -2.978402770880115 1.3113096718240573 -2.324334259499025
35
- -4.0155484139655835 -3.1384268078096667 1.3387488589788057 -2.084673903537648
36
- -0.44509385828355363 -2.2510053061629702 1.1265431574368685 -1.7780413702431372
37
- -1.1896356092245048 -1.2251832285630027 1.1636760063747527 -1.6080243648157353
38
- -0.5166047365590571 0.7641033353626657 -0.2862677570028208 -0.68254820978656
1
+ > GABPA_f1
2
+ -0.1106670158341858 0.013801606113892391 0.6054596108973699 -1.3518085041421573
3
+ 0.3703066892164342 0.15761121480430038 0.009069314183831861 -0.9888619717703555
4
+ 0.47526546359546656 -0.30116785345720876 0.40315229944127723 -1.8638752827041063
5
+ -1.5544255540164387 1.1082369687811493 -0.28140915528344673 -5.307085318232711
6
+ -0.6362037835776333 1.2353381899855975 -3.5801322928552217 -5.717323067092845
7
+ -5.852906870733565 -5.852906870733565 1.3841383838057844 -5.852906870733565
8
+ -5.852906870733565 -5.852906870733565 1.3841383838057844 -5.852906870733565
9
+ 1.3835219739184805 -5.234195600643089 -5.852906870733565 -5.852906870733565
10
+ 1.375634051495666 -5.394962755562365 -5.394962755562365 -3.4011179649597234
11
+ -1.2176198315414393 -3.109079898175406 1.2964067931472267 -5.717323067092844
12
+ -1.3716559438167275 -0.2761401935045087 -1.8504445165866086 1.0404320473626838
13
+ -0.5440863133031892 -0.4810368256197133 0.9073819084470863 -1.1280642594012076
14
+ 0.10557340209290259 -0.018148194552891343 0.43811066953540795 -1.0304105539540909
15
+
16
+ KLF4_f2
17
+ 0.30861857265872605 -2.254321000121579 0.13505703522674192 0.3285194224375633
18
+ -1.2270189677070362 -4.814127713368663 1.3059890687390965 -4.908681463544344
19
+ -2.4434693745211966 -4.648238485031404 1.3588686548279802 -4.441801801188402
20
+ -2.7177827948276128 -3.807353897535657 1.3562728097242616 -3.504104725510225
21
+ -0.5563232977367345 0.5340697765121402 -3.61417723090579 0.5270259776377402
22
+ -1.8687622060887386 -4.381483976582316 1.337932245336098 -3.815629658877517
23
+ -2.0456711238239285 -2.3849751422136793 0.7198551207724353 0.5449254135616943
24
+ -1.3731575303743726 -3.006311209774822 1.2851883354935514 -2.5026044231773548
25
+ -2.103051312277221 -1.8941348100402247 1.249265758393991 -1.4284210948906106
26
+ -1.327712862815294 0.898241563304946 -0.8080773665408136 -0.1816164764745695
27
+ SP1_f1
28
+ -0.24435707885585292 -0.674823404693731 0.8657012535789866 -1.1060188862599287
29
+ -1.063125575209786 -2.111925969423874 1.096062756111034 -0.6138563775212038
30
+ -0.38722762347606526 -2.9739851913218165 1.180780024201026 -4.338927525031577
31
+ -4.563896055436912 -2.916163300253245 1.3684371349982463 -5.077972423609672
32
+ -2.2369752892820247 -3.7196436313302015 1.3510439136452568 -4.8899306705082495
33
+ -0.07473964149331284 0.9449196547620068 -2.6246857648086084 -0.8510983487822477
34
+ -1.9643526491643477 -2.9784027708801304 1.3113096718240418 -2.3243342594990404
35
+ -4.015548413965599 -3.138426807809682 1.3387488589787901 -2.0846739035376634
36
+ -0.44509385828356285 -2.2510053061629796 1.1265431574368594 -1.7780413702431463
37
+ -1.1896356092245128 -1.2251832285630104 1.1636760063747449 -1.608024364815743
38
+ -0.5166047365590577 0.7641033353626651 -0.28626775700282125 -0.6825482097865606
data/test/data/test_collection_single_file_pcm.txt CHANGED
@@ -1,38 +1,38 @@
1
- > GABPA_f1
2
- 615.2572649050138 697.0698715160123 1261.1903440712872 176.43506582414153
3
- 996.4929869323321 805.1878697364007 693.7695793644275 254.5021102832924
4
- 1106.9888035794224 508.19444415177276 1029.8329748714536 104.93632371380718
5
- 143.7121486195701 2086.4279160661263 518.37507049306 1.4374111377025893
6
- 362.9541452731307 2369.473894845734 17.23702397004065 0.2874822275405179
7
- 0.0 0.0 2749.952546316428 0.0
8
- 0.0 0.0 2749.952546316428 0.0
9
- 2748.2567506938462 1.695795622582083 0.0 0.0
10
- 2726.6484322711017 1.1499289101620715 1.1499289101620715 21.00425622500253
11
- 202.05697400573305 28.799402471063658 2518.808687612104 0.2874822275405179
12
- 172.92889618879767 521.1240363384483 106.38197600987633 1949.517637779338
13
- 398.1679460365911 424.20938204069563 1706.4024212088275 221.17279703034018
14
- 764.2587933951809 675.0883944902433 1066.5413633225007 244.06399510852864
15
- KLF4_f2
16
- 1233.46088405354 93.18173277811673 1036.6014857092885 1258.2948629970272
17
- 263.979242343185 5.314520555872139 3347.5949971525274 4.650205486388122
18
- 76.7700780003465 6.643150694840173 3529.4896409394937 8.636095903292224
19
- 57.86097393406657 18.102585643439472 3520.3342027139347 25.24120324653207
20
- 518.1947904009378 1545.9062946905135 22.396758181071043 1535.0411222654507
21
- 137.98151691820345 9.300410972776241 3456.320530770924 17.936506876068467
22
- 115.27647661640499 81.51802997128804 1861.9425868567278 1562.801872093553
23
- 227.8095486111286 42.84555258785854 3278.6396005325996 72.244263806387
24
- 108.73384179997886 134.47328134862394 3162.880454846513 215.45138754285665
25
- 238.49636899561344 2225.9561104691043 402.40727964384774 754.6792064294074
26
-
27
- SP1_f1
28
- 682.6436366358055 443.1455214015781 2075.655346294993 287.211468117951
29
- 299.8883246804867 103.74338315843572 2613.8927022405364 471.1315623708902
30
- 591.4892493324709 42.631827541794564 2845.1654083148564 9.36948726124641
31
- 7.071084742361592 45.29093411231232 3432.8847704374107 3.409183158303573
32
- 91.308984085713 19.1536481364332 3373.656949880137 4.5363903481026
33
- 809.2082973387932 2246.941954176211 61.30766021687515 371.19806071846244
34
- 120.56476435866055 42.4349244403591 3242.1560628684038 83.50022078295852
35
- 13.72524477409959 35.858220519297525 3332.4066864946167 106.66582066236779
36
- 558.1188080161639 90.0084504200356 2694.854973210736 145.67374080342415
37
- 264.0088462230318 254.7175868081866 2796.88087480315 173.0486646159857
1
+ > GABPA_f1
2
+ 615.2572649050138 697.0698715160123 1261.1903440712872 176.43506582414153
3
+ 996.4929869323321 805.1878697364007 693.7695793644275 254.5021102832924
4
+ 1106.9888035794224 508.19444415177276 1029.8329748714536 104.93632371380718
5
+ 143.7121486195701 2086.4279160661263 518.37507049306 1.4374111377025893
6
+ 362.9541452731307 2369.473894845734 17.23702397004065 0.2874822275405179
7
+ 0.0 0.0 2749.952546316428 0.0
8
+ 0.0 0.0 2749.952546316428 0.0
9
+ 2748.2567506938462 1.695795622582083 0.0 0.0
10
+ 2726.6484322711017 1.1499289101620715 1.1499289101620715 21.00425622500253
11
+ 202.05697400573305 28.799402471063658 2518.808687612104 0.2874822275405179
12
+ 172.92889618879767 521.1240363384483 106.38197600987633 1949.517637779338
13
+ 398.1679460365911 424.20938204069563 1706.4024212088275 221.17279703034018
14
+ 764.2587933951809 675.0883944902433 1066.5413633225007 244.06399510852864
15
+ KLF4_f2
16
+ 1233.46088405354 93.18173277811673 1036.6014857092885 1258.2948629970272
17
+ 263.979242343185 5.314520555872139 3347.5949971525274 4.650205486388122
18
+ 76.7700780003465 6.643150694840173 3529.4896409394937 8.636095903292224
19
+ 57.86097393406657 18.102585643439472 3520.3342027139347 25.24120324653207
20
+ 518.1947904009378 1545.9062946905135 22.396758181071043 1535.0411222654507
21
+ 137.98151691820345 9.300410972776241 3456.320530770924 17.936506876068467
22
+ 115.27647661640499 81.51802997128804 1861.9425868567278 1562.801872093553
23
+ 227.8095486111286 42.84555258785854 3278.6396005325996 72.244263806387
24
+ 108.73384179997886 134.47328134862394 3162.880454846513 215.45138754285665
25
+ 238.49636899561344 2225.9561104691043 402.40727964384774 754.6792064294074
26
+
27
+ SP1_f1
28
+ 682.6436366358055 443.1455214015781 2075.655346294993 287.211468117951
29
+ 299.8883246804867 103.74338315843572 2613.8927022405364 471.1315623708902
30
+ 591.4892493324709 42.631827541794564 2845.1654083148564 9.36948726124641
31
+ 7.071084742361592 45.29093411231232 3432.8847704374107 3.409183158303573
32
+ 91.308984085713 19.1536481364332 3373.656949880137 4.5363903481026
33
+ 809.2082973387932 2246.941954176211 61.30766021687515 371.19806071846244
34
+ 120.56476435866055 42.4349244403591 3242.1560628684038 83.50022078295852
35
+ 13.72524477409959 35.858220519297525 3332.4066864946167 106.66582066236779
36
+ 558.1188080161639 90.0084504200356 2694.854973210736 145.67374080342415
37
+ 264.0088462230318 254.7175868081866 2796.88087480315 173.0486646159857
38
38
  519.46013914282 1874.9349086474765 654.5411208373813 439.7198038226514
data/test/data/test_collection_weak.yaml CHANGED
@@ -1,214 +1,231 @@
1
- --- !ruby/object:Bioinform::Collection
2
- container:
3
- - !ruby/object:Bioinform::Motif
4
- parameters: !ruby/object:OpenStruct
5
- table:
6
- :original_data_model: :pwm
7
- :pwm: !ruby/object:Bioinform::PWM
8
- parameters: !ruby/object:OpenStruct
9
- table:
10
- :name: GABPA_f1
11
- :background: &19796448
12
- - 1
13
- - 1
14
- - 1
15
- - 1
16
- :max_hash_size: 1000000
17
- modifiable: true
18
- matrix:
19
- - - -0.1106670158341858
20
- - 0.013801606113892391
21
- - 0.6054596108973699
22
- - -1.3518085041421573
23
- - - 0.37030668921643345
24
- - 0.15761121480429963
25
- - 0.009069314183831202
26
- - -0.9888619717703562
27
- - - 0.47526546359546684
28
- - -0.3011678534572083
29
- - 0.4031522994412777
30
- - -1.8638752827041059
31
- - - -1.5544255540164373
32
- - 1.1082369687811506
33
- - -0.2814091552834454
34
- - -5.30708531823271
35
- - - -0.6362037835776368
36
- - 1.235338189985594
37
- - -3.5801322928552253
38
- - -5.717323067092849
39
- - - -5.852906870733575
40
- - -5.852906870733575
41
- - 1.3841383838057746
42
- - -5.852906870733575
43
- - - -5.852906870733575
44
- - -5.852906870733575
45
- - 1.3841383838057746
46
- - -5.852906870733575
47
- - - 1.3835219739184708
48
- - -5.2341956006430985
49
- - -5.852906870733575
50
- - -5.852906870733575
51
- - - 1.3756340514956562
52
- - -5.394962755562375
53
- - -5.394962755562375
54
- - -3.401117964959733
55
- - - -1.2176198315414444
56
- - -3.109079898175411
57
- - 1.2964067931472216
58
- - -5.717323067092849
59
- - - -1.3716559438167257
60
- - -0.2761401935045069
61
- - -1.8504445165866068
62
- - 1.0404320473626856
63
- - - -0.5440863133031895
64
- - -0.48103682561971345
65
- - 0.907381908447086
66
- - -1.1280642594012078
67
- - - 0.10557340209290218
68
- - -0.01814819455289191
69
- - 0.4381106695354074
70
- - -1.0304105539540915
71
- :rough:
72
- 5.0e-05: 16.0
73
- 0.0001: 15.0
74
- 0.0005: 12.0
75
- :precise:
76
- 5.0e-05: 8.6
77
- 0.0001: 7.6
78
- 0.0005: 4.5
79
- modifiable: true
80
- - !ruby/object:Bioinform::Motif
81
- parameters: !ruby/object:OpenStruct
82
- table:
83
- :original_data_model: :pwm
84
- :pwm: !ruby/object:Bioinform::PWM
85
- parameters: !ruby/object:OpenStruct
86
- table:
87
- :name: KLF4_f2
88
- :background: *19796448
89
- :max_hash_size: 1000000
90
- modifiable: true
91
- matrix:
92
- - - 0.30861857265872605
93
- - -2.254321000121579
94
- - 0.13505703522674192
95
- - 0.3285194224375633
96
- - - -1.227018967707036
97
- - -4.814127713368663
98
- - 1.3059890687390967
99
- - -4.908681463544344
100
- - - -2.443469374521196
101
- - -4.648238485031404
102
- - 1.3588686548279805
103
- - -4.441801801188402
104
- - - -2.7177827948276123
105
- - -3.8073538975356565
106
- - 1.356272809724262
107
- - -3.504104725510225
108
- - - -0.5563232977367343
109
- - 0.5340697765121405
110
- - -3.61417723090579
111
- - 0.5270259776377405
112
- - - -1.8687622060887386
113
- - -4.381483976582316
114
- - 1.337932245336098
115
- - -3.815629658877517
116
- - - -2.045671123823928
117
- - -2.384975142213679
118
- - 0.7198551207724355
119
- - 0.5449254135616948
120
- - - -1.373157530374372
121
- - -3.0063112097748217
122
- - 1.285188335493552
123
- - -2.5026044231773543
124
- - - -2.1030513122772208
125
- - -1.8941348100402244
126
- - 1.249265758393991
127
- - -1.4284210948906104
128
- - - -1.3277128628152939
129
- - 0.8982415633049462
130
- - -0.8080773665408135
131
- - -0.18161647647456935
132
- :rough:
133
- 5.0e-05: 14.0
134
- 0.0001: 13.0
135
- 0.0005: 11.0
136
- :precise:
137
- 5.0e-05: 8.5
138
- 0.0001: 7.9
139
- 0.0005: 5.8
140
- modifiable: true
141
- - !ruby/object:Bioinform::Motif
142
- parameters: !ruby/object:OpenStruct
143
- table:
144
- :original_data_model: :pwm
145
- :pwm: !ruby/object:Bioinform::PWM
146
- parameters: !ruby/object:OpenStruct
147
- table:
148
- :name: SP1_f1
149
- :background: *19796448
150
- :max_hash_size: 1000000
151
- modifiable: true
152
- matrix:
153
- - - -0.24435707885585292
154
- - -0.674823404693731
155
- - 0.8657012535789866
156
- - -1.1060188862599287
157
- - - -1.0631255752097797
158
- - -2.111925969423868
159
- - 1.0960627561110403
160
- - -0.6138563775211977
161
- - - -0.3872276234760535
162
- - -2.9739851913218045
163
- - 1.1807800242010378
164
- - -4.338927525031566
165
- - - -4.563896055436894
166
- - -2.9161633002532277
167
- - 1.3684371349982638
168
- - -5.077972423609655
169
- - - -2.2369752892820083
170
- - -3.7196436313301846
171
- - 1.3510439136452734
172
- - -4.889930670508233
173
- - - -0.07473964149330865
174
- - 0.944919654762011
175
- - -2.6246857648086044
176
- - -0.8510983487822436
177
- - - -1.9643526491643322
178
- - -2.978402770880115
179
- - 1.3113096718240573
180
- - -2.324334259499025
181
- - - -4.0155484139655835
182
- - -3.1384268078096667
183
- - 1.3387488589788057
184
- - -2.084673903537648
185
- - - -0.44509385828355363
186
- - -2.2510053061629702
187
- - 1.1265431574368685
188
- - -1.7780413702431372
189
- - - -1.1896356092245048
190
- - -1.2251832285630027
191
- - 1.1636760063747527
192
- - -1.6080243648157353
193
- - - -0.5166047365590571
194
- - 0.7641033353626657
195
- - -0.2862677570028208
196
- - -0.68254820978656
197
- :rough:
198
- 5.0e-05: 14.0
199
- 0.0001: 14.0
200
- 0.0005: 11.0
201
- :precise:
202
- 5.0e-05: 8.5
203
- 0.0001: 7.7
204
- 0.0005: 5.6
205
- modifiable: true
206
- parameters: !ruby/object:OpenStruct
207
- table:
208
- :rough_discretization: 1
209
- :precise_discretization: 10
210
- :background: *19796448
211
- :pvalues:
212
- - 0.0005
213
- - 0.0001
214
- - 5.0e-05
1
+ --- !ruby/object:Macroape::Collection
2
+ motifs:
3
+ - !ruby/object:Macroape::MotifWithThresholds
4
+ model: !ruby/object:Bioinform::MotifModel::NamedModel
5
+ model: !ruby/object:Bioinform::MotifModel::PWM
6
+ matrix:
7
+ - - -0.1106670158341858
8
+ - 0.013801606113892391
9
+ - 0.6054596108973699
10
+ - -1.3518085041421573
11
+ - - 0.3703066892164342
12
+ - 0.15761121480430038
13
+ - 0.009069314183831861
14
+ - -0.9888619717703555
15
+ - - 0.47526546359546656
16
+ - -0.30116785345720876
17
+ - 0.40315229944127723
18
+ - -1.8638752827041063
19
+ - - -1.5544255540164387
20
+ - 1.1082369687811493
21
+ - -0.28140915528344673
22
+ - -5.307085318232711
23
+ - - -0.6362037835776333
24
+ - 1.2353381899855975
25
+ - -3.5801322928552217
26
+ - -5.717323067092845
27
+ - - -5.852906870733565
28
+ - -5.852906870733565
29
+ - 1.3841383838057844
30
+ - -5.852906870733565
31
+ - - -5.852906870733565
32
+ - -5.852906870733565
33
+ - 1.3841383838057844
34
+ - -5.852906870733565
35
+ - - 1.3835219739184805
36
+ - -5.234195600643089
37
+ - -5.852906870733565
38
+ - -5.852906870733565
39
+ - - 1.375634051495666
40
+ - -5.394962755562365
41
+ - -5.394962755562365
42
+ - -3.4011179649597234
43
+ - - -1.2176198315414393
44
+ - -3.109079898175406
45
+ - 1.2964067931472267
46
+ - -5.717323067092844
47
+ - - -1.3716559438167275
48
+ - -0.2761401935045087
49
+ - -1.8504445165866086
50
+ - 1.0404320473626838
51
+ - - -0.5440863133031892
52
+ - -0.4810368256197133
53
+ - 0.9073819084470863
54
+ - -1.1280642594012076
55
+ - - 0.10557340209290259
56
+ - -0.018148194552891343
57
+ - 0.43811066953540795
58
+ - -1.0304105539540909
59
+ alphabet: &1 !ruby/object:Bioinform::ComplementableAlphabet
60
+ alphabet:
61
+ - :A
62
+ - :C
63
+ - :G
64
+ - :T
65
+ complement_alphabet:
66
+ - :T
67
+ - :G
68
+ - :C
69
+ - :A
70
+ complements_by_letters:
71
+ A: T
72
+ :A: :T
73
+ a: t
74
+ :a: :t
75
+ C: G
76
+ :C: :G
77
+ c: g
78
+ :c: :g
79
+ G: C
80
+ :G: :C
81
+ g: c
82
+ :g: :c
83
+ T: A
84
+ :T: :A
85
+ t: a
86
+ :t: :a
87
+ index_by_letter:
88
+ a: 0
89
+ :a: 0
90
+ A: 0
91
+ :A: 0
92
+ c: 1
93
+ :c: 1
94
+ C: 1
95
+ :C: 1
96
+ g: 2
97
+ :g: 2
98
+ G: 2
99
+ :G: 2
100
+ t: 3
101
+ :t: 3
102
+ T: 3
103
+ :T: 3
104
+ name: GABPA_f1
105
+ rough:
106
+ 5.0e-05: 16.0
107
+ 0.0001: 15.0
108
+ 0.0005: 12.0
109
+ precise:
110
+ 5.0e-05: 8.6
111
+ 0.0001: 7.6
112
+ 0.0005: 4.5
113
+ - !ruby/object:Macroape::MotifWithThresholds
114
+ model: !ruby/object:Bioinform::MotifModel::NamedModel
115
+ model: !ruby/object:Bioinform::MotifModel::PWM
116
+ matrix:
117
+ - - 0.30861857265872605
118
+ - -2.254321000121579
119
+ - 0.13505703522674192
120
+ - 0.3285194224375633
121
+ - - -1.2270189677070362
122
+ - -4.814127713368663
123
+ - 1.3059890687390965
124
+ - -4.908681463544344
125
+ - - -2.4434693745211966
126
+ - -4.648238485031404
127
+ - 1.3588686548279802
128
+ - -4.441801801188402
129
+ - - -2.7177827948276128
130
+ - -3.807353897535657
131
+ - 1.3562728097242616
132
+ - -3.504104725510225
133
+ - - -0.5563232977367345
134
+ - 0.5340697765121402
135
+ - -3.61417723090579
136
+ - 0.5270259776377402
137
+ - - -1.8687622060887386
138
+ - -4.381483976582316
139
+ - 1.337932245336098
140
+ - -3.815629658877517
141
+ - - -2.0456711238239285
142
+ - -2.3849751422136793
143
+ - 0.7198551207724353
144
+ - 0.5449254135616943
145
+ - - -1.3731575303743726
146
+ - -3.006311209774822
147
+ - 1.2851883354935514
148
+ - -2.5026044231773548
149
+ - - -2.103051312277221
150
+ - -1.8941348100402247
151
+ - 1.249265758393991
152
+ - -1.4284210948906106
153
+ - - -1.327712862815294
154
+ - 0.898241563304946
155
+ - -0.8080773665408136
156
+ - -0.1816164764745695
157
+ alphabet: *1
158
+ name: KLF4_f2
159
+ rough:
160
+ 5.0e-05: 14.0
161
+ 0.0001: 13.0
162
+ 0.0005: 11.0
163
+ precise:
164
+ 5.0e-05: 8.5
165
+ 0.0001: 7.9
166
+ 0.0005: 5.8
167
+ - !ruby/object:Macroape::MotifWithThresholds
168
+ model: !ruby/object:Bioinform::MotifModel::NamedModel
169
+ model: !ruby/object:Bioinform::MotifModel::PWM
170
+ matrix:
171
+ - - -0.24435707885585292
172
+ - -0.674823404693731
173
+ - 0.8657012535789866
174
+ - -1.1060188862599287
175
+ - - -1.063125575209786
176
+ - -2.111925969423874
177
+ - 1.096062756111034
178
+ - -0.6138563775212038
179
+ - - -0.38722762347606526
180
+ - -2.9739851913218165
181
+ - 1.180780024201026
182
+ - -4.338927525031577
183
+ - - -4.563896055436912
184
+ - -2.916163300253245
185
+ - 1.3684371349982463
186
+ - -5.077972423609672
187
+ - - -2.2369752892820247
188
+ - -3.7196436313302015
189
+ - 1.3510439136452568
190
+ - -4.8899306705082495
191
+ - - -0.07473964149331284
192
+ - 0.9449196547620068
193
+ - -2.6246857648086084
194
+ - -0.8510983487822477
195
+ - - -1.9643526491643477
196
+ - -2.9784027708801304
197
+ - 1.3113096718240418
198
+ - -2.3243342594990404
199
+ - - -4.015548413965599
200
+ - -3.138426807809682
201
+ - 1.3387488589787901
202
+ - -2.0846739035376634
203
+ - - -0.44509385828356285
204
+ - -2.2510053061629796
205
+ - 1.1265431574368594
206
+ - -1.7780413702431463
207
+ - - -1.1896356092245128
208
+ - -1.2251832285630104
209
+ - 1.1636760063747449
210
+ - -1.608024364815743
211
+ - - -0.5166047365590577
212
+ - 0.7641033353626651
213
+ - -0.28626775700282125
214
+ - -0.6825482097865606
215
+ alphabet: *1
216
+ name: SP1_f1
217
+ rough:
218
+ 5.0e-05: 14.0
219
+ 0.0001: 14.0
220
+ 0.0005: 11.0
221
+ precise:
222
+ 5.0e-05: 8.5
223
+ 0.0001: 7.7
224
+ 0.0005: 5.6
225
+ rough_discretization: 1
226
+ precise_discretization: 10
227
+ background: !ruby/object:Bioinform::WordwiseBackground {}
228
+ pvalues:
229
+ - 0.0005
230
+ - 0.0001
231
+ - 5.0e-05