details: http://www.bx.psu.edu/hg/galaxy/rev/675ad84ae008 changeset: 1525:675ad84ae008 user: guru date: Mon Sep 22 12:02:35 2008 -0400 description: Modified INDEL tools under Regional variation section. 6 file(s) affected in this change: test-data/indelrates_3way.tabular test-data/indels_3way.tabular tools/regVariation/getIndelRates_3way.py tools/regVariation/getIndelRates_3way.xml tools/regVariation/getIndels_3way.xml tools/regVariation/parseMAF_smallIndels.pl diffs (908 lines): diff -r aae4754d6828 -r 675ad84ae008 test-data/indelrates_3way.tabular --- a/test-data/indelrates_3way.tabular Mon Sep 22 10:36:34 2008 -0400 +++ b/test-data/indelrates_3way.tabular Mon Sep 22 12:02:35 2008 -0400 @@ -1,13 +1,15 @@ -#Window Species Window_Start Window_End Insertion_Rate Deletion_Rate -1 canFam2 3356001 3357001 3.80e-03 2.17e-03 -2 canFam2 3357001 3358001 2.46e-03 1.85e-03 -3 canFam2 3358001 3359001 1.23e-03 3.08e-03 -4 canFam2 3359001 3360001 6.76e-03 8.39e-03 -5 canFam2 3360001 3361001 8.41e-03 1.12e-02 -6 canFam2 3361001 3362001 9.27e-03 1.85e-02 -7 canFam2 3362001 3363001 1.17e-02 6.67e-03 -8 canFam2 3363001 3364001 1.97e-02 5.62e-03 -9 canFam2 3364001 3365001 5.92e-03 9.65e-03 -10 canFam2 3366001 3367001 3.69e-03 2.63e-03 -11 canFam2 3367001 3368001 9.89e-03 4.95e-03 -12 canFam2 3368001 3369001 6.90e-03 1.38e-02 +#Block hg18_InsRate panTro2_InsRate canFam2_InsRate hg18_DelRate panTro2_DelRate canFam2_DelRate +1 0.00e+00 6.90e-03 6.90e-03 0.00e+00 0.00e+00 1.38e-02 +2 0.00e+00 0.00e+00 1.27e-02 7.25e-04 0.00e+00 6.36e-03 +3 0.00e+00 0.00e+00 6.21e-03 0.00e+00 0.00e+00 6.21e-03 +4 0.00e+00 0.00e+00 2.07e-02 0.00e+00 0.00e+00 5.18e-03 +5 0.00e+00 0.00e+00 2.54e-02 0.00e+00 0.00e+00 1.69e-02 +6 0.00e+00 0.00e+00 9.61e-04 0.00e+00 0.00e+00 0.00e+00 +7 0.00e+00 0.00e+00 1.97e-02 0.00e+00 0.00e+00 5.62e-03 +8 0.00e+00 1.71e-03 1.17e-02 0.00e+00 1.71e-03 6.67e-03 +9 0.00e+00 0.00e+00 1.05e-02 2.72e-03 0.00e+00 1.83e-02 +10 0.00e+00 3.26e-03 1.51e-02 0.00e+00 0.00e+00 1.89e-02 +12 1.25e-03 0.00e+00 8.70e-03 0.00e+00 0.00e+00 1.24e-02 +13 0.00e+00 0.00e+00 6.76e-03 0.00e+00 0.00e+00 4.73e-02 +14 0.00e+00 0.00e+00 4.93e-03 1.23e-03 1.23e-03 5.55e-03 +15 0.00e+00 0.00e+00 2.29e-02 0.00e+00 0.00e+00 1.38e-02 diff -r aae4754d6828 -r 675ad84ae008 test-data/indels_3way.tabular --- a/test-data/indels_3way.tabular Mon Sep 22 10:36:34 2008 -0400 +++ b/test-data/indels_3way.tabular Mon Sep 22 12:02:35 2008 -0400 @@ -1,149 +1,149 @@ -#block indel_type indel_length ingroup1 ingroup1_start ingroup1_end ingroup1_orient ingroup2 ingroup2_start ingroup2_end ingroup2_orient outgroup outgroup_start outgroup_end outgroup_orient -12 hg18.chr1:802_insert 1 hg18.chr1:802 57213 57213 + panTro2.chrUn:801 9724391 9724392 + canFam2.chr30:805 3360548 3360549 - -2 hg18.chr1:1380_delete 4 hg18.chr1:1380 48103 48104 + panTro2.chrUn:1384 9713713 9713716 + canFam2.chr30:1415 3367755 3367758 - -9 hg18.chr1:367_delete 35 hg18.chr1:367 55389 55390 + panTro2.chrUn:402 9721584 9721618 + canFam2.chr30:382 3361661 3361695 - -14 hg18.chr1:1628_delete 1 hg18.chr1:1628 58770 58771 + panTro2.chrUn:1631 9725949 9725949 + canFam2.chr30:1623 3357056 3357056 - -14 hg18.chr1:1628_delete 4 hg18.chr1:1628 58770 58771 + panTro2.chrUn:1631 9725950 9725953 + canFam2.chr30:1623 3357058 3357061 - -1 panTro2.chrUn:145_insert 2 hg18.chr1:143 46857 46858 + panTro2.chrUn:145 9712465 9712466 + canFam2.chr30:145 3368190 3368191 - -8 panTro2.chrUn:585_insert 4 hg18.chr1:582 54744 54745 + panTro2.chrUn:585 9720936 9720939 + canFam2.chr30:600 3362635 3362636 - -10 panTro2.chrUn:307_insert 35 hg18.chr1:272 55984 55985 + panTro2.chrUn:307 9721981 9722015 + canFam2.chr30:265 3361105 3361106 - -8 panTro2.chrUn:585_delete 1 hg18.chr1:582 54979 54979 + panTro2.chrUn:585 9721173 9721174 + canFam2.chr30:600 3362890 3362890 - -14 panTro2.chrUn:1631_delete 1 hg18.chr1:1628 59015 59015 + panTro2.chrUn:1631 9726197 9726198 + canFam2.chr30:1623 3357328 3357328 - -14 panTro2.chrUn:1631_delete 1 hg18.chr1:1628 60211 60211 + panTro2.chrUn:1631 9727392 9727393 + canFam2.chr30:1623 3358490 3358490 - -1 canFam2.chr30:145_insert 4 hg18.chr1:143 46796 46797 + panTro2.chrUn:145 9712403 9712404 + canFam2.chr30:145 3368127 3368130 - -2 canFam2.chr30:1415_insert 8 hg18.chr1:1380 47138 47139 + panTro2.chrUn:1384 9712747 9712748 + canFam2.chr30:1415 3366730 3366737 - -2 canFam2.chr30:1415_insert 3 hg18.chr1:1380 47263 47264 + panTro2.chrUn:1384 9712872 9712873 + canFam2.chr30:1415 3366862 3366864 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 47293 47294 + panTro2.chrUn:1384 9712902 9712903 + canFam2.chr30:1415 3366895 3366895 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 47312 47313 + panTro2.chrUn:1384 9712921 9712922 + canFam2.chr30:1415 3366915 3366915 - -2 canFam2.chr30:1415_insert 7 hg18.chr1:1380 47440 47441 + panTro2.chrUn:1384 9713049 9713050 + canFam2.chr30:1415 3367044 3367050 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 47528 47529 + panTro2.chrUn:1384 9713137 9713138 + canFam2.chr30:1415 3367138 3367138 - -2 canFam2.chr30:1415_insert 10 hg18.chr1:1380 47546 47547 + panTro2.chrUn:1384 9713155 9713156 + canFam2.chr30:1415 3367157 3367166 - -2 canFam2.chr30:1415_insert 4 hg18.chr1:1380 47562 47563 + panTro2.chrUn:1384 9713171 9713172 + canFam2.chr30:1415 3367183 3367186 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 47648 47649 + panTro2.chrUn:1384 9713257 9713258 + canFam2.chr30:1415 3367273 3367273 - -2 canFam2.chr30:1415_insert 3 hg18.chr1:1380 47672 47673 + panTro2.chrUn:1384 9713281 9713282 + canFam2.chr30:1415 3367298 3367300 - -2 canFam2.chr30:1415_insert 5 hg18.chr1:1380 47734 47735 + panTro2.chrUn:1384 9713343 9713344 + canFam2.chr30:1415 3367361 3367365 - -2 canFam2.chr30:1415_insert 2 hg18.chr1:1380 47759 47760 + panTro2.chrUn:1384 9713368 9713369 + canFam2.chr30:1415 3367391 3367392 - -2 canFam2.chr30:1415_insert 2 hg18.chr1:1380 47835 47836 + panTro2.chrUn:1384 9713444 9713445 + canFam2.chr30:1415 3367469 3367470 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 48017 48018 + panTro2.chrUn:1384 9713626 9713627 + canFam2.chr30:1415 3367653 3367653 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 48035 48036 + panTro2.chrUn:1384 9713644 9713645 + canFam2.chr30:1415 3367672 3367672 - -2 canFam2.chr30:1415_insert 4 hg18.chr1:1380 48091 48092 + panTro2.chrUn:1384 9713700 9713701 + canFam2.chr30:1415 3367729 3367732 - -2 canFam2.chr30:1415_insert 10 hg18.chr1:1380 48103 48104 + panTro2.chrUn:1384 9713712 9713713 + canFam2.chr30:1415 3367745 3367754 - -2 canFam2.chr30:1415_insert 1 hg18.chr1:1380 48232 48233 + panTro2.chrUn:1384 9713845 9713846 + canFam2.chr30:1415 3367870 3367870 - -3 canFam2.chr30:483_insert 15 hg18.chr1:455 48379 48380 + panTro2.chrUn:455 9714289 9714290 + canFam2.chr30:483 3366038 3366052 - -3 canFam2.chr30:483_insert 21 hg18.chr1:455 48426 48427 + panTro2.chrUn:455 9714336 9714337 + canFam2.chr30:483 3366096 3366116 - -3 canFam2.chr30:483_insert 1 hg18.chr1:455 48523 48524 + panTro2.chrUn:455 9714433 9714434 + canFam2.chr30:483 3366213 3366213 - -4 canFam2.chr30:193_insert 8 hg18.chr1:183 52535 52536 + panTro2.chrUn:183 9718438 9718439 + canFam2.chr30:193 3364655 3364662 - -4 canFam2.chr30:193_insert 1 hg18.chr1:183 52555 52556 + panTro2.chrUn:183 9718458 9718459 + canFam2.chr30:193 3364683 3364683 - -4 canFam2.chr30:193_insert 1 hg18.chr1:183 52588 52589 + panTro2.chrUn:183 9718491 9718492 + canFam2.chr30:193 3364717 3364717 - -4 canFam2.chr30:193_insert 4 hg18.chr1:183 52691 52692 + panTro2.chrUn:183 9718594 9718595 + canFam2.chr30:193 3364817 3364820 - -5 canFam2.chr30:118_insert 3 hg18.chr1:115 52709 52710 + panTro2.chrUn:115 9718612 9718613 + canFam2.chr30:118 3364525 3364527 - -5 canFam2.chr30:118_insert 1 hg18.chr1:115 52754 52755 + panTro2.chrUn:115 9718657 9718658 + canFam2.chr30:118 3364571 3364571 - -5 canFam2.chr30:118_insert 4 hg18.chr1:115 52763 52764 + panTro2.chrUn:115 9718666 9718667 + canFam2.chr30:118 3364581 3364584 - -6 canFam2.chr30:1041_insert 1 hg18.chr1:1040 53848 53849 + panTro2.chrUn:1040 9719751 9719752 + canFam2.chr30:1041 3364511 3364511 - -7 canFam2.chr30:356_insert 4 hg18.chr1:335 53869 53870 + panTro2.chrUn:335 9719772 9719773 + canFam2.chr30:356 3363136 3363139 - -7 canFam2.chr30:356_insert 1 hg18.chr1:335 53899 53900 + panTro2.chrUn:335 9719802 9719803 + canFam2.chr30:356 3363168 3363168 - -7 canFam2.chr30:356_insert 1 hg18.chr1:335 53921 53922 + panTro2.chrUn:335 9719824 9719825 + canFam2.chr30:356 3363191 3363191 - -7 canFam2.chr30:356_insert 8 hg18.chr1:335 53938 53939 + panTro2.chrUn:335 9719841 9719842 + canFam2.chr30:356 3363209 3363216 - -7 canFam2.chr30:356_insert 7 hg18.chr1:335 53970 53971 + panTro2.chrUn:335 9719873 9719874 + canFam2.chr30:356 3363249 3363255 - -7 canFam2.chr30:356_insert 5 hg18.chr1:335 54101 54102 + panTro2.chrUn:335 9720004 9720005 + canFam2.chr30:356 3363383 3363387 - -7 canFam2.chr30:356_insert 1 hg18.chr1:335 54164 54165 + panTro2.chrUn:335 9720067 9720068 + canFam2.chr30:356 3363451 3363451 - -8 canFam2.chr30:600_insert 1 hg18.chr1:582 54579 54580 + panTro2.chrUn:585 9720770 9720771 + canFam2.chr30:600 3362472 3362472 - -8 canFam2.chr30:600_insert 1 hg18.chr1:582 54654 54655 + panTro2.chrUn:585 9720845 9720846 + canFam2.chr30:600 3362547 3362547 - -8 canFam2.chr30:600_insert 1 hg18.chr1:582 54691 54692 + panTro2.chrUn:585 9720882 9720883 + canFam2.chr30:600 3362585 3362585 - -8 canFam2.chr30:600_insert 18 hg18.chr1:582 54775 54776 + panTro2.chrUn:585 9720970 9720971 + canFam2.chr30:600 3362667 3362684 - -8 canFam2.chr30:600_insert 1 hg18.chr1:582 54799 54800 + panTro2.chrUn:585 9720994 9720995 + canFam2.chr30:600 3362709 3362709 - -8 canFam2.chr30:600_insert 4 hg18.chr1:582 54944 54945 + panTro2.chrUn:585 9721139 9721140 + canFam2.chr30:600 3362851 3362854 - -8 canFam2.chr30:600_insert 1 hg18.chr1:582 54969 54970 + panTro2.chrUn:585 9721164 9721165 + canFam2.chr30:600 3362880 3362880 - -9 canFam2.chr30:382_insert 1 hg18.chr1:367 55360 55361 + panTro2.chrUn:402 9721554 9721555 + canFam2.chr30:382 3361632 3361632 - -9 canFam2.chr30:382_insert 1 hg18.chr1:367 55378 55379 + panTro2.chrUn:402 9721572 9721573 + canFam2.chr30:382 3361651 3361651 - -9 canFam2.chr30:382_insert 1 hg18.chr1:367 55396 55397 + panTro2.chrUn:402 9721625 9721626 + canFam2.chr30:382 3361703 3361703 - -9 canFam2.chr30:382_insert 2 hg18.chr1:367 55444 55445 + panTro2.chrUn:402 9721673 9721674 + canFam2.chr30:382 3361752 3361753 - -10 canFam2.chr30:265_insert 1 hg18.chr1:272 55776 55777 + panTro2.chrUn:307 9721772 9721773 + canFam2.chr30:265 3360902 3360902 - -10 canFam2.chr30:265_insert 5 hg18.chr1:272 55864 55865 + panTro2.chrUn:307 9721860 9721861 + canFam2.chr30:265 3360991 3360995 - -10 canFam2.chr30:265_insert 2 hg18.chr1:272 55969 55970 + panTro2.chrUn:307 9721965 9721966 + canFam2.chr30:265 3361087 3361088 - -10 canFam2.chr30:265_insert 2 hg18.chr1:272 55980 55981 + panTro2.chrUn:307 9721976 9721977 + canFam2.chr30:265 3361100 3361101 - -12 canFam2.chr30:805_insert 33 hg18.chr1:802 56722 56723 + panTro2.chrUn:801 9723901 9723902 + canFam2.chr30:805 3360035 3360067 - -12 canFam2.chr30:805_insert 1 hg18.chr1:802 56746 56747 + panTro2.chrUn:801 9723925 9723926 + canFam2.chr30:805 3360092 3360092 - -12 canFam2.chr30:805_insert 1 hg18.chr1:802 56836 56837 + panTro2.chrUn:801 9724015 9724016 + canFam2.chr30:805 3360183 3360183 - -12 canFam2.chr30:805_insert 1 hg18.chr1:802 56864 56865 + panTro2.chrUn:801 9724043 9724044 + canFam2.chr30:805 3360212 3360212 - -12 canFam2.chr30:805_insert 1 hg18.chr1:802 56894 56895 + panTro2.chrUn:801 9724073 9724074 + canFam2.chr30:805 3360243 3360243 - -12 canFam2.chr30:805_insert 2 hg18.chr1:802 57161 57162 + panTro2.chrUn:801 9724340 9724341 + canFam2.chr30:805 3360496 3360497 - -12 canFam2.chr30:805_insert 1 hg18.chr1:802 57352 57353 + panTro2.chrUn:801 9724530 9724531 + canFam2.chr30:805 3360680 3360680 - -13 canFam2.chr30:148_insert 2 hg18.chr1:176 58529 58530 + panTro2.chrUn:176 9725707 9725708 + canFam2.chr30:148 3359565 3359566 - -14 canFam2.chr30:1623_insert 1 hg18.chr1:1628 58700 58701 + panTro2.chrUn:1631 9725878 9725879 + canFam2.chr30:1623 3356984 3356984 - -14 canFam2.chr30:1623_insert 1 hg18.chr1:1628 58709 58710 + panTro2.chrUn:1631 9725887 9725888 + canFam2.chr30:1623 3356994 3356994 - -14 canFam2.chr30:1623_insert 1 hg18.chr1:1628 58770 58771 + panTro2.chrUn:1631 9725949 9725950 + canFam2.chr30:1623 3357057 3357057 - -14 canFam2.chr30:1623_insert 1 hg18.chr1:1628 58772 58773 + panTro2.chrUn:1631 9725955 9725956 + canFam2.chr30:1623 3357064 3357064 - -14 canFam2.chr30:1623_insert 15 hg18.chr1:1628 58800 58801 + panTro2.chrUn:1631 9725983 9725984 + canFam2.chr30:1623 3357093 3357107 - -14 canFam2.chr30:1623_insert 9 hg18.chr1:1628 58808 58809 + panTro2.chrUn:1631 9725991 9725992 + canFam2.chr30:1623 3357116 3357124 - -14 canFam2.chr30:1623_insert 1 hg18.chr1:1628 60032 60033 + panTro2.chrUn:1631 9727214 9727215 + canFam2.chr30:1623 3358319 3358319 - -14 canFam2.chr30:1623_insert 4 hg18.chr1:1628 60148 60149 + panTro2.chrUn:1631 9727330 9727331 + canFam2.chr30:1623 3358426 3358429 - -15 canFam2.chr30:218_insert 1 hg18.chr1:230 60326 60327 + panTro2.chrUn:230 9727507 9727508 + canFam2.chr30:218 3356643 3356643 - -15 canFam2.chr30:218_insert 2 hg18.chr1:230 60353 60354 + panTro2.chrUn:230 9727534 9727535 + canFam2.chr30:218 3356671 3356672 - -15 canFam2.chr30:218_insert 1 hg18.chr1:230 60391 60392 + panTro2.chrUn:230 9727572 9727573 + canFam2.chr30:218 3356711 3356711 - -15 canFam2.chr30:218_insert 1 hg18.chr1:230 60466 60467 + panTro2.chrUn:230 9727647 9727648 + canFam2.chr30:218 3356783 3356783 - -15 canFam2.chr30:218_insert 5 hg18.chr1:230 60476 60477 + panTro2.chrUn:230 9727657 9727658 + canFam2.chr30:218 3356794 3356798 - -1 canFam2.chr30:145_delete 1 hg18.chr1:143 46857 46857 + panTro2.chrUn:145 9712464 9712464 + canFam2.chr30:145 3368190 3368191 - -1 canFam2.chr30:145_delete 1 hg18.chr1:143 46900 46900 + panTro2.chrUn:145 9712509 9712509 + canFam2.chr30:145 3368232 3368233 - -2 canFam2.chr30:1415_delete 7 hg18.chr1:1380 47080 47086 + panTro2.chrUn:1384 9712689 9712695 + canFam2.chr30:1415 3366677 3366678 - -2 canFam2.chr30:1415_delete 1 hg18.chr1:1380 47168 47168 + panTro2.chrUn:1384 9712777 9712777 + canFam2.chr30:1415 3366766 3366767 - -2 canFam2.chr30:1415_delete 1 hg18.chr1:1380 47482 47482 + panTro2.chrUn:1384 9713091 9713091 + canFam2.chr30:1415 3367091 3367092 - -2 canFam2.chr30:1415_delete 2 hg18.chr1:1380 47703 47704 + panTro2.chrUn:1384 9713312 9713313 + canFam2.chr30:1415 3367330 3367331 - -2 canFam2.chr30:1415_delete 15 hg18.chr1:1380 48139 48153 + panTro2.chrUn:1384 9713752 9713766 + canFam2.chr30:1415 3367793 3367794 - -2 canFam2.chr30:1415_delete 1 hg18.chr1:1380 48160 48160 + panTro2.chrUn:1384 9713773 9713773 + canFam2.chr30:1415 3367799 3367800 - -2 canFam2.chr30:1415_delete 1 hg18.chr1:1380 48174 48174 + panTro2.chrUn:1384 9713787 9713787 + canFam2.chr30:1415 3367812 3367813 - -2 canFam2.chr30:1415_delete 1 hg18.chr1:1380 48197 48197 + panTro2.chrUn:1384 9713810 9713810 + canFam2.chr30:1415 3367834 3367835 - -2 canFam2.chr30:1415_delete 5 hg18.chr1:1380 48280 48284 + panTro2.chrUn:1384 9713893 9713897 + canFam2.chr30:1415 3367917 3367918 - -3 canFam2.chr30:483_delete 4 hg18.chr1:455 48344 48347 + panTro2.chrUn:455 9714254 9714257 + canFam2.chr30:483 3366005 3366006 - -3 canFam2.chr30:483_delete 4 hg18.chr1:455 48410 48413 + panTro2.chrUn:455 9714320 9714323 + canFam2.chr30:483 3366082 3366083 - -3 canFam2.chr30:483_delete 1 hg18.chr1:455 48470 48470 + panTro2.chrUn:455 9714380 9714380 + canFam2.chr30:483 3366159 3366160 - -4 canFam2.chr30:193_delete 4 hg18.chr1:183 52639 52642 + panTro2.chrUn:183 9718542 9718545 + canFam2.chr30:193 3364767 3364768 - -5 canFam2.chr30:118_delete 3 hg18.chr1:115 52707 52709 + panTro2.chrUn:115 9718610 9718612 + canFam2.chr30:118 3364524 3364525 - -5 canFam2.chr30:118_delete 2 hg18.chr1:115 52743 52744 + panTro2.chrUn:115 9718646 9718647 + canFam2.chr30:118 3364560 3364561 - -7 canFam2.chr30:356_delete 2 hg18.chr1:335 53879 53880 + panTro2.chrUn:335 9719782 9719783 + canFam2.chr30:356 3363148 3363149 - -7 canFam2.chr30:356_delete 4 hg18.chr1:335 54052 54055 + panTro2.chrUn:335 9719955 9719958 + canFam2.chr30:356 3363336 3363337 - -8 canFam2.chr30:600_delete 1 hg18.chr1:582 54634 54634 + panTro2.chrUn:585 9720825 9720825 + canFam2.chr30:600 3362526 3362527 - -8 canFam2.chr30:600_delete 3 hg18.chr1:582 54710 54712 + panTro2.chrUn:585 9720901 9720903 + canFam2.chr30:600 3362603 3362604 - -8 canFam2.chr30:600_delete 4 hg18.chr1:582 54876 54879 + panTro2.chrUn:585 9721071 9721074 + canFam2.chr30:600 3362785 3362786 - -8 canFam2.chr30:600_delete 1 hg18.chr1:582 54984 54984 + panTro2.chrUn:585 9721178 9721178 + canFam2.chr30:600 3362894 3362895 - -9 canFam2.chr30:382_delete 1 hg18.chr1:367 55131 55131 + panTro2.chrUn:402 9721325 9721325 + canFam2.chr30:382 3361420 3361421 - -9 canFam2.chr30:382_delete 6 hg18.chr1:367 55213 55218 + panTro2.chrUn:402 9721407 9721412 + canFam2.chr30:382 3361501 3361502 - -9 canFam2.chr30:382_delete 1 hg18.chr1:367 55308 55308 + panTro2.chrUn:402 9721502 9721502 + canFam2.chr30:382 3361590 3361591 - -9 canFam2.chr30:382_delete 4 hg18.chr1:367 55324 55327 + panTro2.chrUn:402 9721518 9721521 + canFam2.chr30:382 3361605 3361606 - -9 canFam2.chr30:382_delete 7 hg18.chr1:367 55340 55346 + panTro2.chrUn:402 9721534 9721540 + canFam2.chr30:382 3361617 3361618 - -9 canFam2.chr30:382_delete 2 hg18.chr1:367 55386 55387 + panTro2.chrUn:402 9721580 9721581 + canFam2.chr30:382 3361658 3361659 - -9 canFam2.chr30:382_delete 4 hg18.chr1:367 55457 55460 + panTro2.chrUn:402 9721686 9721689 + canFam2.chr30:382 3361765 3361766 - -10 canFam2.chr30:265_delete 11 hg18.chr1:272 55893 55903 + panTro2.chrUn:307 9721889 9721899 + canFam2.chr30:265 3361023 3361024 - -10 canFam2.chr30:265_delete 1 hg18.chr1:272 55924 55924 + panTro2.chrUn:307 9721920 9721920 + canFam2.chr30:265 3361043 3361044 - -10 canFam2.chr30:265_delete 1 hg18.chr1:272 55939 55939 + panTro2.chrUn:307 9721935 9721935 + canFam2.chr30:265 3361057 3361058 - -10 canFam2.chr30:265_delete 1 hg18.chr1:272 55959 55959 + panTro2.chrUn:307 9721955 9721955 + canFam2.chr30:265 3361076 3361077 - -10 canFam2.chr30:265_delete 3 hg18.chr1:272 56001 56003 + panTro2.chrUn:307 9722032 9722034 + canFam2.chr30:265 3361121 3361122 - -12 canFam2.chr30:805_delete 6 hg18.chr1:802 56611 56616 + panTro2.chrUn:801 9723790 9723795 + canFam2.chr30:805 3359929 3359930 - -12 canFam2.chr30:805_delete 1 hg18.chr1:802 56696 56696 + panTro2.chrUn:801 9723875 9723875 + canFam2.chr30:805 3360008 3360009 - -12 canFam2.chr30:805_delete 7 hg18.chr1:802 56911 56917 + panTro2.chrUn:801 9724090 9724096 + canFam2.chr30:805 3360259 3360260 - -12 canFam2.chr30:805_delete 3 hg18.chr1:802 56991 56993 + panTro2.chrUn:801 9724170 9724172 + canFam2.chr30:805 3360332 3360333 - -12 canFam2.chr30:805_delete 5 hg18.chr1:802 57110 57114 + panTro2.chrUn:801 9724289 9724293 + canFam2.chr30:805 3360448 3360449 - -12 canFam2.chr30:805_delete 1 hg18.chr1:802 57217 57217 + panTro2.chrUn:801 9724395 9724395 + canFam2.chr30:805 3360551 3360552 - -12 canFam2.chr30:805_delete 5 hg18.chr1:802 57247 57251 + panTro2.chrUn:801 9724425 9724429 + canFam2.chr30:805 3360580 3360581 - -12 canFam2.chr30:805_delete 2 hg18.chr1:802 57310 57311 + panTro2.chrUn:801 9724488 9724489 + canFam2.chr30:805 3360638 3360639 - -12 canFam2.chr30:805_delete 2 hg18.chr1:802 57379 57380 + panTro2.chrUn:801 9724557 9724558 + canFam2.chr30:805 3360706 3360707 - -12 canFam2.chr30:805_delete 4 hg18.chr1:802 57387 57390 + panTro2.chrUn:801 9724565 9724568 + canFam2.chr30:805 3360712 3360713 - -13 canFam2.chr30:148_delete 3 hg18.chr1:176 58409 58411 + panTro2.chrUn:176 9725587 9725589 + canFam2.chr30:148 3359468 3359469 - -13 canFam2.chr30:148_delete 1 hg18.chr1:176 58434 58434 + panTro2.chrUn:176 9725612 9725612 + canFam2.chr30:148 3359490 3359491 - -13 canFam2.chr30:148_delete 2 hg18.chr1:176 58446 58447 + panTro2.chrUn:176 9725624 9725625 + canFam2.chr30:148 3359501 3359502 - -13 canFam2.chr30:148_delete 8 hg18.chr1:176 58470 58477 + panTro2.chrUn:176 9725648 9725655 + canFam2.chr30:148 3359523 3359524 - -13 canFam2.chr30:148_delete 5 hg18.chr1:176 58488 58492 + panTro2.chrUn:176 9725666 9725670 + canFam2.chr30:148 3359533 3359534 - -13 canFam2.chr30:148_delete 6 hg18.chr1:176 58510 58515 + panTro2.chrUn:176 9725688 9725693 + canFam2.chr30:148 3359550 3359551 - -13 canFam2.chr30:148_delete 5 hg18.chr1:176 58565 58569 + panTro2.chrUn:176 9725743 9725747 + canFam2.chr30:148 3359601 3359602 - -14 canFam2.chr30:1623_delete 1 hg18.chr1:1628 58669 58669 + panTro2.chrUn:1631 9725847 9725847 + canFam2.chr30:1623 3356952 3356953 - -14 canFam2.chr30:1623_delete 3 hg18.chr1:1628 58849 58851 + panTro2.chrUn:1631 9726032 9726034 + canFam2.chr30:1623 3357164 3357165 - -14 canFam2.chr30:1623_delete 10 hg18.chr1:1628 59342 59351 + panTro2.chrUn:1631 9726524 9726533 + canFam2.chr30:1623 3357654 3357655 - -14 canFam2.chr30:1623_delete 1 hg18.chr1:1628 59561 59561 + panTro2.chrUn:1631 9726743 9726743 + canFam2.chr30:1623 3357863 3357864 - -14 canFam2.chr30:1623_delete 11 hg18.chr1:1628 59887 59897 + panTro2.chrUn:1631 9727069 9727079 + canFam2.chr30:1623 3358188 3358189 - -14 canFam2.chr30:1623_delete 5 hg18.chr1:1628 59908 59912 + panTro2.chrUn:1631 9727090 9727094 + canFam2.chr30:1623 3358198 3358199 - -14 canFam2.chr30:1623_delete 6 hg18.chr1:1628 60052 60057 + panTro2.chrUn:1631 9727234 9727239 + canFam2.chr30:1623 3358338 3358339 - -14 canFam2.chr30:1623_delete 4 hg18.chr1:1628 60111 60114 + panTro2.chrUn:1631 9727293 9727296 + canFam2.chr30:1623 3358391 3358392 - -14 canFam2.chr30:1623_delete 2 hg18.chr1:1628 60183 60184 + panTro2.chrUn:1631 9727365 9727366 + canFam2.chr30:1623 3358463 3358464 - -15 canFam2.chr30:218_delete 4 hg18.chr1:230 60400 60403 + panTro2.chrUn:230 9727581 9727584 + canFam2.chr30:218 3356719 3356720 - -15 canFam2.chr30:218_delete 8 hg18.chr1:230 60506 60513 + panTro2.chrUn:230 9727687 9727694 + canFam2.chr30:218 3356827 3356828 - -15 canFam2.chr30:218_delete 10 hg18.chr1:230 60520 60529 + panTro2.chrUn:230 9727701 9727710 + canFam2.chr30:218 3356833 3356834 - +#block indel_type indel_length ingroup1 ingroup1_start ingroup1_end ingroup1_alignSize ingroup1_orient ingroup2 ingroup2_start ingroup2_end ingroup2_alignSize ingroup2_orient outgroup outgroup_start outgroup_end outgroup_alignSize outgroup_orient +12 hg18.chr1_insert 1 hg18.chr1 57213 57213 802 + panTro2.chrUn 9724391 9724392 801 + canFam2.chr30 3360548 3360549 805 - +2 hg18.chr1_delete 4 hg18.chr1 48103 48104 1380 + panTro2.chrUn 9713713 9713716 1384 + canFam2.chr30 3367755 3367758 1415 - +9 hg18.chr1_delete 35 hg18.chr1 55389 55390 367 + panTro2.chrUn 9721584 9721618 402 + canFam2.chr30 3361661 3361695 382 - +14 hg18.chr1_delete 1 hg18.chr1 58770 58771 1628 + panTro2.chrUn 9725949 9725949 1631 + canFam2.chr30 3357056 3357056 1623 - +14 hg18.chr1_delete 4 hg18.chr1 58770 58771 1628 + panTro2.chrUn 9725950 9725953 1631 + canFam2.chr30 3357058 3357061 1623 - +1 panTro2.chrUn_insert 2 hg18.chr1 46857 46858 143 + panTro2.chrUn 9712465 9712466 145 + canFam2.chr30 3368190 3368191 145 - +8 panTro2.chrUn_insert 4 hg18.chr1 54744 54745 582 + panTro2.chrUn 9720936 9720939 585 + canFam2.chr30 3362635 3362636 600 - +10 panTro2.chrUn_insert 35 hg18.chr1 55984 55985 272 + panTro2.chrUn 9721981 9722015 307 + canFam2.chr30 3361105 3361106 265 - +8 panTro2.chrUn_delete 1 hg18.chr1 54979 54979 582 + panTro2.chrUn 9721173 9721174 585 + canFam2.chr30 3362890 3362890 600 - +14 panTro2.chrUn_delete 1 hg18.chr1 59015 59015 1628 + panTro2.chrUn 9726197 9726198 1631 + canFam2.chr30 3357328 3357328 1623 - +14 panTro2.chrUn_delete 1 hg18.chr1 60211 60211 1628 + panTro2.chrUn 9727392 9727393 1631 + canFam2.chr30 3358490 3358490 1623 - +1 canFam2.chr30_insert 4 hg18.chr1 46796 46797 143 + panTro2.chrUn 9712403 9712404 145 + canFam2.chr30 3368127 3368130 145 - +2 canFam2.chr30_insert 8 hg18.chr1 47138 47139 1380 + panTro2.chrUn 9712747 9712748 1384 + canFam2.chr30 3366730 3366737 1415 - +2 canFam2.chr30_insert 3 hg18.chr1 47263 47264 1380 + panTro2.chrUn 9712872 9712873 1384 + canFam2.chr30 3366862 3366864 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 47293 47294 1380 + panTro2.chrUn 9712902 9712903 1384 + canFam2.chr30 3366895 3366895 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 47312 47313 1380 + panTro2.chrUn 9712921 9712922 1384 + canFam2.chr30 3366915 3366915 1415 - +2 canFam2.chr30_insert 7 hg18.chr1 47440 47441 1380 + panTro2.chrUn 9713049 9713050 1384 + canFam2.chr30 3367044 3367050 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 47528 47529 1380 + panTro2.chrUn 9713137 9713138 1384 + canFam2.chr30 3367138 3367138 1415 - +2 canFam2.chr30_insert 10 hg18.chr1 47546 47547 1380 + panTro2.chrUn 9713155 9713156 1384 + canFam2.chr30 3367157 3367166 1415 - +2 canFam2.chr30_insert 4 hg18.chr1 47562 47563 1380 + panTro2.chrUn 9713171 9713172 1384 + canFam2.chr30 3367183 3367186 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 47648 47649 1380 + panTro2.chrUn 9713257 9713258 1384 + canFam2.chr30 3367273 3367273 1415 - +2 canFam2.chr30_insert 3 hg18.chr1 47672 47673 1380 + panTro2.chrUn 9713281 9713282 1384 + canFam2.chr30 3367298 3367300 1415 - +2 canFam2.chr30_insert 5 hg18.chr1 47734 47735 1380 + panTro2.chrUn 9713343 9713344 1384 + canFam2.chr30 3367361 3367365 1415 - +2 canFam2.chr30_insert 2 hg18.chr1 47759 47760 1380 + panTro2.chrUn 9713368 9713369 1384 + canFam2.chr30 3367391 3367392 1415 - +2 canFam2.chr30_insert 2 hg18.chr1 47835 47836 1380 + panTro2.chrUn 9713444 9713445 1384 + canFam2.chr30 3367469 3367470 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 48017 48018 1380 + panTro2.chrUn 9713626 9713627 1384 + canFam2.chr30 3367653 3367653 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 48035 48036 1380 + panTro2.chrUn 9713644 9713645 1384 + canFam2.chr30 3367672 3367672 1415 - +2 canFam2.chr30_insert 4 hg18.chr1 48091 48092 1380 + panTro2.chrUn 9713700 9713701 1384 + canFam2.chr30 3367729 3367732 1415 - +2 canFam2.chr30_insert 10 hg18.chr1 48103 48104 1380 + panTro2.chrUn 9713712 9713713 1384 + canFam2.chr30 3367745 3367754 1415 - +2 canFam2.chr30_insert 1 hg18.chr1 48232 48233 1380 + panTro2.chrUn 9713845 9713846 1384 + canFam2.chr30 3367870 3367870 1415 - +3 canFam2.chr30_insert 15 hg18.chr1 48379 48380 455 + panTro2.chrUn 9714289 9714290 455 + canFam2.chr30 3366038 3366052 483 - +3 canFam2.chr30_insert 21 hg18.chr1 48426 48427 455 + panTro2.chrUn 9714336 9714337 455 + canFam2.chr30 3366096 3366116 483 - +3 canFam2.chr30_insert 1 hg18.chr1 48523 48524 455 + panTro2.chrUn 9714433 9714434 455 + canFam2.chr30 3366213 3366213 483 - +4 canFam2.chr30_insert 8 hg18.chr1 52535 52536 183 + panTro2.chrUn 9718438 9718439 183 + canFam2.chr30 3364655 3364662 193 - +4 canFam2.chr30_insert 1 hg18.chr1 52555 52556 183 + panTro2.chrUn 9718458 9718459 183 + canFam2.chr30 3364683 3364683 193 - +4 canFam2.chr30_insert 1 hg18.chr1 52588 52589 183 + panTro2.chrUn 9718491 9718492 183 + canFam2.chr30 3364717 3364717 193 - +4 canFam2.chr30_insert 4 hg18.chr1 52691 52692 183 + panTro2.chrUn 9718594 9718595 183 + canFam2.chr30 3364817 3364820 193 - +5 canFam2.chr30_insert 3 hg18.chr1 52709 52710 115 + panTro2.chrUn 9718612 9718613 115 + canFam2.chr30 3364525 3364527 118 - +5 canFam2.chr30_insert 1 hg18.chr1 52754 52755 115 + panTro2.chrUn 9718657 9718658 115 + canFam2.chr30 3364571 3364571 118 - +5 canFam2.chr30_insert 4 hg18.chr1 52763 52764 115 + panTro2.chrUn 9718666 9718667 115 + canFam2.chr30 3364581 3364584 118 - +6 canFam2.chr30_insert 1 hg18.chr1 53848 53849 1040 + panTro2.chrUn 9719751 9719752 1040 + canFam2.chr30 3364511 3364511 1041 - +7 canFam2.chr30_insert 4 hg18.chr1 53869 53870 335 + panTro2.chrUn 9719772 9719773 335 + canFam2.chr30 3363136 3363139 356 - +7 canFam2.chr30_insert 1 hg18.chr1 53899 53900 335 + panTro2.chrUn 9719802 9719803 335 + canFam2.chr30 3363168 3363168 356 - +7 canFam2.chr30_insert 1 hg18.chr1 53921 53922 335 + panTro2.chrUn 9719824 9719825 335 + canFam2.chr30 3363191 3363191 356 - +7 canFam2.chr30_insert 8 hg18.chr1 53938 53939 335 + panTro2.chrUn 9719841 9719842 335 + canFam2.chr30 3363209 3363216 356 - +7 canFam2.chr30_insert 7 hg18.chr1 53970 53971 335 + panTro2.chrUn 9719873 9719874 335 + canFam2.chr30 3363249 3363255 356 - +7 canFam2.chr30_insert 5 hg18.chr1 54101 54102 335 + panTro2.chrUn 9720004 9720005 335 + canFam2.chr30 3363383 3363387 356 - +7 canFam2.chr30_insert 1 hg18.chr1 54164 54165 335 + panTro2.chrUn 9720067 9720068 335 + canFam2.chr30 3363451 3363451 356 - +8 canFam2.chr30_insert 1 hg18.chr1 54579 54580 582 + panTro2.chrUn 9720770 9720771 585 + canFam2.chr30 3362472 3362472 600 - +8 canFam2.chr30_insert 1 hg18.chr1 54654 54655 582 + panTro2.chrUn 9720845 9720846 585 + canFam2.chr30 3362547 3362547 600 - +8 canFam2.chr30_insert 1 hg18.chr1 54691 54692 582 + panTro2.chrUn 9720882 9720883 585 + canFam2.chr30 3362585 3362585 600 - +8 canFam2.chr30_insert 18 hg18.chr1 54775 54776 582 + panTro2.chrUn 9720970 9720971 585 + canFam2.chr30 3362667 3362684 600 - +8 canFam2.chr30_insert 1 hg18.chr1 54799 54800 582 + panTro2.chrUn 9720994 9720995 585 + canFam2.chr30 3362709 3362709 600 - +8 canFam2.chr30_insert 4 hg18.chr1 54944 54945 582 + panTro2.chrUn 9721139 9721140 585 + canFam2.chr30 3362851 3362854 600 - +8 canFam2.chr30_insert 1 hg18.chr1 54969 54970 582 + panTro2.chrUn 9721164 9721165 585 + canFam2.chr30 3362880 3362880 600 - +9 canFam2.chr30_insert 1 hg18.chr1 55360 55361 367 + panTro2.chrUn 9721554 9721555 402 + canFam2.chr30 3361632 3361632 382 - +9 canFam2.chr30_insert 1 hg18.chr1 55378 55379 367 + panTro2.chrUn 9721572 9721573 402 + canFam2.chr30 3361651 3361651 382 - +9 canFam2.chr30_insert 1 hg18.chr1 55396 55397 367 + panTro2.chrUn 9721625 9721626 402 + canFam2.chr30 3361703 3361703 382 - +9 canFam2.chr30_insert 2 hg18.chr1 55444 55445 367 + panTro2.chrUn 9721673 9721674 402 + canFam2.chr30 3361752 3361753 382 - +10 canFam2.chr30_insert 1 hg18.chr1 55776 55777 272 + panTro2.chrUn 9721772 9721773 307 + canFam2.chr30 3360902 3360902 265 - +10 canFam2.chr30_insert 5 hg18.chr1 55864 55865 272 + panTro2.chrUn 9721860 9721861 307 + canFam2.chr30 3360991 3360995 265 - +10 canFam2.chr30_insert 2 hg18.chr1 55969 55970 272 + panTro2.chrUn 9721965 9721966 307 + canFam2.chr30 3361087 3361088 265 - +10 canFam2.chr30_insert 2 hg18.chr1 55980 55981 272 + panTro2.chrUn 9721976 9721977 307 + canFam2.chr30 3361100 3361101 265 - +12 canFam2.chr30_insert 33 hg18.chr1 56722 56723 802 + panTro2.chrUn 9723901 9723902 801 + canFam2.chr30 3360035 3360067 805 - +12 canFam2.chr30_insert 1 hg18.chr1 56746 56747 802 + panTro2.chrUn 9723925 9723926 801 + canFam2.chr30 3360092 3360092 805 - +12 canFam2.chr30_insert 1 hg18.chr1 56836 56837 802 + panTro2.chrUn 9724015 9724016 801 + canFam2.chr30 3360183 3360183 805 - +12 canFam2.chr30_insert 1 hg18.chr1 56864 56865 802 + panTro2.chrUn 9724043 9724044 801 + canFam2.chr30 3360212 3360212 805 - +12 canFam2.chr30_insert 1 hg18.chr1 56894 56895 802 + panTro2.chrUn 9724073 9724074 801 + canFam2.chr30 3360243 3360243 805 - +12 canFam2.chr30_insert 2 hg18.chr1 57161 57162 802 + panTro2.chrUn 9724340 9724341 801 + canFam2.chr30 3360496 3360497 805 - +12 canFam2.chr30_insert 1 hg18.chr1 57352 57353 802 + panTro2.chrUn 9724530 9724531 801 + canFam2.chr30 3360680 3360680 805 - +13 canFam2.chr30_insert 2 hg18.chr1 58529 58530 176 + panTro2.chrUn 9725707 9725708 176 + canFam2.chr30 3359565 3359566 148 - +14 canFam2.chr30_insert 1 hg18.chr1 58700 58701 1628 + panTro2.chrUn 9725878 9725879 1631 + canFam2.chr30 3356984 3356984 1623 - +14 canFam2.chr30_insert 1 hg18.chr1 58709 58710 1628 + panTro2.chrUn 9725887 9725888 1631 + canFam2.chr30 3356994 3356994 1623 - +14 canFam2.chr30_insert 1 hg18.chr1 58770 58771 1628 + panTro2.chrUn 9725949 9725950 1631 + canFam2.chr30 3357057 3357057 1623 - +14 canFam2.chr30_insert 1 hg18.chr1 58772 58773 1628 + panTro2.chrUn 9725955 9725956 1631 + canFam2.chr30 3357064 3357064 1623 - +14 canFam2.chr30_insert 15 hg18.chr1 58800 58801 1628 + panTro2.chrUn 9725983 9725984 1631 + canFam2.chr30 3357093 3357107 1623 - +14 canFam2.chr30_insert 9 hg18.chr1 58808 58809 1628 + panTro2.chrUn 9725991 9725992 1631 + canFam2.chr30 3357116 3357124 1623 - +14 canFam2.chr30_insert 1 hg18.chr1 60032 60033 1628 + panTro2.chrUn 9727214 9727215 1631 + canFam2.chr30 3358319 3358319 1623 - +14 canFam2.chr30_insert 4 hg18.chr1 60148 60149 1628 + panTro2.chrUn 9727330 9727331 1631 + canFam2.chr30 3358426 3358429 1623 - +15 canFam2.chr30_insert 1 hg18.chr1 60326 60327 230 + panTro2.chrUn 9727507 9727508 230 + canFam2.chr30 3356643 3356643 218 - +15 canFam2.chr30_insert 2 hg18.chr1 60353 60354 230 + panTro2.chrUn 9727534 9727535 230 + canFam2.chr30 3356671 3356672 218 - +15 canFam2.chr30_insert 1 hg18.chr1 60391 60392 230 + panTro2.chrUn 9727572 9727573 230 + canFam2.chr30 3356711 3356711 218 - +15 canFam2.chr30_insert 1 hg18.chr1 60466 60467 230 + panTro2.chrUn 9727647 9727648 230 + canFam2.chr30 3356783 3356783 218 - +15 canFam2.chr30_insert 5 hg18.chr1 60476 60477 230 + panTro2.chrUn 9727657 9727658 230 + canFam2.chr30 3356794 3356798 218 - +1 canFam2.chr30_delete 1 hg18.chr1 46857 46857 143 + panTro2.chrUn 9712464 9712464 145 + canFam2.chr30 3368190 3368191 145 - +1 canFam2.chr30_delete 1 hg18.chr1 46900 46900 143 + panTro2.chrUn 9712509 9712509 145 + canFam2.chr30 3368232 3368233 145 - +2 canFam2.chr30_delete 7 hg18.chr1 47080 47086 1380 + panTro2.chrUn 9712689 9712695 1384 + canFam2.chr30 3366677 3366678 1415 - +2 canFam2.chr30_delete 1 hg18.chr1 47168 47168 1380 + panTro2.chrUn 9712777 9712777 1384 + canFam2.chr30 3366766 3366767 1415 - +2 canFam2.chr30_delete 1 hg18.chr1 47482 47482 1380 + panTro2.chrUn 9713091 9713091 1384 + canFam2.chr30 3367091 3367092 1415 - +2 canFam2.chr30_delete 2 hg18.chr1 47703 47704 1380 + panTro2.chrUn 9713312 9713313 1384 + canFam2.chr30 3367330 3367331 1415 - +2 canFam2.chr30_delete 15 hg18.chr1 48139 48153 1380 + panTro2.chrUn 9713752 9713766 1384 + canFam2.chr30 3367793 3367794 1415 - +2 canFam2.chr30_delete 1 hg18.chr1 48160 48160 1380 + panTro2.chrUn 9713773 9713773 1384 + canFam2.chr30 3367799 3367800 1415 - +2 canFam2.chr30_delete 1 hg18.chr1 48174 48174 1380 + panTro2.chrUn 9713787 9713787 1384 + canFam2.chr30 3367812 3367813 1415 - +2 canFam2.chr30_delete 1 hg18.chr1 48197 48197 1380 + panTro2.chrUn 9713810 9713810 1384 + canFam2.chr30 3367834 3367835 1415 - +2 canFam2.chr30_delete 5 hg18.chr1 48280 48284 1380 + panTro2.chrUn 9713893 9713897 1384 + canFam2.chr30 3367917 3367918 1415 - +3 canFam2.chr30_delete 4 hg18.chr1 48344 48347 455 + panTro2.chrUn 9714254 9714257 455 + canFam2.chr30 3366005 3366006 483 - +3 canFam2.chr30_delete 4 hg18.chr1 48410 48413 455 + panTro2.chrUn 9714320 9714323 455 + canFam2.chr30 3366082 3366083 483 - +3 canFam2.chr30_delete 1 hg18.chr1 48470 48470 455 + panTro2.chrUn 9714380 9714380 455 + canFam2.chr30 3366159 3366160 483 - +4 canFam2.chr30_delete 4 hg18.chr1 52639 52642 183 + panTro2.chrUn 9718542 9718545 183 + canFam2.chr30 3364767 3364768 193 - +5 canFam2.chr30_delete 3 hg18.chr1 52707 52709 115 + panTro2.chrUn 9718610 9718612 115 + canFam2.chr30 3364524 3364525 118 - +5 canFam2.chr30_delete 2 hg18.chr1 52743 52744 115 + panTro2.chrUn 9718646 9718647 115 + canFam2.chr30 3364560 3364561 118 - +7 canFam2.chr30_delete 2 hg18.chr1 53879 53880 335 + panTro2.chrUn 9719782 9719783 335 + canFam2.chr30 3363148 3363149 356 - +7 canFam2.chr30_delete 4 hg18.chr1 54052 54055 335 + panTro2.chrUn 9719955 9719958 335 + canFam2.chr30 3363336 3363337 356 - +8 canFam2.chr30_delete 1 hg18.chr1 54634 54634 582 + panTro2.chrUn 9720825 9720825 585 + canFam2.chr30 3362526 3362527 600 - +8 canFam2.chr30_delete 3 hg18.chr1 54710 54712 582 + panTro2.chrUn 9720901 9720903 585 + canFam2.chr30 3362603 3362604 600 - +8 canFam2.chr30_delete 4 hg18.chr1 54876 54879 582 + panTro2.chrUn 9721071 9721074 585 + canFam2.chr30 3362785 3362786 600 - +8 canFam2.chr30_delete 1 hg18.chr1 54984 54984 582 + panTro2.chrUn 9721178 9721178 585 + canFam2.chr30 3362894 3362895 600 - +9 canFam2.chr30_delete 1 hg18.chr1 55131 55131 367 + panTro2.chrUn 9721325 9721325 402 + canFam2.chr30 3361420 3361421 382 - +9 canFam2.chr30_delete 6 hg18.chr1 55213 55218 367 + panTro2.chrUn 9721407 9721412 402 + canFam2.chr30 3361501 3361502 382 - +9 canFam2.chr30_delete 1 hg18.chr1 55308 55308 367 + panTro2.chrUn 9721502 9721502 402 + canFam2.chr30 3361590 3361591 382 - +9 canFam2.chr30_delete 4 hg18.chr1 55324 55327 367 + panTro2.chrUn 9721518 9721521 402 + canFam2.chr30 3361605 3361606 382 - +9 canFam2.chr30_delete 7 hg18.chr1 55340 55346 367 + panTro2.chrUn 9721534 9721540 402 + canFam2.chr30 3361617 3361618 382 - +9 canFam2.chr30_delete 2 hg18.chr1 55386 55387 367 + panTro2.chrUn 9721580 9721581 402 + canFam2.chr30 3361658 3361659 382 - +9 canFam2.chr30_delete 4 hg18.chr1 55457 55460 367 + panTro2.chrUn 9721686 9721689 402 + canFam2.chr30 3361765 3361766 382 - +10 canFam2.chr30_delete 11 hg18.chr1 55893 55903 272 + panTro2.chrUn 9721889 9721899 307 + canFam2.chr30 3361023 3361024 265 - +10 canFam2.chr30_delete 1 hg18.chr1 55924 55924 272 + panTro2.chrUn 9721920 9721920 307 + canFam2.chr30 3361043 3361044 265 - +10 canFam2.chr30_delete 1 hg18.chr1 55939 55939 272 + panTro2.chrUn 9721935 9721935 307 + canFam2.chr30 3361057 3361058 265 - +10 canFam2.chr30_delete 1 hg18.chr1 55959 55959 272 + panTro2.chrUn 9721955 9721955 307 + canFam2.chr30 3361076 3361077 265 - +10 canFam2.chr30_delete 3 hg18.chr1 56001 56003 272 + panTro2.chrUn 9722032 9722034 307 + canFam2.chr30 3361121 3361122 265 - +12 canFam2.chr30_delete 6 hg18.chr1 56611 56616 802 + panTro2.chrUn 9723790 9723795 801 + canFam2.chr30 3359929 3359930 805 - +12 canFam2.chr30_delete 1 hg18.chr1 56696 56696 802 + panTro2.chrUn 9723875 9723875 801 + canFam2.chr30 3360008 3360009 805 - +12 canFam2.chr30_delete 7 hg18.chr1 56911 56917 802 + panTro2.chrUn 9724090 9724096 801 + canFam2.chr30 3360259 3360260 805 - +12 canFam2.chr30_delete 3 hg18.chr1 56991 56993 802 + panTro2.chrUn 9724170 9724172 801 + canFam2.chr30 3360332 3360333 805 - +12 canFam2.chr30_delete 5 hg18.chr1 57110 57114 802 + panTro2.chrUn 9724289 9724293 801 + canFam2.chr30 3360448 3360449 805 - +12 canFam2.chr30_delete 1 hg18.chr1 57217 57217 802 + panTro2.chrUn 9724395 9724395 801 + canFam2.chr30 3360551 3360552 805 - +12 canFam2.chr30_delete 5 hg18.chr1 57247 57251 802 + panTro2.chrUn 9724425 9724429 801 + canFam2.chr30 3360580 3360581 805 - +12 canFam2.chr30_delete 2 hg18.chr1 57310 57311 802 + panTro2.chrUn 9724488 9724489 801 + canFam2.chr30 3360638 3360639 805 - +12 canFam2.chr30_delete 2 hg18.chr1 57379 57380 802 + panTro2.chrUn 9724557 9724558 801 + canFam2.chr30 3360706 3360707 805 - +12 canFam2.chr30_delete 4 hg18.chr1 57387 57390 802 + panTro2.chrUn 9724565 9724568 801 + canFam2.chr30 3360712 3360713 805 - +13 canFam2.chr30_delete 3 hg18.chr1 58409 58411 176 + panTro2.chrUn 9725587 9725589 176 + canFam2.chr30 3359468 3359469 148 - +13 canFam2.chr30_delete 1 hg18.chr1 58434 58434 176 + panTro2.chrUn 9725612 9725612 176 + canFam2.chr30 3359490 3359491 148 - +13 canFam2.chr30_delete 2 hg18.chr1 58446 58447 176 + panTro2.chrUn 9725624 9725625 176 + canFam2.chr30 3359501 3359502 148 - +13 canFam2.chr30_delete 8 hg18.chr1 58470 58477 176 + panTro2.chrUn 9725648 9725655 176 + canFam2.chr30 3359523 3359524 148 - +13 canFam2.chr30_delete 5 hg18.chr1 58488 58492 176 + panTro2.chrUn 9725666 9725670 176 + canFam2.chr30 3359533 3359534 148 - +13 canFam2.chr30_delete 6 hg18.chr1 58510 58515 176 + panTro2.chrUn 9725688 9725693 176 + canFam2.chr30 3359550 3359551 148 - +13 canFam2.chr30_delete 5 hg18.chr1 58565 58569 176 + panTro2.chrUn 9725743 9725747 176 + canFam2.chr30 3359601 3359602 148 - +14 canFam2.chr30_delete 1 hg18.chr1 58669 58669 1628 + panTro2.chrUn 9725847 9725847 1631 + canFam2.chr30 3356952 3356953 1623 - +14 canFam2.chr30_delete 3 hg18.chr1 58849 58851 1628 + panTro2.chrUn 9726032 9726034 1631 + canFam2.chr30 3357164 3357165 1623 - +14 canFam2.chr30_delete 10 hg18.chr1 59342 59351 1628 + panTro2.chrUn 9726524 9726533 1631 + canFam2.chr30 3357654 3357655 1623 - +14 canFam2.chr30_delete 1 hg18.chr1 59561 59561 1628 + panTro2.chrUn 9726743 9726743 1631 + canFam2.chr30 3357863 3357864 1623 - +14 canFam2.chr30_delete 11 hg18.chr1 59887 59897 1628 + panTro2.chrUn 9727069 9727079 1631 + canFam2.chr30 3358188 3358189 1623 - +14 canFam2.chr30_delete 5 hg18.chr1 59908 59912 1628 + panTro2.chrUn 9727090 9727094 1631 + canFam2.chr30 3358198 3358199 1623 - +14 canFam2.chr30_delete 6 hg18.chr1 60052 60057 1628 + panTro2.chrUn 9727234 9727239 1631 + canFam2.chr30 3358338 3358339 1623 - +14 canFam2.chr30_delete 4 hg18.chr1 60111 60114 1628 + panTro2.chrUn 9727293 9727296 1631 + canFam2.chr30 3358391 3358392 1623 - +14 canFam2.chr30_delete 2 hg18.chr1 60183 60184 1628 + panTro2.chrUn 9727365 9727366 1631 + canFam2.chr30 3358463 3358464 1623 - +15 canFam2.chr30_delete 4 hg18.chr1 60400 60403 230 + panTro2.chrUn 9727581 9727584 230 + canFam2.chr30 3356719 3356720 218 - +15 canFam2.chr30_delete 8 hg18.chr1 60506 60513 230 + panTro2.chrUn 9727687 9727694 230 + canFam2.chr30 3356827 3356828 218 - +15 canFam2.chr30_delete 10 hg18.chr1 60520 60529 230 + panTro2.chrUn 9727701 9727710 230 + canFam2.chr30 3356833 3356834 218 - diff -r aae4754d6828 -r 675ad84ae008 tools/regVariation/getIndelRates_3way.py --- a/tools/regVariation/getIndelRates_3way.py Mon Sep 22 10:36:34 2008 -0400 +++ b/tools/regVariation/getIndelRates_3way.py Mon Sep 22 12:02:35 2008 -0400 @@ -1,56 +1,56 @@ #!/usr/bin/env python #Guruprasad Ananda -import sys, os, tempfile, string +from galaxy import eggs +import pkg_resources +pkg_resources.require( "bx-python" ) -assert sys.version_info[:2] >= ( 2, 4 ) +import sys, os, tempfile +import traceback +import fileinput +from warnings import warn -fout = open(sys.argv[2],'w') -winsize = int(sys.argv[3]) -species_ind = int(sys.argv[4]) +from galaxy.tools.util.galaxyops import * +from bx.intervals.io import * + +from bx.intervals.operations import quicksect def stop_err(msg): sys.stderr.write(msg) sys.exit() + +def counter(node, start, end, sort_col): + global full, blk_len, blk_list + if node.start < start: + if node.right: + counter(node.right, start, end, sort_col) + elif start <= node.start <= end and start <= node.end <= end: + full += 1 + if node.other[0] not in blk_list: + blk_list.append(node.other[0]) + blk_len += int(node.other[sort_col+2]) + if node.left and node.left.maxend > start: + counter(node.left, start, end, sort_col) + if node.right: + counter(node.right, start, end, sort_col) + elif node.start > end: + if node.left: + counter(node.left, start, end, sort_col) + -def rate_estimator(win, blk_lines, wstart, wend, wspecies): - inserts = 0.0 - deletes = 0.0 - ilengths = {} #dict containing lengths of blocks(without gaps) having insertion in wspecies - dlengths = {} #dict containing lengths of blocks(without gaps) having deletion in wspecies - prev_bnum = -1 - for bline in blk_lines: - items = bline.split('\t') - bnum = int(items[0]) - bevent = items[1] - if not(bevent.startswith(wspecies)): - continue - if bevent.endswith('insert'): - inserts += 1 - #Add lengths only if the insert belongs to a new alignment block - if not(ilengths.has_key(bnum)): - ilengths[bnum] = int(items[species_ind].split(':')[1]) - #prev_bnum = bnum - elif bevent.endswith('delete'): - deletes += 1 - #Add lengths only if the delete belongs to a new alignment block - if not(dlengths.has_key(bnum)): - dlengths[bnum] = int(items[species_ind].split(':')[1]) - #prev_bnum = bnum +infile = sys.argv[1] +fout = open(sys.argv[2],'w') +int_file = sys.argv[3] +if int_file != "None": #User has specified an interval file try: - total_ilength = sum(ilengths.values()) - irate = inserts/total_ilength + fint = open(int_file, 'r') + dbkey_i = sys.argv[4] + chr_col_i, start_col_i, end_col_i, strand_col_i = parse_cols_arg( sys.argv[5] ) except: - irate = 0 - try: - total_dlength = sum(dlengths.values()) - drate = deletes/total_dlength - except: - drate = 0 - print >>fout, "%s\t%s\t%s\t%s\t%.2e\t%.2e" %(win, wspecies, wstart, wend, irate , drate) - + stop_err("Unable to open input Interval file") + def main(): - infile = sys.argv[1] + for i, line in enumerate( file ( infile )): line = line.rstrip('\r\n') if len( line )>0 and not line.startswith( '#' ): @@ -58,71 +58,192 @@ break if i == 30: break # Hopefully we'll never get here... - - if len( elems ) != 15: + + if len( elems ) != 18: stop_err( "This tool only works on tabular data output by 'Fetch Indels from 3-way alignments' tool. The data in your input dataset is either missing or not formatted properly." ) - wspecies = elems[species_ind].split(':')[0].split('.')[0] - fin = open(infile, 'r') - skipped = 0 - blk=0 - win=0 - linestr="" - sorted_infile = tempfile.NamedTemporaryFile() - cmdline = "sort -n -k"+str(species_ind+2)+" -o "+sorted_infile.name+" "+infile - try: - os.system(cmdline) - except: - stop_err("Encountered error while sorting the input file.") - - print >>fout, "#Window\tSpecies\tWindow_Start\tWindow_End\tInsertion_Rate\tDeletion_Rate" - - for line in sorted_infile.readlines(): - line = line.strip("\r\n") - if not(line) or line == "": - continue + for i, line in enumerate( file ( infile )): + line = line.rstrip('\r\n') elems = line.split('\t') try: assert int(elems[0]) - assert len(elems) == 15 - except Exception, eon: + assert len(elems) == 18 + if int_file != "None": + if dbkey_i not in elems[3] and dbkey_i not in elems[8] and dbkey_i not in elems[13]: + stop_err("The species build corresponding to your interval file is not present in the Indel file.") + if dbkey_i in elems[3]: + sort_col = 4 + elif dbkey_i in elems[8]: + sort_col = 9 + elif dbkey_i in elems[13]: + sort_col = 14 + else: + species = [] + species.append( elems[3].split('.')[0] ) + species.append( elems[8].split('.')[0] ) + species.append( elems[13].split('.')[0] ) + sort_col = 0 #Based on block numbers + break + except: continue - if not(elems[1].startswith(wspecies)): #Event doesn't belong to the selected species + + fin = open(infile, 'r') + skipped = 0 + + if int_file == "None": + sorted_infile = tempfile.NamedTemporaryFile() + cmdline = "sort -n -k"+str(1)+" -o "+sorted_infile.name+" "+infile + try: + os.system(cmdline) + except: + stop_err("Encountered error while sorting the input file.") + print >>fout, "#Block\t%s_InsRate\t%s_InsRate\t%s_InsRate\t%s_DelRate\t%s_DelRate\t%s_DelRate" %(species[0],species[1],species[2],species[0],species[1],species[2]) + prev_bnum = -1 + sorted_infile.seek(0) + for line in sorted_infile.readlines(): + line = line.rstrip('\r\n') + elems = line.split('\t') + try: + assert int(elems[0]) + assert len(elems) == 18 + new_bnum = int(elems[0]) + if new_bnum != prev_bnum: + if prev_bnum != -1: + irate = [] + drate = [] + for i,elem in enumerate(inserts): + try: + irate.append(str("%.2e" %(inserts[i]/blen[i]))) + except: + irate.append('0') + try: + drate.append(str("%.2e" %(deletes[i]/blen[i]))) + except: + drate.append('0') + print >>fout, "%s\t%s\t%s" %(prev_bnum, '\t'.join(irate) , '\t'.join(drate)) + inserts = [0.0, 0.0, 0.0] + deletes = [0.0, 0.0, 0.0] + blen = [] + blen.append( int(elems[6]) ) + blen.append( int(elems[11]) ) + blen.append( int(elems[16]) ) + line_sp = elems[1].split('.')[0] + sp_ind = species.index(line_sp) + if elems[1].endswith('insert'): + inserts[sp_ind] += 1 + elif elems[1].endswith('delete'): + deletes[sp_ind] += 1 + prev_bnum = new_bnum + except Exception, ei: + #print >>sys.stderr, ei + continue + irate = [] + drate = [] + for i,elem in enumerate(inserts): + try: + irate.append(str("%.2e" %(inserts[i]/blen[i]))) + except: + irate.append('0') + try: + drate.append(str("%.2e" %(deletes[i]/blen[i]))) + except: + drate.append('0') + print >>fout, "%s\t%s\t%s" %(prev_bnum, '\t'.join(irate) , '\t'.join(drate)) + sys.exit() + + + inf = open(infile, 'r') + start_met = False + end_met = False + sp_file = tempfile.NamedTemporaryFile() + for n, line in enumerate(inf): + line = line.rstrip('\r\n') + elems = line.split('\t') + try: + assert int(elems[0]) + assert len(elems) == 18 + if dbkey_i not in elems[1]: + if not(start_met): + continue + else: + sp_end = n + break + else: + print >>sp_file, line + if not(start_met): + start_met = True + sp_start = n + except: continue - - try: - assert wstart - except NameError: - wstart = int(elems[species_ind+1]) - int(elems[species_ind+1])%winsize + 1 - wend = wstart + winsize - lstart = int(elems[species_ind + 1]) - - if lstart in range(wstart,wend+1): - linestr += line.strip() - linestr += "\n" - else: - try: - win += 1 - blk_lines = linestr.strip().split("\n") - rate_estimator(str(win), blk_lines, str(wstart), str(wend), wspecies) - linestr = "" - except: - skipped += 1 - pass - linestr=line.strip()+"\n" - wstart = int(elems[species_ind+1]) - int(elems[species_ind+1])%winsize + 1 - wend = wstart + winsize - if linestr != "": - try: - win += 1 - blk_lines = linestr.strip().split("\n") - rate_estimator(str(win), blk_lines, str(wstart), str(wend), wspecies) - except: - skipped += 1 + + try: + assert sp_end + except: + sp_end = n+1 + + sp_file.seek(0) + win = NiceReaderWrapper( fileinput.FileInput( int_file ), + chrom_col=chr_col_i, + start_col=start_col_i, + end_col=end_col_i, + strand_col=strand_col_i, + fix_strand=True) + + indel = NiceReaderWrapper( fileinput.FileInput( sp_file.name ), + chrom_col=1, + start_col=sort_col, + end_col=sort_col+1, + strand_col=-1, + fix_strand=True) + + indelTree = quicksect.IntervalTree() + for item in indel: + if type( item ) is GenomicInterval: + indelTree.insert( item, indel.linenum, item.fields ) + result=[] + + global full, blk_len, blk_list + for interval in win: + if type( interval ) is Header: pass - if skipped: - print "Skipped %s windows as invalid." %(skipped) + if type( interval ) is Comment: + pass + elif type( interval ) == GenomicInterval: + chrom = interval.chrom + start = int(interval.start) + end = int(interval.end) + if start > end: + warn( "Interval start after end!" ) + ins_chr = "%s.%s_insert" %(dbkey_i,chrom) + del_chr = "%s.%s_delete" %(dbkey_i,chrom) + irate = 0 + drate = 0 + if ins_chr not in indelTree.chroms and del_chr not in indelTree.chroms: + pass + else: + if ins_chr in indelTree.chroms: + full = 0.0 + blk_len = 0 + blk_list = [] + root = indelTree.chroms[ins_chr] #root node for the chrom insertion tree + counter(root, start, end, sort_col) + if blk_len: + irate = full/blk_len + + if del_chr in indelTree.chroms: + full = 0.0 + blk_len = 0 + blk_list = [] + root = indelTree.chroms[del_chr] #root node for the chrom insertion tree + counter(root, start, end, sort_col) + if blk_len: + drate = full/blk_len + + interval.fields.append(str("%.2e" %irate)) + interval.fields.append(str("%.2e" %drate)) + print >>fout, "\t".join(interval.fields) + fout.flush() + if __name__ == "__main__": - main() - \ No newline at end of file + main() \ No newline at end of file diff -r aae4754d6828 -r 675ad84ae008 tools/regVariation/getIndelRates_3way.xml --- a/tools/regVariation/getIndelRates_3way.xml Mon Sep 22 10:36:34 2008 -0400 +++ b/tools/regVariation/getIndelRates_3way.xml Mon Sep 22 12:02:35 2008 -0400 @@ -1,30 +1,30 @@ -<tool id="getIndelRates_3way" name="Estimate Indel Rates" version="1.0.0"> +<tool id="indelRates_3way" name="Estimate Indel Rates" version="1.0.0"> <description> for 3-way alignments</description> <command interpreter="python"> - getIndelRates_3way.py $input1 $out_file1 $winsize $species + getIndelRates_3way.py $input1 $out_file1 + #if $region.type == "align" + "None" + #else + $region.input2 $input2_dbkey $input2_chromCol,$input2_startCol,$input2_endCol,$input2_strandCol + #end if </command> <inputs> <page> - <param format="tabular" name="input1" type="data" label="Select data"/> - <param name="winsize" size="10" type="integer" value="1000" label="Estimate rates in windows of size" /> - <param name="species" type="select" label="and corresponding to co-ordinates of" multiple="false"> - <option value="3">Species 1 (Ingroup 1)</option> - <option value="7">Species 2 (Ingroup 2)</option> - <option value="11">Species 3 (Outgroup)</option> - </param> - <!-- - <conditional name="region"> - <param name="type" type="select" label="Estimate rates per" multiple="false"> - <option value="align">Alignment block</option> - <option value="win">Window</option> - </param> - <when value="win"> - <param name="winsize" size="10" type="integer" value="1000" label="of size" /> - - </when> - <when value="align" /> + <param format="tabular" name="input1" type="data" label="Select dataset containing Indels"/> + + <conditional name="region"> + <param name="type" type="select" label="Estimate rates corresponding to" multiple="false"> + <option value="align" selected="True">Alignment block</option> + <option value="win">Intervals in your history</option> + </param> + <when value="win"> + <param format="interval" name="input2" type="data" label="Choose intervals"> + <validator type="unspecified_build" /> + </param> + </when> + <when value="align" /> </conditional> - --> + </page> </inputs> <outputs> @@ -34,8 +34,7 @@ <tests> <test> <param name="input1" value="indels_3way.tabular"/> - <param name="winsize" value="1000"/> - <param name="species" value="11"/> + <param name="type" value="align"/> <output name="out_file1" file="indelrates_3way.tabular"/> </test> </tests> @@ -54,8 +53,8 @@ **Note** -Any block/s not containing exactly 3 species will be omitted. - +This tool only works on the output of the 'Estimate Indel Rates for 3-way alignments' tool. + </help> diff -r aae4754d6828 -r 675ad84ae008 tools/regVariation/getIndels_3way.xml --- a/tools/regVariation/getIndels_3way.xml Mon Sep 22 10:36:34 2008 -0400 +++ b/tools/regVariation/getIndels_3way.xml Mon Sep 22 12:02:35 2008 -0400 @@ -1,4 +1,4 @@ -<tool id="getIndels_3way" name="Fetch Indels" version="1.0.1"> +<tool id="indels_3way" name="Fetch Indels" version="1.0.1"> <description> from 3-way alignments</description> <command interpreter="perl"> parseMAF_smallIndels.pl $input1 $out_file1 $outgroup diff -r aae4754d6828 -r 675ad84ae008 tools/regVariation/parseMAF_smallIndels.pl --- a/tools/regVariation/parseMAF_smallIndels.pl Mon Sep 22 10:36:34 2008 -0400 +++ b/tools/regVariation/parseMAF_smallIndels.pl Mon Sep 22 12:02:35 2008 -0400 @@ -58,7 +58,7 @@ #print OFILE "#align\tingroup1\tingroup1_coord\tingroup1_orient\tingroup2\tingroup2_coord\tingroup2_orient\toutgroup\toutgroup_coord\toutgroup_orient\tindel_type\n"; #print OFILE2 "# small indels summary, parsed from MAF 3-way alignment file, coords are translated from (-) to (+) if necessary\n"; -print OFILE2 "#block\tindel_type\tindel_length\tingroup1\tingroup1_start\tingroup1_end\tingroup1_orient\tingroup2\tingroup2_start\tingroup2_end\tingroup2_orient\toutgroup\toutgroup_start\toutgroup_end\toutgroup_orient\n"; +print OFILE2 "#block\tindel_type\tindel_length\tingroup1\tingroup1_start\tingroup1_end\tingroup1_alignSize\tingroup1_orient\tingroup2\tingroup2_start\tingroup2_end\tingroup2_alignSize\tingroup2_orient\toutgroup\toutgroup_start\toutgroup_end\toutgroup_alignSize\toutgroup_orient\n"; # main body of program while ($record = get_next_record($fh) ){ @@ -348,7 +348,8 @@ && (substr($sequence2,$position,1) !~ m/[-*\#$?^@]/) && (substr($sequence3,$position,1) !~ m/[-*\#$?^@]/)){ $ABC = join("",($ABC,"X")); - $indelType = $seq1."_delete"; + my @s = split(/:/, $seq1); + $indelType = $s[0]."_delete"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); @@ -361,7 +362,8 @@ && (substr($sequence2,$position,1) eq "-") && (substr($sequence3,$position,1) !~ m/[-*\$?^]/)){ $ABC = join("",($ABC,"Y")); - $indelType = $seq2."_delete"; + my @s = split(/:/, $seq2); + $indelType = $s[0]."_delete"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); push (@indels,$indel_line); @@ -375,7 +377,8 @@ && (substr($sequence2,$position,1) eq "-") && (substr($sequence3,$position,1) eq "-")){ $ABC = join("",($ABC,"Z")); - $indelType = $seq1."_insert"; + my @s = split(/:/, $seq1); + $indelType = $s[0]."_insert"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); push (@indels,$indel_line); @@ -387,7 +390,8 @@ && (substr($sequence2,$position,1) !~ m/[-*\#$?^@]/) && (substr($sequence3,$position,1) eq "-")){ $ABC = join("",($ABC,"W")); - $indelType = $seq2."_insert"; + my @s = split(/:/, $seq2); + $indelType = $s[0]."_insert"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); push (@indels,$indel_line); @@ -399,7 +403,8 @@ && (substr($sequence2,$position,1) !~ m/[-*\#$?^@]/) && (substr($sequence3,$position,1) eq "-")){ $ABC = join("",($ABC,"S")); - $indelType = $seq3."_delete"; + my @s = split(/:/, $seq3); + $indelType = $s[0]."_delete"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); push (@indels,$indel_line); @@ -411,7 +416,8 @@ && (substr($sequence2,$position,1) eq "-") && (substr($sequence3,$position,1) !~ m/[-*\#$?^@]/)){ $ABC = join("",($ABC,"T")); - $indelType = $seq3."_insert"; + my @s = split(/:/, $seq3); + $indelType = $s[0]."_insert"; #print OFILE "$count\t$seq1\t$coord1\t$orient1\t$seq2\t$coord2\t$orient2\t$seq3\t$coord3\t$orient3\t$indelType\n"; $indel_line = join("\t",($count,$seq1,$coord1,$orient1,$seq2,$coord2,$orient2,$seq3,$coord3,$orient3,$indelType)); push (@indels,$indel_line); @@ -622,6 +628,9 @@ my $event_line = $_; my @events = split(/\t/, $event_line); my $event_type = $events[10]; + my @name_align1 = split(/:/, $events[1]); + my @name_align2 = split(/:/, $events[4]); + my @name_align3 = split(/:/, $events[7]); my $seq1_event_start = my $seq1_event_end = my $seq2_event_start = my $seq2_event_end = my $seq3_event_start = my $seq3_event_end = 0; my $final_event_line = ""; # seq1_insert @@ -634,7 +643,7 @@ $seq2_event_end = ($events[5]); $seq3_event_start = ($events[8]-1); $seq3_event_end = ($events[8]); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); } # seq1_delete elsif ($event_type =~ m/$ingroup1/ && $event_type =~ m/delete/){ @@ -646,7 +655,7 @@ $seq2_event_end = ($events[5]+$events[11]-1); $seq3_event_start = ($events[8]); $seq3_event_end = ($events[8]+$events[11]-1); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); } # seq2_insert elsif ($event_type =~ m/$ingroup2/ && $event_type =~ m/insert/){ @@ -658,7 +667,7 @@ $seq2_event_end = ($events[5]+$events[11]-1); $seq3_event_start = ($events[8]-1); $seq3_event_end = ($events[8]); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); } # seq2_delete elsif ($event_type =~ m/$ingroup2/ && $event_type =~ m/delete/){ @@ -670,7 +679,7 @@ $seq2_event_end = ($events[5]); $seq3_event_start = ($events[8]); $seq3_event_end = ($events[8]+$events[11]-1); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); } # start testing w/seq3_insert elsif ($event_type =~ m/$outgroup/ && $event_type =~ m/insert/){ @@ -682,7 +691,7 @@ $seq2_event_end = ($events[5]); $seq3_event_start = ($events[8]); $seq3_event_end = ($events[8]+$events[11]-1); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); } # seq3_delete elsif ($event_type =~ m/$outgroup/ && $event_type =~ m/delete/){ @@ -694,7 +703,7 @@ $seq2_event_end = ($events[5]+$events[11]-1); $seq3_event_start = ($events[8]-1); $seq3_event_end = ($events[8]); - $final_event_line = join("\t",($events[0],$event_type,$events[11],$events[1],$seq1_event_start,$seq1_event_end,$events[3],$events[4],$seq2_event_start,$seq2_event_end,$events[6],$events[7],$seq3_event_start,$seq3_event_end,$events[9])); + $final_event_line = join("\t",($events[0],$event_type,$events[11],$name_align1[0],$seq1_event_start,$seq1_event_end,$name_align1[1],$events[3],$name_align2[0],$seq2_event_start,$seq2_event_end,$name_align2[1],$events[6],$name_align3[0],$seq3_event_start,$seq3_event_end,$name_align3[1],$events[9])); }