| Previous changeset 2:bf30030e5265 (2020-09-10) Next changeset 4:8705e0d74a0f (2021-03-24) |
|
Commit message:
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/last commit 72dc050116d14e7a1342e7f9a2f7e095033d9a3a" |
|
modified:
lasttrain.xml test-data/last_train.txt |
|
added:
test-data/last_train_E.txt |
| b |
| diff -r bf30030e5265 -r 3de2195f32c0 lasttrain.xml --- a/lasttrain.xml Thu Sep 10 16:08:15 2020 +0000 +++ b/lasttrain.xml Fri Nov 13 09:05:49 2020 +0000 |
| b |
| @@ -1,4 +1,4 @@ -<tool id="last_train" name="LAST-train" version="@LAST_CONDA_VERSION@+galaxy1" profile="18.01"> +<tool id="last_train" name="LAST-train" version="@LAST_CONDA_VERSION@+galaxy2" profile="18.01"> <description>finds the rates (probabilities) of insertion, deletion, and substitutions between two sets of sequences.</description> @@ -18,17 +18,16 @@ last-train -Q $init_options.Q - -r $init_options.r -q $init_options.q - -a $init_options.cost_opt.a -b $init_options.cost_opt.b -A $init_options.cost_opt.A -B $init_options.cost_opt.B - -D $last_train_opt.align_opt.D - -E $last_train_opt.align_opt.E + #if $last_train_opt.align_opt.E != "" + -E $last_train_opt.align_opt.E + #end if -s $last_train_opt.align_opt.s -S $last_train_opt.align_opt.S -T $last_train_opt.align_opt.T @@ -74,7 +73,7 @@ <!-- Training options missing --> <section name="align_opt" title="Alignment options" expanded="true"> <param argument="-D" type="integer" value="1000000" label="Query letters per random alignment"/> - <param argument="-E" type="integer" value="10" label="Maximum expected alignments per square giga"/> + <param argument="-E" type="integer" value="" optional="true" label="Maximum expected alignments per square giga"/> <param argument="-s" type="select" multiple="false" label="Query strand to use"> <option value="0">Reverse</option> <option value="1" selected="true">Forward</option> @@ -111,6 +110,19 @@ <param name="db_opts_input" value="db"/> <param name="database" value="humdb"/> </conditional> + <section name="last_train_opt"> + <section name="align_opt"> + <param name="E" value="10"/> + </section> + </section> + <param name="query_fasta" value="fuguMito.fa"/> + <output name="outfile" file="last_train_E.txt" ftype="txt" lines_diff="22"/> + </test> + <test> + <conditional name="db_opts"> + <param name="db_opts_input" value="db"/> + <param name="database" value="humdb"/> + </conditional> <param name="query_fasta" value="fuguMito.fa"/> <output name="outfile" file="last_train.txt" ftype="txt" lines_diff="22"/> </test> |
| b |
| diff -r bf30030e5265 -r 3de2195f32c0 test-data/last_train.txt --- a/test-data/last_train.txt Thu Sep 10 16:08:15 2020 +0000 +++ b/test-data/last_train.txt Fri Nov 13 09:05:49 2020 +0000 |
| b |
| b'@@ -3,493 +3,493 @@\n # scale of score parameters: 4.5512\n # scale used while training: 91.024\n \n-# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -r5 -q5 -a15 -b3 -A15 -B3 ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+# lastal -j7 -D1000000 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -r5 -q5 -a15 -b3 -A15 -B3 /home/rdallet/galaxy/tools/last/test-data/humdb /tmp/tmpow095T/tmp/tmpmqx0kk84\n \n-# aligned letter pairs: 14901\n-# deletes: 694\n-# inserts: 834\n-# delOpens: 350\n-# insOpens: 402\n-# alignments: 1\n-# mean delete size: 1.98286\n-# mean insert size: 2.07463\n-# matchProb: 0.951836\n-# delOpenProb: 0.0223571\n-# insOpenProb: 0.0256787\n-# delExtendProb: 0.495677\n-# insExtendProb: 0.517986\n+# aligned letter pairs: 14938.3\n+# deletes: 664.27\n+# inserts: 839.49\n+# delOpens: 344.82\n+# insOpens: 404.93\n+# alignments: 3\n+# mean delete size: 1.92643\n+# mean insert size: 2.07317\n+# matchProb: 0.951966\n+# delOpenProb: 0.0219742\n+# insOpenProb: 0.0258048\n+# delExtendProb: 0.480904\n+# insExtendProb: 0.517648\n \n-# substitution percent identity: 71.9408\n+# substitution percent identity: 71.9318\n \n # count matrix (query letters = columns, reference letters = rows):\n # A C G T \n-# A 3291 532 387 390 \n-# C 552 3221 180 685 \n-# G 235 102 1561 84.7 \n-# T 335 554 146 2651 \n+# A 3296.3 533.237 387.81 392.24 \n+# C 553.59 3241.5 182.39 686.22 \n+# G 232.54 102.399 1565.4 84.91 \n+# T 335.173 558.68 147.16 2651 \n \n # probability matrix (query letters = columns, reference letters = rows):\n # A C G T \n-# A 0.220773 0.0356887 0.0259615 0.0261627 \n-# C 0.0370303 0.216077 0.0120751 0.0459525 \n-# G 0.0157647 0.00684256 0.104718 0.00568201 \n-# T 0.0224731 0.0371645 0.00979425 0.177839 \n+# A 0.22048 0.0356667 0.0259395 0.0262358 \n+# C 0.0370281 0.216815 0.0121996 0.0458993 \n+# G 0.0155539 0.00684918 0.104705 0.00567939 \n+# T 0.0224188 0.0373685 0.00984312 0.177318 \n \n-# delExistCost: 346\n-# insExistCost: 342\n-# delExtendCost: 62\n+# delExistCost: 343\n+# insExistCost: 341\n+# delExtendCost: 64\n # insExtendCost: 58\n \n # score matrix (query letters = columns, reference letters = rows):\n # A C G T\n-# A 76 -90 -59 -105\n-# C -87 73 -129 -54\n-# G -88 -164 145 -167\n+# A 76 -90 -59 -104\n+# C -87 73 -128 -55\n+# G -89 -164 145 -167\n # T -112 -66 -127 90\n \n-# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.4322 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+# lastal -j7 -D1000000 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.3148 -p- /home/rdallet/galaxy/tools/last/test-data/humdb /tmp/tmpow095T/tmp/tmpmqx0kk84\n \n-# aligned letter pairs: 14771\n-# deletes: 379.3\n-# inserts: 567.1\n-# delOpens: 185.2\n-# insOpens: 246.1\n-# alignments: 2\n-# mean delete size: 2.04806\n-# mean insert size: 2.30435\n-# matchProb: 0.971438\n-# delOpenProb: 0.01218\n-# insOpenProb: 0.0161851\n-# delExtendProb: 0.511732\n-# insExtendProb: 0.566038\n+# aligned letter pairs: 14338.3\n+# deletes: 327.44\n+# inserts: 474.13\n+# delOpens: 166.73\n+# insOpens: 216.45\n+# alignments: 10\n+# mean delete size: 1.96389\n+# mean insert size: 2.19048\n+# matchProb: 0.973244\n+# delOpenProb: 0.0113172\n+# insOpenProb: 0.014692\n+# delExtendProb: 0.490807\n+# insExtendProb: 0.54348\n \n-# substitution percent identity: 70.0105\n+# substitution percent identity: 70.6019\n \n # count matrix (query letters = columns, reference letters = rows):\n # A C G T \n-#'..b'0639368 0.103501 0.00476505 \n-# T 0.024887 0.0453133 0.00905532 0.169074 \n+# A 0.206677 0.0425032 0.0298997 0.0284356 \n+# C 0.0435997 0.200279 0.0113607 0.0547344 \n+# G 0.018313 0.00631353 0.10472 0.0048222 \n+# T 0.0245251 0.0452087 0.00883101 0.169776 \n \n-# delExistCost: 586\n-# insExistCost: 543\n+# delExistCost: 588\n+# insExistCost: 541\n # delExtendCost: 32\n-# insExtendCost: 29\n+# insExtendCost: 30\n \n # score matrix (query letters = columns, reference letters = rows):\n # A C G T\n-# A 74 -69 -42 -94\n-# C -68 70 -132 -35\n-# G -70 -166 147 -180\n-# T -99 -45 -132 88\n+# A 75 -70 -43 -94\n+# C -68 71 -132 -35\n+# G -71 -168 146 -180\n+# T -100 -45 -135 88\n \n-# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.0834 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+# lastal -j7 -D1000000 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.4704 -p- /home/rdallet/galaxy/tools/last/test-data/humdb /tmp/tmpow095T/tmp/tmpmqx0kk84\n \n-# aligned letter pairs: 14981\n-# deletes: 196\n-# inserts: 384.7\n-# delOpens: 57.87\n-# insOpens: 104.51\n-# alignments: 2\n-# mean delete size: 3.3869\n-# mean insert size: 3.68099\n-# matchProb: 0.989081\n-# delOpenProb: 0.00382071\n-# insOpenProb: 0.0069\n-# delExtendProb: 0.704745\n-# insExtendProb: 0.728334\n+# aligned letter pairs: 14897.4\n+# deletes: 188.951\n+# inserts: 356.964\n+# delOpens: 55.8286\n+# insOpens: 100.647\n+# alignments: 5\n+# mean delete size: 3.38448\n+# mean insert size: 3.54669\n+# matchProb: 0.989211\n+# delOpenProb: 0.00370711\n+# insOpenProb: 0.00668312\n+# delExtendProb: 0.704534\n+# insExtendProb: 0.718047\n \n-# substitution percent identity: 67.93\n+# substitution percent identity: 68.1409\n \n # count matrix (query letters = columns, reference letters = rows):\n # A C G T \n-# A 3093 648.8 451.2 427.6 \n-# C 656 2998 169.9 821.4 \n-# G 273.8 95.75 1550 71.36 \n-# T 372.7 678.6 135.61 2532 \n+# A 3081.6 633.731 445.81 424.08 \n+# C 650.28 2986.2 169.49 816.1 \n+# G 273.05 94.136 1561.4 71.9 \n+# T 365.673 674.17 131.672 2530.4 \n \n # probability matrix (query letters = columns, reference letters = rows):\n # A C G T \n-# A 0.206534 0.0433235 0.0301288 0.0285529 \n-# C 0.0438042 0.200191 0.011345 0.0548488 \n-# G 0.0182829 0.00639368 0.103501 0.00476505 \n-# T 0.024887 0.0453133 0.00905532 0.169074 \n+# A 0.206684 0.0425046 0.0299007 0.0284432 \n+# C 0.0436146 0.200286 0.0113678 0.0547362 \n+# G 0.0183136 0.00631375 0.104724 0.00482237 \n+# T 0.0245259 0.0452169 0.0088313 0.169715 \n \n-# delExistCost: 586\n-# insExistCost: 543\n+# delExistCost: 588\n+# insExistCost: 541\n # delExtendCost: 32\n-# insExtendCost: 29\n+# insExtendCost: 30\n \n # score matrix (query letters = columns, reference letters = rows):\n # A C G T\n-# A 74 -69 -42 -94\n-# C -68 70 -132 -35\n-# G -70 -166 147 -180\n-# T -99 -45 -132 88\n+# A 75 -70 -43 -94\n+# C -68 71 -132 -35\n+# G -71 -168 146 -180\n+# T -100 -45 -135 88\n \n #last -X 0\n #last -Q 0\n-#last -t4.80115\n+#last -t4.72795\n #last -a 29\n #last -A 28\n #last -b 2\n@@ -500,5 +500,5 @@\n A C G T\n A 4 -3 -2 -5\n C -3 4 -7 -2\n-G -3 -8 7 -9\n+G -4 -8 7 -9\n T -5 -2 -7 4\n' |
| b |
| diff -r bf30030e5265 -r 3de2195f32c0 test-data/last_train_E.txt --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/last_train_E.txt Fri Nov 13 09:05:49 2020 +0000 |
| b |
| b'@@ -0,0 +1,504 @@\n+# lastal version: 1021\n+# maximum percent identity: 100\n+# scale of score parameters: 4.5512\n+# scale used while training: 91.024\n+\n+# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -r5 -q5 -a15 -b3 -A15 -B3 ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+\n+# aligned letter pairs: 14901\n+# deletes: 694\n+# inserts: 834\n+# delOpens: 350\n+# insOpens: 402\n+# alignments: 1\n+# mean delete size: 1.98286\n+# mean insert size: 2.07463\n+# matchProb: 0.951836\n+# delOpenProb: 0.0223571\n+# insOpenProb: 0.0256787\n+# delExtendProb: 0.495677\n+# insExtendProb: 0.517986\n+\n+# substitution percent identity: 71.9408\n+\n+# count matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 3291 532 387 390 \n+# C 552 3221 180 685 \n+# G 235 102 1561 84.7 \n+# T 335 554 146 2651 \n+\n+# probability matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 0.220773 0.0356887 0.0259615 0.0261627 \n+# C 0.0370303 0.216077 0.0120751 0.0459525 \n+# G 0.0157647 0.00684256 0.104718 0.00568201 \n+# T 0.0224731 0.0371645 0.00979425 0.177839 \n+\n+# delExistCost: 346\n+# insExistCost: 342\n+# delExtendCost: 62\n+# insExtendCost: 58\n+\n+# score matrix (query letters = columns, reference letters = rows):\n+# A C G T\n+# A 76 -90 -59 -105\n+# C -87 73 -129 -54\n+# G -88 -164 145 -167\n+# T -112 -66 -127 90\n+\n+# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.4322 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+\n+# aligned letter pairs: 14771\n+# deletes: 379.3\n+# inserts: 567.1\n+# delOpens: 185.2\n+# insOpens: 246.1\n+# alignments: 2\n+# mean delete size: 2.04806\n+# mean insert size: 2.30435\n+# matchProb: 0.971438\n+# delOpenProb: 0.01218\n+# insOpenProb: 0.0161851\n+# delExtendProb: 0.511732\n+# insExtendProb: 0.566038\n+\n+# substitution percent identity: 70.0105\n+\n+# count matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 3158 583.4 429.9 391.6 \n+# C 589 3065 156.8 774 \n+# G 252.2 88.64 1571 68.46 \n+# T 342.6 630.1 131.09 2566 \n+\n+# probability matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 0.21341 0.0394248 0.0290516 0.0264634 \n+# C 0.0398032 0.207126 0.0105962 0.0523051 \n+# G 0.0170431 0.00599008 0.106165 0.00462637 \n+# T 0.0231521 0.0425807 0.00885876 0.173404 \n+\n+# delExistCost: 406\n+# insExistCost: 400\n+# delExtendCost: 60\n+# insExtendCost: 51\n+\n+# score matrix (query letters = columns, reference letters = rows):\n+# A C G T\n+# A 75 -79 -48 -102\n+# C -78 72 -140 -41\n+# G -79 -174 146 -185\n+# T -107 -52 -136 89\n+\n+# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t90.8564 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+\n+# aligned letter pairs: 14881\n+# deletes: 258.8\n+# inserts: 446.1\n+# delOpens: 112.91\n+# insOpens: 168\n+# alignments: 2\n+# mean delete size: 2.29209\n+# mean insert size: 2.65536\n+# matchProb: 0.981278\n+# delOpenProb: 0.00744548\n+# insOpenProb: 0.0110782\n+# delExtendProb: 0.563717\n+# insExtendProb: 0.623403\n+\n+# substitution percent identity: 68.9366\n+\n+# count matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 3126 618.3 445 406.6 \n'..b' 0.0113452 0.0548495 \n+# G 0.0182832 0.00638041 0.103502 0.00476511 \n+# T 0.0248873 0.0453139 0.00912288 0.169076 \n+\n+# delExistCost: 584\n+# insExistCost: 542\n+# delExtendCost: 32\n+# insExtendCost: 29\n+\n+# score matrix (query letters = columns, reference letters = rows):\n+# A C G T\n+# A 74 -69 -42 -94\n+# C -68 70 -132 -35\n+# G -70 -166 146 -180\n+# T -99 -45 -132 88\n+\n+# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t90.815 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+\n+# aligned letter pairs: 14981\n+# deletes: 197\n+# inserts: 384.7\n+# delOpens: 57.97\n+# insOpens: 104.51\n+# alignments: 2\n+# mean delete size: 3.39831\n+# mean insert size: 3.68099\n+# matchProb: 0.989075\n+# delOpenProb: 0.00382729\n+# insOpenProb: 0.00689995\n+# delExtendProb: 0.705736\n+# insExtendProb: 0.728334\n+\n+# substitution percent identity: 67.93\n+\n+# count matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 3093 648.8 451.2 427.6 \n+# C 656 2998 169.9 821.4 \n+# G 273.8 95.75 1550 71.36 \n+# T 372.7 678.6 135.61 2532 \n+\n+# probability matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 0.206534 0.0433235 0.0301288 0.0285529 \n+# C 0.0438042 0.200191 0.011345 0.0548488 \n+# G 0.0182829 0.00639368 0.103501 0.00476505 \n+# T 0.024887 0.0453133 0.00905532 0.169074 \n+\n+# delExistCost: 586\n+# insExistCost: 543\n+# delExtendCost: 32\n+# insExtendCost: 29\n+\n+# score matrix (query letters = columns, reference letters = rows):\n+# A C G T\n+# A 74 -69 -42 -94\n+# C -68 70 -132 -35\n+# G -70 -166 147 -180\n+# T -99 -45 -132 88\n+\n+# lastal -j7 -D1000000 -E10 -s1 -S1 -T0 -m10 -k1 -P1 -X0 -Q0 -t91.0834 -p- ref_db /tmp/tmpikDSIL/tmp/tmpDOHHwB\n+\n+# aligned letter pairs: 14981\n+# deletes: 196\n+# inserts: 384.7\n+# delOpens: 57.87\n+# insOpens: 104.51\n+# alignments: 2\n+# mean delete size: 3.3869\n+# mean insert size: 3.68099\n+# matchProb: 0.989081\n+# delOpenProb: 0.00382071\n+# insOpenProb: 0.0069\n+# delExtendProb: 0.704745\n+# insExtendProb: 0.728334\n+\n+# substitution percent identity: 67.93\n+\n+# count matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 3093 648.8 451.2 427.6 \n+# C 656 2998 169.9 821.4 \n+# G 273.8 95.75 1550 71.36 \n+# T 372.7 678.6 135.61 2532 \n+\n+# probability matrix (query letters = columns, reference letters = rows):\n+# A C G T \n+# A 0.206534 0.0433235 0.0301288 0.0285529 \n+# C 0.0438042 0.200191 0.011345 0.0548488 \n+# G 0.0182829 0.00639368 0.103501 0.00476505 \n+# T 0.024887 0.0453133 0.00905532 0.169074 \n+\n+# delExistCost: 586\n+# insExistCost: 543\n+# delExtendCost: 32\n+# insExtendCost: 29\n+\n+# score matrix (query letters = columns, reference letters = rows):\n+# A C G T\n+# A 74 -69 -42 -94\n+# C -68 70 -132 -35\n+# G -70 -166 147 -180\n+# T -99 -45 -132 88\n+\n+#last -X 0\n+#last -Q 0\n+#last -t4.80115\n+#last -a 29\n+#last -A 28\n+#last -b 2\n+#last -B 1\n+#last -s 1\n+#last -S 1\n+# score matrix (query letters = columns, reference letters = rows):\n+ A C G T\n+A 4 -3 -2 -5\n+C -3 4 -7 -2\n+G -3 -8 7 -9\n+T -5 -2 -7 4\n' |