htsworkflow/pipelines/test/test_runfolder030.py

   1 #!/usr/bin/env python
   2
   3 from datetime import datetime, date
   4 import os
   5 import tempfile
   6 import shutil
   7 from unittest import TestCase
   8
   9 from htsworkflow.pipelines import firecrest
  10 from htsworkflow.pipelines import bustard
  11 from htsworkflow.pipelines import gerald
  12 from htsworkflow.pipelines import runfolder
  13 from htsworkflow.pipelines import ElementTree
  14
  15 from htsworkflow.pipelines.test.simulate_runfolder import *
  16
  17
  18 def make_summary_htm(gerald_dir):
  19     summary_htm="""<!--RUN_TIME Wed Jul  2 06:47:44 2008 -->
  20 <!--SOFTWARE_VERSION @(#) $Id: jerboa.pl,v 1.94 2007/12/04 09:59:07 rshaw Exp $-->
  21 <html>
  22 <body>
  23
  24 <a name="Top"><h2><title>080627_HWI-EAS229_0036_3055HAXX Summary</title></h2></a>
  25 <h1>Summary Information For Experiment 080627_HWI-EAS229_0036_3055HAXX on Machine HWI-EAS229</h1>
  26 <h2><br></br>Chip Summary<br></br></h2>
  27 <table border="1" cellpadding="5">
  28 <tr><td>Machine</td><td>HWI-EAS229</td></tr>
  29 <tr><td>Run Folder</td><td>080627_HWI-EAS229_0036_3055HAXX</td></tr>
  30 <tr><td>Chip ID</td><td>unknown</td></tr>
  31 </table>
  32 <h2><br></br>Chip Results Summary<br></br></h2>
  33 <table border="1" cellpadding="5">
  34 <tr>
  35 <td>Clusters</td>
  36 <td>Clusters (PF)</td>
  37 <td>Yield (kbases)</td>
  38 </tr>
  39 <tr><td>80933224</td>
  40 <td>43577803</td>
  41 <td>1133022</td>
  42 </tr>
  43 </table>
  44 <h2><br></br>Lane Parameter Summary<br></br></h2>
  45 <table border="1" cellpadding="5">
  46 <tr>
  47 <td>Lane</td>
  48 <td>Sample ID</td>
  49 <td>Sample Target</td>
  50 <td>Sample Type</td>
  51 <td>Length</td>
  52 <td>Filter</td>
  53 <td>Num Tiles</td>
  54 <td>Tiles</td>
  55 </tr>
  56 <tr>
  57 <td>1</td>
  58 <td>unknown</td>
  59 <td>mm9</td>
  60 <td>ELAND</td>
  61 <td>26</td>
  62 <td>'((CHASTITY>=0.6))'</td>
  63 <td>100</td>
  64 <td><a href="#Lane1">Lane 1</a></td>
  65 </tr>
  66 <tr>
  67 <td>2</td>
  68 <td>unknown</td>
  69 <td>mm9</td>
  70 <td>ELAND</td>
  71 <td>26</td>
  72 <td>'((CHASTITY>=0.6))'</td>
  73 <td>100</td>
  74 <td><a href="#Lane2">Lane 2</a></td>
  75 </tr>
  76 <tr>
  77 <td>3</td>
  78 <td>unknown</td>
  79 <td>mm9</td>
  80 <td>ELAND</td>
  81 <td>26</td>
  82 <td>'((CHASTITY>=0.6))'</td>
  83 <td>100</td>
  84 <td><a href="#Lane3">Lane 3</a></td>
  85 </tr>
  86 <tr>
  87 <td>4</td>
  88 <td>unknown</td>
  89 <td>elegans170</td>
  90 <td>ELAND</td>
  91 <td>26</td>
  92 <td>'((CHASTITY>=0.6))'</td>
  93 <td>100</td>
  94 <td><a href="#Lane4">Lane 4</a></td>
  95 </tr>
  96 <tr>
  97 <td>5</td>
  98 <td>unknown</td>
  99 <td>elegans170</td>
 100 <td>ELAND</td>
 101 <td>26</td>
 102 <td>'((CHASTITY>=0.6))'</td>
 103 <td>100</td>
 104 <td><a href="#Lane5">Lane 5</a></td>
 105 </tr>
 106 <tr>
 107 <td>6</td>
 108 <td>unknown</td>
 109 <td>elegans170</td>
 110 <td>ELAND</td>
 111 <td>26</td>
 112 <td>'((CHASTITY>=0.6))'</td>
 113 <td>100</td>
 114 <td><a href="#Lane6">Lane 6</a></td>
 115 </tr>
 116 <tr>
 117 <td>7</td>
 118 <td>unknown</td>
 119 <td>elegans170</td>
 120 <td>ELAND</td>
 121 <td>26</td>
 122 <td>'((CHASTITY>=0.6))'</td>
 123 <td>100</td>
 124 <td><a href="#Lane7">Lane 7</a></td>
 125 </tr>
 126 <tr>
 127 <td>8</td>
 128 <td>unknown</td>
 129 <td>elegans170</td>
 130 <td>ELAND</td>
 131 <td>26</td>
 132 <td>'((CHASTITY>=0.6))'</td>
 133 <td>100</td>
 134 <td><a href="#Lane8">Lane 8</a></td>
 135 </tr>
 136 </table>
 137 <h2><br></br>Lane Results Summary<br></br></h2>
 138 <table border="1" cellpadding="5">
 139 <tr>
 140 <td colspan="2">Lane Info</td>
 141 <td colspan="8">Tile Mean +/- SD for Lane</td>
 142 </tr>
 143 <tr>
 144 <td>Lane </td>
 145 <td>Lane Yield (kbases) </td>
 146 <td>Clusters (raw)</td>
 147 <td>Clusters (PF) </td>
 148 <td>1st Cycle Int (PF) </td>
 149 <td>% intensity after 20 cycles (PF) </td>
 150 <td>% PF Clusters </td>
 151 <td>% Align (PF) </td>
 152 <td>Alignment Score (PF) </td>
 153 <td> % Error Rate (PF) </td>
 154 </tr>
 155 <tr>
 156 <td>1</td>
 157 <td>158046</td>
 158 <td>96483 +/- 9074</td>
 159 <td>60787 +/- 4240</td>
 160 <td>329 +/- 35</td>
 161 <td>101.88 +/- 6.03</td>
 162 <td>63.21 +/- 3.29</td>
 163 <td>70.33 +/- 0.24</td>
 164 <td>9054.08 +/- 59.16</td>
 165 <td>0.46 +/- 0.18</td>
 166 </tr>
 167 <tr>
 168 <td>2</td>
 169 <td>156564</td>
 170 <td>133738 +/- 7938</td>
 171 <td>60217 +/- 1926</td>
 172 <td>444 +/- 39</td>
 173 <td>92.62 +/- 7.58</td>
 174 <td>45.20 +/- 3.31</td>
 175 <td>51.98 +/- 0.74</td>
 176 <td>6692.04 +/- 92.49</td>
 177 <td>0.46 +/- 0.09</td>
 178 </tr>
 179 <tr>
 180 <td>3</td>
 181 <td>185818</td>
 182 <td>152142 +/- 10002</td>
 183 <td>71468 +/- 2827</td>
 184 <td>366 +/- 36</td>
 185 <td>91.53 +/- 8.66</td>
 186 <td>47.19 +/- 3.80</td>
 187 <td>82.24 +/- 0.44</td>
 188 <td>10598.68 +/- 64.13</td>
 189 <td>0.41 +/- 0.04</td>
 190 </tr>
 191 <tr>
 192 <td>4</td>
 193 <td>34953</td>
 194 <td>15784 +/- 2162</td>
 195 <td>13443 +/- 1728</td>
 196 <td>328 +/- 40</td>
 197 <td>97.53 +/- 9.87</td>
 198 <td>85.29 +/- 1.91</td>
 199 <td>80.02 +/- 0.53</td>
 200 <td>10368.82 +/- 71.08</td>
 201 <td>0.15 +/- 0.05</td>
 202 </tr>
 203 <tr>
 204 <td>5</td>
 205 <td>167936</td>
 206 <td>119735 +/- 8465</td>
 207 <td>64590 +/- 2529</td>
 208 <td>417 +/- 37</td>
 209 <td>88.69 +/- 14.79</td>
 210 <td>54.10 +/- 2.59</td>
 211 <td>76.95 +/- 0.32</td>
 212 <td>9936.47 +/- 65.75</td>
 213 <td>0.28 +/- 0.02</td>
 214 </tr>
 215 <tr>
 216 <td>6</td>
 217 <td>173463</td>
 218 <td>152177 +/- 8146</td>
 219 <td>66716 +/- 2493</td>
 220 <td>372 +/- 39</td>
 221 <td>87.06 +/- 9.86</td>
 222 <td>43.98 +/- 3.12</td>
 223 <td>78.80 +/- 0.43</td>
 224 <td>10162.28 +/- 49.65</td>
 225 <td>0.38 +/- 0.03</td>
 226 </tr>
 227 <tr>
 228 <td>7</td>
 229 <td>149287</td>
 230 <td>84649 +/- 7325</td>
 231 <td>57418 +/- 3617</td>
 232 <td>295 +/- 28</td>
 233 <td>89.40 +/- 8.23</td>
 234 <td>67.97 +/- 1.82</td>
 235 <td>33.38 +/- 0.25</td>
 236 <td>4247.92 +/- 32.37</td>
 237 <td>1.00 +/- 0.03</td>
 238 </tr>
 239 <tr>
 240 <td>8</td>
 241 <td>106953</td>
 242 <td>54622 +/- 4812</td>
 243 <td>41136 +/- 3309</td>
 244 <td>284 +/- 37</td>
 245 <td>90.21 +/- 9.10</td>
 246 <td>75.39 +/- 2.27</td>
 247 <td>48.33 +/- 0.29</td>
 248 <td>6169.21 +/- 169.50</td>
 249 <td>0.86 +/- 1.22</td>
 250 </tr>
 251 <tr><td colspan="13">Tile mean across chip</td></tr>
 252 <tr>
 253 <td>Av.</td>
 254 <td></td>
 255 <td>101166</td>
 256 <td>54472</td>
 257 <td>354</td>
 258 <td>92.36</td>
 259 <td>60.29</td>
 260 <td>65.25</td>
 261 <td>8403.69</td>
 262 <td>0.50</td>
 263 </tr>
 264 </table>
 265 <h2><br></br>Expanded Lane Summary<br></br></h2>
 266 <table border="1" cellpadding="5">
 267 <tr>
 268
 269 <tr><td colspan="2">Lane Info</td>
 270 <td colspan="2">Phasing Info</td>
 271 <td colspan="2">Raw Data (tile mean)</td>
 272 <td colspan="7">Filtered Data (tile mean)</td></tr>
 273 <td>Lane </td>
 274 <td>Clusters (tile mean) (raw)</td>
 275 <td>% Phasing </td>
 276 <td>% Prephasing </td>
 277 <td>% Error Rate (raw) </td>
 278 <td> Equiv Perfect Clusters (raw) </td>
 279 <td>% retained </td>
 280 <td>Cycle 2-4 Av Int (PF) </td>
 281 <td>Cycle 2-10 Av % Loss (PF) </td>
 282 <td>Cycle 10-20 Av % Loss (PF) </td>
 283 <td>% Align (PF) </td>
 284 <td>% Error Rate (PF) </td>
 285 <td> Equiv Perfect Clusters (PF) </td>
 286 </tr>
 287 <tr>
 288 <td>1</td>
 289 <td>96483</td>
 290 <td>0.7700</td>
 291 <td>0.3100</td>
 292 <td>1.00</td>
 293 <td>49676</td>
 294 <td>63.21</td>
 295 <td>317 +/- 32</td>
 296 <td>0.13 +/- 0.44</td>
 297 <td>-1.14 +/- 0.34</td>
 298 <td>70.33</td>
 299 <td>0.46</td>
 300 <td>41758</td>
 301 </tr>
 302 <tr>
 303 <td>2</td>
 304 <td>133738</td>
 305 <td>0.7700</td>
 306 <td>0.3100</td>
 307 <td>1.22</td>
 308 <td>40467</td>
 309 <td>45.20</td>
 310 <td>415 +/- 33</td>
 311 <td>0.29 +/- 0.40</td>
 312 <td>-0.79 +/- 0.35</td>
 313 <td>51.98</td>
 314 <td>0.46</td>
 315 <td>30615</td>
 316 </tr>
 317 <tr>
 318 <td>3</td>
 319 <td>152142</td>
 320 <td>0.7700</td>
 321 <td>0.3100</td>
 322 <td>1.30</td>
 323 <td>78588</td>
 324 <td>47.19</td>
 325 <td>344 +/- 26</td>
 326 <td>0.68 +/- 0.51</td>
 327 <td>-0.77 +/- 0.42</td>
 328 <td>82.24</td>
 329 <td>0.41</td>
 330 <td>57552</td>
 331 </tr>
 332 <tr>
 333 <td>4</td>
 334 <td>15784</td>
 335 <td>0.7700</td>
 336 <td>0.3100</td>
 337 <td>0.29</td>
 338 <td>11095</td>
 339 <td>85.29</td>
 340 <td>306 +/- 34</td>
 341 <td>0.20 +/- 0.69</td>
 342 <td>-1.28 +/- 0.66</td>
 343 <td>80.02</td>
 344 <td>0.15</td>
 345 <td>10671</td>
 346 </tr>
 347 <tr>
 348 <td>5</td>
 349 <td>119735</td>
 350 <td>0.7700</td>
 351 <td>0.3100</td>
 352 <td>0.85</td>
 353 <td>60335</td>
 354 <td>54.10</td>
 355 <td>380 +/- 32</td>
 356 <td>0.34 +/- 0.49</td>
 357 <td>-1.55 +/- 4.69</td>
 358 <td>76.95</td>
 359 <td>0.28</td>
 360 <td>49015</td>
 361 </tr>
 362 <tr>
 363 <td>6</td>
 364 <td>152177</td>
 365 <td>0.7700</td>
 366 <td>0.3100</td>
 367 <td>1.21</td>
 368 <td>70905</td>
 369 <td>43.98</td>
 370 <td>333 +/- 27</td>
 371 <td>0.57 +/- 0.50</td>
 372 <td>-0.91 +/- 0.39</td>
 373 <td>78.80</td>
 374 <td>0.38</td>
 375 <td>51663</td>
 376 </tr>
 377 <tr>
 378 <td>7</td>
 379 <td>84649</td>
 380 <td>0.7700</td>
 381 <td>0.3100</td>
 382 <td>1.38</td>
 383 <td>21069</td>
 384 <td>67.97</td>
 385 <td>272 +/- 20</td>
 386 <td>1.15 +/- 0.52</td>
 387 <td>-0.84 +/- 0.58</td>
 388 <td>33.38</td>
 389 <td>1.00</td>
 390 <td>18265</td>
 391 </tr>
 392 <tr>
 393 <td>8</td>
 394 <td>54622</td>
 395 <td>0.7700</td>
 396 <td>0.3100</td>
 397 <td>1.17</td>
 398 <td>21335</td>
 399 <td>75.39</td>
 400 <td>262 +/- 31</td>
 401 <td>1.10 +/- 0.59</td>
 402 <td>-1.01 +/- 0.47</td>
 403 <td>48.33</td>
 404 <td>0.86</td>
 405 <td>19104</td>
 406 </tr>
 407 </table>
 408 <b><br></br>IVC Plots</b>
 409 <p> <a href='IVC.htm' target="_blank"> IVC.htm
 410  </a></p>
 411 <b><br></br>All Intensity Plots</b>
 412 <p> <a href='All.htm' target="_blank"> All.htm
 413  </a></p>
 414 <b><br></br>Error graphs: </b>
 415 <p> <a href='Error.htm' target="_blank"> Error.htm
 416  </a></p>
 417 <td><a href="#Top">Back to top</a></td>
 418 <a name="Lane1"><h2><br></br>Lane 1<br></br></h2></a>
 419 <table border="1" cellpadding="5">
 420 <tr>
 421 <td>Lane </td>
 422 <td>Tile </td>
 423 <td>Clusters (raw)</td>
 424 <td>Av 1st Cycle Int (PF) </td>
 425 <td>Av % intensity after 20 cycles (PF) </td>
 426 <td>% PF Clusters </td>
 427 <td>% Align (PF) </td>
 428 <td>Av Alignment Score (PF) </td>
 429 <td>% Error Rate (PF) </td>
 430 </tr>
 431 <tr>
 432 <td>1</td>
 433 <td>0001</td>
 434 <td>114972</td>
 435 <td>326.48</td>
 436 <td>94.39</td>
 437 <td>57.44</td>
 438 <td>70.2</td>
 439 <td>9038.6</td>
 440 <td>0.44</td>
 441 </tr>
 442 </table>
 443 <td><a href="#Top">Back to top</a></td>
 444 <a name="Lane2"><h2><br></br>Lane 2<br></br></h2></a>
 445 <table border="1" cellpadding="5">
 446 <tr>
 447 <td>Lane </td>
 448 <td>Tile </td>
 449 <td>Clusters (raw)</td>
 450 <td>Av 1st Cycle Int (PF) </td>
 451 <td>Av % intensity after 20 cycles (PF) </td>
 452 <td>% PF Clusters </td>
 453 <td>% Align (PF) </td>
 454 <td>Av Alignment Score (PF) </td>
 455 <td>% Error Rate (PF) </td>
 456 </tr>
 457 <tr>
 458 <td>2</td>
 459 <td>0001</td>
 460 <td>147793</td>
 461 <td>448.12</td>
 462 <td>83.68</td>
 463 <td>38.57</td>
 464 <td>53.7</td>
 465 <td>6905.4</td>
 466 <td>0.54</td>
 467 </tr>
 468 </table>
 469 <td><a href="#Top">Back to top</a></td>
 470 <a name="Lane3"><h2><br></br>Lane 3<br></br></h2></a>
 471 <table border="1" cellpadding="5">
 472 <tr>
 473 <td>Lane </td>
 474 <td>Tile </td>
 475 <td>Clusters (raw)</td>
 476 <td>Av 1st Cycle Int (PF) </td>
 477 <td>Av % intensity after 20 cycles (PF) </td>
 478 <td>% PF Clusters </td>
 479 <td>% Align (PF) </td>
 480 <td>Av Alignment Score (PF) </td>
 481 <td>% Error Rate (PF) </td>
 482 </tr>
 483 <tr>
 484 <td>3</td>
 485 <td>0001</td>
 486 <td>167904</td>
 487 <td>374.05</td>
 488 <td>86.91</td>
 489 <td>40.36</td>
 490 <td>81.3</td>
 491 <td>10465.0</td>
 492 <td>0.47</td>
 493 </tr>
 494 </table>
 495 <td><a href="#Top">Back to top</a></td>
 496 <a name="Lane4"><h2><br></br>Lane 4<br></br></h2></a>
 497 <table border="1" cellpadding="5">
 498 <tr>
 499 <td>Lane </td>
 500 <td>Tile </td>
 501 <td>Clusters (raw)</td>
 502 <td>Av 1st Cycle Int (PF) </td>
 503 <td>Av % intensity after 20 cycles (PF) </td>
 504 <td>% PF Clusters </td>
 505 <td>% Align (PF) </td>
 506 <td>Av Alignment Score (PF) </td>
 507 <td>% Error Rate (PF) </td>
 508 </tr>
 509 <tr>
 510 <td>4</td>
 511 <td>0001</td>
 512 <td>20308</td>
 513 <td>276.85</td>
 514 <td>92.87</td>
 515 <td>84.26</td>
 516 <td>80.4</td>
 517 <td>10413.8</td>
 518 <td>0.16</td>
 519 </tr>
 520 </table>
 521 <td><a href="#Top">Back to top</a></td>
 522 <a name="Lane5"><h2><br></br>Lane 5<br></br></h2></a>
 523 <table border="1" cellpadding="5">
 524 <tr>
 525 <td>Lane </td>
 526 <td>Tile </td>
 527 <td>Clusters (raw)</td>
 528 <td>Av 1st Cycle Int (PF) </td>
 529 <td>Av % intensity after 20 cycles (PF) </td>
 530 <td>% PF Clusters </td>
 531 <td>% Align (PF) </td>
 532 <td>Av Alignment Score (PF) </td>
 533 <td>% Error Rate (PF) </td>
 534 </tr>
 535 </table>
 536 <td><a href="#Top">Back to top</a></td>
 537 <a name="Lane6"><h2><br></br>Lane 6<br></br></h2></a>
 538 <table border="1" cellpadding="5">
 539 <tr>
 540 <td>Lane </td>
 541 <td>Tile </td>
 542 <td>Clusters (raw)</td>
 543 <td>Av 1st Cycle Int (PF) </td>
 544 <td>Av % intensity after 20 cycles (PF) </td>
 545 <td>% PF Clusters </td>
 546 <td>% Align (PF) </td>
 547 <td>Av Alignment Score (PF) </td>
 548 <td>% Error Rate (PF) </td>
 549 </tr>
 550 <tr>
 551 <td>6</td>
 552 <td>0001</td>
 553 <td>166844</td>
 554 <td>348.12</td>
 555 <td>77.59</td>
 556 <td>38.13</td>
 557 <td>79.7</td>
 558 <td>10264.4</td>
 559 <td>0.44</td>
 560 </tr>
 561 </table>
 562 <td><a href="#Top">Back to top</a></td>
 563 <a name="Lane7"><h2><br></br>Lane 7<br></br></h2></a>
 564 <table border="1" cellpadding="5">
 565 <tr>
 566 <td>Lane </td>
 567 <td>Tile </td>
 568 <td>Clusters (raw)</td>
 569 <td>Av 1st Cycle Int (PF) </td>
 570 <td>Av % intensity after 20 cycles (PF) </td>
 571 <td>% PF Clusters </td>
 572 <td>% Align (PF) </td>
 573 <td>Av Alignment Score (PF) </td>
 574 <td>% Error Rate (PF) </td>
 575 </tr>
 576 <tr>
 577 <td>7</td>
 578 <td>0001</td>
 579 <td>98913</td>
 580 <td>269.90</td>
 581 <td>86.66</td>
 582 <td>64.55</td>
 583 <td>33.2</td>
 584 <td>4217.5</td>
 585 <td>1.02</td>
 586 </tr>
 587 </table>
 588 <td><a href="#Top">Back to top</a></td>
 589 <a name="Lane8"><h2><br></br>Lane 8<br></br></h2></a>
 590 <table border="1" cellpadding="5">
 591 <tr>
 592 <td>Lane </td>
 593 <td>Tile </td>
 594 <td>Clusters (raw)</td>
 595 <td>Av 1st Cycle Int (PF) </td>
 596 <td>Av % intensity after 20 cycles (PF) </td>
 597 <td>% PF Clusters </td>
 598 <td>% Align (PF) </td>
 599 <td>Av Alignment Score (PF) </td>
 600 <td>% Error Rate (PF) </td>
 601 </tr>
 602 <tr>
 603 <td>8</td>
 604 <td>0001</td>
 605 <td>64972</td>
 606 <td>243.60</td>
 607 <td>89.40</td>
 608 <td>73.17</td>
 609 <td>48.3</td>
 610 <td>6182.8</td>
 611 <td>0.71</td>
 612 </tr>
 613 </table>
 614 <td><a href="#Top">Back to top</a></td>
 615 </body>
 616 </html>
 617 """
 618     pathname = os.path.join(gerald_dir, 'Summary.htm')
 619     f = open(pathname, 'w')
 620     f.write(summary_htm)
 621     f.close()
 622
 623 def make_eland_results(gerald_dir):
 624     eland_result = """>HWI-EAS229_24_207BTAAXX:1:7:599:759    ACATAGNCACAGACATAAACATAGACATAGAC U0      1       1       3       chrUextra.fa    28189829        R       D.
 625 >HWI-EAS229_24_207BTAAXX:1:7:205:842    AAACAANNCTCCCAAACACGTAAACTGGAAAA  U1      0       1       0       chr2L.fa        8796855 R       DD      24T
 626 >HWI-EAS229_24_207BTAAXX:1:7:776:582    AGCTCANCCGATCGAAAACCTCNCCAAGCAAT        NM      0       0       0
 627 >HWI-EAS229_24_207BTAAXX:1:7:205:842    AAACAANNCTCCCAAACACGTAAACTGGAAAA        U1      0       1       0       Lambda.fa        8796855 R       DD      24T
 628 """
 629     for i in range(1,9):
 630         pathname = os.path.join(gerald_dir,
 631                                 's_%d_eland_result.txt' % (i,))
 632         f = open(pathname, 'w')
 633         f.write(eland_result)
 634         f.close()
 635
 636 def make_runfolder(obj=None):
 637     """
 638     Make a fake runfolder, attach all the directories to obj if defined
 639     """
 640     # make a fake runfolder directory
 641     temp_dir = tempfile.mkdtemp(prefix='tmp_runfolder_')
 642
 643     runfolder_dir = os.path.join(temp_dir,
 644                                  '080102_HWI-EAS229_0010_207BTAAXX')
 645     os.mkdir(runfolder_dir)
 646
 647     data_dir = os.path.join(runfolder_dir, 'Data')
 648     os.mkdir(data_dir)
 649
 650     firecrest_dir = os.path.join(data_dir,
 651                                  'C1-33_Firecrest1.8.28_12-04-2008_diane'
 652                                  )
 653     os.mkdir(firecrest_dir)
 654     matrix_dir = os.path.join(firecrest_dir, 'Matrix')
 655     os.mkdir(matrix_dir)
 656     matrix_filename = os.path.join(matrix_dir, 's_matrix.txt')
 657     make_matrix(matrix_filename)
 658
 659     bustard_dir = os.path.join(firecrest_dir,
 660                                'Bustard1.8.28_12-04-2008_diane')
 661     os.mkdir(bustard_dir)
 662     make_phasing_params(bustard_dir)
 663
 664     gerald_dir = os.path.join(bustard_dir,
 665                               'GERALD_12-04-2008_diane')
 666     os.mkdir(gerald_dir)
 667     make_gerald_config_026(gerald_dir)
 668     make_summary_htm(gerald_dir)
 669     make_eland_results(gerald_dir)
 670
 671     if obj is not None:
 672         obj.temp_dir = temp_dir
 673         obj.runfolder_dir = runfolder_dir
 674         obj.data_dir = data_dir
 675         obj.firecrest_dir = firecrest_dir
 676         obj.matrix_dir = matrix_dir
 677         obj.bustard_dir = bustard_dir
 678         obj.gerald_dir = gerald_dir
 679
 680
 681 class RunfolderTests(TestCase):
 682     """
 683     Test components of the runfolder processing code
 684     which includes firecrest, bustard, and gerald
 685     """
 686     def setUp(self):
 687         # attaches all the directories to the object passed in
 688         make_runfolder(self)
 689
 690     def tearDown(self):
 691         shutil.rmtree(self.temp_dir)
 692
 693     def test_firecrest(self):
 694         """
 695         Construct a firecrest object
 696         """
 697         f = firecrest.firecrest(self.firecrest_dir)
 698         self.failUnlessEqual(f.software, 'Firecrest')
 699         self.failUnlessEqual(f.version, '1.8.28')
 700         self.failUnlessEqual(f.start, 1)
 701         self.failUnlessEqual(f.stop, 33)
 702         self.failUnlessEqual(f.user, 'diane')
 703         self.failUnlessEqual(f.date, date(2008,4,12))
 704
 705         xml = f.get_elements()
 706         # just make sure that element tree can serialize the tree
 707         xml_str = ElementTree.tostring(xml)
 708
 709         f2 = firecrest.Firecrest(xml=xml)
 710         self.failUnlessEqual(f.software, f2.software)
 711         self.failUnlessEqual(f.version,  f2.version)
 712         self.failUnlessEqual(f.start,    f2.start)
 713         self.failUnlessEqual(f.stop,     f2.stop)
 714         self.failUnlessEqual(f.user,     f2.user)
 715         self.failUnlessEqual(f.date,     f2.date)
 716
 717     def test_bustard(self):
 718         """
 719         construct a bustard object
 720         """
 721         b = bustard.bustard(self.bustard_dir)
 722         self.failUnlessEqual(b.software, 'Bustard')
 723         self.failUnlessEqual(b.version, '1.8.28')
 724         self.failUnlessEqual(b.date,    date(2008,4,12))
 725         self.failUnlessEqual(b.user,    'diane')
 726         self.failUnlessEqual(len(b.phasing), 8)
 727         self.failUnlessAlmostEqual(b.phasing[8].phasing, 0.0099)
 728
 729         xml = b.get_elements()
 730         b2 = bustard.Bustard(xml=xml)
 731         self.failUnlessEqual(b.software, b2.software)
 732         self.failUnlessEqual(b.version,  b2.version)
 733         self.failUnlessEqual(b.date,     b2.date )
 734         self.failUnlessEqual(b.user,     b2.user)
 735         self.failUnlessEqual(len(b.phasing), len(b2.phasing))
 736         for key in b.phasing.keys():
 737             self.failUnlessEqual(b.phasing[key].lane,
 738                                  b2.phasing[key].lane)
 739             self.failUnlessEqual(b.phasing[key].phasing,
 740                                  b2.phasing[key].phasing)
 741             self.failUnlessEqual(b.phasing[key].prephasing,
 742                                  b2.phasing[key].prephasing)
 743
 744     def test_gerald(self):
 745         # need to update gerald and make tests for it
 746         g = gerald.gerald(self.gerald_dir)
 747
 748         self.failUnlessEqual(g.software, 'GERALD')
 749         self.failUnlessEqual(g.version, '1.68.2.2')
 750         self.failUnlessEqual(g.date, datetime(2008,4,19,19,8,30))
 751         self.failUnlessEqual(len(g.lanes), len(g.lanes.keys()))
 752         self.failUnlessEqual(len(g.lanes), len(g.lanes.items()))
 753
 754
 755         # list of genomes, matches what was defined up in
 756         # make_gerald_config.
 757         # the first None is to offset the genomes list to be 1..9
 758         # instead of pythons default 0..8
 759         genomes = [None, '/g/dm3', '/g/equcab1', '/g/equcab1', '/g/canfam2',
 760                          '/g/hg18', '/g/hg18', '/g/hg18', '/g/hg18', ]
 761
 762         # test lane specific parameters from gerald config file
 763         for i in range(1,9):
 764             cur_lane = g.lanes[i]
 765             self.failUnlessEqual(cur_lane.analysis, 'eland')
 766             self.failUnlessEqual(cur_lane.eland_genome, genomes[i])
 767             self.failUnlessEqual(cur_lane.read_length, '32')
 768             self.failUnlessEqual(cur_lane.use_bases, 'Y'*32)
 769
 770         # test data extracted from summary file
 771         clusters = [None,
 772                     (96483, 9074), (133738, 7938),
 773                     (152142, 10002), (15784, 2162),
 774                     (119735, 8465), (152177, 8146),
 775                     (84649, 7325), (54622, 4812),]
 776
 777         self.failUnlessEqual(len(g.summary), 1)
 778         for i in range(1,9):
 779             summary_lane = g.summary[0][i]
 780             self.failUnlessEqual(summary_lane.cluster, clusters[i])
 781             self.failUnlessEqual(summary_lane.lane, i)
 782
 783         xml = g.get_elements()
 784         # just make sure that element tree can serialize the tree
 785         xml_str = ElementTree.tostring(xml)
 786         g2 = gerald.Gerald(xml=xml)
 787
 788         # do it all again after extracting from the xml file
 789         self.failUnlessEqual(g.version, g2.version)
 790         self.failUnlessEqual(g.date, g2.date)
 791         self.failUnlessEqual(len(g.lanes.keys()), len(g2.lanes.keys()))
 792         self.failUnlessEqual(len(g.lanes.items()), len(g2.lanes.items()))
 793
 794         # test lane specific parameters from gerald config file
 795         for i in range(1,9):
 796             g_lane = g.lanes[i]
 797             g2_lane = g2.lanes[i]
 798             self.failUnlessEqual(g_lane.analysis, g2_lane.analysis)
 799             self.failUnlessEqual(g_lane.eland_genome, g2_lane.eland_genome)
 800             self.failUnlessEqual(g_lane.read_length, g2_lane.read_length)
 801             self.failUnlessEqual(g_lane.use_bases, g2_lane.use_bases)
 802
 803         # test (some) summary elements
 804         self.failUnlessEqual(len(g.summary), 1)
 805         for i in range(1,9):
 806             g_summary = g.summary[0][i]
 807             g2_summary = g2.summary[0][i]
 808             self.failUnlessEqual(g_summary.cluster, g2_summary.cluster)
 809             self.failUnlessEqual(g_summary.lane, g2_summary.lane)
 810
 811             g_eland = g.eland_results
 812             g2_eland = g2.eland_results
 813             for key in g_eland:
 814                 g_results = g_eland[key]
 815                 g2_results = g2_eland[key]
 816                 self.failUnlessEqual(g_results.reads,
 817                                      g2_results.reads)
 818                 self.failUnlessEqual(len(g_results.mapped_reads),
 819                                      len(g2_results.mapped_reads))
 820                 for k in g_results.mapped_reads.keys():
 821                     self.failUnlessEqual(g_results.mapped_reads[k],
 822                                          g2_results.mapped_reads[k])
 823
 824                 self.failUnlessEqual(len(g_results.match_codes),
 825                                      len(g2_results.match_codes))
 826                 for k in g_results.match_codes.keys():
 827                     self.failUnlessEqual(g_results.match_codes[k],
 828                                          g2_results.match_codes[k])
 829
 830
 831     def test_eland(self):
 832         dm3_map = { 'chrUextra.fa' : 'dm3/chrUextra.fa',
 833                     'chr2L.fa': 'dm3/chr2L.fa',
 834                     'Lambda.fa': 'Lambda.fa'}
 835         genome_maps = { 1:dm3_map, 2:dm3_map, 3:dm3_map, 4:dm3_map,
 836                         5:dm3_map, 6:dm3_map, 7:dm3_map, 8:dm3_map }
 837         eland = gerald.eland(self.gerald_dir, genome_maps=genome_maps)
 838
 839         for key in eland:
 840             lane = eland[key]
 841             self.failUnlessEqual(lane.reads, 4)
 842             self.failUnlessEqual(lane.sample_name, "s")
 843             self.failUnlessEqual(lane.lane_id, key.lane)
 844             self.failUnlessEqual(len(lane.mapped_reads), 3)
 845             self.failUnlessEqual(lane.mapped_reads['Lambda.fa'], 1)
 846             self.failUnlessEqual(lane.mapped_reads['dm3/chr2L.fa'], 1)
 847             self.failUnlessEqual(lane.match_codes['U1'], 2)
 848             self.failUnlessEqual(lane.match_codes['NM'], 1)
 849
 850         xml = eland.get_elements()
 851         # just make sure that element tree can serialize the tree
 852         xml_str = ElementTree.tostring(xml)
 853         e2 = gerald.ELAND(xml=xml)
 854
 855         for key in eland:
 856             l1 = eland[key]
 857             l2 = e2[key]
 858             self.failUnlessEqual(l1.reads, l2.reads)
 859             self.failUnlessEqual(l1.sample_name, l2.sample_name)
 860             self.failUnlessEqual(l1.lane_id, l2.lane_id)
 861             self.failUnlessEqual(len(l1.mapped_reads), len(l2.mapped_reads))
 862             self.failUnlessEqual(len(l1.mapped_reads), 3)
 863             for k in l1.mapped_reads.keys():
 864                 self.failUnlessEqual(l1.mapped_reads[k],
 865                                      l2.mapped_reads[k])
 866
 867             self.failUnlessEqual(len(l1.match_codes), 9)
 868             self.failUnlessEqual(len(l1.match_codes), len(l2.match_codes))
 869             for k in l1.match_codes.keys():
 870                 self.failUnlessEqual(l1.match_codes[k],
 871                                      l2.match_codes[k])
 872
 873     def test_runfolder(self):
 874         runs = runfolder.get_runs(self.runfolder_dir)
 875
 876         # do we get the flowcell id from the filename?
 877         self.failUnlessEqual(len(runs), 1)
 878         self.failUnlessEqual(runs[0].serialization_filename, 'run_207BTAAXX_2008-04-19.xml')
 879
 880         # do we get the flowcell id from the FlowcellId.xml file
 881         make_flowcell_id(self.runfolder_dir, '207BTAAXY')
 882         runs = runfolder.get_runs(self.runfolder_dir)
 883         self.failUnlessEqual(len(runs), 1)
 884         self.failUnlessEqual(runs[0].serialization_filename, 'run_207BTAAXY_2008-04-19.xml')
 885
 886         r1 = runs[0]
 887         xml = r1.get_elements()
 888         xml_str = ElementTree.tostring(xml)
 889
 890         r2 = runfolder.PipelineRun(xml=xml)
 891         self.failUnlessEqual(r1.serialization_filename, r2.serialization_filename)
 892         self.failIfEqual(r2.image_analysis, None)
 893         self.failIfEqual(r2.bustard, None)
 894         self.failIfEqual(r2.gerald, None)
 895
 896
 897 def suite():
 898     from unittest import TestSuite, defaultTestLoader
 899     suite = TestSuite()
 900     suite.addTests(defaultTestLoader.loadTestsFromTestCase(RunfolderTests))
 901     return suite
 902
 903 if __name__ == "__main__":
 904     from unittest import main
 905     main(defaultTest="suite")