|
75 | 75 | "</div>"
|
76 | 76 | ]
|
77 | 77 | },
|
| 78 | + { |
| 79 | + "cell_type": "code", |
| 80 | + "execution_count": null, |
| 81 | + "metadata": {}, |
| 82 | + "outputs": [], |
| 83 | + "source": [] |
| 84 | + }, |
78 | 85 | {
|
79 | 86 | "cell_type": "code",
|
80 | 87 | "execution_count": 3,
|
|
162 | 169 | "# load MC_length.csv\n"
|
163 | 170 | ]
|
164 | 171 | },
|
| 172 | + { |
| 173 | + "cell_type": "code", |
| 174 | + "execution_count": null, |
| 175 | + "metadata": {}, |
| 176 | + "outputs": [], |
| 177 | + "source": [] |
| 178 | + }, |
165 | 179 | {
|
166 | 180 | "cell_type": "code",
|
167 | 181 | "execution_count": 4,
|
|
249 | 263 | "# load MZ_length.csv\n"
|
250 | 264 | ]
|
251 | 265 | },
|
| 266 | + { |
| 267 | + "cell_type": "code", |
| 268 | + "execution_count": null, |
| 269 | + "metadata": {}, |
| 270 | + "outputs": [], |
| 271 | + "source": [] |
| 272 | + }, |
252 | 273 | {
|
253 | 274 | "cell_type": "code",
|
254 | 275 | "execution_count": 5,
|
|
383 | 404 | "</div>"
|
384 | 405 | ]
|
385 | 406 | },
|
| 407 | + { |
| 408 | + "cell_type": "code", |
| 409 | + "execution_count": null, |
| 410 | + "metadata": {}, |
| 411 | + "outputs": [], |
| 412 | + "source": [] |
| 413 | + }, |
386 | 414 | {
|
387 | 415 | "cell_type": "code",
|
388 | 416 | "execution_count": 7,
|
|
429 | 457 | "# store the genotype dataframe in the gwas.h5 dataset side by side with the phenotype\n"
|
430 | 458 | ]
|
431 | 459 | },
|
| 460 | + { |
| 461 | + "cell_type": "code", |
| 462 | + "execution_count": null, |
| 463 | + "metadata": {}, |
| 464 | + "outputs": [], |
| 465 | + "source": [] |
| 466 | + }, |
432 | 467 | {
|
433 | 468 | "cell_type": "code",
|
434 | 469 | "execution_count": 9,
|
|
450 | 485 | "# does the file system on disk match the size in memory ?"
|
451 | 486 | ]
|
452 | 487 | },
|
| 488 | + { |
| 489 | + "cell_type": "code", |
| 490 | + "execution_count": null, |
| 491 | + "metadata": {}, |
| 492 | + "outputs": [], |
| 493 | + "source": [] |
| 494 | + }, |
453 | 495 | {
|
454 | 496 | "cell_type": "code",
|
455 | 497 | "execution_count": 10,
|
|
493 | 535 | "Remove N/A from the phenotype dataframe and make sure that the genotype and phenotype dataframes only contain accessions that occur in both"
|
494 | 536 | ]
|
495 | 537 | },
|
| 538 | + { |
| 539 | + "cell_type": "code", |
| 540 | + "execution_count": null, |
| 541 | + "metadata": {}, |
| 542 | + "outputs": [], |
| 543 | + "source": [] |
| 544 | + }, |
496 | 545 | {
|
497 | 546 | "cell_type": "code",
|
498 | 547 | "execution_count": 11,
|
|
518 | 567 | "#Remove NaNs from the phenotype dataset\n"
|
519 | 568 | ]
|
520 | 569 | },
|
| 570 | + { |
| 571 | + "cell_type": "code", |
| 572 | + "execution_count": null, |
| 573 | + "metadata": {}, |
| 574 | + "outputs": [], |
| 575 | + "source": [] |
| 576 | + }, |
521 | 577 | {
|
522 | 578 | "cell_type": "code",
|
523 | 579 | "execution_count": 12,
|
|
915 | 971 | "</div>"
|
916 | 972 | ]
|
917 | 973 | },
|
| 974 | + { |
| 975 | + "cell_type": "code", |
| 976 | + "execution_count": null, |
| 977 | + "metadata": {}, |
| 978 | + "outputs": [], |
| 979 | + "source": [] |
| 980 | + }, |
918 | 981 | {
|
919 | 982 | "cell_type": "code",
|
920 | 983 | "execution_count": 13,
|
|
1002 | 1065 | "$$"
|
1003 | 1066 | ]
|
1004 | 1067 | },
|
| 1068 | + { |
| 1069 | + "cell_type": "code", |
| 1070 | + "execution_count": null, |
| 1071 | + "metadata": {}, |
| 1072 | + "outputs": [], |
| 1073 | + "source": [] |
| 1074 | + }, |
1005 | 1075 | {
|
1006 | 1076 | "cell_type": "code",
|
1007 | 1077 | "execution_count": 14,
|
|
1092 | 1162 | "Run the standard linear regression for all 3 phenotypes (raw, box-cox and log transformed) and genetate the Manhattan plots "
|
1093 | 1163 | ]
|
1094 | 1164 | },
|
| 1165 | + { |
| 1166 | + "cell_type": "code", |
| 1167 | + "execution_count": null, |
| 1168 | + "metadata": {}, |
| 1169 | + "outputs": [], |
| 1170 | + "source": [] |
| 1171 | + }, |
1095 | 1172 | {
|
1096 | 1173 | "cell_type": "code",
|
1097 | 1174 | "execution_count": 15,
|
|
1197 | 1274 | "\n"
|
1198 | 1275 | ]
|
1199 | 1276 | },
|
| 1277 | + { |
| 1278 | + "cell_type": "code", |
| 1279 | + "execution_count": null, |
| 1280 | + "metadata": {}, |
| 1281 | + "outputs": [], |
| 1282 | + "source": [] |
| 1283 | + }, |
1200 | 1284 | {
|
1201 | 1285 | "cell_type": "code",
|
1202 | 1286 | "execution_count": 16,
|
|
1254 | 1338 | "generate qq-plots and check the inflation"
|
1255 | 1339 | ]
|
1256 | 1340 | },
|
| 1341 | + { |
| 1342 | + "cell_type": "code", |
| 1343 | + "execution_count": null, |
| 1344 | + "metadata": {}, |
| 1345 | + "outputs": [], |
| 1346 | + "source": [] |
| 1347 | + }, |
1257 | 1348 | {
|
1258 | 1349 | "cell_type": "code",
|
1259 | 1350 | "execution_count": 17,
|
|
1314 | 1405 | "</div>"
|
1315 | 1406 | ]
|
1316 | 1407 | },
|
| 1408 | + { |
| 1409 | + "cell_type": "code", |
| 1410 | + "execution_count": null, |
| 1411 | + "metadata": {}, |
| 1412 | + "outputs": [], |
| 1413 | + "source": [] |
| 1414 | + }, |
1317 | 1415 | {
|
1318 | 1416 | "cell_type": "code",
|
1319 | 1417 | "execution_count": 18,
|
|
1356 | 1454 | "#normalize it\n"
|
1357 | 1455 | ]
|
1358 | 1456 | },
|
| 1457 | + { |
| 1458 | + "cell_type": "code", |
| 1459 | + "execution_count": null, |
| 1460 | + "metadata": {}, |
| 1461 | + "outputs": [], |
| 1462 | + "source": [] |
| 1463 | + }, |
1359 | 1464 | {
|
1360 | 1465 | "cell_type": "code",
|
1361 | 1466 | "execution_count": 21,
|
|
1393 | 1498 | "# Run linear mixed model\n"
|
1394 | 1499 | ]
|
1395 | 1500 | },
|
| 1501 | + { |
| 1502 | + "cell_type": "code", |
| 1503 | + "execution_count": null, |
| 1504 | + "metadata": {}, |
| 1505 | + "outputs": [], |
| 1506 | + "source": [] |
| 1507 | + }, |
1396 | 1508 | {
|
1397 | 1509 | "cell_type": "code",
|
1398 | 1510 | "execution_count": 23,
|
|
1490 | 1602 | "# retrieve the P-values, the Betas, and the standard errors.\n"
|
1491 | 1603 | ]
|
1492 | 1604 | },
|
| 1605 | + { |
| 1606 | + "cell_type": "code", |
| 1607 | + "execution_count": null, |
| 1608 | + "metadata": {}, |
| 1609 | + "outputs": [], |
| 1610 | + "source": [] |
| 1611 | + }, |
1493 | 1612 | {
|
1494 | 1613 | "cell_type": "code",
|
1495 | 1614 | "execution_count": 24,
|
|
1539 | 1658 | ""
|
1540 | 1659 | ]
|
1541 | 1660 | },
|
| 1661 | + { |
| 1662 | + "cell_type": "code", |
| 1663 | + "execution_count": null, |
| 1664 | + "metadata": {}, |
| 1665 | + "outputs": [], |
| 1666 | + "source": [] |
| 1667 | + }, |
1542 | 1668 | {
|
1543 | 1669 | "cell_type": "code",
|
1544 | 1670 | "execution_count": 25,
|
|
0 commit comments