worksheet18
Suzanne
October 27, 2015
Task 1: There is no answer for this task, because I will install “xlsx” package.
Task 2:
Install the xlsx package and read the CompleteGeneticData.xlsx into R. Save in “CompleteData”
require(xlsx)## Loading required package: xlsx
## Loading required package: rJava
## Loading required package: xlsxjarssetwd("/Users/Suzanne/Desktop/Bioinformatics/")
CompleteData<-read.xlsx2("CompleteGeneticData.xlsx", 1)Task 3:
summary(CompleteData)## year colony Individual free_slave Habitat Transect
## 2009: 583 P1 : 45 1 :534 0:2383 MI:1202 MI.1:389
## 2010:1281 O1 : 40 2 :526 1: 683 NY:1075 MI.2:813
## 2012:1202 M1 : 38 3 :524 WV: 789 NY.2:777
## P4 : 33 4 :512 NY.3:298
## G1 : 25 5 :490 WV.1:285
## H1 : 25 6 : 36 WV.3: 96
## (Other):2860 (Other):444 WV.4:408
## transect.x transect.y GT218_1 GT218_2
## 795 : 25 3583 : 25 112 :1974 112 :2027
## 1020 : 20 7773 : 25 NA : 273 114 : 324
## 1075 : 20 895 : 25 104 : 244 NA : 275
## 13630 : 20 12148 : 20 114 : 230 116 : 243
## 13689 : 20 12180 : 20 108 : 124 118 : 71
## 13696 : 20 12264 : 20 110 : 104 110 : 31
## (Other):2941 (Other):2931 (Other): 117 (Other): 95
## T223_1 T223_2 L18_1 L18_2 GT1_1
## 116 :2298 116 :2128 135 :649 147 :902 198 : 640
## 114 : 452 118 : 506 141 :574 145 :499 200 : 359
## NA : 140 120 : 212 145 :499 143 :287 208 : 289
## 118 : 50 NA : 137 143 :498 149 :287 196 : 200
## 102 : 37 114 : 48 147 :419 151 :253 202 : 195
## 120 : 27 110 : 10 NA :206 141 :233 210 : 194
## (Other): 62 (Other): 25 (Other):221 (Other):605 (Other):1189
## GT1_2 L5_1 L5_2 Myrt3_1 Myrt3_2
## 214 : 373 124 :1112 142 : 518 189 :956 193 :574
## 220 : 365 126 : 536 134 : 329 187 :847 195 :561
## 218 : 288 134 : 306 136 : 296 193 :349 197 :483
## 212 : 232 132 : 299 126 : 236 191 :345 189 :478
## 216 : 230 136 : 192 132 : 223 NA :139 191 :448
## 208 : 194 142 : 151 146 : 206 185 :131 187 :203
## (Other):1384 (Other): 470 (Other):1258 (Other):299 (Other):319
## UniqueInd UniqueColony Plot
## MI.1.F10.1: 2 WV.P1 : 25 MI.I : 245
## MI.1.F11.5: 2 NY.G1 : 20 NY.K : 219
## MI.2.I27.3: 2 NY.G3 : 20 MI.L : 180
## MI.2.I37.1: 2 NY.H1 : 20 NY.L : 180
## MI.2.J13.3: 2 NY.J1 : 20 MI.H : 129
## MI.1.A2.1 : 1 NY.K1 : 20 MI.D : 113
## (Other) :3055 (Other):2941 (Other):2000head(CompleteData)## year colony Individual free_slave Habitat Transect transect.x transect.y
## 1 2012 A2 1 0 MI MI.1 13520 570
## 2 2012 A2 2 0 MI MI.1 13520 570
## 3 2012 A2 3 0 MI MI.1 13520 570
## 4 2012 A2 4 0 MI MI.1 13520 570
## 5 2012 A2 5 0 MI MI.1 13520 570
## 6 2012 B10 1 0 MI MI.1 5952 316
## GT218_1 GT218_2 T223_1 T223_2 L18_1 L18_2 GT1_1 GT1_2 L5_1 L5_2 Myrt3_1
## 1 114 116 102 116 135 149 208 208 124 126 191
## 2 114 114 102 116 135 149 208 208 124 126 193
## 3 114 116 102 116 135 149 208 208 124 126 197
## 4 112 112 102 116 135 151 208 208 124 126 197
## 5 112 112 102 116 135 149 208 208 124 126 197
## 6 112 112 116 116 145 147 198 214 126 126 193
## Myrt3_2 UniqueInd UniqueColony Plot
## 1 197 MI.1.A2.1 MI.A2 MI.A
## 2 201 MI.1.A2.2 MI.A2 MI.A
## 3 197 MI.1.A2.3 MI.A2 MI.A
## 4 197 MI.1.A2.4 MI.A2 MI.A
## 5 197 MI.1.A2.5 MI.A2 MI.A
## 6 197 MI.1.B10.1 MI.B10 MI.BTask 4: Microsattelite is a segment of repetitive DNA in which certain DNA motif are repeated from 5-50 times. Microsattelite occur at thousands in the human genome and they are notable for their high mutation rate and high diversity in the population.
Task 5:
WVPlot<-subset(CompleteData, CompleteData$Plot == "WV.R")
head(WVPlot)## year colony Individual free_slave Habitat Transect transect.x
## 2800 2010 R1 1 0 WV WV.4 9599
## 2801 2010 R1 2 0 WV WV.4 9599
## 2802 2010 R1 3 0 WV WV.4 9599
## 2803 2010 R1 4 0 WV WV.4 9599
## 2804 2010 R1 5 0 WV WV.4 9599
## 2805 2010 R13 1 0 WV WV.4 9545
## transect.y GT218_1 GT218_2 T223_1 T223_2 L18_1 L18_2 GT1_1 GT1_2 L5_1
## 2800 7504 110 110 122 128 NA NA 222 224 120
## 2801 7504 112 112 120 128 NA NA 208 224 122
## 2802 7504 108 108 120 120 133 135 208 224 124
## 2803 7504 110 110 122 122 133 135 222 224 120
## 2804 7504 112 112 120 128 133 135 208 224 122
## 2805 7475 NA NA 116 118 143 153 200 218 124
## L5_2 Myrt3_1 Myrt3_2 UniqueInd UniqueColony Plot
## 2800 132 183 191 WV.4.R1.1 WV.R1 WV.R
## 2801 124 169 183 WV.4.R1.2 WV.R1 WV.R
## 2802 124 185 201 WV.4.R1.3 WV.R1 WV.R
## 2803 132 181 191 WV.4.R1.4 WV.R1 WV.R
## 2804 124 185 201 WV.4.R1.5 WV.R1 WV.R
## 2805 124 195 195 WV.4.R13.1 WV.R13 WV.R#Convert to numeric data
as.numeric(WVPlot$transect.x) -> WVPlot.transectx
as.numeric(WVPlot$transect.y) -> WVPlot.transecty
plot(WVPlot.transectx, WVPlot.transecty, col="red", main="West Virginia Ant Coordination")
Task 6
require(ggplot2)## Loading required package: ggplot2require(ggtree)## Loading required package: ggtreeas.numeric(CompleteData$GT218_1)->Ant.GT218_1
as.numeric(CompleteData$GT218_2)->Ant.GT218_2
as.numeric(CompleteData$T223_1)->Ant.T223_1
as.numeric(CompleteData$T223_2)->Ant.T223_2
as.numeric(CompleteData$L18_1)->Ant.L18_1
as.numeric(CompleteData$L18_2)->Ant.L18_2
as.numeric(CompleteData$GT1_1)->Ant.GT1_1
as.numeric(CompleteData$GT1_2)->Ant.GT1_2
as.numeric(CompleteData$L5_1)->Ant.L5_1
as.numeric(CompleteData$L5_2)->Ant.L5_2
as.numeric(CompleteData$Myrt3_1)->Ant.Myrt3_1
as.numeric(CompleteData$Myrt3_2)->Ant.Myrt3_2
hist(Ant.GT218_1)
hist(Ant.GT218_2)
hist(Ant.T223_1)
hist(Ant.T223_2)
hist(Ant.L18_1)
hist(Ant.L18_2)
hist(Ant.L5_1)
hist(Ant.L5_2)
hist(Ant.Myrt3_1)
hist(Ant.Myrt3_2)
Task 7
#Counting
require(plyr)## Loading required package: plyr
##
## Attaching package: 'plyr'
##
## The following object is masked from 'package:ggtree':
##
## .count(CompleteData$free_slave)## x freq
## 1 0 2383
## 2 1 683Task 8
#Selecting Colony and free_slave column
unique(CompleteData[,c(2,4)])## colony free_slave
## 1 A2 0
## 6 B10 0
## 11 B11 0
## 16 B13 0
## 21 B14 0
## 25 B15 0
## 30 B19 0
## 35 B2 0
## 40 B26 0
## 45 B27 0
## 50 B29 0
## 55 B3 0
## 60 B30 0
## 65 B31 0
## 70 B32 0
## 74 B33 0
## 79 B34 0
## 84 B35 0
## 89 B36 0
## 94 B37 0
## 99 B38 0
## 104 B39 0
## 109 B5 0
## 112 C11 0
## 115 C12 0
## 119 C14 0
## 123 C19 0
## 128 C2 0
## 133 C22 0
## 138 C23 0
## 143 C25 0
## 148 C27 0
## 153 C28 0
## 158 C3 0
## 163 C4 0
## 167 C7 0
## 172 C9 0
## 177 D1 0
## 181 D10 0
## 185 D12 0
## 190 D14 0
## 195 D15 0
## 196 D16 0
## 200 D18 0
## 204 D2 0
## 209 D20 0
## 214 D21 0
## 219 D23 0
## 222 D24 0
## 227 D25 0
## 232 D26 0
## 237 D27 0
## 242 D28 0
## 247 D29 0
## 252 D30 0
## 257 D31 0
## 262 D34 0
## 267 D35 0
## 272 D4 0
## 277 D5 0
## 282 D7 0
## 287 D9 0
## 290 E1 0
## 295 E10 0
## 300 E11 0
## 305 E13 0
## 310 E6 0
## 315 E7 0
## 319 E8 0
## 324 E9 0
## 329 F1 0
## 334 F10 0
## 339 F11 0
## 344 F13 0
## 349 F14 0
## 354 F15 0
## 358 F17 0
## 363 F18 0
## 368 F20 0
## 373 F21 0
## 378 F22 0
## 383 F23 0
## 386 F24 0
## 390 F25 0
## 395 F27 0
## 400 F28 0
## 405 F3 0
## 410 F5 0
## 413 F7 0
## 417 F8 0
## 418 F9 0
## 423 G1 0
## 428 G10 0
## 433 G11 0
## 438 G12 0
## 442 G13 0
## 447 G14 0
## 452 G15 0
## 457 G16 0
## 462 G17 0
## 467 G18 0
## 471 G19 0
## 476 G2 0
## 481 G20 0
## 484 G21 0
## 489 G23 0
## 493 G25 0
## 498 G26 0
## 503 G27 0
## 507 G28 0
## 511 G3 0
## 512 G4 0
## 517 G5 0
## 522 G7 0
## 527 G8 0
## 531 H1 0
## 536 H10 0
## 540 H13 0
## 545 H14 0
## 550 H15 0
## 555 H16 0
## 560 H18 0
## 565 H23 0
## 570 H25 0
## 575 H26 0
## 580 H28 0
## 585 H29 0
## 590 H3 0
## 595 H31 0
## 600 H37 0
## 605 H38 0
## 610 H39 0
## 615 H40 0
## 620 H41 0
## 625 H42 0
## 629 H43 0
## 633 H44 0
## 638 H45 0
## 643 H5 0
## 648 H6 0
## 653 H7 0
## 655 H9 0
## 660 I1 0
## 665 I11 0
## 669 I12 0
## 674 I13 0
## 679 I14 0
## 683 I15 0
## 687 I16 0
## 692 I17 0
## 697 I18 0
## 702 I19 0
## 707 I2 0
## 711 I21 0
## 716 I22 0
## 721 I23 0
## 726 I24 0
## 731 I25 0
## 736 I26 0
## 741 I27 0
## 746 I28 0
## 751 I29 0
## 756 I3 0
## 761 I30 0
## 766 I31 0
## 771 I32 0
## 776 I33 0
## 781 I34 0
## 786 I35 0
## 791 I36 0
## 795 I37 0
## 801 I38 0
## 806 I39 0
## 811 I4 0
## 814 I40 0
## 816 I41 0
## 820 I42 0
## 825 I43 0
## 830 I44 0
## 834 I45 0
## 839 I46 0
## 842 I47 0
## 845 I48 0
## 850 I49 0
## 855 I5 0
## 860 I50 0
## 865 I51 0
## 870 I52 0
## 875 I53 0
## 880 I54 0
## 885 I6 0
## 890 I7 0
## 895 I8 0
## 900 I9 0
## 905 J1 0
## 910 J13 0
## 915 J3 0
## 920 J5 0
## 925 K1 0
## 930 K11 0
## 935 K12 0
## 940 K14 0
## 945 K16 0
## 950 K2 0
## 955 K21 0
## 960 K25 0
## 965 K27 0
## 970 K3 0
## 975 K49 0
## 980 K5 0
## 985 K56 0
## 990 K6 0
## 995 K62 0
## 999 K63 0
## 1004 K75 0
## 1005 K76 0
## 1009 K79 0
## 1014 K8 0
## 1019 K9 0
## 1023 L10 0
## 1028 L13 0
## 1031 L14 0
## 1036 L15 0
## 1039 L19 0
## 1041 L23 0
## 1046 L25 0
## 1051 L26 0
## 1053 L27 0
## 1058 L33 0
## 1063 L38 0
## 1067 L39 0
## 1072 L40 0
## 1077 L41 0
## 1082 L42 0
## 1087 L43 0
## 1090 L46 0
## 1095 L47 0
## 1100 L5 0
## 1103 L50 0
## 1108 L52 0
## 1113 L54 0
## 1118 L57 0
## 1123 L58 0
## 1128 L59 0
## 1133 L60 0
## 1138 L61 0
## 1143 L62 0
## 1148 L63 0
## 1153 L66 0
## 1158 L71 0
## 1163 L74 0
## 1168 L75 0
## 1173 L80 0
## 1178 L81 0
## 1183 L82 0
## 1188 L83 0
## 1193 L85 0
## 1198 L86 0
## 1203 G1 1
## 1211 G3 1
## 1227 G6 0
## 1242 G9 1
## 1247 H1 1
## 1267 H12 0
## 1292 H17 0
## 1297 H2 0
## 1307 H4 0
## 1327 H8 0
## 1337 I1 1
## 1351 I10 0
## 1405 I20 0
## 1450 J1 1
## 1470 J10 0
## 1475 J11 0
## 1480 J12 0
## 1485 J13 1
## 1490 J14 0
## 1495 J2 0
## 1505 J4 0
## 1515 J6 0
## 1520 J7 0
## 1525 J8 0
## 1530 J9 0
## 1535 K1 1
## 1555 K10 1
## 1580 K12 1
## 1600 K13 0
## 1605 K14 1
## 1625 K15 1
## 1650 K17 0
## 1655 K18 0
## 1660 K19 0
## 1670 K20 0
## 1680 K22 0
## 1685 K23 0
## 1690 K24 0
## 1700 K26 0
## 1710 K28 0
## 1715 K29 0
## 1724 K4 0
## 1739 K7 0
## 1754 L1 1
## 1768 L11 0
## 1773 L12 0
## 1793 L16 0
## 1798 L17 0
## 1802 L18 0
## 1812 L2 0
## 1817 L20 1
## 1837 L21 0
## 1842 L22 1
## 1867 L24 0
## 1872 L25 1
## 1892 L3 0
## 1897 L4 0
## 1902 L5 1
## 1914 L6 0
## 1919 L7 0
## 1924 L8 0
## 1929 L9 0
## 1934 M1 1
## 1954 M2 0
## 1959 M3 0
## 1964 M4 0
## 1969 M5 0
## 1973 M6 0
## 1977 N1 1
## 1997 N2 1
## 2009 N3 0
## 2014 N4 0
## 2019 O1 1
## 2023 O2 0
## 2028 O3 0
## 2033 O4 1
## 2034 O5 0
## 2039 O6 0
## 2044 P1 1
## 2046 P2 0
## 2051 P3 0
## 2056 P4 1
## 2070 P5 0
## 2075 P6 0
## 2080 Q1 0
## 2085 Q10 0
## 2090 Q2 0
## 2095 Q3 0
## 2100 Q4 0
## 2105 Q5 0
## 2110 Q7 0
## 2115 Q8 0
## 2120 Q9 0
## 2125 R1 1
## 2145 R2 0
## 2150 R3 0
## 2155 R4 0
## 2160 R5 0
## 2165 R6 0
## 2170 R7 0
## 2175 R8 0
## 2179 A1 0
## 2189 A3 0
## 2194 A4 0
## 2199 A5 0
## 2204 A6 1
## 2224 A7 0
## 2226 B1 0
## 2241 B4 0
## 2251 C1 0
## 2256 C10 0
## 2266 C13 0
## 2286 C5 0
## 2291 C6 0
## 2301 C8 0
## 2315 D11 0
## 2325 D3 0
## 2335 D6 0
## 2352 E12 0
## 2362 E3 0
## 2364 E4 0
## 2366 E5 0
## 2396 F2 0
## 2406 F4 0
## 2415 F6 0
## 2425 F8 1
## 2453 M2 1
## 2468 M3 1
## 2489 N1 0
## 2494 N2 0
## 2509 N5 0
## 2514 N6 1
## 2551 O10 1
## 2566 O11 0
## 2571 O12 0
## 2576 O13 0
## 2581 O14 0
## 2596 O4 0
## 2606 O7 0
## 2611 O9 1
## 2641 P12 0
## 2646 P13 0
## 2651 P15 0
## 2656 P17 0
## 2666 P20 0
## 2671 P21 0
## 2676 P23 0
## 2681 P26 0
## 2705 P8 0
## 2709 P9 0
## 2718 Q11 0
## 2723 Q12 0
## 2728 Q13 0
## 2733 Q14 0
## 2738 Q15 0
## 2743 Q16 1
## 2780 Q9 1
## 2800 R1 0
## 2805 R13 0
## 2810 R14 0
## 2815 R15 0
## 2819 R16 0
## 2824 R3 1
## 2858 R9 0
## 2863 S1 0
## 2868 S2 0
## 2873 S3 0
## 2878 S7 0
## 2883 T1 0
## 2888 T10 1
## 2893 T11 0
## 2897 T22 0
## 2902 T3 0
## 2907 T4 1
## 2927 T5 0
## 2929 T8 0
## 2934 T9 0
## 2980 H11 0
## 3043 D8 0
## 3056 E2 0