This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Creating biplot PCA from metadata

Hello Biostar Community!

I would like to ask, how can I create a biplot PCA from metadata. I would like to plot the samples on a PCA plot containing the plotted variability in the x and y-axises. Moreover, the top 5 microbes that shaping the place of the samples in the PCA plot, which are displayed as vectors (arrows). The data is the following:

structure(list(AT_A_16 = c(0, 57260.86957, 0, 2906.832298, 0, 
559.0062112, 695.6521739, 0, 0, 0, 0, 0, 0, 0, 80.74534161, 0, 
6.211180124, 18.63354037, 2496.89441, 0, 0, 12.42236025, 68.32298137, 
0, 0, 347.826087, 24.8447205, 6.211180124, 0, 689.4409938, 1832.298137, 
6.211180124, 4472.049689, 6.211180124, 664.5962733, 0, 0, 801.242236, 
0, 422.3602484), AT_A_22 = c(64.51612903, 96677.41935, 0, 903.2258065, 
0, 451.6129032, 6064.516129, 0, 0, 0, 322.5806452, 96.77419355, 
0, 0, 0, 0, 32.25806452, 290.3225806, 870.9677419, 0, 0, 32.25806452, 
193.5483871, 0, 0, 64.51612903, 161.2903226, 0, 0, 64.51612903, 
161.2903226, 32.25806452, 387.0967742, 32.25806452, 11225.80645, 
0, 129.0322581, 612.9032258, 32.25806452, 96.77419355), AT_A_26 = c(126.2886598, 
958.7628866, 10.30927835, 4211.340206, 12.88659794, 139.1752577, 
113.4020619, 0, 5.154639175, 0, 0, 46.39175258, 0, 0, 2814.43299, 
208.7628866, 12.88659794, 652.0618557, 3884.020619, 0, 0, 41.2371134, 
3963.917526, 0, 0, 28.35051546, 231.9587629, 0, 0, 15.46391753, 
149.4845361, 38.65979381, 260.3092784, 149.4845361, 927.8350515, 
0, 438.1443299, 10023.19588, 301.5463918, 110.8247423), AT_A_32 = c(0, 
781937.5, 62.5, 50, 112.5, 3050, 0, 0, 0, 0, 0, 23612.5, 0, 0, 
12.5, 0, 175, 21312.5, 137.5, 0, 0, 87.5, 5150, 0, 0, 12.5, 1562.5, 
0, 0, 0, 337.5, 62.5, 350, 87.5, 16250, 0, 25, 175, 1850, 250
), AT_A_36 = c(40.6504065, 37642.27642, 0, 130.0813008, 0, 780.4878049, 
73.17073171, 0, 40.6504065, 0, 0, 1422.764228, 0, 0, 32.5203252, 
1560.97561, 32.5203252, 8048.780488, 520.3252033, 0, 0, 414.6341463, 
3788.617886, 0, 0, 73.17073171, 154.4715447, 0, 0, 48.7804878, 
113.8211382, 373.9837398, 40.6504065, 601.6260163, 4601.626016, 
0, 24.3902439, 560.9756098, 154.4715447, 40.6504065), AT_A_41 = c(0.898472597, 
2740.34142, 0, 2872.416891, 0, 889.4878706, 1654.986523, 0, 341.4195867, 
0, 0, 157.2327044, 0, 0, 13.47708895, 0, 0, 115.0044924, 516.621743, 
0, 0, 26.0557053, 61.09613657, 0, 0, 2778.077269, 46.72057502, 
0.898472597, 0, 315.3638814, 15371.96765, 213.836478, 2774.483378, 
0.898472597, 108.7151842, 0, 44.92362983, 3868.823001, 210.2425876, 
21297.39443), AT_A_46 = c(0, 0, 15.38461538, 71.79487179, 0, 
119523.0769, 20.51282051, 0, 153.8461538, 0, 0, 502.5641026, 
0, 0, 2466.666667, 0, 0, 1112.820513, 13353.84615, 0, 0, 87.17948718, 
210.2564103, 0, 0, 194.8717949, 0, 66.66666667, 0, 0, 1184.615385, 
420.5128205, 46.15384615, 123.0769231, 10.25641026, 0, 28282.05128, 
61553.84615, 0, 1656.410256), AT_B_11 = c(30.3030303, 169545.4545, 
0, 60.60606061, 0, 1545.454545, 0, 0, 0, 0, 0, 0, 0, 0, 303.030303, 
0, 0, 0, 181.8181818, 0, 0, 0, 0, 0, 0, 0, 60.60606061, 0, 0, 
0, 16393.93939, 0, 76363.63636, 121.2121212, 1666.666667, 0, 
333.3333333, 242.4242424, 0, 0), AT_B_13 = c(79.13669065, 724568.3453, 
0, 21.58273381, 0, 8093.52518, 14.38848921, 0, 100.7194245, 0, 
0, 1683.453237, 0, 0, 755.3956835, 50.35971223, 21.58273381, 
4071.942446, 338.1294964, 0, 0, 7.194244604, 158.2733813, 0, 
0, 7.194244604, 194.2446043, 0, 0, 0, 2604.316547, 1417.266187, 
1726.618705, 57.55395683, 5676.258993, 0, 64.74820144, 417.2661871, 
223.0215827, 230.2158273), AT_B_24 = c(305.5555556, 2177000, 
0, 166.6666667, 0, 111.1111111, 55.55555556, 0, 0, 0, 0, 55.55555556, 
0, 0, 138.8888889, 27.77777778, 0, 0, 250, 0, 27.77777778, 27.77777778, 
166.6666667, 0, 0, 83.33333333, 83.33333333, 27.77777778, 0, 
0, 186027.7778, 0, 694.4444444, 972.2222222, 2000, 0, 750, 527.7777778, 
27.77777778, 638.8888889), AT_B_26 = c(1197.879859, 173724.3816, 
0, 127.2084806, 0, 1102.473498, 3.533568905, 0, 0, 0, 7.067137809, 
28.26855124, 0, 0, 279.1519435, 14.13427562, 3.533568905, 14.13427562, 
10876.32509, 0, 922.2614841, 0, 166.0777385, 0, 0, 21.20141343, 
367.4911661, 0, 0, 0, 1413.427562, 91.87279152, 7989.399293, 
2392.226148, 2462.897527, 0, 1385.159011, 10141.34276, 28.26855124, 
215.5477032), AT_B_37 = c(150L, 2728500L, 0L, 350L, 0L, 7050L, 
100L, 0L, 600L, 0L, 0L, 50L, 0L, 0L, 200L, 0L, 50L, 0L, 5300L, 
0L, 50L, 0L, 0L, 0L, 0L, 50L, 50L, 0L, 0L, 0L, 141950L, 50L, 
872150L, 300L, 39600L, 0L, 150L, 300L, 100L, 400L), AT_B_42 = c(0, 
4941210.526, 0, 0, 0, 421.0526316, 0, 0, 947.3684211, 0, 0, 210.5263158, 
0, 0, 0, 0, 105.2631579, 52.63157895, 9315.789474, 0, 0, 52.63157895, 
210.5263158, 0, 0, 0, 736.8421053, 0, 0, 0, 38736.84211, 0, 126842.1053, 
105.2631579, 947.3684211, 0, 0, 157.8947368, 105.2631579, 0), 
    BT_A_11 = c(0, 8394.230769, 0, 125, 0, 384.6153846, 0, 19.23076923, 
    19.23076923, 0, 0, 134.6153846, 0, 0, 0, 0, 0, 1769.230769, 
    471.1538462, 0, 0, 288.4615385, 9.615384615, 0, 0, 769.2307692, 
    500, 0, 0, 0, 750, 0, 9.615384615, 0, 0, 0, 9.615384615, 
    4961.538462, 0, 1009.615385), BT_A_16 = c(0, 212.7192982, 
    0, 0, 0, 271.9298246, 0, 4.385964912, 2.192982456, 0, 0, 
    416.6666667, 0, 0, 0, 0, 0, 129.3859649, 2635.964912, 0, 
    0, 206.1403509, 2.192982456, 0, 0, 311.4035088, 660.0877193, 
    0, 0, 0, 383.7719298, 0, 739.0350877, 0, 0, 0, 0, 2800.438596, 
    0, 171.0526316), BT_A_22 = c(28.57142857, 76857.14286, 0, 
    628.5714286, 0, 4857.142857, 0, 28.57142857, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 600, 57.14285714, 28.57142857, 0, 0, 0, 0, 
    0, 9685.714286, 542.8571429, 0, 0, 0, 0, 0, 228.5714286, 
    0, 0, 0, 0, 7685.714286, 0, 85.71428571), BT_A_26 = c(0, 
    8114.832536, 0, 0, 0, 363.6363636, 0, 0, 0, 0, 0, 2612.440191, 
    0, 0, 0, 0, 0, 4.784688995, 684.2105263, 0, 0, 57.41626794, 
    0, 0, 0, 1502.392344, 215.3110048, 0, 0, 0, 71.77033493, 
    0, 2114.832536, 0, 0, 0, 0, 1392.344498, 0, 287.0813397), 
    BT_A_32 = c(0, 255214.2857, 0, 0, 0, 285.7142857, 0, 71.42857143, 
    0, 0, 0, 142.8571429, 0, 0, 0, 0, 0, 0, 357.1428571, 142.8571429, 
    0, 0, 0, 0, 0, 0, 142.8571429, 0, 0, 0, 142.8571429, 0, 71.42857143, 
    0, 0, 0, 142.8571429, 500, 0, 142.8571429), BT_A_36 = c(0, 
    21454.54545, 0, 90.90909091, 0, 19909.09091, 0, 45.45454545, 
    0, 0, 0, 10772.72727, 0, 0, 0, 0, 0, 0, 9181.818182, 90.90909091, 
    0, 0, 45.45454545, 0, 0, 26454.54545, 500, 0, 0, 0, 90.90909091, 
    0, 16954.54545, 0, 45.45454545, 0, 90.90909091, 7045.454545, 
    0, 9181.818182), BT_A_41 = c(25.42372881, 203.3898305, 0, 
    177.9661017, 0, 8830.508475, 0, 25.42372881, 330.5084746, 
    0, 0, 1330.508475, 0, 0, 0, 0, 0, 220.3389831, 13449.15254, 
    8.474576271, 0, 0, 279.6610169, 0, 0, 1067.79661, 33.89830508, 
    0, 0, 0, 16.94915254, 0, 1338.983051, 0, 8.474576271, 0, 
    677.9661017, 1025.423729, 0, 720.3389831), BT_A_46 = c(0, 
    1258.547009, 0, 0, 0, 113.2478632, 0, 0, 0, 0, 0, 260.6837607, 
    0, 0, 0, 0, 0, 42.73504274, 363.2478632, 0, 0, 365.3846154, 
    0, 0, 0, 290.5982906, 282.0512821, 0, 0, 0, 427.3504274, 
    0, 1448.717949, 0, 0, 0, 0, 1410.25641, 0, 10.68376068), 
    BT_B_11 = c(0, 32307.69231, 0, 0, 0, 5435.897436, 0, 0, 564.1025641, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 128.2051282, 0, 0, 
    820.5128205, 230.7692308, 0, 0, 0, 25.64102564, 0, 21820.51282, 
    0, 0, 76.92307692, 461.5384615, 76.92307692, 1025.641026, 
    0), BT_B_13 = c(0, 217000, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 142.8571429, 0, 142.8571429, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 5571.428571, 0, 714.2857143, 0, 0, 0, 0, 0, 
    16857.14286, 0), BT_B_24 = c(0, 121333.3333, 0, 0, 0, 666.6666667, 
    0, 0, 0, 200, 0, 0, 0, 0, 66.66666667, 0, 0, 0, 0, 66.66666667, 
    0, 133.3333333, 0, 0, 0, 2200, 0, 0, 0, 0, 133.3333333, 0, 
    74666.66667, 0, 0, 0, 400, 0, 12800, 0), BT_B_26 = c(0, 237285.7143, 
    0, 0, 0, 0, 0, 0, 0, 142.8571429, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 428.5714286, 285.7142857, 0, 0, 0, 1000, 
    0, 275000, 0, 0, 0, 0, 142.8571429, 6428.571429, 0), BT_B_34 = c(0, 
    24697.67442, 46.51162791, 0, 0, 325.5813953, 0, 0, 46.51162791, 
    139.5348837, 0, 69.76744186, 0, 93.02325581, 0, 0, 0, 581.3953488, 
    883.7209302, 23.25581395, 0, 186.0465116, 46.51162791, 0, 
    0, 465.1162791, 395.3488372, 0, 0, 0, 4720.930233, 0, 10093.02326, 
    69.76744186, 0, 23.25581395, 255.8139535, 767.4418605, 2139.534884, 
    0), BT_B_37 = c(0L, 53240L, 40L, 120L, 0L, 1840L, 0L, 40L, 
    80L, 280L, 40L, 40L, 40L, 120L, 0L, 0L, 0L, 760L, 2560L, 
    200L, 0L, 560L, 120L, 40L, 0L, 1160L, 560L, 0L, 40L, 0L, 
    8240L, 0L, 18800L, 80L, 0L, 0L, 240L, 1680L, 3680L, 0L), 
    BT_B_42 = c(0, 9164.179104, 0, 0, 0, 4.975124378, 0, 0, 0, 
    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 1119.402985, 0, 0, 0, 4.975124378, 0, 990.0497512, 
    0), BT_B_45 = c(0, 14133.33333, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
    0, 0, 0, 0, 0, 33.33333333, 0, 0, 50, 0, 0, 0, 0, 0, 0, 266.6666667, 
    0, 0, 0, 1133.333333, 0, 19550, 0, 0, 283.3333333, 750, 366.6666667, 
    1033.333333, 0), BT_C_12 = c(0, 80, 0, 0, 160, 373.3333333, 
    0, 13.33333333, 0, 0, 13.33333333, 133.3333333, 240, 120, 
    0, 0, 0, 53.33333333, 20426.66667, 0, 0, 146.6666667, 160, 
    0, 1093.333333, 26800, 2133.333333, 0, 0, 53.33333333, 21306.66667, 
    0, 40, 0, 0, 0, 266.6666667, 22320, 26.66666667, 0), BT_C_27 = c(0, 
    125, 0, 6916.666667, 0, 3208.333333, 7416.666667, 500, 583.3333333, 
    0, 0, 0, 125, 0, 83.33333333, 0, 41.66666667, 916.6666667, 
    416.6666667, 41.66666667, 0, 125, 3250, 0, 0, 125, 41.66666667, 
    0, 0, 0, 541.6666667, 0, 333.3333333, 0, 0, 125, 5750, 125, 
    41.66666667, 0), BT_C_45 = c(114.2857143, 0, 0, 2900, 0, 
    2828.571429, 485.7142857, 1414.285714, 57.14285714, 0, 0, 
    0, 0, 0, 200, 0, 0, 571.4285714, 0, 57.14285714, 0, 0, 2514.285714, 
    0, 0, 0, 0, 0, 0, 0, 28.57142857, 0, 0, 0, 57.14285714, 0, 
    11157.14286, 0, 0, 0), BT_C_47 = c(0, 0, 0, 0, 0, 52.63157895, 
    3263.157895, 0, 0, 0, 0, 157.8947368, 105.2631579, 3684.210526, 
    52.63157895, 0, 105.2631579, 6736.842105, 263.1578947, 0, 
    0, 894.7368421, 52.63157895, 0, 52.63157895, 894.7368421, 
    157.8947368, 0, 0, 578.9473684, 50578.94737, 0, 0, 0, 0, 
    0, 0, 13368.42105, 894.7368421, 0), BT_D_13 = c(0, 0, 0, 
    0, 0, 378.3783784, 0, 0, 0, 148.6486486, 0, 2040.540541, 
    0, 81.08108108, 54.05405405, 0, 0, 94.59459459, 7162.162162, 
    0, 0, 1743.243243, 40.54054054, 148.6486486, 27.02702703, 
    5121.621622, 716.2162162, 0, 0, 13.51351351, 6851.351351, 
    0, 10162.16216, 0, 0, 0, 13.51351351, 8283.783784, 864.8648649, 
    4770.27027), BT_D_22 = c(0, 2346.153846, 0, 76.92307692, 
    0, 29884.61538, 0, 115.3846154, 0, 0, 500, 0, 0, 0, 0, 0, 
    0, 10846.15385, 2884.615385, 0, 0, 38.46153846, 307.6923077, 
    38.46153846, 0, 4461.538462, 76.92307692, 0, 0, 38.46153846, 
    8346.153846, 0, 12153.84615, 38.46153846, 0, 0, 769.2307692, 
    230.7692308, 730.7692308, 38.46153846), BT_D_24 = c(12.77955272, 
    460.0638978, 0, 0, 0, 0, 0, 0, 0, 0, 0, 405.7507987, 0, 0, 
    6.389776358, 0, 0, 0, 2677.316294, 0, 0, 0, 207.6677316, 
    175.7188498, 0, 1658.146965, 25.55910543, 0, 0, 0, 2444.089457, 
    0, 1610.223642, 0, 0, 0, 19.16932907, 146.9648562, 1773.162939, 
    916.9329073), BT_D_42 = c(29.41176471, 88.23529412, 29.41176471, 
    617.6470588, 0, 14352.94118, 0, 529.4117647, 147.0588235, 
    0, 147.0588235, 29.41176471, 29.41176471, 352.9411765, 117.6470588, 
    0, 0, 2088.235294, 134176.4706, 0, 0, 58.82352941, 470.5882353, 
    0, 0, 20176.47059, 88.23529412, 0, 0, 29.41176471, 8794.117647, 
    0, 1647.058824, 0, 0, 117.6470588, 882.3529412, 4352.941176, 
    5970.588235, 88.23529412), BT_E_14 = c(0, 69.76744186, 23.25581395, 
    953.4883721, 0, 2581.395349, 0, 0, 0, 0, 0, 69.76744186, 
    0, 0, 139.5348837, 0, 0, 5465.116279, 2930.232558, 23.25581395, 
    0, 465.1162791, 162.7906977, 23.25581395, 0, 4209.302326, 
    0, 0, 186.0465116, 116.2790698, 395.3488372, 0, 465.1162791, 
    93.02325581, 23.25581395, 0, 418.6046512, 1627.906977, 279.0697674, 
    69.76744186), BT_E_25 = c(0, 68.96551724, 103.4482759, 2310.344828, 
    0, 5758.62069, 0, 0, 0, 0, 0, 68.96551724, 0, 0, 275.862069, 
    0, 0, 8827.586207, 1827.586207, 0, 0, 241.3793103, 241.3793103, 
    0, 0, 9275.862069, 68.96551724, 0, 68.96551724, 103.4482759, 
    517.2413793, 0, 137.9310345, 34.48275862, 103.4482759, 0, 
    1068.965517, 3241.37931, 206.8965517, 34.48275862), BT_E_35 = c(0, 
    0, 0, 0, 0, 333.3333333, 0, 222.2222222, 0, 0, 0, 0, 0, 0, 
    0, 0, 888.8888889, 0, 222.2222222, 0, 111.1111111, 6111.111111, 
    111.1111111, 0, 0, 111.1111111, 35888.88889, 0, 0, 0, 540666.6667, 
    0, 111.1111111, 0, 0, 0, 0, 294222.2222, 111.1111111, 0), 
    BT_E_42 = c(0, 102.5641026, 1333.333333, 435.8974359, 0, 
    128.2051282, 0, 51.28205128, 0, 0, 0, 25.64102564, 230.7692308, 
    0, 0, 0, 0, 102.5641026, 2461.538462, 0, 25.64102564, 256.4102564, 
    0, 0, 0, 461.5384615, 51.28205128, 0, 0, 153.8461538, 1025.641026, 
    0, 820.5128205, 0, 0, 0, 153.8461538, 692.3076923, 333.3333333, 
    205.1282051)), class = "data.frame", row.names = c("Actinomyces_sp._oral_taxon_897", 
"Aggregatibacter_actinomycetemcomitans", "Aggregatibacter_aphrophilus", 
"Atopobium_parvulum", "Campylobacter_gracilis", "Candidatus_Saccharibacteria", 
"Capnocytophaga_gingivalis", "Capnocytophaga_haemolytica", "Capnocytophaga_leadbetteri", 
"Capnocytophaga_sp._ChDC_OS43", "Capnocytophaga_sputigena", "Cardiobacterium_hominis", 
"Corynebacterium_kroppenstedtii", "Desulfomicrobium_orale", "Dialister_pneumosintes", 
"Eikenella_corrodens", "Enterobacter_cloacae", "Filifactor_alocis", 
"Fusobacterium_nucleatum", "Lactobacillus_jensenii", "Lautropia_mirabilis", 
"Leptotrichia_buccalis", "Leptotrichia_sp._oral_taxon_212", "Leptotrichia_sp._oral_taxon_498", 
"Olsenella_sp._oral_taxon_807", "Parvimonas_micra", "Porphyromonas_asaccharolytica", 
"Porphyromonas_gingivalis", "Prevotella_dentalis", "Prevotella_denticola", 
"Prevotella_intermedia", "Prevotella_melaninogenica", "Prevotella_oris", 
"Prevotella_sp._oral_taxon_299", "Pseudopropionibacterium_propionicum", 
"Rothia_mucilaginosa", "Selenomonas_sputigena", "Tannerella_forsythia", 
"Tannerella_sp._oral_taxon_HOT-286", "Treponema_sp._OMZ_838"))

The output could be something like this:

https://www.researchgate.net/publication/337989444/figure/fig3/AS:840046450061337@1577294089569/The-biplot-and-scree-plot-for-the-analysis-of-the-human-gut-microbiome-data-using-both-H.jpg

I hope the community can help me out to solve this problem.

biplot ggplot2
• 2,368 views • link
written by Roland • Roland

I suggest you read the vignette of e.g. PCAtools. It should contain everything you need. By the way @all, this is R dput output so you can copy/paste it into R directly.

• 0 views • link
written by ATpoint ATpoint

Thank you ATpoint! PCAtools is a great option for solving the problem (I already found it). Although, I have trouble transferring the given example to my data. In this vignette, the example material is about gene expression analysis. It is great, but it is hard for me to decipher the code to the given metadata to make the PCA biplot. (Sorry, I'm new in R code writing).

• 0 views • link
written by Roland • Roland

OP data has multiple organisms to plot unlike limited number in the shared image. Please follow, ATpoint instructions. You would get some thing like this:

pca_plot

and scree plot like:

screeplot

• 0 views • link
written by cpad0112 cpad0112

Thanks, cpad0112. Can you share the R code with me which you use to give these plots?

• 0 views • link
written by Roland • Roland

1 answer

hi Roland,

Could you reupload your data in txt format? I think it will be good for all of us to understand the data in readable format.

As you have reference, I think PCA can be different, based on your objective for your datasets. Please visit this link https://sites.ualberta.ca/~ahamann/teaching/renr690/index.html to find more relevant examples for your dataset.

Hope it helps!

• 0 views • link
written by hakimbazol • hakimbazol

Hi hakimbazol!

This dput output can be paste into R directly as ATpoint had written earlier, therefore re-upload the data in text format is not necessary. Thank you for the link. This self-learning material is great to dig deeper into the topic.

• 0 views • link
written by Roland • Roland

Log in to answer this question.

More posts like this

No similar posts found.