PCA loading plot
rosanmar opened this issue · comments
Hi, I would like to know if it is possible to obtain the loading plot in the PCA analysis. I can only get the Score plot. It would help me a lot to have a more accurate view of the data. Thanks!
You can easily access rotation scores and feature loadings in the mvaresults object that you get out of mva
mvaresults <- mva(data_normalized, measure = "Area", method = "PCA")
head(mvaresults$loadings)
#> p1 p2 p3 p4 p5 p6
#> 1 -0.04486626 -0.0233747391 -0.02287171 -0.0001824736 -0.11510403 0.10940792
#> 2 -0.06824449 -0.0041885108 -0.10580046 -0.0271234534 -0.05546431 0.04938349
#> 3 -0.05685793 0.0005886418 -0.08676486 -0.0105830023 -0.05827554 0.09475925
#> 4 -0.07189545 0.0122874373 -0.08121652 -0.0047797565 -0.07815611 0.08942695
#> 5 -0.05769839 0.0191061415 -0.06930820 0.0074809106 -0.12747176 0.06469317
#> 6 -0.06703077 -0.0172104696 -0.08123090 -0.0222336836 -0.02194360 0.14513379
#> p7 p8 p9 p10 p11 p12
#> 1 0.041422864 -0.123401876 0.062488158 -0.07354506 -0.072472752 0.06127880
#> 2 -0.002641356 0.024756163 -0.027674854 0.03606265 -0.008551648 0.10877558
#> 3 -0.002939514 -0.024244310 0.022280400 0.02903706 -0.028059333 0.04165076
#> 4 0.004178734 0.010924320 -0.020351285 0.04147909 -0.002295194 0.06791264
#> 5 0.042523774 -0.009729941 -0.017658042 0.07323154 -0.080672000 0.04562555
#> 6 0.051002617 -0.032604989 0.001773531 0.01593442 -0.005125500 0.01516734
#> p13 p14 p15 p16 p17 p18
#> 1 -0.101870593 0.09815173 0.141787153 0.034732585 0.059012853 0.03850636
#> 2 0.001371712 0.02484810 0.065049476 0.028121947 -0.015897704 -0.00527741
#> 3 -0.066706070 -0.04278449 -0.092226897 0.054104472 -0.154535843 0.05144231
#> 4 -0.043459893 0.01568352 -0.001005736 0.008276927 -0.004047336 -0.02446107
#> 5 -0.029622134 0.02087661 0.047224964 -0.126033033 0.025858293 -0.11239465
#> 6 0.056604628 -0.02346504 -0.058938814 0.031138657 -0.044391858 -0.04313277
#> p19 p20 p21 p22 p23 p24
#> 1 0.08735057 -0.023171998 0.1327614587 0.143515538 0.017939290 0.022034086
#> 2 0.11714317 0.002029921 0.0863722055 -0.013607537 0.007089923 0.013205412
#> 3 -0.07283001 0.091112524 -0.0849109083 0.143208236 0.009746848 0.012963286
#> 4 0.04687795 -0.012546376 0.0733380260 -0.031099794 -0.002185009 0.020077987
#> 5 0.05266569 -0.019254358 0.0936993506 0.051854809 0.044529168 -0.051850745
#> 6 0.01738002 0.034460499 0.0006764378 0.000419968 -0.008940267 -0.003577616
#> p25 p26 p27 p28 p29 p30
#> 1 -0.08018621 -0.185873658 0.071979006 -0.1797587379 -0.01475394 -0.0898808441
#> 2 0.05753981 0.078977584 -0.001519507 -0.0001887463 0.03304144 0.0316588592
#> 3 -0.13430893 -0.120268941 0.065336383 0.0694995333 -0.04210952 -0.1065655993
#> 4 -0.01315190 0.029543886 -0.030397421 0.0164037116 0.02957865 0.0004006193
#> 5 -0.04443170 0.062118642 -0.111382037 -0.0002494434 -0.14720892 -0.1444244667
#> 6 -0.03688617 -0.008309826 -0.026150740 -0.0183052204 0.01578169 -0.0076053224
#> p31 p32 p33 p34 p35 p36
#> 1 0.19680094 -0.073313211 0.143210303 0.11575151 0.079779108 -0.12212705
#> 2 -0.01716728 0.015515933 -0.006823624 0.01058728 0.067893446 0.00434836
#> 3 0.20716507 0.151799833 -0.048203747 0.02706126 -0.086087612 -0.02546880
#> 4 0.05332261 -0.002234615 -0.002740621 0.02195654 0.038125575 0.03832301
#> 5 -0.12189552 -0.111593044 0.100929223 -0.04682216 0.122059894 -0.11715653
#> 6 0.04013675 -0.013802894 -0.046485265 0.02199375 -0.008693271 -0.01381856
#> p37 p38 p39 p40 p41
#> 1 -0.064761343 0.0464734042 -0.018826614 -0.1625078046 0.022150272
#> 2 0.020340294 -0.0086062917 -0.013022199 0.0227267812 -0.013628586
#> 3 0.089553876 0.2392170503 0.141294601 0.0507552024 -0.004970093
#> 4 0.026502505 0.0009704052 -0.005765791 0.0079784152 -0.002567018
#> 5 0.071363136 -0.0472534963 -0.196216872 -0.0006502088 0.093888513
#> 6 0.002937943 -0.0624690809 -0.014324027 -0.0249568821 -0.010661841
#> p42 p43 p44 p45 p46 p47
#> 1 0.061575593 0.06371584 0.002368088 0.05398453 -0.04479277 0.07029665
#> 2 -0.040983679 0.04660136 0.031113107 -0.04166941 0.05449903 0.06638949
#> 3 -0.007192564 -0.13055651 -0.050809408 0.05753822 -0.10570869 0.09074203
#> 4 0.023666501 -0.10090235 0.145264101 0.01842521 0.04465017 -0.07046376
#> 5 -0.041274547 0.05219034 -0.113364519 -0.09273369 -0.01139080 0.06016911
#> 6 -0.097450820 0.12884173 0.042805271 0.03738526 -0.01062511 -0.01198347
#> p48 p49 p50 p51 p52 p53
#> 1 -0.039157610 -0.018659476 0.025656832 0.015796183 -0.03123130 0.10398039
#> 2 0.076567358 0.100391995 0.030225296 -0.031444802 0.07215529 0.03700429
#> 3 0.140156318 0.146798496 -0.000348664 0.208762054 0.02683236 0.02217379
#> 4 0.009997167 0.031175316 -0.058012141 -0.081188864 0.03573016 0.06084736
#> 5 0.016585190 -0.007281378 -0.033409371 -0.003697608 0.07778175 0.08738922
#> 6 -0.078560315 -0.048563258 -0.058780513 -0.008313705 0.10416144 -0.03026025
#> p54 p55 p56
#> 1 -0.022447268 0.029989331 1.677175e-08
#> 2 -0.102920138 -0.003963734 3.789119e-08
#> 3 -0.081605517 -0.052167020 1.099639e-08
#> 4 0.012820158 -0.013551350 3.090635e-08
#> 5 0.039494155 0.092428200 3.100631e-08
#> 6 -0.004072756 0.037759084 -2.787232e-08
head(mvaresults$scores)
#> p1 p2 p3 p4 p5 p6 p7
#> S1A -3.389052 -9.783666 2.170264 -0.1381608 0.3898506 -7.547779 1.7744696
#> S2A -8.617481 -9.519327 2.155308 -2.1006989 0.1635756 -5.458006 0.2970577
#> S3A -8.093241 -6.082544 3.648055 -1.3647316 1.9769127 2.200922 -4.3734197
#> S4A -11.230227 -11.793822 2.828469 1.2301022 -1.9791670 2.846245 4.1847916
#> S5A -11.046872 -10.568540 1.614010 -2.9355782 0.9754839 -2.248875 2.6948012
#> S6A -11.217205 -7.553303 4.539788 1.4530670 -2.2743519 5.027765 4.6714424
#> p8 p9 p10 p11 p12 p13
#> S1A -0.5527409 1.609809 -1.0974229 1.7643018 -1.0622011 3.9603446
#> S2A -1.3562399 1.020424 1.1821638 -0.2822290 -0.8105609 0.5022525
#> S3A 0.4786930 7.505775 -3.0457816 1.8156550 2.9885354 0.5422828
#> S4A 2.6243623 -5.054472 -1.9918639 -0.4520386 1.4328927 1.3878084
#> S5A -0.3135096 1.551402 -0.3997732 1.1751316 -1.7143864 -4.3496838
#> S6A 5.6468546 -2.640643 -0.9740625 -2.5520324 -1.3991995 0.2086560
#> p14 p15 p16 p17 p18 p19
#> S1A -0.98753330 0.18144563 -2.3919224 0.03335976 -0.0549729 2.9940190
#> S2A -2.57110796 -1.31631840 -0.5033193 0.57023702 -1.6670968 0.6620278
#> S3A 0.08387708 -1.03239241 -1.3562597 -0.41041365 4.7716781 -1.4251001
#> S4A -0.34734940 0.06740679 -2.2907055 -1.93567801 0.8966249 -1.3748868
#> S5A -0.38734848 -1.12376955 1.1327551 0.54339140 -0.9577151 -1.5715385
#> S6A -1.87416718 -1.52561389 -0.5245885 -0.92741859 0.4059875 -1.1882350
#> p20 p21 p22 p23 p24 p25
#> S1A -0.9453414 1.8981966 -1.6873041 0.5985171 -1.15171465 -0.13250058
#> S2A -0.1947738 -1.2777145 0.1143270 -0.2617331 -0.82949445 0.06194476
#> S3A -1.3198005 -0.7707923 -1.0298894 0.2215337 0.53882718 -0.58213914
#> S4A -0.9966085 -1.4198805 0.7901539 0.2433820 1.42759416 -0.31621381
#> S5A 1.0288627 -0.6159911 0.7495257 0.2617134 0.48701917 1.13458096
#> S6A 0.1532440 2.1799007 0.1015316 -0.5883413 0.02968717 -0.03153017
#> p26 p27 p28 p29 p30 p31
#> S1A -0.83531219 1.1782938 0.46563737 0.9595102 0.42808437 -0.4474506
#> S2A 1.45780695 -0.3339886 -0.67661162 -1.2998638 0.05393809 -0.2947462
#> S3A 1.17238389 -0.3722343 0.79027247 0.9882649 0.15908415 0.3004675
#> S4A -0.02359825 0.1263715 -1.59178275 -0.8888971 1.19893748 -0.9644964
#> S5A 0.55233896 0.3443943 -0.01768317 -0.7205369 0.60387511 -0.5576576
#> S6A 0.13671744 0.6636323 1.23199624 0.7048083 -1.93376292 -0.7303524
#> p32 p33 p34 p35 p36 p37
#> S1A -0.5154476 -0.8254394 -0.1644401 1.0272981 0.48768823 0.06574612
#> S2A 0.3443014 1.1049848 0.8609025 -0.6980224 -0.75710563 0.05084846
#> S3A 0.7301498 0.7323349 -0.4600249 -0.6966259 0.06456891 0.14305978
#> S4A -0.2872269 -0.2851235 0.7056463 0.1619820 -0.21096218 -0.68311746
#> S5A 0.5323703 -1.6969022 -0.1499577 -1.4140969 0.14364860 -0.40110845
#> S6A 0.6329406 0.8282167 -0.9095093 0.9184934 -0.36437165 0.35065205
#> p38 p39 p40 p41 p42 p43
#> S1A 0.2705323 0.02425644 0.17021476 0.98507785 0.17433633 -0.13801865
#> S2A 1.0515692 -0.66412382 -0.64986922 0.01307083 0.29890552 0.14720659
#> S3A -0.5121970 -0.09959737 -0.02354705 0.43273435 0.07568789 0.01727799
#> S4A -0.5119569 0.18028081 0.14333264 0.34905603 0.55680782 -0.09145678
#> S5A -0.1503646 -0.36463465 -0.31910584 0.85898450 -1.12895306 0.11878245
#> S6A 0.7249559 0.06383262 0.03433319 -0.35261103 -0.64743849 0.35302887
#> p44 p45 p46 p47 p48 p49
#> S1A -0.4285355 -0.14164237 -0.5056658 -0.36088144 -0.13365404 -0.072973728
#> S2A 1.2974050 0.63204517 0.2729308 0.18178705 -1.47856026 0.307450676
#> S3A 0.1129909 -0.06578999 -0.1101750 0.08656873 -0.23771047 -0.178336149
#> S4A -0.8569712 -0.21693871 0.4989003 -0.95013898 0.18870139 0.391694852
#> S5A -0.6176003 -0.53750168 0.2430985 0.69075635 0.24233823 -0.367584487
#> S6A 0.2210085 0.44719414 -0.3317279 0.95764767 -0.03981357 0.002108038
#> p50 p51 p52 p53 p54 p55
#> S1A -0.5130158 -0.010960726 0.04925003 0.7524236 0.109834104 0.12430692
#> S2A -0.2225566 -0.220043048 0.19979093 -0.4599694 -0.284382492 0.06240105
#> S3A 0.3530716 0.003229078 -0.02687068 -0.2243258 0.109630101 -0.10789731
#> S4A -0.2258803 -0.327339574 0.09504706 -0.5460712 -0.115620791 0.09043329
#> S5A 0.0389916 0.261059074 -0.34763108 0.8268310 0.340989129 0.49375362
#> S6A 0.2948872 -0.033388944 0.10736295 0.1780890 -0.006969587 -0.18751794
#> p56
#> S1A -1.406289e-07
#> S2A -1.406289e-07
#> S3A -1.406289e-07
#> S4A -1.406289e-07
#> S5A -1.406289e-07
#> S6A -1.406289e-07Created on 2022-10-10 by the reprex package (v2.0.1)
Thank you !!!, but is it possible to obtain the PCA loading plots (the visualization), as is done with OPLS or OPLS-DA (plot_mva_loadings(mvaresults, color_by="Class", top.n=10))?
Sorry I didn't realise you're after plotting them. For now, you can use lipidr internal functions to help you do that. I'll consider adding support in the near future.
library(ggplot2)
#> Warning: package 'ggplot2' was built under R version 4.1.1
mvaresults <- mva(data_normalized, measure = "Area", method = "PCA")
m = lipidr:::.get_loading_matrix(mvaresults, components = c(1,2), color_by = "Class")
ggplot(m[[1]], aes(p1, p2, color=Class)) + geom_point()
Created on 2022-10-11 by the reprex package (v2.0.1)
It works! :) thanks!