Single-hidden-layer MLP genomic predictor (base R)
Usage
morie_deep_learning_genomic(
x,
y,
markers,
hidden = 16,
n_epochs = 200,
lr = 0.01,
l2 = 0.001,
seed = 0,
deterministic_seed = NULL
)Arguments
- x
Fixed-effect design (optional).
- y
Numeric response.
- markers
Genotype matrix (n x m).
Hidden units (default 16).
- n_epochs
Training epochs.
- lr
Learning rate.
- l2
L2 weight decay.
- seed
Seed.
- deterministic_seed
Optional integer; if supplied, RNG state is derived via
morie_det_rng()keyed on ("dlgen", deterministic_seed) so Py<->R streams agree on the canonical fixture. WhenNULL(default) behaviour is unchanged.
Examples
set.seed(1)
morie_deep_learning_genomic(
x = rnorm(50), y = rnorm(50),
markers = matrix(sample(0:2, 200, TRUE), 50, 4)
)
#> $estimate
#> [1] 0.02306992
#>
#> $y_hat
#> [1] -0.1309198369 0.1823161826 0.3137844154 0.3365042825 -0.1467055303
#> [6] -0.1958574161 0.3535211433 0.2486850648 -0.2422029433 -0.0061339805
#> [11] -0.1054771584 -0.0024123869 0.0817833266 -0.0975784835 0.0819257669
#> [16] 0.0817906632 0.5683571014 -0.0004156605 -0.0916686492 -0.0910024224
#> [21] 0.6072377468 -0.1735506034 0.0939894991 -0.2104725921 -0.2745777690
#> [26] -0.0762698352 -0.1963319905 -0.1979572809 -0.1596652622 0.1685448453
#> [31] 0.2673641463 -0.2947862324 -0.1769591084 -0.2049747298 0.1162378551
#> [36] 0.0789192522 0.3165452009 0.1554742177 0.2076572728 -0.2678929068
#> [41] 0.3575552040 -0.0509320889 0.2563822752 -0.1378550662 -0.1551458109
#> [46] -0.2268298460 0.1174905870 -0.0107890312 0.2856917372 -0.1988969585
#>
#> $beta
#> numeric(0)
#>
#> $W1
#> [,1] [,2] [,3] [,4] [,5] [,6]
#> [1,] -0.0508747 0.01498292 -0.4270162 -0.12390384 0.19961628 0.5660231
#> [2,] 0.2740052 0.39154143 0.5700234 -0.03916366 -0.04638319 -1.1849134
#> [3,] -0.5906332 0.51656911 -1.0058337 0.51388525 -0.12464722 0.2989972
#> [4,] 0.5497256 0.09233617 -0.2693640 0.05155039 0.35250185 0.1976694
#> [,7] [,8] [,9] [,10] [,11] [,12]
#> [1,] -0.2178671 0.4361722 -0.5878621 0.19632126 0.5663655 0.4614946
#> [2,] 0.5083224 0.8628428 -0.1378485 -0.43585537 -1.1383375 0.2267454
#> [3,] -0.1918647 0.1500493 -0.4721006 1.31395781 0.3715815 -0.1964104
#> [4,] -0.1325482 -0.2081392 -0.1258844 0.08239864 -0.6592255 0.6507856
#> [,13] [,14] [,15] [,16]
#> [1,] -0.3339488 0.4704115 0.18888965 0.06885681
#> [2,] -0.2649883 0.1984754 0.09558975 0.38559855
#> [3,] -0.5019242 0.5027962 -0.69896986 0.47678766
#> [4,] -0.3393561 -0.1978301 0.89545953 -0.02673931
#>
#> $b1
#> [1] -0.0025680574 0.0002421252 -0.0114359373 0.0274998204 -0.0044596141
#> [6] -0.0232930607 -0.0024747278 -0.0132214814 -0.0117566458 -0.0224102474
#> [11] 0.0008546500 0.0144312330 -0.0044522772 0.0121615980 -0.0007282422
#> [16] -0.0011479076
#>
#> $w2
#> [1] -0.04747545 0.26031479 -0.20561644 0.47107162 -0.11340355 0.30914930
#> [7] 0.43669710 0.15022254 0.10618931 -0.28486760 0.01015920 0.26246554
#> [13] 0.14287982 -0.08173484 -0.16218616 0.04339678
#>
#> $b2
#> [1] 0.03872849
#>
#> $loss_curve
#> [1] 0.9225911 0.9169106 0.9114704 0.9062600 0.9012696 0.8964895 0.8919107
#> [8] 0.8875243 0.8833222 0.8792962 0.8754389 0.8717430 0.8682014 0.8648076
#> [15] 0.8615551 0.8584380 0.8554503 0.8525866 0.8498415 0.8472100 0.8446871
#> [22] 0.8422682 0.8399490 0.8377250 0.8355923 0.8335470 0.8315852 0.8297036
#> [29] 0.8278986 0.8261669 0.8245056 0.8229115 0.8213819 0.8199139 0.8185050
#> [36] 0.8171527 0.8158545 0.8146082 0.8134115 0.8122625 0.8111590 0.8100991
#> [43] 0.8090810 0.8081030 0.8071633 0.8062603 0.8053925 0.8045584 0.8037565
#> [50] 0.8029856 0.8022443 0.8015314 0.8008457 0.8001860 0.7995513 0.7989405
#> [57] 0.7983526 0.7977867 0.7972418 0.7967171 0.7962117 0.7957248 0.7952557
#> [64] 0.7948035 0.7943677 0.7939475 0.7935423 0.7931515 0.7927744 0.7924105
#> [71] 0.7920593 0.7917201 0.7913927 0.7910763 0.7907707 0.7904753 0.7901898
#> [78] 0.7899137 0.7896466 0.7893882 0.7891382 0.7888961 0.7886617 0.7884346
#> [85] 0.7882146 0.7880013 0.7877946 0.7875940 0.7873994 0.7872106 0.7870273
#> [92] 0.7868493 0.7866763 0.7865082 0.7863448 0.7861858 0.7860312 0.7858807
#> [99] 0.7857342 0.7855915 0.7854525 0.7853170 0.7851848 0.7850560 0.7849302
#> [106] 0.7848075 0.7846876 0.7845705 0.7844561 0.7843442 0.7842348 0.7841277
#> [113] 0.7840230 0.7839204 0.7838199 0.7837214 0.7836249 0.7835303 0.7834374
#> [120] 0.7833463 0.7832569 0.7831691 0.7830828 0.7829980 0.7829146 0.7828326
#> [127] 0.7827519 0.7826725 0.7825944 0.7825174 0.7824416 0.7823668 0.7822932
#> [134] 0.7822205 0.7821488 0.7820781 0.7820083 0.7819394 0.7818713 0.7818041
#> [141] 0.7817376 0.7816719 0.7816070 0.7815427 0.7814792 0.7814163 0.7813540
#> [148] 0.7812924 0.7812314 0.7811709 0.7811110 0.7810516 0.7809928 0.7809344
#> [155] 0.7808765 0.7808191 0.7807622 0.7807057 0.7806496 0.7805939 0.7805387
#> [162] 0.7804838 0.7804293 0.7803751 0.7803213 0.7802678 0.7802147 0.7801618
#> [169] 0.7801093 0.7800571 0.7800051 0.7799534 0.7799020 0.7798509 0.7798000
#> [176] 0.7797494 0.7796990 0.7796488 0.7795989 0.7795491 0.7794996 0.7794503
#> [183] 0.7794012 0.7793523 0.7793035 0.7792550 0.7792066 0.7791584 0.7791103
#> [190] 0.7790625 0.7790147 0.7789672 0.7789197 0.7788725 0.7788253 0.7787783
#> [197] 0.7787315 0.7786847 0.7786381 0.7785916
#>
#> $se
#> [1] 0.8823521
#>
#> $n
#> [1] 50
#>
#> $method
#> [1] "MLP-1H base-R"
#>