PlantDeepSEA

Predicting Regulatory Effect of Genomic Variants

Statistics and Data Evaluation

Statistics of Data Used in PlantDeepSEA

Species
Reads number
 Mapping rate Duplication rate Mapped reads ( q >30) TSS enrichment Peak number AUROC
Bdistachyon_flag_leaf_1 94067702 0.97 0.41 49948552 13.45 61280 0.94
Bdistachyon_flag_leaf_2 63932496 0.96 0.34 37358896 13.10 56088 0.94
Bdistachyon_flower_1 39572726 0.95 0.58 13350236 13.73 51581 0.95
Bdistachyon_flower_2 24329952 0.96 0.55 8465850 14.75 45663 0.96
Bdistachyon_panicle_1 116923382 0.97 0.60 39842576 15.73 66431 0.95
Bdistachyon_root_1 14543028 0.47 0.15 4985401 7.47 17848 0.96
Bdistachyon_root_2 45701156 0.51 0.19 16335644 6.97 46648 0.96
Bdistachyon_young_leaf_1 10870214 0.96 0.13 8573030 9.78 32611 0.95
Bdistachyon_young_leaf_2 10291646 0.98 0.12 7935817 8.15 25245 0.95
               
MH63_flag_leaf_1 126342026 0.99 0.29 67822335 9.10 83771 0.93
MH63_flag_leaf_2 64745662 0.99 0.23 30410515 6.83 58225 0.95
MH63_flower_2c_1 85892532 0.99 0.16 57881493 7.70 91919 0.97
MH63_flower_2c_2 122252060 0.99 0.25 75131980 9.22 97974 0.98
MH63_lemma_1 74239198 0.99 0.24 48165596 10.19 92319 0.95
MH63_lemma_2 85247604 0.99 0.21 56179824 9.81 96716 0.95
MH63_panicle_1 58832756 0.98 0.44 24165690 14.84 66847 0.96
MH63_panicle_2 33309586 0.99 0.35 14620120 15.59 54404 0.97
MH63_panicle_3 51162146 0.99 0.36 21968846 15.72 62186 0.97
MH63_panicle_4 55158396 0.98 0.34 25736079 11.75 71983 0.96
MH63_panicle_5 46253072 0.99 0.31 25128785 11.95 72647 0.96
MH63_root_1 223711752 0.98 0.63 66247510 15.61 83155 0.95
MH63_root_2 68284992 0.99 0.44 31913324 14.21 52070 0.96
MH63_young_leaf_1 138938116 0.99 0.51 44111400 13.01 64920 0.95
MH63_young_leaf_2 70109302 0.99 0.43 27587710 14.21 52070 0.95
 
ZS97_flag_leaf_1
 92533216 0.98 0.28 49541050 14.77 79501 0.95
ZS97_flag_leaf_2 163670488 0.97 0.62 52962753 14.22 77310 0.95
ZS97_flower_1 101666618 0.98 0.25 65770237 12.84 109599 0.94
ZS97_flower_2 98606866 0.99 0.24 63957818 13.18 99573 0.94
ZS97_lemma_1 37055650 0.99 0.15 25899484 11.66 84317 0.96
ZS97_lemma_2 38347774 0.99 0.17 26442996 12.02 81764 0.96
ZS97_panicle_1 57620486 0.97 0.37 28078266 14.38 65456 0.96
ZS97_panicle_2 24321634 0.99 0.32 10985233 13.95 51842 0.97
ZS97_panicle_3 36435606 0.98 0.35 15184026 13.70 55265 0.96
ZS97_panicle_4 57332524 0.99 0.28 28415206 10.31 66366 0.96
ZS97_panicle_5 65002916 0.99 0.36 28751790 10.72 66250 0.96
ZS97_root_1 166991452 0.98 0.58 52947523 15.53 83093 0.95
ZS97_root_2 74643946 0.99 0.43 33806877 15.76 73842 0.95
ZS97_young_leaf_1 174433758 0.98 0.60 45111050 17.78 62008 0.95
ZS97_young_leaf_2 28235594 0.98 0.38 11624830 17.22 35404 0.96
               
Sitalica_flag_leaf_1 141996604 0.99 0.25 85826001 6.06 65251 0.95
Sitalica_flag_leaf_2 100706220 0.99 0.21 63590531 6.29 58482 0.95
Sitalica_flower_1 131086536 0.99 0.23 91347631 7.20 95685 0.95
Sitalica_flower_2 138357024 0.99 0.21 98776879 7.34 89544 0.95
Sitalica_panicle_1 177674200 0.99 0.20 125600542 6.39 101296 0.95
Sitalica_panicle_2 150142666 0.99 0.23 100278310 6.38 93938 0.95
Sitalica_root_2c_1 25735750 0.90 0.56 7811308 7.48 32704 0.98
Sitalica_young_leaf_2c_1 70067138 0.97 0.44 29928285 8.26 70194 0.97
Sitalica_young_leaf_2c_2 57397792 0.98 0.56 19724755 9.74 41994 0.96
               
Sorghum_flag_leaf_1 130334958 0.99 0.44 52409705 11.24 56465 0.98
Sorghum_flag_leaf_2 144450460 0.99 0.41 60226969 10.82 70472 0.98
Sorghum_flower_1 203189918 1.00 0.16 133020280 7.67 142580 0.97
Sorghum_flower_2 245343676 1.00 0.15 159542821 7.32 159156 0.97
Sorghum_lemma_1 95665980 1.00 0.17 65182860 8.99 104655 0.97
Sorghum_lemma_2 169146264 1.00 0.16 114027776 7.67 115553 0.97
Sorghum_panicle_bottom_1 84595194 0.98 0.32 38245112 7.69 80219 0.97
Sorghum_panicle_bottom_2 182882314 0.99 0.56 52812432 8.01 87226 0.97
Sorghum_panicle_top_1 37071094 0.85 0.28 16029710 8.17 49753 0.98
Sorghum_panicle_top_2 39628252 0.99 0.31 19196228 8.86 57743 0.98
Sorghum_root_2c_1 63639878 0.87 0.52 10997618 10.90 50778 0.99
Sorghum_root_2c_2 397222962 0.99 0.78 60817144 12.39 83349 0.97
Sorghum_young_leaf_2c_1 112887230 0.96 0.42 29067302 15.35 60549 0.98
Sorghum_young_leaf_2c_2 8595822 0.99 0.15 5260625 13.03 32671 0.99
               
Zmays_ear_big_bottom_1 92636560 1.00 0.32 40646406 10.99 79423 0.98
Zmays_ear_big_bottom_2 96513184 0.99 0.36 38565782 11.25 80683 0.98
Zmays_ear_big_top_1 96724598 1.00 0.34 40941794 10.56 78920 0.98
Zmays_ear_big_top_2 101609846 0.99 0.37 38880627 10.25 75897 0.98
Zmays_ear_small_1 91987754 0.99 0.39 36185687 11.05 78159 0.98
Zmays_ear_small_2 96011440 0.99 0.31 42669858 11.05 88322 0.98
Zmays_flag_leaf_1 95249354 1.00 0.37 43666323 8.55 52096 0.98
Zmays_flag_leaf_2 100750444 1.00 0.43 39967001 9.49 63572 0.98
Zmays_flower_1 105904206 0.99 0.48 21233571 5.37 24667 0.98
Zmays_flower_2 112607990 1.00 0.29 55306202 5.53 26295 0.99
Zmays_root_2c_1 226773650 0.50 0.29 40789638 15.08 98405 0.98
Zmays_root_2c_2 158419674 0.43 0.29 22939197 14.79 82732 0.99
Zmays_root_2c_3 159349756 1.00 0.32 80542696 11.95 90462 0.98
Zmays_tassel_bottom_1 94275220 1.00 0.30 42490103 8.87 56771 0.98
Zmays_tassel_bottom_2 86178832 1.00 0.35 35440479 9.71 62743 0.98
Zmays_tassel_top_1 180483274 1.00 0.42 71876863 9.08 70640 0.98
Zmays_young_leaf_2c_1 141333474 0.95 0.34 41835977 16.62 90765 0.99
Zmays_young_leaf_2c_2 103976508 0.95 0.29 30775805 15.40 75124 0.99
Zmays_young_leaf_2c_3 126330162 0.97 0.40 57470896 13.05 82855 0.98
 
Arabidopsis_7days_leaf_rep1
 45,225,502 99.49% 30.40% 13,461,588 12.32 25,571 0.92
Arabidopsis_7days_leaf_rep2 149,379,644 71.71% 30.00% 30,345,758 15.54 33,398 0.94
Arabidopsis_root_tip_rep1 47,952,800 98.71% 6.04% 29,813,691 5.31 17,272 0.95
Arabidopsis_root_tip_rep2 121,576,490 98.58% 8.50% 73,908,585 3.98 10,784 0.95
Arabidopsis_root_non_hair_cell_rep1 94,079,852 99.49% 10.17% 60,213,985 11.19 34,494 0.95
Arabidopsis_root_non_hair_cell_rep2 24,296,952 99.36% 5.79% 15,406,787 9.94 23,224 0.96
Arabidopsis_root_hair_cell_rep1 109,162,074 99.30% 10.40% 68,423,950 9.62 33,853 0.94
Arabidopsis_root_hair_cell_rep2 29,171,548 99.38% 6.42% 18,573,026 10.88 26,433 0.95
Arabidopsis_stem_cell_rep1 84,687,814 99.49% 21.81% 27,662,167 14.57 29,395 0.94
Arabidopsis_stem_cell_rep2 99,733,622 99.51% 20.35% 36,838,477 14.40 31,004 0.96
Arabidopsis_stem_cell_rep3 151,660,948 99.53% 25.65% 42,330,835 13.97 30,946 0.94
Arabidopsis_mesophyll_cell_rep1 112,729,514 99.14% 32.76% 12,581,426 15.35 21,455 0.95
Arabidopsis_mesophyll_cell_rep2 99,938,318 99.32% 28.60% 18,268,744 16.10 23,916 0.94
Arabidopsis_mesophyll_cell_rep3 100,129,142 99.27% 25.78% 10,905,730 16.10 21,512 0.96
Arabidopsis_mesophyll_cell_rep3 100,129,142 99.27% 25.78% 10,905,730 16.10 21,512 0.96

 

 

 

 

 

Quality Control

In order to obtain more accurate training results, we use a series of quality control measures to ensure the accuracy of the deep learning model input data.

Principal component analysis (PCA)

Figure 1. PCA plot   of  of read counts  for each library shows that biological replicates of samples in  Brachypodium distachyon (A), Sorghum bicolor (B), Setaria italica (C) and Zea mays (D). RT, root; YL, young leaf; FL, flag leaf; YP, young panicle; SP, stamen & pistil.

Enrichment of ATAC-seq reads centered at TSSs (transcription start sites)

Figure 2. Enrichment of ATAC-seq reads centered at TSSs, cut sites number is normalized by quantile normalization at regions flanking the TSS (from −3000 to +3000) of samples in  Brachypodium distachyon (A), Sorghum bicolor (B), Setaria italica (C) and Zea mays (D). RT, root; YL, young leaf; FL, flag leaf; YP, young panicle; SP, stamen & pistil.

Evaluation of Deep Learning Models

Receiver operating characteristic (ROC)

Figure 3. Receiver operating characteristic (ROC) curve for different samples of rice cultivar Zhenshan97.