# Load libraries
library(tidyverse)
## Warning: package 'ggplot2' was built under R version 4.5.2
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.6.0
## ✔ ggplot2 4.0.1 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.2.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(ggridges)
# Load the dataset
MET <- read.csv("/Users/maxineharlemon/DrMax_Biology/Using_R_for_biostatistics_Datasets/METABRIC_RNA_Mutation.csv")
# Inspect column names to confirm variables
colnames(MET)
## [1] "patient_id" "age_at_diagnosis"
## [3] "type_of_breast_surgery" "cancer_type"
## [5] "cancer_type_detailed" "cellularity"
## [7] "chemotherapy" "pam50_._claudin.low_subtype"
## [9] "cohort" "er_status_measured_by_ihc"
## [11] "er_status" "neoplasm_histologic_grade"
## [13] "her2_status_measured_by_snp6" "her2_status"
## [15] "tumor_other_histologic_subtype" "hormone_therapy"
## [17] "inferred_menopausal_state" "integrative_cluster"
## [19] "primary_tumor_laterality" "lymph_nodes_examined_positive"
## [21] "mutation_count" "nottingham_prognostic_index"
## [23] "oncotree_code" "overall_survival_months"
## [25] "overall_survival" "pr_status"
## [27] "radio_therapy" "X3.gene_classifier_subtype"
## [29] "tumor_size" "tumor_stage"
## [31] "death_from_cancer" "brca1"
## [33] "brca2" "palb2"
## [35] "pten" "tp53"
## [37] "atm" "cdh1"
## [39] "chek2" "nbn"
## [41] "nf1" "stk11"
## [43] "bard1" "mlh1"
## [45] "msh2" "msh6"
## [47] "pms2" "epcam"
## [49] "rad51c" "rad51d"
## [51] "rad50" "rb1"
## [53] "rbl1" "rbl2"
## [55] "ccna1" "ccnb1"
## [57] "cdk1" "ccne1"
## [59] "cdk2" "cdc25a"
## [61] "ccnd1" "cdk4"
## [63] "cdk6" "ccnd2"
## [65] "cdkn2a" "cdkn2b"
## [67] "myc" "cdkn1a"
## [69] "cdkn1b" "e2f1"
## [71] "e2f2" "e2f3"
## [73] "e2f4" "e2f5"
## [75] "e2f6" "e2f7"
## [77] "e2f8" "src"
## [79] "jak1" "jak2"
## [81] "stat1" "stat2"
## [83] "stat3" "stat5a"
## [85] "stat5b" "mdm2"
## [87] "tp53bp1" "adam10"
## [89] "adam17" "aph1a"
## [91] "aph1b" "arrdc1"
## [93] "cir1" "ctbp1"
## [95] "ctbp2" "cul1"
## [97] "dll1" "dll3"
## [99] "dll4" "dtx1"
## [101] "dtx2" "dtx3"
## [103] "dtx4" "ep300"
## [105] "fbxw7" "hdac1"
## [107] "hdac2" "hes1"
## [109] "hes5" "heyl"
## [111] "itch" "jag1"
## [113] "jag2" "kdm5a"
## [115] "lfng" "maml1"
## [117] "maml2" "maml3"
## [119] "ncor2" "ncstn"
## [121] "notch1" "notch2"
## [123] "notch3" "nrarp"
## [125] "numb" "numbl"
## [127] "psen1" "psen2"
## [129] "psenen" "rbpj"
## [131] "rbpjl" "rfng"
## [133] "snw1" "spen"
## [135] "hes2" "hes4"
## [137] "hes7" "hey1"
## [139] "hey2" "acvr1"
## [141] "acvr1b" "acvr1c"
## [143] "acvr2a" "acvr2b"
## [145] "acvrl1" "akt1"
## [147] "akt1s1" "akt2"
## [149] "apaf1" "arl11"
## [151] "atr" "aurka"
## [153] "bad" "bcl2"
## [155] "bcl2l1" "bmp10"
## [157] "bmp15" "bmp2"
## [159] "bmp3" "bmp4"
## [161] "bmp5" "bmp6"
## [163] "bmp7" "bmpr1a"
## [165] "bmpr1b" "bmpr2"
## [167] "braf" "casp10"
## [169] "casp3" "casp6"
## [171] "casp7" "casp8"
## [173] "casp9" "chek1"
## [175] "csf1" "csf1r"
## [177] "cxcl8" "cxcr1"
## [179] "cxcr2" "dab2"
## [181] "diras3" "dlec1"
## [183] "dph1" "egfr"
## [185] "eif4e" "eif4ebp1"
## [187] "eif5a2" "erbb2"
## [189] "erbb3" "erbb4"
## [191] "fas" "fgf1"
## [193] "fgfr1" "folr1"
## [195] "folr2" "folr3"
## [197] "foxo1" "foxo3"
## [199] "gdf11" "gdf2"
## [201] "gsk3b" "hif1a"
## [203] "hla.g" "hras"
## [205] "igf1" "igf1r"
## [207] "inha" "inhba"
## [209] "inhbc" "itgav"
## [211] "itgb3" "izumo1r"
## [213] "kdr" "kit"
## [215] "kras" "map2k1"
## [217] "map2k2" "map2k3"
## [219] "map2k4" "map2k5"
## [221] "map3k1" "map3k3"
## [223] "map3k4" "map3k5"
## [225] "mapk1" "mapk12"
## [227] "mapk14" "mapk3"
## [229] "mapk4" "mapk6"
## [231] "mapk7" "mapk8"
## [233] "mapk9" "mdc1"
## [235] "mlst8" "mmp1"
## [237] "mmp10" "mmp11"
## [239] "mmp12" "mmp13"
## [241] "mmp14" "mmp15"
## [243] "mmp16" "mmp17"
## [245] "mmp19" "mmp2"
## [247] "mmp21" "mmp23b"
## [249] "mmp24" "mmp25"
## [251] "mmp26" "mmp27"
## [253] "mmp28" "mmp3"
## [255] "mmp7" "mmp9"
## [257] "mtor" "nfkb1"
## [259] "nfkb2" "opcml"
## [261] "pdgfa" "pdgfb"
## [263] "pdgfra" "pdgfrb"
## [265] "pdpk1" "peg3"
## [267] "pik3ca" "pik3r1"
## [269] "pik3r2" "plagl1"
## [271] "ptk2" "rab25"
## [273] "rad51" "raf1"
## [275] "rassf1" "rheb"
## [277] "rictor" "rps6"
## [279] "rps6ka1" "rps6ka2"
## [281] "rps6kb1" "rps6kb2"
## [283] "rptor" "slc19a1"
## [285] "smad1" "smad2"
## [287] "smad3" "smad4"
## [289] "smad5" "smad6"
## [291] "smad7" "smad9"
## [293] "sptbn1" "terc"
## [295] "tert" "tgfb1"
## [297] "tgfb2" "tgfb3"
## [299] "tgfbr1" "tgfbr2"
## [301] "tgfbr3" "tsc1"
## [303] "tsc2" "vegfa"
## [305] "vegfb" "wfdc2"
## [307] "wwox" "zfyve9"
## [309] "arid1a" "arid1b"
## [311] "cbfb" "gata3"
## [313] "kmt2c" "kmt2d"
## [315] "myh9" "ncor1"
## [317] "pde4dip" "ptprd"
## [319] "ros1" "runx1"
## [321] "tbx3" "abcb1"
## [323] "abcb11" "abcc1"
## [325] "abcc10" "bbc3"
## [327] "bmf" "cyp2c8"
## [329] "cyp3a4" "fgf2"
## [331] "fn1" "map2"
## [333] "map4" "mapt"
## [335] "nr1i2" "slco1b3"
## [337] "tubb1" "tubb4a"
## [339] "tubb4b" "twist1"
## [341] "adgra2" "afdn"
## [343] "aff2" "agmo"
## [345] "agtr2" "ahnak"
## [347] "ahnak2" "akap9"
## [349] "alk" "apc"
## [351] "arid2" "arid5b"
## [353] "asxl1" "asxl2"
## [355] "bap1" "bcas3"
## [357] "birc6" "cacna2d3"
## [359] "ccnd3" "chd1"
## [361] "clk3" "clrn2"
## [363] "col12a1" "col22a1"
## [365] "col6a3" "ctcf"
## [367] "ctnna1" "ctnna3"
## [369] "dnah11" "dnah2"
## [371] "dnah5" "dtwd2"
## [373] "fam20c" "fanca"
## [375] "fancd2" "flt3"
## [377] "foxp1" "frmd3"
## [379] "gh1" "gldc"
## [381] "gpr32" "gps2"
## [383] "hdac9" "herc2"
## [385] "hist1h2bc" "kdm3a"
## [387] "kdm6a" "klrg1"
## [389] "l1cam" "lama2"
## [391] "lamb3" "large1"
## [393] "ldlrap1" "lifr"
## [395] "lipi" "magea8"
## [397] "map3k10" "map3k13"
## [399] "men1" "mtap"
## [401] "muc16" "myo1a"
## [403] "myo3a" "ncoa3"
## [405] "nek1" "nf2"
## [407] "npnt" "nr2f1"
## [409] "nr3c1" "nras"
## [411] "nrg3" "nt5e"
## [413] "or6a2" "palld"
## [415] "pbrm1" "ppp2cb"
## [417] "ppp2r2a" "prkacg"
## [419] "prkce" "prkcq"
## [421] "prkcz" "prkg1"
## [423] "prps2" "prr16"
## [425] "ptpn22" "ptprm"
## [427] "rasgef1b" "rpgr"
## [429] "ryr2" "sbno1"
## [431] "setd1a" "setd2"
## [433] "setdb1" "sf3b1"
## [435] "sgcd" "shank2"
## [437] "siah1" "sik1"
## [439] "sik2" "smarcb1"
## [441] "smarcc1" "smarcc2"
## [443] "smarcd1" "spaca1"
## [445] "stab2" "stmn2"
## [447] "syne1" "taf1"
## [449] "taf4b" "tbl1xr1"
## [451] "tg" "thada"
## [453] "thsd7a" "ttyh1"
## [455] "ubr5" "ush2a"
## [457] "usp9x" "utrn"
## [459] "zfp36l1" "ackr3"
## [461] "akr1c1" "akr1c2"
## [463] "akr1c3" "akr1c4"
## [465] "akt3" "ar"
## [467] "bche" "cdk8"
## [469] "cdkn2c" "cyb5a"
## [471] "cyp11a1" "cyp11b2"
## [473] "cyp17a1" "cyp19a1"
## [475] "cyp21a2" "cyp3a43"
## [477] "cyp3a5" "cyp3a7"
## [479] "ddc" "hes6"
## [481] "hsd17b1" "hsd17b10"
## [483] "hsd17b11" "hsd17b12"
## [485] "hsd17b13" "hsd17b14"
## [487] "hsd17b2" "hsd17b3"
## [489] "hsd17b4" "hsd17b6"
## [491] "hsd17b7" "hsd17b8"
## [493] "hsd3b1" "hsd3b2"
## [495] "hsd3b7" "mecom"
## [497] "met" "ncoa2"
## [499] "nrip1" "pik3r3"
## [501] "prkci" "prkd1"
## [503] "ran" "rdh5"
## [505] "sdc4" "serpini1"
## [507] "shbg" "slc29a1"
## [509] "sox9" "spry2"
## [511] "srd5a1" "srd5a2"
## [513] "srd5a3" "st7"
## [515] "star" "tnk2"
## [517] "tulp4" "ugt2b15"
## [519] "ugt2b17" "ugt2b7"
## [521] "pik3ca_mut" "tp53_mut"
## [523] "muc16_mut" "ahnak2_mut"
## [525] "kmt2c_mut" "syne1_mut"
## [527] "gata3_mut" "map3k1_mut"
## [529] "ahnak_mut" "dnah11_mut"
## [531] "cdh1_mut" "dnah2_mut"
## [533] "kmt2d_mut" "ush2a_mut"
## [535] "ryr2_mut" "dnah5_mut"
## [537] "herc2_mut" "pde4dip_mut"
## [539] "akap9_mut" "tg_mut"
## [541] "birc6_mut" "utrn_mut"
## [543] "tbx3_mut" "col6a3_mut"
## [545] "arid1a_mut" "lama2_mut"
## [547] "notch1_mut" "cbfb_mut"
## [549] "ncor2_mut" "col12a1_mut"
## [551] "col22a1_mut" "pten_mut"
## [553] "akt1_mut" "atr_mut"
## [555] "thada_mut" "ncor1_mut"
## [557] "stab2_mut" "myh9_mut"
## [559] "runx1_mut" "nf1_mut"
## [561] "map2k4_mut" "ros1_mut"
## [563] "lamb3_mut" "arid1b_mut"
## [565] "erbb2_mut" "sf3b1_mut"
## [567] "shank2_mut" "ep300_mut"
## [569] "ptprd_mut" "usp9x_mut"
## [571] "setd2_mut" "setd1a_mut"
## [573] "thsd7a_mut" "afdn_mut"
## [575] "erbb3_mut" "rb1_mut"
## [577] "myo1a_mut" "alk_mut"
## [579] "fanca_mut" "adgra2_mut"
## [581] "ubr5_mut" "pik3r1_mut"
## [583] "myo3a_mut" "asxl2_mut"
## [585] "apc_mut" "ctcf_mut"
## [587] "asxl1_mut" "fancd2_mut"
## [589] "taf1_mut" "kdm6a_mut"
## [591] "ctnna3_mut" "brca1_mut"
## [593] "ptprm_mut" "foxo3_mut"
## [595] "usp28_mut" "gldc_mut"
## [597] "brca2_mut" "cacna2d3_mut"
## [599] "arid2_mut" "aff2_mut"
## [601] "lifr_mut" "sbno1_mut"
## [603] "kdm3a_mut" "ncoa3_mut"
## [605] "bap1_mut" "l1cam_mut"
## [607] "pbrm1_mut" "chd1_mut"
## [609] "jak1_mut" "setdb1_mut"
## [611] "fam20c_mut" "arid5b_mut"
## [613] "egfr_mut" "map3k10_mut"
## [615] "smarcc2_mut" "erbb4_mut"
## [617] "npnt_mut" "nek1_mut"
## [619] "agmo_mut" "zfp36l1_mut"
## [621] "smad4_mut" "sik1_mut"
## [623] "casp8_mut" "prkcq_mut"
## [625] "smarcc1_mut" "palld_mut"
## [627] "dcaf4l2_mut" "bcas3_mut"
## [629] "cdkn1b_mut" "gps2_mut"
## [631] "men1_mut" "stk11_mut"
## [633] "sik2_mut" "ptpn22_mut"
## [635] "brip1_mut" "flt3_mut"
## [637] "nrg3_mut" "fbxw7_mut"
## [639] "ttyh1_mut" "taf4b_mut"
## [641] "or6a2_mut" "map3k13_mut"
## [643] "hdac9_mut" "prkacg_mut"
## [645] "rpgr_mut" "large1_mut"
## [647] "foxp1_mut" "clk3_mut"
## [649] "prkcz_mut" "lipi_mut"
## [651] "ppp2r2a_mut" "prkce_mut"
## [653] "gh1_mut" "gpr32_mut"
## [655] "kras_mut" "nf2_mut"
## [657] "chek2_mut" "ldlrap1_mut"
## [659] "clrn2_mut" "acvrl1_mut"
## [661] "agtr2_mut" "cdkn2a_mut"
## [663] "ctnna1_mut" "magea8_mut"
## [665] "prr16_mut" "dtwd2_mut"
## [667] "akt2_mut" "braf_mut"
## [669] "foxo1_mut" "nt5e_mut"
## [671] "ccnd3_mut" "nr3c1_mut"
## [673] "prkg1_mut" "tbl1xr1_mut"
## [675] "frmd3_mut" "smad2_mut"
## [677] "sgcd_mut" "spaca1_mut"
## [679] "rasgef1b_mut" "hist1h2bc_mut"
## [681] "nr2f1_mut" "klrg1_mut"
## [683] "mbl2_mut" "mtap_mut"
## [685] "ppp2cb_mut" "smarcd1_mut"
## [687] "nras_mut" "ndfip1_mut"
## [689] "hras_mut" "prps2_mut"
## [691] "smarcb1_mut" "stmn2_mut"
## [693] "siah1_mut"
# Convert categorical variables to factors
MET$cellularity <- as.factor(MET$cellularity)
MET$mutation_status <- as.factor(MET$brca1_mut)
#Ridge Plot
ggplot(MET, aes(x = brca1, y = factor(cellularity), fill = factor(cellularity))) +
geom_density_ridges(alpha = 0.7, color = "white") +
labs(
title = "Distribution of BRCA1 Expression by Tumor Cellularity",
x = "BRCA1 Expression",
y = "Cellularity"
) +
theme_ridges() +
theme(
legend.position = "none",
plot.title = element_text(hjust = 0.5, face = "bold")
)
## Picking joint bandwidth of 0.281
#Faceted Ridge plot
ggplot(MET, aes(x = brca1, y = cellularity, fill = cellularity)) +
geom_density_ridges(alpha = 0.7, color = "white") +
stat_summary(fun = median, geom = "point", color = "black", size = 2) +
facet_wrap(~ mutation_status) +
labs(
title = "Distribution of BRCA1 Expression by Cellularity and Mutation Status",
x = "BRCA1 Expression",
y = "Tumor Cellularity"
) +
theme_ridges() +
theme(plot.title = element_text(hjust = 0.5, face = "bold"))
## Picking joint bandwidth of 0.282
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of NaN
## Picking joint bandwidth of 0.503
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
## Warning in FUN(X[[i]], ...): no non-missing arguments to max; returning -Inf
#one way anova
library(tidyverse)
library(effectsize)
## Warning: package 'effectsize' was built under R version 4.5.2
library(ggpubr)
anova_model <- aov(brca1 ~ cellularity, data = MET)
TukeyHSD(anova_model)
## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = brca1 ~ cellularity, data = MET)
##
## $cellularity
## diff lwr upr p adj
## High- 0.221130375 -0.135430320 0.57769107 0.3818717
## Low- -0.198194537 -0.588939601 0.19255053 0.5603116
## Moderate- 0.004621331 -0.355034873 0.36427754 0.9999870
## Low-High -0.419324912 -0.617752744 -0.22089708 0.0000004
## Moderate-High -0.216509044 -0.343175872 -0.08984222 0.0000689
## Moderate-Low 0.202815868 -0.001122016 0.40675375 0.0519021
#Linear Models with covariate
lm_model <- lm(brca1 ~ cellularity + age_at_diagnosis + brca1_mut, data = MET)
summary(lm_model)
##
## Call:
## lm(formula = brca1 ~ cellularity + age_at_diagnosis + brca1_mut,
## data = MET)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.5040 -0.6675 -0.0798 0.5274 4.6402
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.611338 0.169404 -3.609 0.000316 ***
## cellularityHigh 0.206705 0.137947 1.498 0.134188
## cellularityLow -0.194618 0.151209 -1.287 0.198226
## cellularityModerate -0.017717 0.139108 -0.127 0.898670
## age_at_diagnosis 0.008904 0.001771 5.028 5.44e-07 ***
## brca1_mutC305S -0.229319 0.985378 -0.233 0.816003
## brca1_mutD1692N -0.771559 0.986630 -0.782 0.434305
## brca1_mutD420G -0.206567 0.985231 -0.210 0.833953
## brca1_mutD560Efs*6 -0.816604 0.987019 -0.827 0.408148
## brca1_mutE1287K -0.160619 0.985103 -0.163 0.870499
## brca1_mutE143K -0.913498 0.987026 -0.926 0.354823
## brca1_mutE1494Kfs*11 -1.514440 0.984890 -1.538 0.124298
## brca1_mutE1836K -1.028153 0.985637 -1.043 0.297021
## brca1_mutE391K -0.650329 0.985027 -0.660 0.509198
## brca1_mutE880Rfs*13 -0.823881 0.986516 -0.835 0.403745
## brca1_mutE914K 1.085910 0.984931 1.103 0.270377
## brca1_mutF709Sfs*29 -1.285412 0.985892 -1.304 0.192461
## brca1_mutG1087E 1.331524 0.985197 1.352 0.176690
## brca1_mutI171M 0.374069 0.986299 0.379 0.704534
## brca1_mutI216S -0.360132 0.985278 -0.366 0.714770
## brca1_mutI946V -0.696910 0.985235 -0.707 0.479435
## brca1_mutK1667Qfs*11 -1.267960 0.985552 -1.287 0.198412
## brca1_mutL1439F -0.043258 0.985210 -0.044 0.964983
## brca1_mutL502Sfs*2 -0.260279 0.984905 -0.264 0.791602
## brca1_mutM1827L -0.255456 0.985240 -0.259 0.795445
## brca1_mutQ202Kfs*32 -1.341011 0.984912 -1.362 0.173503
## brca1_mutR1074T -0.206311 0.985669 -0.209 0.834228
## brca1_mutR1737T -0.690224 0.986205 -0.700 0.484091
## brca1_mutR613K -1.022885 0.984988 -1.038 0.299184
## brca1_mutS1266T -0.456964 0.986872 -0.463 0.643388
## brca1_mutS153R 0.143552 0.985107 0.146 0.884156
## brca1_mutS1551C -1.787396 0.985759 -1.813 0.069959 .
## brca1_mutS282* -0.893809 0.984981 -0.907 0.364293
## brca1_mutT150Pfs*13 -0.843435 0.985201 -0.856 0.392050
## brca1_mutV1654Cfs*4 -0.924792 0.986002 -0.938 0.348407
## brca1_mutV452A -0.263758 0.985895 -0.268 0.789089
## brca1_mutW372R 0.050171 0.985098 0.051 0.959387
## brca1_mutX1453_splice -0.048254 0.985317 -0.049 0.960946
## brca1_mutX1663_splice -0.915226 0.985054 -0.929 0.352951
## brca1_mutX1760_splice 3.332169 0.985794 3.380 0.000739 ***
## brca1_mutY1127H 0.079797 0.696803 0.115 0.908839
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.9844 on 1863 degrees of freedom
## Multiple R-squared: 0.05192, Adjusted R-squared: 0.03156
## F-statistic: 2.55 on 40 and 1863 DF, p-value: 4.32e-07
anova(lm_model)
## Analysis of Variance Table
##
## Response: brca1
## Df Sum Sq Mean Sq F value Pr(>F)
## cellularity 3 38.38 12.7926 13.2026 1.572e-08 ***
## age_at_diagnosis 1 25.64 25.6378 26.4595 2.974e-07 ***
## brca1_mut 36 34.83 0.9676 0.9986 0.4719
## Residuals 1863 1805.15 0.9689
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#Effect size
eta_squared(lm_model)
## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## ------------------------------------------------
## cellularity | 0.02 | [0.01, 1.00]
## age_at_diagnosis | 0.01 | [0.01, 1.00]
## brca1_mut | 0.02 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].
eta_squared(lm_model, partial = TRUE)
## # Effect Size for ANOVA (Type I)
##
## Parameter | Eta2 (partial) | 95% CI
## ------------------------------------------------
## cellularity | 0.02 | [0.01, 1.00]
## age_at_diagnosis | 0.01 | [0.01, 1.00]
## brca1_mut | 0.02 | [0.00, 1.00]
##
## - One-sided CIs: upper bound fixed at [1.00].
pairwise <- pairwise.t.test(MET$brca1, MET$cellularity,
p.adjust.method = "bonferroni")
pairwise
##
## Pairwise comparisons using t tests with pooled SD
##
## data: MET$brca1 and MET$cellularity
##
## High Low
## High 0.666 - -
## Low 1.000 3.7e-07 -
## Moderate 1.000 7.0e-05 0.064
##
## P value adjustment method: bonferroni
ggplot(MET, aes(x = cellularity, y = brca1, fill = cellularity)) +
geom_boxplot(alpha = 0.7) +
stat_compare_means(method = "anova", label.y = max(MET$brca1)) +
stat_compare_means(method = "t.test",
comparisons = list(c("Low","Moderate"),
c("Low","High"),
c("Moderate","High")),
label = "p.signif") +
labs(
title = "BRCA1 Expression Across Tumor Cellularity Groups",
x = "Tumor Cellularity",
y = "BRCA1 Expression"
) +
theme_minimal() +
theme(
plot.title = element_text(hjust = 0.5, face = "bold"),
legend.position = "none"
)
