/nr_mutations

NR_mutation_Analysis

setwd(R"(D:\OneDrive - St John's National Academy of Health Sciences\Shared Folder\Snijesh\data\cbioportal\brca)")
library(maftools)
library(dplyr)
nrs <- c("AR", "ESR1", "PGR", "NR3C1", "VDR")
# genes %>% dplyr::filter(Hugo_Symbol %in% rows_to_filter)


METABRIC


Samples: 2433


df = read.maf(maf = "brca_metabric_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 4212 
-Summarizing
--Possible FLAGS among top ten genes:
  MUC16
  AHNAK2
  SYNE1
  DNAH11
-Processing clinical data
--Missing clinical data
-Finished in 0.750s elapsed (0.500s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
MB-5275  0000661500081

	
MB-4791  000040 600046

	
MB-4667  001031 801041

	
MTS-T1284000030 401035

	
MTS-T0340110025 401032

	
MB-4938  110025 102030

	
MB-0897  000022 600028

	
MB-3525  000024 101026

	
MB-4079  201020 100024

	
MB-3363  300016 103023





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA  5 53421065  01 001112975975

	
TP53  12140297 5101260520 885861861

	
MUC16   6 4 82 465 140 00 499409409

	
AHNAK2  4 1 02 524  51 00 537395395

	
SYNE1   2 1 30 314 110 60 337293293

	
KMT2C  6719 40 148 670 90 314277277

	
GATA3  5080 51  53  70810 277267267

	
MAP3K110075142  78 510160 336236236

	
CDH1   7251 70  28 630181 240233233

	
DNAH11  1 2 20 224 120 00 241226226





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 1 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
NR3C10000120000121212





sets = c("MUC16", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




TCGA


Samples: 1066


df = read.maf(maf = "brca_tcga_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
--Removed 4243 duplicated variants
-Silent variants: 43355 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
  FLG
-Processing clinical data
--Missing clinical data
-Finished in 17.2s elapsed (13.2s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
TCGA-AN-A046-01   312 004472757690 05340

	
TCGA-AC-A23H-01  16 3 103622403773104135

	
TCGA-EW-A2FV-013825 0 00  19  0034 03878

	
TCGA-D8-A27V-012868 0 10 140 16044 13070

	
TCGA-BH-A18G-01 12940120 969 46133 21232

	
TCGA-AN-A0AK-01 13247332 808 47033 11103

	
TCGA-A8-A09Z-01 10945221 818 39334 21073

	
TCGA-D8-A1XK-01  6815 20 780 17261 0 945

	
TCGA-BH-A0HF-01   1 1 00 745 49027 0 823

	
TCGA-AO-A128-01  30 3 20 728 26223 1 815





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA 0 0151370 00 00386346346

	
TP53  4714 50216460240352346346

	
TTN   21 0 11259200 60308186186

	
GATA3 2465 10 13 40230130127127

	
CDH1  3432 40 15310130129127127

	
MUC16 15 1 00128 80 00152109109

	
KMT2C 2210 10 45340 30115 97 97

	
MAP3K13932 40 29220 40130 89 89

	
FLG    1 0 20 69 40 00 76 66 66

	
RYR2   2 0 00 74 30 40 83 65 65





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 5 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR1 101061000999

	
AR   100051100888

	
PGR  010070000877

	
NR3C1000031000444

	
VDR  000020000222





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Alterations in PTEN and ESR1 promote clinical resistance to alpelisib plus aromatase inhibitors


Breast Cancer (MSK, Nature Cancer 2020)


REF: 32864625


Samples: 141


df = read.maf(maf = "breast_alpelisib_2020_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 55 
-Summarizing
--Mutiple centers found
NA;MSKCC-Processing clinical data
--Missing clinical data
-Finished in 0.140s elapsed (0.040s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
P040-04-Post-cfDNA201054111069

	
P009-04-Post-cfDNA010052 80061

	
P040-02-Pre-cfDNA 200147 91060

	
P009-02-Pre-cfDNA 000027 30030

	
P002-02-Pre-cfDNA 220016 60026

	
P-0000247-T02-IM5 010017 20020

	
P046-04-Post-cfDNA000017 10018

	
P054-04-Post-cfDNA000016 00016

	
P-0000138-T02-IM3 000013 10014

	
P-0000216-T02-IM3 0000 8 100 9





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA0010139 000140110110

	
ESR1  0000 60 000 60 38 38

	
TP53  7110 451730 74 36 36

	
ARID1A2400 12 600 24 23 23

	
CDH1  4700  5 111 19 19 19

	
NF1   2000 15 920 28 17 17

	
APC   0000 22 200 24 12 12

	
BRCA2 0020 17 200 21 12 12

	
MTOR  0010 13 300 17 12 12

	
PTEN  1100 11 300 16 12 12





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 2 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR1000060000603838

	
AR  00001200012 7 7





sets = c("ARID1A", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Proteogenomic Landscape of Breast Cancer Tumorigenesis and Targeted Therapy


33212010
Proteogenomic landscape of breast cancer (CPTAC, Cell 2020)


Samples : 122


df = read.maf(maf = "brca_cptac_2020_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 9470 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
  HMCN1
  AHNAK
  OBSCN
  FLG
-Processing clinical data
--Missing clinical data
-Finished in 2.710s elapsed (1.720s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
X01BR043  8 1 2173283941108167859

	
X18BR003  2 0 01 891 843 15 1 997

	
X11BR00310018 50 623 271 23 0 797

	
X15BR003  3 1 00 579 584 12 1 658

	
X05BR038  0 0 10 332 420  6 1 382

	
X05BR029 4611 42 256 180 10 1 348

	
X11BR031  3 0 00 304 330  6 0 346

	
X01BR018 18 0123 256 101  8 0 308

	
X21BR001  5 0 10 229 180  9 1 263

	
X01BR027  4 0 00 149 120  6 1 172





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  80202714020535050

	
PIK3CA015039 0000454040

	
TTN   000086 3000893333

	
MUC16 200034 1000371515

	
HMCN1 000020 2020241313

	
AHNAK 000020 1000211313

	
OBSCN 000019 1000201313

	
ABCA13000015 4000191313

	
FLG   000024 0000241212

	
MAP3K14110 6 2020161111





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 4 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
AR   000030000333

	
PGR  000020000222

	
ESR1 000010000111

	
NR3C1000010000111





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Dynamics of genomic clones in breast cancer patient xenografts at single-cell resolution


REF : 25470049
Breast Cancer Xenografts (British Columbia, Nature 2015)


Samples: 117


df = read.maf(maf = "brca_bccrc_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 29 
-Summarizing
--Mutiple centers found
BC;--Possible FLAGS among top ten genes:
  USH2A
-Processing clinical data
--Missing clinical data
-Finished in 0.500s elapsed (0.260s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
SA214 00001741801193

	
SA106 4220116 305132

	
SA218 7110111 600126

	
SA06515060 85 901116

	
SA071 1000 86 104 92

	
SA054 2000 65 304 74

	
SA077 0010 64 500 70

	
SA031 1000 61 201 65

	
SA084 0100 521000 63

	
SA225 2020 52 700 63





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  100023803353535

	
PIK3CA0010 6000 7 7 7

	
USH2A 0000 7000 7 6 6

	
MYO3A 0000 5100 6 6 6

	
PTEN  2000 4000 6 5 5

	
ATR   1000 4000 5 4 4

	
COL6A30000 3100 4 4 4

	
GPR1120000 4000 4 4 4

	
LRP2  0000 4000 4 4 4

	
MDN1  0000 3100 4 4 4





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 1 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
NR3C110002000333





sets = c("USH2A", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Sequence analysis of mutations and translocations across breast cancer subtypes


REF: 22722202
Breast Invasive Carcinoma (Broad, Nature 2012)


Samples: 103


df = read.maf(maf = "brca_broad_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 1282 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  FLG
  MUC16
-Processing clinical data
--Missing clinical data
-Finished in 0.880s elapsed (0.560s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
BR-M-191111020321130231

	
BR-M-037100012620030150

	
BR-V-0433000113 5061128

	
BR-V-0270000102 8130114

	
BR-V-0672000 93 8020105

	
BR-M-0452000 89 5041101

	
BR-M-1165950 74 4031101

	
BR-V-0020000 64 9030 76

	
BR-V-0372000 66 2031 74

	
BR-M-0551100 59 4000 65





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  2000214040313030

	
PIK3CA0000300000302828

	
TTN   0000112000131212

	
KMT2C 1000 32010 7 7 7

	
AKT1  0000 60000 6 6 6

	
FLG   0000 60000 6 6 6

	
MUC16 0000 60000 6 6 6

	
MUC2  0010 50000 6 6 6

	
DMD   0300 20000 5 5 5

	
RYR3  0000 50000 5 4 4





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 3 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR1000010000111

	
PGR 010000000111

	
VDR 000010000111





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




The landscape of cancer genes and mutational processes in breast cancer


REF: 22722201
Breast Invasive Carcinoma (Sanger, Nature 2012)
Samples: 100


df = read.maf(maf = "brca_sanger_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 1889 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
  SYNE1
-Processing clinical data
--Missing clinical data
-Finished in 0.690s elapsed (0.500s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
PD4203a 2100405380151462

	
PD4120a 1000413391 50459

	
PD4937a 0100319210 60347

	
PD4127a 3000200310 20236

	
PD4100a22230151 91 81197

	
PD4601a 1101133170 20155

	
PD4119a 0000133140 50152

	
PD4596a 1010111150 30131

	
PD4123a 2010100 60 40113

	
PD4844a 6030 95 70 20113





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  6 021206030383737

	
PIK3CA0 010330000343030

	
TTN   0 110272010322626

	
GATA3 11300 10010161515

	
MLL3  1 200 72010131111

	
MUC16 0 000 91000101010

	
CDH1  4 000 3300010 8 8

	
FSIP2 0 000 62000 8 7 7

	
SYNE1 0 000 71000 8 7 7

	
BIRC6 0 000 70000 7 7 7





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 2 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
AR 000010000111

	
PGR000010000111





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




PIK3CA and MAP3K1 alterations imply luminal A status and are associated with clinical benefit from pan-PI3K inhibitor buparlisib and letrozole in ER+ metastatic breast cancer


REF: 31552290
Breast Cancer (MSK, NPJ Breast Cancer 2019)


Samples : 70


df = read.maf(maf = "brca_mskcc_2019_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
--Removed 1 duplicated variants
-Silent variants: 2 
-Summarizing
--Mutiple centers found
MSK-IMPACT341;MSK-IMPACT-Processing clinical data
--Missing clinical data
-Finished in 0.160s elapsed (0.070s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
s_DS_bkm_057_T 01002120024

	
s_DS_bkm_081_T 00002310024

	
s_DS_bkm_067_T 02101620021

	
s_DS_bkm_078_T100011530019

	
s_DS_bkm_078_T200011530019

	
s_DS_bkm_065_T 21011300017

	
s_DS_bkm_020_T 10001140016

	
s_DS_bkm_061_T 00001401116

	
s_DS_bkm_073_T 20001400016

	
s_DS_bkm_076_T 00001500015





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA011040000423535

	
TP53  010020210242222

	
ATM   000018010191616

	
CDH1  4300 3510161515

	
MAP3K16100 8300181313

	
GATA3 3610 3000131212

	
KMT2C 4000 6300131212

	
NOTCH2600014000201010

	
ERBB2 000010000101010

	
MDC1  0010 7100 9 9 9





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 2 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR100006000655

	
AR  00100000111





sets = c("ATM", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




The clonal and mutational evolution spectrum of primary triple-negative breast cancers


REF: 22495314
Breast Invasive Carcinoma (British Columbia, Nature 2012)


Samples : 65


df = read.maf(maf = "brca_bccrc_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 29 
-Summarizing
--Mutiple centers found
BC;--Possible FLAGS among top ten genes:
  USH2A
-Processing clinical data
--Missing clinical data
-Finished in 0.370s elapsed (0.260s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
SA214 00001741801193

	
SA106 4220116 305132

	
SA218 7110111 600126

	
SA06515060 85 901116

	
SA071 1000 86 104 92

	
SA054 2000 65 304 74

	
SA077 0010 64 500 70

	
SA031 1000 61 201 65

	
SA084 0100 521000 63

	
SA225 2020 52 700 63





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  100023803353535

	
PIK3CA0010 6000 7 7 7

	
USH2A 0000 7000 7 6 6

	
MYO3A 0000 5100 6 6 6

	
PTEN  2000 4000 6 5 5

	
ATR   1000 4000 5 4 4

	
COL6A30000 3100 4 4 4

	
GPR1120000 4000 4 4 4

	
LRP2  0000 4000 4 4 4

	
MDN1  0000 3100 4 4 4





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 1 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
NR3C110002000333





sets = c("USH2A", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Whole-Exome Sequencing Analysis of the Progression from Non-Low-Grade Ductal Carcinoma In Situ to Invasive Ductal Carcinoma


REF: 32220886
Breast Cancer (MSK, Clinical Cancer Res 2020)


Samples: 60


df = read.maf(maf = "brca_pareja_msk_2020_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 45 
-Summarizing
--Possible FLAGS among top ten genes:
  MUC16
  TTN
-Processing clinical data
--Missing clinical data
-Finished in 0.400s elapsed (0.220s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
30DCIS 10002653423305

	
30IDC  20102142613247

	
25DCIS110301561612189

	
25IDC 110201501412180

	
19IDC 11040112 203132

	
21IDC  3010110 603123

	
23DCIS 5140100 804122

	
21DCIS 4010100 503113

	
2IDCA  6110 95 203108

	
23IDC  4120 89 704107





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53    442113401292929

	
PIK3CA  020022000242222

	
GATA3   3800 1102151515

	
MUC16   0000 9000 9 9 9

	
AGGF1   0000 8000 8 8 8

	
TTN     0000 9000 9 7 7

	
CDC27   0000 6200 8 7 7

	
CCAR1   3000 0400 7 7 7

	
KIF5A   0000 7000 7 7 7

	
ARHGAP220020 2200 6 6 6





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 0 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>







sets = c("GATA3", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png






The Metastatic Breast Cancer Project (Provisional, December 2021)


Sample: 379


df = read.maf(maf = "brca_mbcproject_2022_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 24952 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
  HMCN1
-Processing clinical data
--Missing clinical data
-Finished in 3.280s elapsed (2.510s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
MBC-MBCProject_7wCjtKIW-Tumor-SM-GQCN4      8410107612301021224

	
MBC-MBCProject_57iLiJIl-Tumor-SM-CGLIV      2000 650 652 84 731

	
RP-1156_MBCProject_JXUNUQI8_BLOOD_P_v1_Exome1010 488 600150 565

	
RP-1156_MBCProject_rLt0uZhz_BLOOD_P_v1_Exome1110 330 312 50 371

	
RP-1156_MBCProject_bBIxhQUD_BLOOD_P_v2_Exome2001 314 350 51 358

	
MBC-MBCProject_K7f6fdUz-Tumor-SM-AZ5MA      1000 311 281 60 347

	
RP-1156_MBCProject_0jUXcgsJ_BLOOD_P_v2_Exome2110 288 261 50 324

	
RP-1156_MBCProject_W4FBsLSx_T3_v2_Exome     3510 269 280 30 309

	
MBC-MBCProject_99CdCOHm-Tumor-SM-CGLF4      1200 270  21 10 277

	
RP-1156_MBCProject_W4FBsLSx_T1_v2_Exome     2010 242 272 11 276





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53   10 740 7811040114112112

	
TTN     1 200 90 9000102 81 81

	
PIK3CA  0 110 76 0000 78 76 76

	
CDH1   11 500 1019072 54 54 54

	
IGDCC4  0 000120 0000120 50 50

	
ESR1    0 000 49 1000 50 43 43

	
MUC16   0 211 39 2010 46 40 40

	
HMCN1   0 300 32 1030 39 38 38

	
ZKSCAN1 03400  2 2000 38 37 37

	
GIMAP6  0 000 41 3000 44 36 36





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 4 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR1 0000491000504343

	
PGR  0000 40000 4 4 4

	
NR3C10000 10010 2 2 2

	
VDR  0000 01000 1 1 1





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Mutational Profile of Metastatic Breast Cancers: A Retrospective Analysis


REF: 28027327
Metastatic Breast Cancer (INSERM, PLoS Med 2016)
Samples: 216


df = read.maf(maf = "brca_igr_2015_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 7046 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
-Processing clinical data
--Missing clinical data
-Finished in 1.670s elapsed (1.170s cpu) 



A data.table: 10 × 10


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><dbl>



	
MBC_1890 80769794100870

	
MBC_8  0 20628741 42711

	
MBC_45 0 50563582130641

	
MBC_71 0 81396481 60460

	
MBC_82 1 70379500 10438

	
MBC_2070 33295332 45345

	
MBC_92 0 31296293 80340

	
MBC_29 0 21272381 60320

	
MBC_31 0101234230 71276

	
MBC_1450 10210162 30232





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  11134914090878484

	
PIK3CA0 2467 1000746565

	
TTN   1 1244 7000554040

	
GATA3 0180 5 1000242222

	
ESR1  0 0221 0000232222

	
RYR2  0 0019 3010231919

	
MAP3K10150 3 6000241818

	
FSIP2 0 2114 0000171616

	
CDH1  0110 1 1020151515

	
MUC16 0 0015 3000181414





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


Warning message in titv(maf = maf, useSyn = TRUE, plot = FALSE):
"Non standard Ti/Tv class: 4TRUE"



png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 3 × 12


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR1002210000232222

	
AR  010 30000 4 4 4

	
VDR 000 10010 2 2 2





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




Multi-omics profiling of younger Asian breast cancers reveals distinctive molecular signatures


REF: 29713003
Breast Cancer (SMC 2018)
Samples : 186


df = read.maf(maf = "brca_smc_2018_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
-Silent variants: 22 
-Summarizing
--Possible FLAGS among top ten genes:
  TTN
  MUC16
  SYNE1
-Processing clinical data
--Missing clinical data
-Finished in 0.780s elapsed (0.540s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
brca_smc_2018_BB01_1111 01027333071316

	
brca_smc_2018_BR255   71169161 7040205

	
brca_smc_2018_BB01_1032 101152 9051171

	
brca_smc_2018_BB01_1122 111128 8110143

	
brca_smc_2018_BB01_0473 10012311021141

	
brca_smc_2018_BR097   6 102115 4130132

	
brca_smc_2018_BB01_0611 010117 9000128

	
brca_smc_2018_BB01_0881 200 9916100119

	
brca_smc_2018_BB01_0990 000108 7021118

	
brca_smc_2018_BR069   2 210 99 4040112





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
TP53  9 4205416040898989

	
PIK3CA0 20056 0000585353

	
TTN   1 00028 0000292323

	
GATA3 12000 1 0020242323

	
MUC16 0 00013 0000131212

	
CSMD3 0 000 9 001010 9 9

	
MAP3K12 210 5 000010 9 9

	
MAML3 0 008 0 0000 8 8 8

	
ARID1A2 300 1 2000 8 7 7

	
SYNE1 0 000 7 1000 8 7 7





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 1 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
AR000130000444





sets = c("TTN", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




INK4 Tumor Suppressor Proteins Mediate Resistance to CDK4/6 Kinase Inhibitors


Metastatic Breast Cancer (MSK, Cancer Discovery 2022)
REF: 34544752


Samples: 1365


df = read.maf(maf = "breast_ink4_msk_2021_data_mutations.txt")


-Reading
-Validating
--Removed 24 duplicated variants
-Silent variants: 21 
-Summarizing
--Mutiple centers found
MSKCC;-Processing clinical data
--Missing clinical data
-Finished in 0.610s elapsed (0.400s cpu) 



samp = getSampleSummary(df)
head(samp, 10)


A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
P-0039857-T01-IM6010067903181

	
P-0009602-T01-IM5100040500046

	
P-0011567-T02-IM6001034712045

	
P-0004987-T01-IM5110034404044

	
P-0002713-T01-IM3000037311042

	
P-0009364-T02-IM6120034301041

	
P-0027986-T01-IM6010031602040

	
P-0002124-T01-IM3000035400039

	
P-0030930-T01-IM6501028401039

	
P-0003233-T04-IM6000034310038





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA 2  0170614 00 00633533533

	
TP53  40 17 60240490350387373373

	
ESR1   1  1 60296 00 10305283283

	
CDH1  69 54 40 21760293256253253

	
GATA3 52142 21 35 60140252245245

	
KMT2C 37  7 20 68660 30183152152

	
MAP3K154 36 50 37250 50162123123

	
ARID1A32 19 00 20430 30117104104

	
AKT1   0  0 14100 10 00106104104

	
FOXA1 10  3192 77 10 00112103103





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 3 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR111602960010305283283

	
AR  0020 143000 19 19 19

	
PGR 0000  70000  7  7  7





sets = c("CDH1", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png




The Genomic Landscape of Endocrine-Resistant Advanced Breast Cancers


Breast Cancer (MSK, Cancer Cell 2018)
REF: 30205045


Samples: 1918


df = read.maf("breast_msk_2018_data_mutations.txt")
samp = getSampleSummary(df)
head(samp, 10)


-Reading
-Validating
--Removed 50 duplicated variants
-Silent variants: 46 
-Summarizing
--Mutiple centers found
MSKCC;-Processing clinical data
--Missing clinical data
-Finished in 1.020s elapsed (0.660s cpu) 



A data.table: 10 × 11


	
Tumor_Sample_BarcodeFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_Sitetotal

	
<fct><int><int><int><int><int><int><int><int><int><dbl>



	
P-0016773-T01-IM60000389410140444

	
P-0009602-T01-IM51000 40 50 00 46

	
P-0004987-T01-IM51100 34 40 40 44

	
P-0002713-T01-IM30000 37 31 10 42

	
P-0002124-T01-IM30000 35 40 00 39

	
P-0002713-T02-IM60000 29 60 01 36

	
P-0000138-T01-IM31000 24 70 10 33

	
P-0002858-T01-IM31000 29 10 10 32

	
P-0004555-T01-IM51000 23 70 00 31

	
P-0014136-T01-IM50000 29 20 00 31





genes = getGeneSummary(df)
head(genes,10)


A data.table: 10 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
PIK3CA 3  1201801  00 00826725725

	
TP53  90 341923851060590695680680

	
CDH1  80 66 70 25 860384306303303

	
GATA3 51168 51 47  70190298288288

	
ESR1   0  1 40168  10 10175164164

	
MAP3K169 50 50 48 350130220155155

	
PTEN  34 22 70 51 270140155137137

	
MLL3  27  9 20 55 500 50148130130

	
AKT1   1  0 03104  10 00109107107

	
ARID1A27 20 11 24 360 40113106106





plotmafSummary(maf = df, rmOutlier = TRUE, addStat = 'median', dashboard = TRUE, titvRaw = FALSE)


png


genes %>% dplyr::filter(Hugo_Symbol %in% nrs)


A data.table: 3 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR101401681010175164164

	
AR  0021 142000 19 19 19

	
PGR 0000  31010  5  4  4





sets = c("CDH1", "TP53", "PIK3CA")
sts <- c(sets, nrs)
oncoplot(maf=df, genes = sts)


png


WARNING !!!!!!!!!!!


The Analysis is Completed. Below are test data. Don't Consider


















dplyr::filter(as.data.frame(genes),
              Hugo_Symbol == "ESR1" | Hugo_Symbol == "PGR" | Hugo_Symbol == "NR3C1" | Hugo_Symbol == "AR" )


A data.frame: 3 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR101401681010175164164

	
AR  0021 142000 19 19 19

	
PGR 0000  31010  5  4  4





rows_to_filter <- c("AR", "ESR1", "PGR", "NR3C1", "VDR")


genes %>% dplyr::filter(Hugo_Symbol %in% rows_to_filter)


A data.table: 3 × 13


	
Hugo_SymbolFrame_Shift_DelFrame_Shift_InsIn_Frame_DelIn_Frame_InsMissense_MutationNonsense_MutationNonstop_MutationSplice_SiteTranslation_Start_SitetotalMutatedSamplesAlteredSamples

	
<chr><int><int><int><int><int><int><int><int><int><dbl><int><int>



	
ESR101401681010175164164

	
AR  0021 142000 19 19 19

	
PGR 0000  31010  5  4  4







genes = c("TP53", "PIK3CA", "GATA3", "NR3C1", "PGR", "AR", "ESR1")


oncoplot(maf=df, genes = genes)


png






# First, let's create your dataframe
data <- data.frame(
    ID = c("a1", "a2", "a3", "a4", "a5", "a6", "a7", "a8", "a9", "a10", "a11", "a12"),
    SA1 = c(9, 2, 10, 4, 0, 10, 1, 8, 5, 1, 1, 5),
    SA2 = c(10, 8, 1, 7, 0, 4, 0, 1, 9, 9, 2, 5),
    SA3 = c(9, 2, 10, 2, 3, 3, 5, 1, 5, 9, 5, 0),
    SA4 = c(5, 9, 0, 9, 2, 1, 9, 3, 9, 1, 1, 6),
    SA5 = c(8, 10, 9, 2, 8, 9, 8, 7, 10, 6, 10, 7),
    SA6 = c(0, 10, 2, 4, 0, 2, 7, 7, 4, 6, 4, 7),
    SA7 = c(2, 5, 2, 4, 1, 4, 6, 5, 7, 3, 6, 6))
data
# # Define the list of rows you want to filter
# rows_to_filter <- c("a2", "a5", "a6", "a9", "a11")

# # Filter the dataframe based on the specified rows
# filtered_data <- data %>% filter(ID %in% rows_to_filter)

# # Print the filtered dataframe
# filtered_data



A data.frame: 12 × 8


	
IDSA1SA2SA3SA4SA5SA6SA7

	
<chr><dbl><dbl><dbl><dbl><dbl><dbl><dbl>



	
a1  910 95 8 02

	
a2  2 8 2910105

	
a3 10 1100 9 22

	
a4  4 7 29 2 44

	
a5  0 0 32 8 01

	
a6 10 4 31 9 24

	
a7  1 0 59 8 76

	
a8  8 1 13 7 75

	
a9  5 9 5910 47

	
a10 1 9 91 6 63

	
a11 1 2 5110 46

	
a12 5 5 06 7 76





# Define the list of columns you want to filter
columns_to_filter <- c("SA1", "SA3", "SA4", "SA7", "AGFH")
# Find the intersection of specified columns and existing columns in the dataframe
valid_columns <- intersect(columns_to_filter, colnames(data))
valid_columns

<style>
.list-inline {list-style: none; margin:0; padding: 0}
.list-inline>li {display: inline-block}
.list-inline>li:not(:last-child)::after {content: "\00b7"; padding: 0 .5ex}
</style>

  1. 'SA1'
  2. 'SA3'
  3. 'SA4'
  4. 'SA7'


# Filter the dataframe based on the valid columns
filtered_data <- data[, c("ID", valid_columns)]
filtered_data


A data.frame: 12 × 5


	
IDSA1SA3SA4SA7

	
<chr><dbl><dbl><dbl><dbl>



	
a1  9 952

	
a2  2 295

	
a3 101002

	
a4  4 294

	
a5  0 321

	
a6 10 314

	
a7  1 596

	
a8  8 135

	
a9  5 597

	
a10 1 913

	
a11 1 516

	
a12 5 066





# Define the list of columns you want to filter
columns_to_filter <- c("SA1", "SA3", "SA4", "SA7", "AGFH")

# Find the intersection of specified columns and existing columns in the dataframe
valid_columns <- intersect(columns_to_filter, colnames(data))

# Filter the dataframe based on the valid columns
filtered_data <- data[, c("ID", valid_columns)]

# Print the filtered dataframe
print(filtered_data)