import pandas as pd
import matplotlib.pyplot as plt

TCGA_BRCA_MC3_Public = pd.read_csv(r"C:\Users\QBPAM\Downloads\'25 summer BigData AI Cancer class by Yongmei Wang\mc3_BRCA_mc3.txt.gz", sep = '\t')
TCGA_BRCA_MC3_Public

#effect columns give types of mutations present
mutation_type_counts = TCGA_BRCA_MC3_Public['effect'].value_counts()
mutation_type_counts

effect
Missense_Mutation         45634
Silent                    17122
Frame_Shift_Del            8522
3'UTR                      6695
Nonsense_Mutation          3666
Intron                     3212
5'UTR                      2492
Splice_Site                1399
RNA                        1160
Frame_Shift_Ins             610
3'Flank                     530
5'Flank                     443
In_Frame_Del                441
Translation_Start_Site       74
Nonstop_Mutation             66
In_Frame_Ins                 34
large deletion               19
Name: count, dtype: int64

sample_types = TCGA_BRCA_MC3_Public['sample'].value_counts()
sample_types

sample
TCGA-AC-A23H-01    6405
TCGA-EW-A2FV-01    4231
TCGA-D8-A27V-01    3332
TCGA-5L-AAT1-01    1995
TCGA-BH-A18G-01    1899
                   ... 
TCGA-AO-A03U-01       7
TCGA-A2-A25F-01       6
TCGA-LL-A440-01       6
TCGA-AC-A2FK-01       3
TCGA-EW-A1P1-01       3
Name: count, Length: 791, dtype: int64

gene_types = TCGA_BRCA_MC3_Public['gene'].value_counts()
gene_types

gene
PIK3CA         315
TTN            285
TP53           273
MUC16          141
CDH1           108
              ... 
DHFR             1
ZNF354B          1
HSP90AB2P        1
RP5-828H9.1      1
C20orf78         1
Name: count, Length: 18065, dtype: int64

gene_types_top50 = gene_types.head(50)

plt.figure(figsize = (10,8))
gene_types_top50.plot(kind = 'barh', color = 'magenta', edgecolor = 'black')
plt.xlabel("Number of Mutations")
plt.ylabel("Gene")
plt.title("Top 50 Most Frequently Mutated Genes in TCGA BRCA (MC3)")
plt.gca().invert_yaxis()
plt.tight_layout()
plt.show()

TCGA_LAML = pd.read_csv(r"C:\Users\QBPAM\Downloads\'25 summer BigData AI Cancer class by Yongmei Wang\TCGA.LAML.sampleMap_mutation_wustl.gz", sep = '\t')
TCGA_LAML

mutation_type_counts1 = TCGA_LAML['effect'].value_counts()
mutation_type_counts1

effect
Missense_Mutation    1539
Silent                510
Frame_Shift_Ins       124
Nonsense_Mutation     117
RNA                   110
Frame_Shift_Del        67
Splice_Site            54
In_Frame_Ins           51
In_Frame_Del           11
3'UTR                   1
Intron                  1
Name: count, dtype: int64

sample_types1 = TCGA_LAML['sample'].value_counts()
sample_types1

sample
TCGA-AB-3009-03    51
TCGA-AB-3002-03    36
TCGA-AB-2807-03    35
TCGA-AB-2927-03    30
TCGA-AB-2959-03    29
                   ..
TCGA-AB-2834-03     1
TCGA-AB-2823-03     1
TCGA-AB-2883-03     1
TCGA-AB-2909-03     1
TCGA-AB-2954-03     1
Name: count, Length: 197, dtype: int64

gene_types1 = TCGA_LAML['gene'].value_counts()
gene_types1

gene
DNMT3A          57
FLT3            56
NPM1            55
TET2            28
RUNX1           21
                ..
CTCF             1
LOC100130734     1
LOC100132903     1
CILP2            1
RPL32            1
Name: count, Length: 1890, dtype: int64

gene_types_top25 = gene_types1.head(25)

plt.figure(figsize = (10,8))
gene_types_top25.plot(kind = 'barh', color = 'pink', edgecolor = 'black')
plt.xlabel("Number of Mutations")
plt.ylabel("Gene")
plt.title("Top 25 Most Frequently Mutated Genes in TCGA Acute Lymphoblastic Leukemia")
plt.gca().invert_yaxis()
plt.tight_layout()
plt.show()

	sample	chr	start	end	reference	alt	gene	effect	Amino_Acid_Change	DNA_VAF	SIFT	PolyPhen
0	TCGA-3C-AAAU-01	10	122668955	122668955	G	A	WDR11	3'UTR	NaN	0.39	NaN	NaN
1	TCGA-3C-AAAU-01	10	8115874	8115875	-	A	GATA3	Frame_Shift_Ins	p.P409Afs*99	0.34	NaN	NaN
2	TCGA-3C-AAAU-01	11	65272906	65272908	AAA	-	MALAT1	RNA	NaN	0.27	NaN	NaN
3	TCGA-3C-AAAU-01	11	66082467	66082467	C	T	CD248	Missense_Mutation	p.E678K	0.07	tolerated(0.12)	benign(0.001)
4	TCGA-3C-AAAU-01	11	66193652	66193652	G	C	NPAS4	3'UTR	NaN	0.20	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...
92114	TCGA-Z7-A8R6-01	9	95396703	95396703	C	T	IPPK	Missense_Mutation	p.E379K	0.16	deleterious(0.01)	probably_damaging(0.968)
92115	TCGA-Z7-A8R6-01	X	123217344	123217344	C	T	STAG2	Missense_Mutation	p.L1000F	0.39	deleterious(0)	probably_damaging(1)
92116	TCGA-Z7-A8R6-01	X	30671631	30671631	G	A	GK	5'UTR	NaN	0.36	NaN	NaN
92117	TCGA-Z7-A8R6-01	X	51151398	51151398	C	G	CXorf67	3'UTR	NaN	0.32	NaN	NaN
92118	TCGA-Z7-A8R6-01	X	54014379	54014379	T	A	PHF8	Splice_Site	p.X613_splice	0.07	NaN	NaN

	sample	chr	start	end	reference	alt	gene	effect	DNA_VAF	RNA_VAF	Amino_Acid_Change
0	TCGA-AB-2802-03	chrMT	14767	14767	T	C	MT-CYB	Missense_Mutation	NaN	NaN	p.I7T
1	TCGA-AB-2802-03	chr1	119270684	119270684	T	A	TBX15	Missense_Mutation	NaN	NaN	p.I59F
2	TCGA-AB-2802-03	chr1	150324146	150324146	T	C	TCHHL1	Missense_Mutation	NaN	NaN	p.Q879R
3	TCGA-AB-2802-03	chr2	25310747	25310747	G	A	DNMT3A	Missense_Mutation	NaN	NaN	p.R882C
4	TCGA-AB-2802-03	chr2	208821357	208821357	C	T	IDH1	Missense_Mutation	NaN	NaN	p.R132H
...	...	...	...	...	...	...	...	...	...	...	...
2580	TCGA-AB-3012-03	chr19	52567974	52567974	G	A	DHX34	Missense_Mutation	NaN	NaN	p.V648I
2581	TCGA-AB-3012-03	chr22	20654724	20654724	C	T	TOP3B	Missense_Mutation	NaN	NaN	p.V147M
2582	TCGA-AB-3012-03	chr22	28018596	28018596	G	T	EWSR1	Splice_Site	NaN	NaN	e11+1
2583	TCGA-AB-3012-03	chr12	11883488	11883500	ATCGATCTCCTCA	-	ETV6	Frame_Shift_Del	NaN	NaN	p.Y104fs
2584	TCGA-AB-3012-03	chr16	2752700	2752701	-	TC	SRRM2	Frame_Shift_Ins	NaN	NaN	p.S724fs