add readme and test data

docker-compose.yml

@@ -13,6 +13,7 @@ services:
       - "./processed:/app/processed"
       - "./study:/app/study"
       - "./template:/app/template"
+      - "./reports:/app/reports"
     networks:
       - miracum-cbioportal_cbioportal_net
 

testdata/clinical.csv

@@ -0,0 +1,2 @@
+PID;NACHNAME;VORNAME
+Patient_example;Watson;Mary Jane

testdata/somaticGermline_Patient_example.maf

@@ -0,0 +1,22 @@
+Hugo_Symbol	Entrez_Gene_Id	Center	NCBI_Build	Chromosome	Start_Position	End_Position	Strand	Variant_Classification	Variant_Type	Reference_Allele	Tumor_Seq_Allele1	Tumor_Seq_Allele2	dbSNP_RS	dbSNP_Val_Status	Tumor_Sample_Barcode	Matched_Norm_Sample_Barcode	Match_Norm_Seq_Allele1	Match_Norm_Seq_Allele2	Tumor_Validation_Allele1	Tumor_Validation_Allele2	Match_Norm_Validation_Allele1	Match_Norm_Validation_Allele2	Verification_Status	Validation_Status	Mutation_Status	Sequencing_Phase	Sequencing_Source	Validation_Method	Score	BAM_File	Sequencer	HGVSp_Short	Amino_Acid_Change	TxChange	Transcript_Id	ENSEMBL_Gene_Id	t_ref_count	t_alt_count	n_ref_count	n_alt_count
+CCDC62	84660	MIRACUM-Pipe	GRCh37	chr12	123286212	123286212	+	Missense_Mutation	SNP	G	G	A	rs569908909		Patient_example_TD	Patient_example_GD	G	A						NA	Somatic							p.E507K	p.E507K	c.1519G>A	ENST00000253079	ENSG00000130783	20	15	44	0
+PDE3A	5139	MIRACUM-Pipe	GRCh37	chr12	20803415	20803415	+	Missense_Mutation	SNP	A	A	C	NA		Patient_example_TD	Patient_example_GD	A	C						NA	Somatic							p.N936H	p.N936H	c.2806A>C	ENST00000359062	ENSG00000172572	16	8	26	0
+C2CD5	9847	MIRACUM-Pipe	GRCh37	chr12	22623827	22623827	+	Missense_Mutation	SNP	C	C	T	rs750393334		Patient_example_TD	Patient_example_GD	C	T						NA	Somatic							p.A806T	p.A806T	c.2416G>A	ENST00000545552	ENSG00000111731	21	8	17	0
+KRAS	3845	MIRACUM-Pipe	GRCh37	chr12	25398284	25398284	+	Missense_Mutation	SNP	C	C	A	rs121913529		Patient_example_TD	Patient_example_GD	C	A						NA	Somatic							p.G12V	p.G12V	c.35G>T	ENST00000256078	ENSG00000133703	100	36	132	0
+ARHGAP9	64333	MIRACUM-Pipe	GRCh37	chr12	57872994	57872994	+	Missense_Mutation	SNP	G	G	A	rs367755619		Patient_example_TD	Patient_example_GD	G	A						NA	Somatic							p.R137C	p.R137C	c.409C>T	ENST00000393797	ENSG00000123329	46	21	72	0
+BTBD11	121551	MIRACUM-Pipe	GRCh37	chr12	108012039	108012039	+	Missense_Mutation	SNP	C	C	T	rs369797681		Patient_example_TD	Patient_example_GD	C	T						NA	Germline							p.P779L	p.P779L	c.2336C>T	ENST00000280758	ENSG00000151136	17	13	16	33
+PRH2	5555	MIRACUM-Pipe	GRCh37	chr12	11083297	11083297	+	Missense_Mutation	SNP	G	G	A	rs147911411		Patient_example_TD	Patient_example_GD	G	A						NA	Germline							p.R46H	p.R46H	c.137G>A	ENST00000381847	ENSG00000134551	38	45	58	52
+PRB4	5545	MIRACUM-Pipe	GRCh37	chr12	11461549	11461549	+	Missense_Mutation	SNP	G	G	C	rs11054243		Patient_example_TD	Patient_example_GD	G	C						NA	Germline							p.P123R	p.P123R	c.368C>G	ENST00000279575	ENSG00000230657	12	2	11	4
+PRB4	5545	MIRACUM-Pipe	GRCh37	chr12	11461592	11461592	+	Nonsense_Mutation	SNP	G	G	A	rs199532199		Patient_example_TD	Patient_example_GD	G	A						NA	Germline							p.Q109X	p.Q109X	c.325C>T	ENST00000279575	ENSG00000230657	10	5	11	10
+GATC	283459	MIRACUM-Pipe	GRCh37	chr12	120884481	120884481	+	Missense_Mutation	SNP	G	G	A	rs376375391		Patient_example_TD	Patient_example_GD	G	A						NA	Germline							p.A66T	p.A66T	c.196G>A	ENST00000551806	ENSG00000257218	182	146	62	46
+KMT5A	387893	MIRACUM-Pipe	GRCh37	chr12	123889492	123889492	+	Missense_Mutation	SNP	A	A	C	rs61955124		Patient_example_TD	Patient_example_GD	A	C						NA	Germline							p.D240A	p.D240A	c.719A>C	ENST00000330479	ENSG00000183955	16	6	20	11
+KMT5A	387893	MIRACUM-Pipe	GRCh37	chr12	123892186	123892186	+	Missense_Mutation	SNP	T	T	C	rs61955127		Patient_example_TD	Patient_example_GD	T	C						NA	Germline							p.L332P	p.L332P	c.995T>C	ENST00000330479	ENSG00000183955	84	48	103	50
+CAPRIN2	65981	MIRACUM-Pipe	GRCh37	chr12	30882208	30882208	+	Missense_Mutation	SNP	C	C	T	rs138797190		Patient_example_TD	Patient_example_GD	C	T						NA	Germline							p.E386K	p.E386K	c.1156G>A	ENST00000251071	ENSG00000110888	15	27	13	37
+FAM186A	121006	MIRACUM-Pipe	GRCh37	chr12	50746513	50746513	+	Missense_Mutation	SNP	C	C	A	NA		Patient_example_TD	Patient_example_GD	C	A						NA	Germline							p.A1368S	p.A1368S	c.4102G>T	ENST00000327337	ENSG00000185958	9	9	22	24
+CELA1	1990	MIRACUM-Pipe	GRCh37	chr12	51740409	51740409	+	Missense_Mutation	SNP	T	T	G	rs117443541		Patient_example_TD	Patient_example_GD	T	G						NA	Germline							p.Y5S	p.Y5S	c.14A>C	ENST00000293636	ENSG00000139610	0	18	0	19
+CELA1	1990	MIRACUM-Pipe	GRCh37	chr12	51740410	51740410	+	Missense_Mutation	SNP	A	A	G	rs116944010		Patient_example_TD	Patient_example_GD	A	G						NA	Germline							p.Y5H	p.Y5H	c.13T>C	ENST00000293636	ENSG00000139610	0	18	0	19
+CELA1	1990	MIRACUM-Pipe	GRCh37	chr12	51740413	51740413	+	Frame_Shift_Ins	INS	-	-	C	rs377599213		Patient_example_TD	Patient_example_GD	-	C						NA	Germline							p.L4Afs*21	p.L4Afs*21	c.insG9_10>NA	NA	ENSG00000139610	0	18	0	20
+KRT2	3849	MIRACUM-Pipe	GRCh37	chr12	53045615	53045615	+	In_Frame_Ins	INS	-	-	CCTCCAAAGCCGCTGCCG	rs532019270		Patient_example_TD	Patient_example_GD	-	CCTCCAAAGCCGCTGCCG						NA	Germline							p.F108_S109insGGGSGF	p.F108_S109insGGGSGF	c.insCGGCAGCGGCTTTGGAGG311_312>NA	NA	ENSG00000172867	30	8	32	11
+LRP1	4035	MIRACUM-Pipe	GRCh37	chr12	57590915	57590915	+	Missense_Mutation	SNP	G	G	A	rs145303173		Patient_example_TD	Patient_example_GD	G	A						NA	Germline							p.G3015S	p.G3015S	c.9043G>A	ENST00000243077	ENSG00000123384	117	157	35	67
+ATN1	1822	MIRACUM-Pipe	GRCh37	chr12	7045891	7045891	+	In_Frame_Ins	INS	-	-	CAGCAG	rs797045323		Patient_example_TD	Patient_example_GD	-	CAGCAG						NA	Germline							p.Q502_H503insQQ	p.Q502_H503insQQ	c.insCAGCAG1461_1462>NA	NA	ENSG00000111676	101	103	69	49
+FOXJ2	55810	MIRACUM-Pipe	GRCh37	chr12	8195312	8195312	+	Missense_Mutation	SNP	G	G	A	rs376085291		Patient_example_TD	Patient_example_GD	G	A						NA	LoH							p.R131Q	p.R131Q	c.392G>A	ENST00000162391	ENSG00000065970	23	92	34	28

testdata/somaticGermline_Patient_example_CNV.seg

@@ -0,0 +1,11 @@
+ID	chrom	loc.start	loc.end	num.mark	seg.mean
+Patient_example_TD	12	674672	2983724	246581	1.58496250072116
+Patient_example_TD	12	2994282	9322230	615125	1
+Patient_example_TD	12	48183489	48192836	5852	2.32192809488736
+Patient_example_TD	12	57579374	57619581	30796	1.58496250072116
+Patient_example_TD	12	113495496	113629701	25977	1.32192809488736
+Patient_example_TD	12	122016726	122278013	50311	1.58496250072116
+Patient_example_TD	12	123320028	123482194	56212	1.58496250072116
+Patient_example_TD	12	124499894	125509939	56584	1.8073549220576
+Patient_example_TD	12	132271024	132414668	35303	2.16992500144231
+Patient_example_TD	12	132623676	133209468	54245	2

testdata/somaticGermline_Patient_example_CNV_cbioportal.txt

@@ -0,0 +1,199 @@
+Hugo_Symbol	Entrez_Gene_Id	Patient_example_TD
+ADIPOR2	79602	2
+ACNA1C	NA	2
+ACNA1C-AS1	NA	2
+ACNA1C-AS2	NA	2
+ACNA1C-AS4	NA	2
+ACNA1C-IT2	NA	2
+ACNA1C-IT3	NA	2
+ACNA2D4	NA	2
+CP1B	NA	2
+RC1	NA	2
+BXL14	NA	2
+KBP4	NA	2
+OXM1	NA	2
+TFG2	NA	2
+TFG2-AS1	NA	2
+INC00940	NA	2
+INC00942	NA	2
+OC105369595	NA	2
+OC107984507	NA	2
+RTM2	NA	2
+IR3649	NA	2
+INJ2	NA	2
+INJ2-AS1	NA	2
+RIP2	NA	2
+AD52	NA	2
+EX52	NA	2
+NK1	NA	2
+NT5B	NA	2
+A2M	2	2
+2M-AS1	NA	2
+2ML1	NA	2
+CRBP	NA	2
+CSM4	NA	2
+ICDA	NA	2
+KAP3	NA	2
+NO2	NA	2
+POBEC1	NA	2
+TN1	NA	2
+12orf4	NA	2
+12orf57	NA	2
+1R	NA	2
+1RL	NA	2
+1RL-AS1	NA	2
+1S	NA	2
+3AR1	NA	2
+CND2	NA	2
+CND2-AS1	NA	2
+D163	NA	2
+D163L1	NA	2
+D27	NA	2
+D27-AS1	NA	2
+D4	NA	2
+D9	NA	2
+DCA3	NA	2
+HD4	NA	2
+LEC4A	NA	2
+LEC4C	NA	2
+LEC4D	NA	2
+LEC4E	NA	2
+LEC6A	NA	2
+LSTN3	NA	2
+OPS7A	NA	2
+RACR2A	NA	2
+PPA3	NA	2
+STNP2	NA	2
+YRK4	NA	2
+MG1	NA	2
+AM66C	NA	2
+AM86FP	NA	2
+AM90A1	NA	2
+GF23	NA	2
+GF6	NA	2
+OXJ2	NA	2
+ALNT8	NA	2
+APDH	NA	2
+AU1	NA	2
+DF3	NA	2
+NB3	NA	2
+PR162	NA	2
+FFO1	NA	2
+NG4	NA	2
+CNA1	1255	2
+CNA5	NA	2
+CNA6	NA	2
+LRG1	116844	2
+AG3	NA	2
+INC00612	NA	2
+INC00937	NA	2
+INC02417	NA	2
+INC02443	NA	2
+INC02449	NA	2
+OC100128253	NA	2
+OC105369632	NA	2
+PAR5	NA	2
+PCAT3	NA	2
+RRC23	NA	2
+TBR	NA	2
+6PR	NA	2
+FAP5	NA	2
+IR141	NA	2
+IR200C	NA	2
+IR200CHG	NA	2
+LF2	NA	2
+RPL51	NA	2
+ANOG	NA	2
+ANOGNB	NA	2
+CAPD2	NA	2
+DUFA9	NA	2
+ECAP1	NA	2
+OP2	NA	2
+TF3	NA	2
+3H3	NA	2
+ARP11	NA	2
+EX5	NA	2
+HB2	NA	2
+HC1	NA	2
+IANP	NA	2
+LEKHG6	NA	2
+OU5F1P3	NA	2
+RMT8	NA	2
+TMS	NA	2
+TPN6	NA	2
+ZP	NA	2
+AD51AP1	NA	2
+BP5	NA	2
+HNO1	NA	2
+IMKLB	NA	2
+NU7-1	NA	2
+PL13P5	NA	2
+CARNA10	NA	2
+CARNA11	NA	2
+CARNA12	NA	2
+CNN1A	NA	2
+LC2A14	NA	2
+LC2A3	NA	2
+NORA120	NA	2
+PSB2	NA	2
+APBPL	NA	2
+EAD4	NA	2
+HCAT155	NA	2
+IGAR	NA	2
+NFRSF1A	NA	2
+PI1	NA	2
+SPAN9	NA	2
+ULP3	NA	2
+SP5	389058	2
+AMP1	NA	2
+WF	NA	2
+NF384	NA	2
+NF705A	NA	2
+LRP1	4035	2
+IR1228	NA	2
+XPH4	NA	2
+CFAP73	387885	2
+DX54	NA	2
+TX1	NA	2
+IR7106	NA	2
+ASAL1	NA	2
+ITA1	NA	2
+HPD	3242	2
+DM2B	NA	2
+INC01089	NA	2
+IR548AQ	NA	2
+ORN3	NA	2
+RAI1	10743	2
+HOF	NA	2
+ETD1B	NA	2
+MEM120B	NA	2
+ABCB9	23457	2
+RL6IP4	NA	2
+IP1R	NA	2
+GFOD2	81577	2
+ITPNM2	NA	2
+PS37B	NA	2
+BRI3BP	140707	2
+HX37	NA	2
+IR5188	NA	2
+IR6880	NA	2
+COR2	NA	2
+FLNA	2316	2
+CARB1	NA	2
+BC	NA	2
+NF664-RFLNA	NA	2
+MMP17	4326	2
+US1	NA	2
+FSWAP	NA	2
+LK1	NA	2
+DDX51	317781	2
+BRSL1	NA	2
+ALNT9	NA	2
+INC02361	NA	2
+OC100130238	NA	2
+OC101928416	NA	2
+RCOL1	NA	2
+IR6763	NA	2
+OC4L	NA	2
+2RX2	NA	2
+OLE	NA	2

testdata/somaticGermline_Patient_example_mutsig_cbioportal_contribution.txt

@@ -0,0 +1,32 @@
+ENTITY_STABLE_ID	NAME	DESCRIPTION	Patient_example_TD
+mutational_signature_contribution_AC1	AC1	spontaneous deamination	0.274031792508634
+mutational_signature_contribution_AC10	AC10	altered POL E	0
+mutational_signature_contribution_AC11	AC11	alkylating agents, temozolomide	0
+mutational_signature_contribution_AC12	AC12	unknown	0
+mutational_signature_contribution_AC13	AC13	APOBEC	0.093382951702147
+mutational_signature_contribution_AC14	AC14	unknown	0.0891036748178115
+mutational_signature_contribution_AC15	AC15	defect DNA MMR	0
+mutational_signature_contribution_AC16	AC16	unknown	0
+mutational_signature_contribution_AC17	AC17	unknown	0
+mutational_signature_contribution_AC18	AC18	unknown	0
+mutational_signature_contribution_AC19	AC19	unknown	0
+mutational_signature_contribution_AC2	AC2	APOBEC	0
+mutational_signature_contribution_AC20	AC20	associated w. small indels at repeats	0.12146179889146
+mutational_signature_contribution_AC21	AC21	unknown	0
+mutational_signature_contribution_AC22	AC22	aristocholic acid	0
+mutational_signature_contribution_AC23	AC23	unknown	0
+mutational_signature_contribution_AC24	AC24	aflatoxin	0
+mutational_signature_contribution_AC25	AC25	unknown	0
+mutational_signature_contribution_AC26	AC26	defect DNA MMR	0
+mutational_signature_contribution_AC27	AC27	unknown	0
+mutational_signature_contribution_AC28	AC28	unknown	0.222390048365079
+mutational_signature_contribution_AC29	AC29	tobacco chewing	0.199629733714868
+mutational_signature_contribution_AC3	AC3	defect DNA DSB repair hom. recomb.	0
+mutational_signature_contribution_AC30	AC30	unknown	0
+mutational_signature_contribution_AC4	AC4	tobacco mutatgens, benzo(a)pyrene	0
+mutational_signature_contribution_AC5	AC5	unknown	0
+mutational_signature_contribution_AC6	AC6	defect DNA MMR, found in MSI tumors	0
+mutational_signature_contribution_AC7	AC7	UV light exposure	0
+mutational_signature_contribution_AC8	AC8	unknown	0
+mutational_signature_contribution_AC9	AC9	POL eta and SHM	0
+mutational_signature_contribution_unassigned	unassigned	unknown	0

testdata/somaticGermline_Patient_example_mutsig_cbioportal_limit.txt

@@ -0,0 +1,32 @@
+ENTITY_STABLE_ID	NAME	DESCRIPTION	Patient_example_TD
+mutational_signature_limit_AC1	AC1	spontaneous deamination	0
+mutational_signature_limit_AC10	AC10	altered POL E	1
+mutational_signature_limit_AC11	AC11	alkylating agents, temozolomide	1
+mutational_signature_limit_AC12	AC12	unknown	1
+mutational_signature_limit_AC13	AC13	APOBEC	0
+mutational_signature_limit_AC14	AC14	unknown	0
+mutational_signature_limit_AC15	AC15	defect DNA MMR	1
+mutational_signature_limit_AC16	AC16	unknown	1
+mutational_signature_limit_AC17	AC17	unknown	1
+mutational_signature_limit_AC18	AC18	unknown	1
+mutational_signature_limit_AC19	AC19	unknown	1
+mutational_signature_limit_AC2	AC2	APOBEC	1
+mutational_signature_limit_AC20	AC20	associated w. small indels at repeats	0
+mutational_signature_limit_AC21	AC21	unknown	1
+mutational_signature_limit_AC22	AC22	aristocholic acid	1
+mutational_signature_limit_AC23	AC23	unknown	1
+mutational_signature_limit_AC24	AC24	aflatoxin	1
+mutational_signature_limit_AC25	AC25	unknown	1
+mutational_signature_limit_AC26	AC26	defect DNA MMR	1
+mutational_signature_limit_AC27	AC27	unknown	1
+mutational_signature_limit_AC28	AC28	unknown	0
+mutational_signature_limit_AC29	AC29	tobacco chewing	0
+mutational_signature_limit_AC3	AC3	defect DNA DSB repair hom. recomb.	1
+mutational_signature_limit_AC30	AC30	unknown	1
+mutational_signature_limit_AC4	AC4	tobacco mutatgens, benzo(a)pyrene	1
+mutational_signature_limit_AC5	AC5	unknown	1
+mutational_signature_limit_AC6	AC6	defect DNA MMR, found in MSI tumors	1
+mutational_signature_limit_AC7	AC7	UV light exposure	1
+mutational_signature_limit_AC8	AC8	unknown	1
+mutational_signature_limit_AC9	AC9	POL eta and SHM	1
+mutational_signature_limit_unassigned	unassigned	unknown	1