Atarva regions

data/catalogs/STRchive-disease-loci.T2T-chm13.atarva.bed

@@ -0,0 +1,84 @@
+#chrom	start	stop	motif	motif_len	id
+chr1	870158	870178	GGCGCGGAGC	10	HMNR7_VWA1
+chr1	57245935	57245973	GAAAT	5	SCA37_DAB1
+chr1	94266544	94266567	GCC	3	OPDM_ABCD3
+chr1	148519695	148519738	GGC	3	NIID_NOTCH2NLC
+chr1	154328121	154330802	GGCTNNGGGGNGCGGTGGAGCCCGGGGCNGGNCTGNTNTCCGGGGCCGAGGTGACANCNTG	61	ADTKD_MUC1
+chr1	155728131	155728159	GGGCC	5	NME_NAXE
+chr2	96703674	96703732	AAATG	5	FAME2_STARD7
+chr2	100563685	100563738	GCC	3	FRA2A_AFF3
+chr2	176581179	176581224	GCN	3	SD5_HOXD13
+chr2	191369982	191370024	GCA	3	GDPAG_GLS
+chr3	63956302	63956333	CAG	3	SCA7_ATXN7
+chr3	63956333	63956345	CCG	3	SCA7_ATXN7_flank
+chr3	131917482	131917557	CAGG	4	DM2_CNBP
+chr3	131917557	131917597	CAGA	4	DM2_CNBP_flank
+chr3	131917597	131917635	CA	2	DM2_CNBP_flank
+chr3	141687011	141687054	NGC	3	BPES_FOXL2
+chr3	186521667	186521706	TTTCA	5	FAME4_YEATS2
+chr4	3073603	3073687	CAG	3	HD_HTT
+chr4	3073687	3073693	CAACAG	6	HD_HTT_flank
+chr4	3073693	3073729	CCG	3	HD_HTT_flank
+chr4	39318077	39318136	AAGGG	5	CANVAS_RFC1
+chr4	41719745	41719805	GCN	3	CCHS_PHOX2B
+chr4	162693303	162693405	TTTCA	5	FAME7_RAPGEF2
+chr5	10295525	10295593	TTTCA	5	FAME3_MARCHF6
+chr5	147414733	147414780	GCT	3	SCA12_PPP2R2B
+chr6	16200188	16200282	CTG	3	SCA1_ATXN1
+chr6	45257567	45257618	GCN	3	CCD_RUNX2
+chr6	171935458	171935569	GCA	3	SCA17_TBP
+chr7	27335684	27335720	NGC	3	HFG_HOXA13-III
+chr7	27335813	27335849	NGC	3	HFG_HOXA13-II
+chr7	27335912	27335954	NGC	3	HFG_HOXA13-I
+chr7	56047900	56047939	GCG	3	FRA7A_ZNF713
+chr8	105716409	105716441	CGC	3	OPDM1_LRP12
+chr8	119495247	119495353	TGAAA	5	FAME1_SAMD12
+chr9	27584063	27584155	GGCCCC	6	FTDALS1_C9orf72
+chr9	81210834	81210861	GAA	3	FRDA_FXN
+chr9	81210861	81210877	A	1	FRDA_FXN_flank
+chr9	142886568	142886595	GCC	3	HSAN-VIII_PRDM12
+chr10	80695718	80695748	GGC	3	OPML1_NUTM2B-AS1
+chr11	119226662	119226696	CGG	3	JBS_CBL
+chr12	6947903	6947941	CAG	3	DRPLA_ATN1
+chr12	50468095	50468118	GGC	3	FRA12A_DIP2B
+chr12	111575873	111575940	CTG	3	SCA2_ATXN2
+chr12	123532573	123532603	GGC	3	OPDM4_RILPL1
+chr13	69361243	69361270	CTG	3	SCA8_ATXN8OS
+chr13	69361270	69361300	CTA	3	SCA8_ATXN8OS_flank
+chr13	99196358	99196404	GCN	3	HPE5_ZIC2
+chr13	101377549	101377792	GAA	3	SCA27B_FGF14
+chr14	17522488	17522519	GCN	3	OPMD_PABPN1
+chr14	86300519	86300603	CTG	3	SCA3_ATXN3
+chr15	20458510	20458536	GCG	3	ALS1_NIPA1
+chr15	86324038	86324057	TTTG	4	pre-MIR7-2_CHNG3
+chr15	87088411	87088452	GCT	3	CPEO_POLG
+chr16	17477909	17478002	GCC	3	DBQD2_XYLT1
+chr16	24890366	24890430	TTTCA	5	FAME6_TNRC6A
+chr16	72284666	72284761	TGGAA	5	SCA31_BEAN1
+chr16	73638636	73638724	CAG	3	SCA_THAP11
+chr16	78605502	78605569	GCC	3	SCA4_ZFHX3
+chr16	93675723	93675776	CTG	3	HDL2_JPH3
+chr17	17754961	17755053	TTTCA	5	FAME8_RAI1
+chr17	81047404	81047534	CCTCGCTGTGCCGCTGCCGA	20	RCPS_EIF4A3
+chr18	55789233	55789288	CAG	3	FECD3_TCF4
+chr19	13333136	13333176	CTG	3	SCA6_CACNA1A
+chr19	14622655	14622692	CCG	3	OPDM2_GIPC1
+chr19	18921630	18921645	GTC	3	EDM1-PSACH_COMP
+chr19	48597739	48597756	CAG	3	DM1_DMPK
+chr20	2683189	2683230	GGCCTG	6	SCA36_NOP56
+chr20	2683230	2683248	CGCCTG	6	SCA36_NOP56_flank
+chr20	4738633	4738705	CCTCATGGTGGTGGCTGGGGGCAG	24	CJD_PRNP
+chr20	4738705	4738732	CCTCAGGGCGGTGGTGGCTGGGGGCAG	27	CJD_PRNP_flank
+chr21	42132054	42132091	CGCGGGGCGGGG	12	EPM1_CSTB
+chr22	20143615	20143660	GCN	3	TOF_TBX1
+chr22	46280059	46280134	ATTCT	5	SCA10_ATXN10
+chrX	24597766	24597802	NGC	3	PRTS_ARX
+chrX	24597886	24597934	NGC	3	EIEE1_ARX
+chrX	30882677	30882743	TTC	3	DMD_DMD
+chrX	30882743	30882751	T	1	DMD_DMD_flank
+chrX	65975147	65975250	GCA	3	SBMA_AR
+chrX	69887153	69887230	AGAGGG	6	XDP_TAF1
+chrX	135876774	135876804	GCN	3	VACTERLX_ZIC3
+chrX	138816203	138816248	NGC	3	XLMR_SOX3
+chrX	146176677	146176769	CGG	3	FXS_FMR1
+chrX	146765190	146765342	GCC	3	FRAXE_AFF2

data/catalogs/STRchive-disease-loci.hg19.atarva.bed

@@ -0,0 +1,84 @@
+#chrom	start	stop	motif	motif_len	id
+chr1	1371178	1371198	GGCGCGGAGC	10	HMNR7_VWA1
+chr1	57832715	57832793	GAAAT	5	SCA37_DAB1
+chr1	94883977	94884000	GCC	3	OPDM_ABCD3
+chr1	145209323	145209354	GGC	3	NIID_NOTCH2NLC
+chr1	155160981	155162030	GGCTNNGGGGNGCGGTGGAGCCCGGGGCNGGNCTGNTNTCCGGGGCCGAGGTGACANCNTG	61	ADTKD_MUC1
+chr1	156561557	156561575	GGGCC	5	NME_NAXE
+chr2	96862804	96862862	AAATG	5	FAME2_STARD7
+chr2	100721260	100721286	GCC	3	FRA2A_AFF3
+chr2	176957786	176957831	GCN	3	SD5_HOXD13
+chr2	191745598	191745646	GCA	3	GDPAG_GLS
+chr3	63898360	63898391	CAG	3	SCA7_ATXN7
+chr3	63898391	63898403	CCG	3	SCA7_ATXN7_flank
+chr3	128891419	128891499	CAGG	4	DM2_CNBP
+chr3	128891499	128891539	CAGA	4	DM2_CNBP_flank
+chr3	128891539	128891577	CA	2	DM2_CNBP_flank
+chr3	138664861	138664904	NGC	3	BPES_FOXL2
+chr3	183429975	183430014	TTTCA	5	FAME4_YEATS2
+chr4	3076603	3076660	CAG	3	HD_HTT
+chr4	3076660	3076666	CAACAG	6	HD_HTT_flank
+chr4	3076666	3076702	CCG	3	HD_HTT_flank
+chr4	39350044	39350103	AAGGG	5	CANVAS_RFC1
+chr4	41747989	41748049	GCN	3	CCHS_PHOX2B
+chr4	160263678	160263770	TTTCA	5	FAME7_RAPGEF2
+chr5	10356455	10356523	TTTCA	5	FAME3_MARCHF6
+chr5	146258290	146258322	GCT	3	SCA12_PPP2R2B
+chr6	16327864	16327955	CTG	3	SCA1_ATXN1
+chr6	45390487	45390538	GCN	3	CCD_RUNX2
+chr6	170870994	170871105	GCA	3	SCA17_TBP
+chr7	27239297	27239351	NGC	3	HFG_HOXA13-III
+chr7	27239444	27239480	NGC	3	HFG_HOXA13-II
+chr7	27239543	27239585	NGC	3	HFG_HOXA13-I
+chr7	55955293	55955332	GCG	3	FRA7A_ZNF713
+chr8	105601198	105601227	CGC	3	OPDM1_LRP12
+chr8	119379051	119379157	TGAAA	5	FAME1_SAMD12
+chr9	27573482	27573544	GGCCCC	6	FTDALS1_C9orf72
+chr9	71652202	71652220	GAA	3	FRDA_FXN
+chr9	71652220	71652236	A	1	FRDA_FXN_flank
+chr9	133556992	133557028	GCC	3	HSAN-VIII_PRDM12
+chr10	81586139	81586160	GGC	3	OPML1_NUTM2B-AS1
+chr11	119076999	119077033	CGG	3	JBS_CBL
+chr12	7045879	7045938	CAG	3	DRPLA_ATN1
+chr12	50898784	50898807	GGC	3	FRA12A_DIP2B
+chr12	112036753	112036823	CTG	3	SCA2_ATXN2
+chr12	124018267	124018297	GGC	3	OPDM4_RILPL1
+chr13	70713515	70713561	CTG	3	SCA8_ATXN8OS
+chr13	70713561	70713591	CTA	3	SCA8_ATXN8OS_flank
+chr13	100637702	100637748	GCN	3	HPE5_ZIC2
+chr13	102813924	102814076	GAA	3	SCA27B_FGF14
+chr14	23790681	23790712	GCN	3	OPMD_PABPN1
+chr14	92537354	92537396	CTG	3	SCA3_ATXN3
+chr15	23086363	23086389	GCG	3	ALS1_NIPA1
+chr15	89112664	89112683	TTTG	4	pre-MIR7-2_CHNG3
+chr15	89876819	89876860	GCT	3	CPEO_POLG
+chr16	17564764	17564779	GCC	3	DBQD2_XYLT1
+chr16	24624759	24624853	TTTCA	5	FAME6_TNRC6A
+chr16	66524299	66524369	TGGAA	5	SCA31_BEAN1
+chr16	67876765	67876853	CAG	3	SCA_THAP11
+chr16	72821593	72821657	GCC	3	SCA4_ZFHX3
+chr16	87637888	87637935	CTG	3	HDL2_JPH3
+chr17	17711672	17711774	TTTCA	5	FAME8_RAI1
+chr17	78120808	78120938	CCTCGCTGTGCCGCTGCCGA	20	RCPS_EIF4A3
+chr18	53253384	53253460	CAG	3	FECD3_TCF4
+chr19	13318672	13318712	CTG	3	SCA6_CACNA1A
+chr19	14606853	14606887	CCG	3	OPDM2_GIPC1
+chr19	18896844	18896860	GTC	3	EDM1-PSACH_COMP
+chr19	46273462	46273524	CAG	3	DM1_DMPK
+chr20	2633378	2633403	GGCCTG	6	SCA36_NOP56
+chr20	2633403	2633421	CGCCTG	6	SCA36_NOP56_flank
+chr20	4680043	4680139	CCTCATGGTGGTGGCTGGGGGCAG	24	CJD_PRNP
+chr20	4680139	4680166	CCTCAGGGCGGTGGTGGCTGGGGGCAG	27	CJD_PRNP_flank
+chr21	45196323	45196360	CGCGGGGCGGGG	12	EPM1_CSTB
+chr22	19754285	19754330	GCN	3	TOF_TBX1
+chr22	46191234	46191304	ATTCT	5	SCA10_ATXN10
+chrX	25031646	25031682	NGC	3	PRTS_ARX
+chrX	25031766	25031814	NGC	3	EIEE1_ARX
+chrX	31302674	31302722	TTC	3	DMD_DMD
+chrX	31302722	31302730	T	1	DMD_DMD_flank
+chrX	66765158	66765261	GCA	3	SBMA_AR
+chrX	70672904	70672981	AGAGGG	6	XDP_TAF1
+chrX	136648985	136649015	GCN	3	VACTERLX_ZIC3
+chrX	139586481	139586526	NGC	3	XLMR_SOX3
+chrX	146993567	146993629	CGG	3	FXS_FMR1
+chrX	147582124	147582273	GCC	3	FRAXE_AFF2

data/catalogs/STRchive-disease-loci.hg38.atarva.bed

@@ -0,0 +1,84 @@
+#chrom	start	stop	motif	motif_len	id
+chr1	1435798	1435818	GGCGCGGAGC	10	HMNR7_VWA1
+chr1	57367043	57367121	GAAAT	5	SCA37_DAB1
+chr1	94418421	94418444	GCC	3	OPDM_ABCD3
+chr1	149390802	149390842	GGC	3	NIID_NOTCH2NLC
+chr1	155188505	155192239	GGCTNNGGGGNGCGGTGGAGCCCGGGGCNGGNCTGNTNTCCGGGGCCGAGGTGACANCNTG	61	ADTKD_MUC1
+chr1	156591765	156591783	GGGCC	5	NME_NAXE
+chr2	96197066	96197124	AAATG	5	FAME2_STARD7
+chr2	100104798	100104824	GCC	3	FRA2A_AFF3
+chr2	176093058	176093103	GCN	3	SD5_HOXD13
+chr2	190880872	190880920	GCA	3	GDPAG_GLS
+chr3	63912684	63912715	CAG	3	SCA7_ATXN7
+chr3	63912715	63912727	CCG	3	SCA7_ATXN7_flank
+chr3	129172576	129172656	CAGG	4	DM2_CNBP
+chr3	129172656	129172696	CAGA	4	DM2_CNBP_flank
+chr3	129172696	129172734	CA	2	DM2_CNBP_flank
+chr3	138946019	138946062	NGC	3	BPES_FOXL2
+chr3	183712187	183712226	TTTCA	5	FAME4_YEATS2
+chr4	3074876	3074933	CAG	3	HD_HTT
+chr4	3074933	3074939	CAACAG	6	HD_HTT_flank
+chr4	3074939	3074975	CCG	3	HD_HTT_flank
+chr4	39348424	39348483	AAGGG	5	CANVAS_RFC1
+chr4	41745972	41746032	GCN	3	CCHS_PHOX2B
+chr4	159342526	159342618	TTTCA	5	FAME7_RAPGEF2
+chr5	10356343	10356411	TTTCA	5	FAME3_MARCHF6
+chr5	146878727	146878759	GCT	3	SCA12_PPP2R2B
+chr6	16327633	16327724	CTG	3	SCA1_ATXN1
+chr6	45422750	45422801	GCN	3	CCD_RUNX2
+chr6	170561906	170562017	GCA	3	SCA17_TBP
+chr7	27199678	27199732	NGC	3	HFG_HOXA13-III
+chr7	27199825	27199861	NGC	3	HFG_HOXA13-II
+chr7	27199924	27199966	NGC	3	HFG_HOXA13-I
+chr7	55887600	55887639	GCG	3	FRA7A_ZNF713
+chr8	104588970	104588999	CGC	3	OPDM1_LRP12
+chr8	118366812	118366918	TGAAA	5	FAME1_SAMD12
+chr9	27573484	27573546	GGCCCC	6	FTDALS1_C9orf72
+chr9	69037286	69037304	GAA	3	FRDA_FXN
+chr9	69037304	69037320	A	1	FRDA_FXN_flank
+chr9	130681605	130681641	GCC	3	HSAN-VIII_PRDM12
+chr10	79826383	79826404	GGC	3	OPML1_NUTM2B-AS1
+chr11	119206289	119206323	CGG	3	JBS_CBL
+chr12	6936716	6936775	CAG	3	DRPLA_ATN1
+chr12	50505001	50505024	GGC	3	FRA12A_DIP2B
+chr12	111598949	111599019	CTG	3	SCA2_ATXN2
+chr12	123533720	123533750	GGC	3	OPDM4_RILPL1
+chr13	70139383	70139429	CTG	3	SCA8_ATXN8OS
+chr13	70139429	70139459	CTA	3	SCA8_ATXN8OS_flank
+chr13	99985448	99985494	GCN	3	HPE5_ZIC2
+chr13	102161574	102161726	GAA	3	SCA27B_FGF14
+chr14	23321472	23321503	GCN	3	OPMD_PABPN1
+chr14	92071010	92071052	CTG	3	SCA3_ATXN3
+chr15	22786677	22786703	GCG	3	ALS1_NIPA1
+chr15	88569433	88569452	TTTG	4	pre-MIR7-2_CHNG3
+chr15	89333588	89333629	GCT	3	CPEO_POLG
+chr16	17470907	17470922	GCC	3	DBQD2_XYLT1
+chr16	24613438	24613532	TTTCA	5	FAME6_TNRC6A
+chr16	66490396	66490466	TGGAA	5	SCA31_BEAN1
+chr16	67842862	67842950	CAG	3	SCA_THAP11
+chr16	72787694	72787758	GCC	3	SCA4_ZFHX3
+chr16	87604282	87604329	CTG	3	HDL2_JPH3
+chr17	17808358	17808460	TTTCA	5	FAME8_RAI1
+chr17	80147009	80147139	CCTCGCTGTGCCGCTGCCGA	20	RCPS_EIF4A3
+chr18	55586153	55586229	CAG	3	FECD3_TCF4
+chr19	13207858	13207898	CTG	3	SCA6_CACNA1A
+chr19	14496041	14496075	CCG	3	OPDM2_GIPC1
+chr19	18786034	18786050	GTC	3	EDM1-PSACH_COMP
+chr19	45770204	45770266	CAG	3	DM1_DMPK
+chr20	2652732	2652757	GGCCTG	6	SCA36_NOP56
+chr20	2652757	2652775	CGCCTG	6	SCA36_NOP56_flank
+chr20	4699397	4699493	CCTCATGGTGGTGGCTGGGGGCAG	24	CJD_PRNP
+chr20	4699493	4699520	CCTCAGGGCGGTGGTGGCTGGGGGCAG	27	CJD_PRNP_flank
+chr21	43776442	43776479	CGCGGGGCGGGG	12	EPM1_CSTB
+chr22	19766762	19766807	GCN	3	TOF_TBX1
+chr22	45795354	45795424	ATTCT	5	SCA10_ATXN10
+chrX	25013529	25013565	NGC	3	PRTS_ARX
+chrX	25013649	25013697	NGC	3	EIEE1_ARX
+chrX	31284557	31284605	TTC	3	DMD_DMD
+chrX	31284605	31284613	T	1	DMD_DMD_flank
+chrX	67545316	67545419	GCA	3	SBMA_AR
+chrX	71453054	71453131	AGAGGG	6	XDP_TAF1
+chrX	137566826	137566856	GCN	3	VACTERLX_ZIC3
+chrX	140504316	140504361	NGC	3	XLMR_SOX3
+chrX	147912049	147912111	CGG	3	FXS_FMR1
+chrX	148500604	148500753	GCC	3	FRAXE_AFF2

scripts/environment.yml

@@ -25,6 +25,8 @@ dependencies:
   - r-purrr
   - gfortran
   - pysam
+  - htslib
+  - bedtools
   - nodejs # build website locally
   - pyliftover
   - pip

scripts/make-catalog.py

@@ -126,6 +126,75 @@ def trgt_catalog(row, genome = 'hg38', struc_type = 'default'):
 
     return definition
 
+def atarva_catalog(row, genome = 'hg38'):
+    r"""
+    :param row: dictionary with STR data for a single locus
+    :param genome: genome build (hg19, hg38 or T2T)
+    :return: atarva format catalog string which is a modified BED format with fields: chrom start stop motif motif_len [id]
+
+    Note, compound loci will be split into multiple entries, one for each motif. Overlapping loci are okay.
+    For loci with multiple pathogenic motifs, only the first motif will be used. Atarva does motif decomposition, so alternate motifs should be detected by the caller.
+
+    >>> atarva_catalog({'chrom': 'chr1', 'start_hg38': 100, 'stop_hg38': 200, 'pathogenic_motif_reference_orientation': ['CAG'], 'flank_motif': '', 'gene': 'mygene', 'id': 'myid', 'pathogenic_min': 10, 'inheritance': 'AD', 'disease': 'Disease Name'}, 'hg38')
+    'chr1\t100\t200\tCAG\t3\tmyid'
+
+    >>> atarva_catalog({'chrom': 'chr1', 'start_hg38': 100, 'stop_hg38': 200, 'pathogenic_motif_reference_orientation': ['AAGGG', 'ACAGG'], 'flank_motif': '', 'gene': 'mygene', 'id': 'myid', 'pathogenic_min': 10, 'inheritance': 'AD', 'disease': 'Disease Name'}, 'hg38')
+    'chr1\t100\t200\tAAGGG\t5\tmyid'
+
+    >>> atarva_catalog({'chrom': 'chr1', 'start_hg38': 100, 'stop_hg38': 200, 'pathogenic_motif_reference_orientation': ['CAG'], 'flank_motif': '(CAG)nCAACAG(CCG)12', 'gene': 'mygene', 'id': 'myid', 'pathogenic_min': 10, 'inheritance': 'AD', 'disease': 'Disease Name'}, 'hg38')
+    'chr1\t100\t200\tCAG\t3\tmyid\nchr1\t200\t206\tCAACAG\t6\tmyid_flank\nchr1\t206\t242\tCCG\t3\tmyid_flank'
+
+    >>> atarva_catalog({'chrom': 'chr1', 'start_hg38': 100, 'stop_hg38': 200, 'pathogenic_motif_reference_orientation': ['CAG'], 'flank_motif': '(CAG)n(CCG)10(CAA)10', 'gene': 'mygene', 'id': 'myid', 'pathogenic_min': 10, 'inheritance': 'AD', 'disease': 'Disease Name'}, 'hg38')
+    'chr1\t100\t200\tCAG\t3\tmyid\nchr1\t200\t230\tCCG\t3\tmyid_flank\nchr1\t230\t260\tCAA\t3\tmyid_flank'
+    """
+    bed_string = ''
+
+    motif_field = 'pathogenic_motif_reference_orientation'
+    id_field = 'id'
+    start = int(row['start_' + genome])
+    stop = int(row['stop_' + genome])
+
+    motifs = row[motif_field]
+    this_id = row[id_field]
+
+    motif = motifs[0] # use first motif only
+    motif_len = len(motif)
+    bed_string += f"{row['chrom']}\t{start}\t{stop}\t{motif}\t{motif_len}\t{this_id}\n"
+
+    # check for flanking motif(s)
+    if row['flank_motif'] != '' and row['flank_motif'] is not None:
+    # get motifs in parentheses using regex
+        flank_motif = row['flank_motif']
+
+        split_flank_counts = re.split(r"[ATCGN]+", flank_motif, )
+        all_flank_motifs_counts = []
+        for i in range(1, len(split_flank_counts)):
+            all_flank_motifs_counts.append(split_flank_counts[i].replace('(', '').replace(')', ''))
+
+        all_flank_motifs = ''
+        for char in flank_motif:
+            if char in ['(', ')', 'n', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9']:
+                all_flank_motifs += ' '
+            else:
+                all_flank_motifs += char
+
+        all_flank_motifs = all_flank_motifs.split()
+
+        flank_start = stop
+        flank_stop = stop
+        for motif, count in zip(all_flank_motifs, all_flank_motifs_counts):
+            if count == '':
+                count = 1
+            if count == 'n':
+                continue
+            else:
+                flank_stop += int(count) * len(motif)
+            bed_string += f"{row['chrom']}\t{flank_start}\t{flank_stop}\t{motif}\t{len(motif)}\t{this_id}_flank\n"
+            flank_start = flank_stop
+
+    return bed_string.rstrip('\n')
+
+
 def extended_bed(row, fields = [], genome = 'hg38'):
     r"""
     :param row: dictionary with STR data for a single locus
@@ -191,6 +260,12 @@ def main(input: str, output: str, *, format: str = 'TRGT', genome: str = 'hg38',
         with open(output, 'w') as out_file:
             for row in data:
                 out_file.write(trgt_catalog(row, genome) + '\n')
+    elif format.lower() == 'atarva':
+        with open(output, 'w') as out_file:
+            header = '#' + '\t'.join(['chrom', 'start', 'stop', 'motif', 'motif_len', 'id']) + '\n'
+            out_file.write(header)
+            for row in data:
+                out_file.write(atarva_catalog(row, genome) + '\n')
     elif format.lower() == 'bed':
         fields_list = fields.split(',')
         header = '#' + '\t'.join(['chrom', 'start', 'stop'] + fields_list) + '\n'