Adding code for producing figure S2B

25b3fa24 · Matteo Barcella · fe1537a3 · 25b3fa24 · 25b3fa24 · 25b3fa24
Commit 25b3fa24 authored Apr 14, 2026 by Matteo Barcella
--- a/DNA_Repair_signatures_LoFurnoDellaVolpe.gmt
+++ b/DNA_Repair_signatures_LoFurnoDellaVolpe.gmt
+Base excision repair (BER)	dnarepair	UNG	SMUG1	MBD4	TDG	OGG1	MUTYH	NTHL1	MPG	NEIL1	NEIL2	NEIL3
+Other BER and strand break joining factors	dnarepair	APEX1	APEX2	LIG3	XRCC1	PNKP	APLF	HMCES
+Poly(ADP-ribose) polymerase (PARP) enzymes that bind to DNA	dnarepair	PARP1	PARP2	PARP3	PARG	PARPBP
+Direct reversal of damage	dnarepair	MGMT	ALKBH2	ALKBH3
+Repair of DNA-protein crosslinks	dnarepair	TDP1	TDP2	SPRTN
+Mismatch excision repair (MMR)	dnarepair	MSH2	MSH3	MSH6	MLH1	PMS2	MSH4	MSH5	MLH3	PMS1	PMS2P3	HFM1
+Nucleotide excision repair (NER)	dnarepair	XPC	RAD23B	CETN2	RAD23A	XPA	DDB1	DDB2	RPA1	RPA2	RPA3	TFIIH	ERCC3	ERCC2	GTF2H1	GTF2H2	GTF2H3	GTF2H4	GTF2H5	GTF2E2	CDK7	CCNH	MNAT1	ERCC5	ERCC1	ERCC4	LIG1
+NER-related	dnarepair	ERCC8	ERCC6 	UVSSA	XAB2	MMS19
+Homologous recombination	dnarepair	RAD51	RAD51B	RAD51D	HELQ	SWI5	ZSWIM7	SPIDR	PDS5B	DMC1	XRCC2	XRCC3	RAD52	RAD54L	RAD54B	BRCA1	BARD1	ABRAXAS1	PAXIP1	SMC5	SMC6	SHLD2	SHLD3	SEM1	RAD50	MRE11A	NBN	RBBP8	MUS81	EME1	EME2	SLX1A 	SLX1B
+Fanconi anemia	dnarepair	FANCA	FANCB	FANCC	BRCA2	FANCD2	FANCE	FANCF	FANCG	FANCI	BRIP1	FANCL	FANCM	PALB2	RAD51C	SLX4	FAAP20	FAAP24	FAAP100	UBE2T
+Non-homologous end-joining	dnarepair	XRCC6	XRCC5	PRKDC	LIG4	XRCC4	DCLRE1C	NHEJ1
+Modulation of nucleotide pools	dnarepair	NUDT1	DUT	RRM2B	PARK7	DNPH1	NUDT15	NUDT18
+DNA polymerases	dnarepair	POLA1	POLB	POLD1	POLD2	POLD3	POLD4	POLE	POLE2	POLE3	POLE4	REV3L	MAD2L2	REV1	POLG	POLH	POLI	POLQ	POLK	POLL	POLM	POLN	PRIMPOL	DNTT
+Editing and processing nucleases	dnarepair	FEN1	FAN1	TREX1	TREX2	EXO1	APTX 	SPO11	ENDOV	DNA2	DCLRE1A	DCLRE1B	EXO5
+Ubiquitination and modification	dnarepair	UBE2A	UBE2B	RAD18	SHPRH	HLTF	RNF168	RNF8	RNF4	UBE2V2 	UBE2N	USP1	WDR48	HERC2
+Chromatin Structure and Modification	dnarepair	H2AX	CHAF1A	SETMAR	ATRX
+Genes defective in diseases associated with sensitivity to DNA damaging agents	dnarepair	BLM	RMI1	TOP3A	WRN	RECQL4	ATM	MPLKIP
+Other identified genes with known or suspected DNA repair function	dnarepair	RPA4	PRPF19	RECQL	RECQL5	RDM1	NABP2
+Other conserved DNA damage response genes	dnarepair	ATR	ATRIP	MDC1	PCNA	RAD1	RAD9A	HUS1	RAD17	CHEK1	CHEK2	TP53	TP53BP1	RIF1	TOPBP1	CLK2	PER1
--- a/DNA_damage_and_repair_genesets.v7.2.Hs.alias_aligned.gmt
+++ b/DNA_damage_and_repair_genesets.v7.2.Hs.alias_aligned.gmt
+BIOCARTA_CDC25_PATHWAY	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/BIOCARTA_CDC25_PATHWAY	ATM	CDC25A	CDC25B	CDC25C	CDK1	CHEK1	MYT1	WEE1	YWHAH
+BIOCARTA_CHEMICAL_PATHWAY	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/BIOCARTA_CHEMICAL_PATHWAY	AKT1	APAF1	ATM	BAD	BAX	BCL2	BID	CASP3	CASP6	CASP7	CASP9	EIF2S1	PARP1	PRKCA	PRKCB	STAT1	TLN1	TP53
+BIOCARTA_P53_PATHWAY	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/BIOCARTA_P53_PATHWAY	APAF1	ATM	BAX	BCL2	CCND1	CCNE1	CDK2	CDK4	CDKN1A	E2F1	GADD45A	MDM2	PCNA	RB1	TIMP3	TP53
+GOBP_DNA_REPAIR	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/GOBP_DNA_REPAIR	ABL1	ABRAXAS1	ACTB	ACTL6A	ACTL6B	ACTR2	ACTR5	ACTR8	ADPRS	AGER	AKTIP	ALKBH1	ALKBH2	ALKBH3	ANKLE1	AP5S1	AP5Z1	APEX1	APEX2	APLF	APTX	ARID1A	ARID1B	ARID2	ASCC1	ASCC2	ASCC3	ASF1A	ASTE1	ATM	ATP23	ATR	ATRIP	ATRX	ATXN3	ATXN7	ATXN7L3	AUNIP	AXIN2	BABAM1	BABAM2	BACH1	BARD1	BCCIP	BCL7A	BCL7B	BCL7C	BLM	BOD1L1	BRCA1	BRCA2	BRCC3	BRD7	BRD8	BRIP1	BRME1	BTG2	C11orf54	C14orf39	C1QBP	CBX8	CCDC117	CDC14B	CDC45	CDC5L	CDC7	CDCA5	CDK1	CDK2	CDK7	CDK9	CDKN2D	CEBPG	CENPS	CENPX	CEP164	CETN2	CGAS	CHAF1A	CHAF1B	CHD1L	CHD4	CHEK1	CHEK2	CHRNA4	CIB1	CINP	CLSPN	COMMD1	CREBBP	CRY2	CSNK1E	CSNK2A1	CSNK2A2	CSNK2A3	CTBP1-AS2	CUL4A	CUL4B	CYREN	DCLRE1A	DCLRE1B	DCLRE1C	DDB1	DDB2	DDX1	DDX11	DEK	DHX9	DMAP1	DMC1	DNA2	DNTT	DOT1L	DPF1	DPF2	DPF3	DTL	DTX3L	DYRK1B	EEPD1	EGFR	EID3	ELOF1	EME1	EME2	EMSY	ENDOV	ENY2	EP400	EPC1	EPC2	ERCC1	ERCC2	ERCC3	ERCC4	ERCC5	ERCC6	ERCC6L	ERCC6L2	ERCC8	ESCO2	ETAA1	EXD2	EXO1	EXO5	EXOSC10	EYA1	EYA2	EYA3	EYA4	FAAP100	FAAP20	FAAP24	FAM111A	FAM168A	FAN1	FANCA	FANCB	FANCC	FANCD2	FANCE	FANCF	FANCG	FANCI	FANCL	FANCM	FBH1	FBXO6	FBXW7	FEN1	FGF10	FH	FIGNL1	FIRRM	FMN2	FMR1	FOXM1	FTO	FUS	FZR1	GADD45A	GCNA	GEN1	GGN	GINS2	GINS4	GTF2H1	GTF2H2	GTF2H2C	GTF2H3	GTF2H4	GTF2H5	H2AC25	H2AX	HDAC10	HDGFL2	HELB	HELQ	HERC2	HINFP	HLTF	HMCES	HMGA1	HMGA2	HMGB1	HMGB2	HMGN1	HPF1	HROB	HSF1	HSF2BP	HTATSF1	HUS1	HUS1B	HUWE1	IER3	IFFO1	ING3	INIP	INO80	INO80B	INO80C	INO80D	INO80E	INTS3	JMY	KASH5	KAT2A	KAT2B	KAT5	KAT7	KDM1A	KDM2A	KDM4D	KHDC3L	KIF22	KIN	KLHL15	KMT5A	KMT5B	KMT5C	LIG1	LIG3	LIG4	MACROH2A1	MAD2L2	MAGEF1	MAJIN	MARF1	MBD4	MBTD1	MC1R	MCM2	MCM3	MCM4	MCM5	MCM6	MCM7	MCM8	MCM9	MCMDC2	MCRS1	MDC1	MEAF6	MEIOB	MEIOC	MEN1	MGME1	MGMT	MIR221	MLH1	MLH3	MMS19	MMS22L	MNAT1	MORF4L1	MORF4L2	MPG	MPND	MRE11	MRGBP	MRNIP	MSH2	MSH3	MSH4	MSH5	MSH6	MTA1	MUS81	MUTYH	NABP1	NABP2	NBN	NEIL1	NEIL2	NEIL3	NEURL4	NFRKB	NHEJ1	NIPBL	NME3	NONO	NOP53	NPAS2	NPM1	NSD2	NSMCE1	NSMCE2	NSMCE3	NSMCE4A	NTHL1	NUCKS1	NUDT1	NUDT16L1	NYNRIN	OGG1	OOEP	OTUB1	OTUD4	PAGR1	PALB2	PARG	PARK7	PARP1	PARP10	PARP2	PARP3	PARP4	PARP9	PARPBP	PAXIP1	PAXX	PBRM1	PCLAF	PCNA	PDS5A	PDS5B	PELI1	PHF10	PIAS4	PIF1	PLK1	PML	PMS1	PMS2	PMS2P1	PMS2P3	PMS2P5	PMS2P6	PNKP	POGZ	POLA1	POLB	POLD1	POLD2	POLD3	POLD4	POLDIP2	POLE	POLE2	POLG	POLH	POLI	POLK	POLL	POLM	POLN	POLQ	POLR2I	POT1	PPP4C	PPP4R2	PPP4R3A	PPP4R3B	PPP4R3C	PPP5C	PRDM9	PRIMPOL	PRKCG	PRKDC	PRMT1	PRMT6	PRPF19	PSMD14	PSME4	PTTG1	PWWP3A	RAD1	RAD17	RAD18	RAD21	RAD21L1	RAD23A	RAD23B	RAD50	RAD51	RAD51AP1	RAD51B	RAD51C	RAD51D	RAD52	RAD54B	RAD54L	RAD9A	RAD9B	RADX	RBBP4	RBBP8	RBX1	RCHY1	REC8	RECQL	RECQL4	RECQL5	REV1	REV3L	REXO4	RFC1	RFC2	RFC3	RFC4	RFC5	RFWD3	RHNO1	RIF1	RIOX1	RMI1	RMI2	RNASEH2A	RNASEH2B	RNASEH2C	RNF111	RNF113A	RNF126	RNF138	RNF168	RNF169	RNF8	RPA1	RPA2	RPA3	RPA4	RPS3	RRM1	RRM2B	RTEL1	RUVBL1	RUVBL2	SAMHD1	SEM1	SENP3	SETD2	SETD7	SETMAR	SETX	SF3B3	SF3B5	SFPQ	SFR1	SGF29	SHLD1	SHLD2	SHLD3	SHPRH	SIRT1	SIRT6	SIRT7	SKP2	SLC30A9	SLF1	SLF2	SLX1A	SLX1B	SLX4	SMARCA2	SMARCA4	SMARCA5	SMARCAD1	SMARCAL1	SMARCB1	SMARCC1	SMARCC2	SMARCD1	SMARCD2	SMARCD3	SMARCE1	SMC1A	SMC3	SMC5	SMC6	SMCHD1	SMG1	SMUG1	SPATA22	SPIDR	SPIRE1	SPIRE2	SPO11	SPRTN	SSRP1	STK19	STUB1	SUMO1	SUPT16H	SUPT20H	SUPT3H	SUPT7L	SUV39H1	SWI5	SWSAP1	SYCP1	TADA1	TADA2B	TADA3	TAF10	TAF12	TAF2	TAF4	TAF5	TAF5L	TAF6	TAF6L	TAF7	TAF9	TAOK1	TAOK3	TDG	TDP1	TDP2	TENT4A	TERB1	TERB2	TERF2	TERF2IP	TEX12	TEX15	TEX264	TFIP11	TFPT	TICRR	TIGAR	TIMELESS	TMEM161A	TNKS1BP1	TNP1	TONSL	TOP2B	TOP3A	TOP3B	TOPBP1	TP53	TP53BP1	TP73	TRAIP	TREX1	TREX2	TRIM28	TRIP12	TRIP13	TRRAP	TTC5	TTF2	TWIST1	UBE2A	UBE2B	UBE2D3	UBE2N	UBE2NL	UBE2T	UBE2U	UBE2V1	UBE2V2	UBE2W	UBQLN4	UBR5	UCHL5	UFL1	UHRF1	UIMC1	UNG	UPF1	USP1	USP10	USP22	USP28	USP3	USP43	USP44	USP45	USP47	USP51	USP7	USP9X	UVRAG	UVSSA	VCP	VCPIP1	VPS72	WAS	WDHD1	WDR33	WDR48	WRAP53	WRN	WRNIP1	XAB2	XNDC1N	XPA	XPC	XRCC1	XRCC2	XRCC3	XRCC4	XRCC5	XRCC6	YEATS4	YY1	ZBTB1	ZBTB7A	ZCWPW1	ZFYVE26	ZGRF1	ZMPSTE24	ZMYND8	ZNF365	ZNF668	ZRANB3	ZSWIM7
+GOBP_DNA_DAMAGE_RESPONSE	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/GOBP_DNA_DAMAGE_RESPONSE	ABL1	ABRAXAS1	ACD	ACER2	ACKR3	ACTB	ACTL6A	ACTL6B	ACTR2	ACTR5	ACTR8	ADPRS	AEN	AGER	AIM2	AKTIP	ALKBH1	ALKBH2	ALKBH3	ALKBH7	ALKBH8	ANKLE1	ANKRD1	AP5S1	AP5Z1	APBB1	APC	APEX1	APEX2	APLF	APTX	ARID1A	ARID1B	ARID2	ARMT1	ASCC1	ASCC2	ASCC3	ASF1A	ASH2L	ASTE1	ATAD3A	ATAD5	ATF2	ATM	ATMIN	ATP23	ATR	ATRIP	ATRX	ATXN3	ATXN7	ATXN7L3	AUNIP	AXIN2	BABAM1	BABAM2	BACH1	BAD	BAG6	BAK1	BARD1	BATF	BAX	BAZ1B	BBC3	BCCIP	BCL2	BCL2A1	BCL2L1	BCL2L10	BCL2L11	BCL2L12	BCL2L2	BCL3	BCL6	BCL7A	BCL7B	BCL7C	BCLAF1	BID	BLM	BOD1L1	BOK	BRAT1	BRCA1	BRCA2	BRCC3	BRD4	BRD7	BRD8	BRIP1	BRME1	BRSK1	BTG2	C11orf54	C14orf39	C1QBP	CASP2	CASP3	CASP9	CBL	CBX1	CBX3	CBX5	CBX8	CCAR2	CCDC117	CCDC13	CCND1	CCNK	CD44	CD74	CDC14B	CDC45	CDC5L	CDC7	CDCA5	CDIP1	CDK1	CDK2	CDK3	CDK5RAP3	CDK6	CDK7	CDK9	CDKN1A	CDKN1B	CDKN2A	CDKN2AIP	CDKN2D	CEBPG	CENPS	CENPX	CEP164	CEP63	CETN2	CFAP410	CGAS	CHAF1A	CHAF1B	CHCHD6	CHD1L	CHD2	CHD4	CHEK1	CHEK2	CHRNA4	CIB1	CIDEB	CINP	CIP2A	CLOCK	CLSPN	CLU	COMMD1	COPS3	CRADD	CREBBP	CRIP1	CRY1	CRY2	CSNK1E	CSNK2A1	CSNK2A2	CSNK2A3	CTBP1-AS2	CTC1	CTLA4	CUL4A	CUL4B	CXCL12	CYREN	DCLRE1A	DCLRE1B	DCLRE1C	DCUN1D5	DDB1	DDB2	DDIAS	DDIT3	DDIT4	DDX1	DDX11	DDX5	DEK	DELE1	DGCR8	DGKZ	DHX9	DMAP1	DMC1	DNA2	DNTT	DONSON	DOT1L	DPF1	DPF2	DPF3	DTL	DTX3L	DYNLL1	DYRK1A	DYRK1B	DYRK2	DYRK3	E2F1	E2F7	EEF1E1	EEPD1	EGFR	EGLN3	EI24	EID3	EIF2AK4	ELL3	ELOF1	EME1	EME2	EMSY	ENDOG	ENDOV	ENY2	EP300	EP400	EPC1	EPC2	EPHA2	ERCC1	ERCC2	ERCC3	ERCC4	ERCC5	ERCC6	ERCC6L	ERCC6L2	ERCC8	ESCO2	ETAA1	EXD2	EXO1	EXO5	EXOSC10	EYA1	EYA2	EYA3	EYA4	FAAP100	FAAP20	FAAP24	FAM111A	FAM168A	FAN1	FANCA	FANCB	FANCC	FANCD2	FANCE	FANCF	FANCG	FANCI	FANCL	FANCM	FBH1	FBXO31	FBXO4	FBXO45	FBXO5	FBXO6	FBXW7	FEM1B	FEN1	FGF10	FH	FIGNL1	FIRRM	FLYWCH1	FMN2	FMR1	FNIP2	FOXM1	FOXN3	FOXO1	FOXO3	FOXO4	FOXP1	FTO	FUS	FZR1	GADD45A	GCNA	GEN1	GFI1	GGN	GIGYF2	GINS2	GINS4	GML	GNB1L	GNL1	GRB2	GTF2H1	GTF2H2	GTF2H2C	GTF2H3	GTF2H4	GTF2H5	GTSE1	H2AC25	H2AX	HDAC10	HDAC3	HDGFL2	HELB	HELQ	HERC2	HIC1	HINFP	HIPK1	HIPK2	HLTF	HMCES	HMGA1	HMGA2	HMGB1	HMGB2	HMGN1	HNRNPK	HPF1	HROB	HSF1	HSF2BP	HTATSF1	HTRA2	HUS1	HUS1B	HUWE1	IER3	IFFO1	IFI16	IKBKE	IKBKG	IMMP2L	ING2	ING3	ING4	INIP	INO80	INO80B	INO80C	INO80D	INO80E	INTS3	INTS7	IRF3	IRF7	JMY	KASH5	KAT2A	KAT2B	KAT5	KAT7	KDM1A	KDM2A	KDM4D	KHDC3L	KIF22	KIN	KLHL15	KMT5A	KMT5B	KMT5C	LIG1	LIG3	LIG4	LYN	MACROD1	MACROD2	MACROH2A1	MAD2L2	MAEL	MAGEF1	MAJIN	MAP2K6	MAP3K20	MAPK1	MAPK12	MAPK14	MAPK15	MAPK3	MAPKAPK2	MAPT	MARCHF7	MARF1	MASTL	MBD4	MBTD1	MBTPS1	MBTPS2	MC1R	MCL1	MCM10	MCM2	MCM3	MCM4	MCM5	MCM6	MCM7	MCM8	MCM9	MCMDC2	MCRS1	MCTS1	MDC1	MDM2	MDM4	MEAF6	MEIOB	MEIOC	MEN1	METTL3	MGME1	MGMT	MICA	MIF	MIR193A	MIR221	MIR34A	MLH1	MLH3	MLST8	MMS19	MMS22L	MNAT1	MNDA	MOAP1	MORC2	MORF4L1	MORF4L2	MPG	MPND	MRE11	MRGBP	MRNIP	MSH2	MSH3	MSH4	MSH5	MSH6	MSL2	MSX1	MTA1	MTCH2	MTOR	MTREX	MUC1	MUS81	MUTYH	MYC	MYO6	NABP1	NABP2	NACC2	NBN	NCOA6	NDRG1	NDUFS6	NEDD4	NEIL1	NEIL2	NEIL3	NEK11	NEK4	NEURL4	NFAT5	NFATC2	NFATC4	NFRKB	NHEJ1	NIPBL	NKX3-1	NME3	NONO	NOP53	NPAS2	NPM1	NRBP1	NRBP2	NRDE2	NSD2	NSMCE1	NSMCE2	NSMCE3	NSMCE4A	NTHL1	NUAK1	NUCKS1	NUDT1	NUDT16L1	NUPR1	NUPR2	NYNRIN	OARD1	OGG1	OOEP	OTUB1	OTUD4	PAGR1	PAK1	PALB2	PARG	PARK7	PARP1	PARP10	PARP2	PARP3	PARP4	PARP9	PARPBP	PAXIP1	PAXX	PBRM1	PCLAF	PCNA	PDS5A	PDS5B	PELI1	PHF1	PHF10	PHF13	PHLDA3	PIAS1	PIAS4	PIDD1	PIERCE1	PIF1	PIK3R1	PLA2R1	PLK1	PLK2	PLK3	PLK5	PMAIP1	PML	PMS1	PMS2	PMS2P1	PMS2P3	PMS2P5	PMS2P6	PNKP	POGZ	POLA1	POLB	POLD1	POLD2	POLD3	POLD4	POLDIP2	POLE	POLE2	POLE3	POLG	POLH	POLI	POLK	POLL	POLM	POLN	POLQ	POLR2I	POT1	PPM1D	PPP1CA	PPP1R10	PPP1R15A	PPP2R5C	PPP4C	PPP4R2	PPP4R3A	PPP4R3B	PPP4R3C	PPP5C	PRAP1	PRDM9	PRIMPOL	PRKCD	PRKCG	PRKDC	PRMT1	PRMT6	PRPF19	PSEN1	PSMD10	PSMD14	PSME4	PTPN11	PTTG1	PTTG1IP	PWWP3A	PYCARD	PYHIN1	RAD1	RAD17	RAD18	RAD21	RAD21L1	RAD23A	RAD23B	RAD50	RAD51	RAD51AP1	RAD51B	RAD51C	RAD51D	RAD52	RAD54B	RAD54L	RAD9A	RAD9B	RADX	RASSF1	RBBP4	RBBP5	RBBP6	RBBP8	RBM24	RBM38	RBX1	RCHY1	REC8	RECQL	RECQL4	RECQL5	REV1	REV3L	REXO4	RFC1	RFC2	RFC3	RFC4	RFC5	RFWD3	RHNO1	RIF1	RINT1	RIOX1	RMI1	RMI2	RNASEH2A	RNASEH2B	RNASEH2C	RNF111	RNF113A	RNF126	RNF138	RNF168	RNF169	RNF8	RPA1	RPA2	RPA3	RPA4	RPL26	RPS27L	RPS3	RPS6KA6	RPTOR	RRM1	RRM2B	RTEL1	RUVBL1	RUVBL2	SAMHD1	SDE2	SEM1	SENP3	SESN2	SETD1A	SETD2	SETD7	SETMAR	SETX	SF3B3	SF3B5	SFN	SFPQ	SFR1	SFRP2	SGF29	SGK1	SHISA5	SHLD1	SHLD2	SHLD3	SHPRH	SIRT1	SIRT4	SIRT6	SIRT7	SKIL	SKP2	SLC30A9	SLF1	SLF2	SLFN11	SLX1A	SLX1B	SLX4	SMARCA2	SMARCA4	SMARCA5	SMARCAD1	SMARCAL1	SMARCB1	SMARCC1	SMARCC2	SMARCD1	SMARCD2	SMARCD3	SMARCE1	SMC1A	SMC3	SMC5	SMC6	SMCHD1	SMG1	SMUG1	SMYD2	SNAI1	SNAI2	SNW1	SOD2	SOX4	SP100	SPATA22	SPDYA	SPIDR	SPINDOC	SPIRE1	SPIRE2	SPO11	SPRED1	SPRED2	SPRTN	SSRP1	STK11	STK19	STK33	STK38	STUB1	STXBP4	SUMO1	SUPT16H	SUPT20H	SUPT3H	SUPT7L	SUSD6	SUV39H1	SWI5	SWSAP1	SYCP1	SYF2	TADA1	TADA2B	TADA3	TAF1	TAF10	TAF12	TAF2	TAF4	TAF5	TAF5L	TAF6	TAF6L	TAF7	TAF9	TAF9B	TANK	TAOK1	TAOK2	TAOK3	TDG	TDP1	TDP2	TELO2	TENT4A	TERB1	TERB2	TERF2	TERF2IP	TEX12	TEX15	TEX264	TFAP4	TFDP3	TFIP11	TFPT	TICRR	TIGAR	TIMELESS	TIPIN	TIPRL	TLK1	TLK2	TMEM109	TMEM161A	TNF	TNFRSF1A	TNFRSF1B	TNKS1BP1	TNP1	TONSL	TOP2A	TOP2B	TOP3A	TOP3B	TOPBP1	TOPORS	TP53	TP53BP1	TP63	TP73	TPT1	TRAF6	TRAIP	TREX1	TREX2	TRIAP1	TRIM28	TRIM32	TRIM39	TRIP12	TRIP13	TRRAP	TTC5	TTF2	TTI1	TTI2	TWIST1	UACA	UBA1	UBA6	UBA7	UBE2A	UBE2B	UBE2D3	UBE2E2	UBE2N	UBE2NL	UBE2T	UBE2U	UBE2V1	UBE2V2	UBE2W	UBQLN4	UBR5	UCHL5	UFL1	UHRF1	UIMC1	UNG	UPF1	URI1	USP1	USP10	USP16	USP22	USP28	USP3	USP43	USP44	USP45	USP47	USP51	USP7	USP9X	UVRAG	UVSSA	VAV3	VCP	VCPIP1	VPS72	VRK1	VRK2	VRK3	WAC	WAS	WDHD1	WDR33	WDR4	WDR48	WDR76	WNK1	WNK2	WNK3	WNT1	WRAP53	WRN	WRNIP1	XAB2	XIAP	XNDC1N	XPA	XPC	XRCC1	XRCC2	XRCC3	XRCC4	XRCC5	XRCC6	YAP1	YEATS4	YJU2	YY1	ZBTB1	ZBTB38	ZBTB4	ZBTB40	ZBTB7A	ZC3H12A	ZCWPW1	ZDHHC16	ZFYVE26	ZGRF1	ZMAT3	ZMPSTE24	ZMYND8	ZNF365	ZNF385A	ZNF432	ZNF668	ZNF830	ZNHIT1	ZRANB3	ZSWIM7
+GOBP_MITOTIC_INTRA_S_DNA_DAMAGE_CHECKPOINT_SIGNALING	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/GOBP_MITOTIC_INTRA_S_DNA_DAMAGE_CHECKPOINT_SIGNALING	ATF2	CHEK2	EME1	EME2	FANCD2	HUS1	HUS1B	MDC1	MRE11	MSH2	MUS81	NEK11	RAD17	RAD9A	RAD9B	TIPIN	XPC
+GOBP_NEGATIVE_REGULATION_OF_INTRINSIC_APOPTOTIC_SIGNALING_PATHWAY_IN_RESPONSE_TO_DNA_DAMAGE_BY_P53_CLASS_MEDIATOR	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/GOBP_NEGATIVE_REGULATION_OF_INTRINSIC_APOPTOTIC_SIGNALING_PATHWAY_IN_RESPONSE_TO_DNA_DAMAGE_BY_P53_CLASS_MEDIATOR	ATAD5	BCL2	BCL2L12	CD44	CD74	ELL3	ING2	KDM1A	MARCHF7	MIF	MUC1	SIRT1	TAF9	TAF9B	TRIAP1	ZNF385A
+GOBP_SIGNAL_TRANSDUCTION_IN_RESPONSE_TO_DNA_DAMAGE	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/GOBP_SIGNAL_TRANSDUCTION_IN_RESPONSE_TO_DNA_DAMAGE	ABL1	ABRAXAS1	ACER2	ANKRD1	ATAD5	ATF2	ATM	ATR	ATRIP	ATRX	BABAM1	BABAM2	BARD1	BATF	BCL3	BID	BLM	BRCA1	BRCA2	BRCC3	BRD4	BRIP1	BRSK1	CASP2	CASP9	CCAR2	CCND1	CD44	CD74	CDC14B	CDC5L	CDK1	CDK2	CDK5RAP3	CDKN1A	CDKN1B	CDKN2A	CEP63	CHEK1	CHEK2	CLOCK	CLSPN	COPS3	CRADD	CRY1	CUL4A	DDX5	DGKZ	DONSON	DOT1L	DTL	DTX3L	DYRK1A	DYRK3	E2F1	E2F7	EEF1E1	EIF2AK4	EME1	EME2	ERCC6	ETAA1	FANCD2	FBXO31	FBXO4	FBXO6	FEM1B	FOXM1	FOXN3	FOXO3	FOXO4	FZR1	GADD45A	GIGYF2	GML	GNB1L	GRB2	GTSE1	H2AX	HIC1	HINFP	HIPK2	HUS1	HUS1B	IER3	ING4	INTS7	KAT5	KDM1A	KMT5A	LYN	MAD2L2	MAP2K6	MAP3K20	MAPK12	MAPK14	MAPK3	MARCHF7	MBTPS1	MBTPS2	MDC1	MDM2	MDM4	MIF	MRE11	MRNIP	MSH2	MSX1	MUC1	MUS81	MYO6	NBN	NDRG1	NDUFS6	NEK11	NOP53	NPM1	PARP9	PAXIP1	PIDD1	PLA2R1	PLK1	PLK2	PLK3	PMAIP1	PML	PPM1D	PPP1R10	PPP2R5C	PRAP1	PRKDC	PRPF19	PSMD10	PTPN11	PTTG1IP	PYHIN1	RAD1	RAD17	RAD51	RAD9A	RAD9B	RBM38	RFWD3	RHNO1	RINT1	RNASEH2B	RNF8	RPA2	RPA4	RPL26	RPS27L	RPS6KA6	SDE2	SESN2	SIRT1	SMYD2	SNAI1	SNAI2	SOX4	SP100	SPRED1	SPRED2	STK33	STK38	SYF2	TAOK1	TAOK2	TAOK3	TELO2	TFAP4	TICRR	TIPIN	TIPRL	TOPBP1	TP53	TP53BP1	TREX1	TRIAP1	TRIM39	TTI1	TTI2	TWIST1	UFL1	UIMC1	USP10	USP28	WAC	WDR76	WNT1	XPC	YJU2	ZMPSTE24	ZNF385A	ZNF830	ZNHIT1
+KYNG_DNA_DAMAGE_UP	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/KYNG_DNA_DAMAGE_UP	ABCC1	ADAM11	ADAM12	ADAMTS3	ADH6	ADSL	AHCY	AKAP6	ALDH8A1	AP1G1	APPBP2	ARNT	ARNT2	ASMTL	ATF7	ATP5MJ	ATP6V0A1	ATP6V0B	ATP7A	AVPR1A	BAP1	BCL2L2	BDH2	C1QTNF6	C3AR1	CACNA1I	CCL13	CCL28	CD8A	CEPT1	CHL1	CHRNA7	CHRNE	CKS2	CNKSR1	COL17A1	CRABP2	CTNND1	CXADR	CXCR4	CYB5A	CYBB	CYBRD1	CYP19A1	CYP39A1	DBT	DCT	DCTD	DDX18	DIS3	DLX4	DNALI1	DOCK2	DSC2	DUSP5	EFNB3	EGFR	EIF4A1	ELF4	EML4	ENPP5	ENTPD1	EPHA1	ERCC5	EVI2A	FADS1	FAN1	FBLN1	FOLH1	FRZB	FUT4	GCLC	GDF11	GGA3	GM2A	GNPNAT1	GSTA2	GYPB	H2AJ	HBEGF	HCLS1	HELZ	HIBADH	HLA-DQB1	HNMT	HNRNPC	HNRNPD	HOXD9	HPCA	HSF2	IGFBP1	IL16	IL18R1	IL1R1	INSL4	ITIH2	ITPKB	KCNK1	KIF14	KIFC1	LCP2	LDHD	LIG4	LINS1	LIPC	LRBA	LRP1	LRRFIP2	MECOM	MEF2C	MET	MGAT2	MITF	MMP7	MPP3	MSX2	MTA1	MYB	MYO5B	N4BP1	NCOR1	NDEL1	NFYB	NRCAM	NRK	NRP2	PCDH1	PCSK5	PCYT2	PDCD10	PDCD2	PDE3A	PDE4DIP	PDHA1	PFN1	PHF3	PHLDA1	PLCL1	PLD6	POFUT1	POLR2A	PPIEL	PPOX	PPP1R12C	PPP2CB	PPP3CA	PRG2	PRLR	PTGFRN	PTH	PTPRCAP	PTPRK	PTPRN2	QPCT	RAB1B	RAB6A	RAB7A	RAB9A	RBBP6	RBM3	RBM5	RBM6	RBP4	RIT2	RNF168	ROPN1L	RPS6KA3	RPS6KB1	RUFY3	SCD	SEC22A	SEC23A	SGPL1	SIAH1	SIRT5	SKAP1	SLC1A3	SLC30A5	SLC6A1	SLC6A12	SLC9A6	SLCO2A1	SMAD4	SOX7	SOX9	SP140	SP3	STAT3	STAT5B	SYK	SYNC	TCEA2	TFDP2	THOC1	TIE1	TOPBP1	TRAF6	UBE2N	UBR2	USP1	USP9X	VASP	VCAM1	WNT5A	ZNF507
+KYNG_DNA_DAMAGE_DN	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/KYNG_DNA_DAMAGE_DN	ACE	ACTN4	ADAMTS1	AGPAT1	AKAP12	ALDH3B2	ALDH9A1	ANKRD11	ANXA1	AP3B2	APBA3	ARF1	ARPC1B	ATOX1	ATP5ME	ATRX	BEX3	BNIP3L	BTG3	CAB39	CALU	CCN2	CCNA2	CCNC	CCND1	CCNH	CCNL2	CD36	CD53	CD69	CDC25A	CDCA7	CEBPB	CIB2	CIR1	CNN1	COG6	COL3A1	COPB2	COPS7A	CREBBP	CRHBP	CRYAB	CSDE1	CSF2RB	CSNK1A1	CTCF	CXCL2	CYCS	CYP51A1	DAXX	DNAJA1	DSCAM	EFNB1	EGR1	EIF3L	EIF4E	ENDOU	EPS8L1	ESD	FBLN2	FGF2	FGFR4	FLOT1	FMO4	FN1	GADD45A	GALNT2	GBP1	GLRX	GOLGA4	GOLPH3	GPD2	GYPB	HEXB	HGF	HLA-DQA1	HSD17B10	HSPB8	ID1	IFNGR1	IFNGR2	IGF1	IGFBP3	IL10RB	IL11RA	INPP1	IRF2	ITGAL	ITGB1	ITGB5	ITGB8	KRT13	LCK	LCN2	LDHC	LIMS1	LOX	LSP1P4	MARK3	MINK1	C1ORF61	MOK	MORF4L1	MT1H	MT1X	MYD88	NDRG1	NDUFB6	NET1	NGF	NMT1	NNMT	NRP2	OAZ1	PAFAH1B3	PBX1	PCK2	PCNA	PDCD5	PDGFRL	POLR2F	PPA1	PPP1R14A	PPP2CA	PRDX4	PRELP	PRKAB1	PRKAB2	PRKACA	PRKD2	PRMT1	PRSS23	PSG1	PSG2	PTGER4	PTPN18	RAB11B	RAB2A	RAB6A	RAB7A	RABGGTB	RAP2A	RBL1	RHOB	RHOBTB3	RHOD	RIN2	RPL7A	SAA1	SEM1	SEMA3B	SEMA4D	SEMA7A	SERPINB2	SERPINB6	SERPINE2	SGCB	SLC31A2	SLC35B1	SNX8	SOD1	SSR3	ST6GALNAC2	SUOX	TAF10	TAF1C	TBCA	TCF7L2	TFPI2	TGFB3	TIA1	TLE1	TNFRSF10B	TP53I11	TPM1	TPR	TWF1	TXNRD2	UGCG	VDAC3	VIM
+MODULE_403	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/MODULE_403	ATR	CCNB1	CCNE2	CDC20	CDC25B	CDC45	CDK1	CDK2	CDK4	CENPA	CHD3	DPP7	DTYMK	E2F1	EREG	FEN1	FTCD	G0S2	H2AZ1	KPNA2	MCM3	MCM6	MELK	MKI67	MSH2	MYBL2	NEK2	PCNA	PLK1	PLK4	PRKX	RECQL4	RPA1	SNX11	TFDP1	TK1	TOP2A	TOPBP1	TRUB1	UBE2V2	UNG	VPS50	VRK1	WEE1	XRCC3	XRCC5
+REACTOME_DNA_DAMAGE_REVERSAL	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/REACTOME_DNA_DAMAGE_REVERSAL	ALKBH2	ALKBH3	ALKBH5	ASCC1	ASCC2	ASCC3	FTO	MGMT
+REACTOME_G1_S_DNA_DAMAGE_CHECKPOINTS	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/REACTOME_G1_S_DNA_DAMAGE_CHECKPOINTS	ADRM1	ATM	CCNA1	CCNA2	CCNE1	CCNE2	CDC25A	CDK2	CDKN1A	CDKN1B	CDKN2A	CHEK1	CHEK2	COP1	MDM2	MDM4	PCBP4	PHF20	PSMA1	PSMA2	PSMA3	PSMA4	PSMA5	PSMA6	PSMA7	PSMB1	PSMB2	PSMB3	PSMB4	PSMB5	PSMB6	PSMB7	PSMC1	PSMC2	PSMC3	PSMC4	PSMC5	PSMC6	PSMD1	PSMD11	PSMD12	PSMD13	PSMD14	PSMD2	PSMD3	PSMD6	PSMD7	PSMD8	RPS27A	SEM1	TP53	UBA52	UBB	UBC	ZNF385A
+REACTOME_G2_M_DNA_DAMAGE_CHECKPOINT	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/REACTOME_G2_M_DNA_DAMAGE_CHECKPOINT	ABRAXAS1	ATM	ATR	ATRIP	BABAM1	BABAM2	BARD1	BLM	BRCA1	BRCC3	BRIP1	CCNA1	CCNA2	CCNB1	CDC25C	CDK1	CHEK1	CHEK2	DNA2	EXO1	H2AX	H2BC1	H2BC10	H2BC11	H2BC12	H2BC12L	H2BC13	H2BC14	H2BC15	H2BC17	H2BC21	H2BC26	H2BC3	H2BC4	H2BC5	H2BC6	H2BC7	H2BC8	H2BC9	HIST3H3	H4C1	H4C11	H4C12	H4C13	H4C14	H4C15	H4C16	H4C2	H4C3	H4C4	H4C5	H4C6	H4C8	H4C9	HERC2	HUS1	KAT5	MDC1	MRE11	NBN	NSD2	PIAS4	RAD1	RAD17	RAD50	RAD9A	RAD9B	RBBP8	RFC2	RFC3	RFC4	RFC5	RHNO1	RMI1	RMI2	RNF168	RNF8	RPA1	RPA2	RPA3	SFN	TOP3A	TOPBP1	TP53	TP53BP1	UBE2N	UBE2V2	UIMC1	WEE1	WRN	YWHAB	YWHAE	YWHAG	YWHAH	YWHAQ	YWHAZ
+REACTOME_P53_DEPENDENT_G1_DNA_DAMAGE_RESPONSE	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/REACTOME_P53_DEPENDENT_G1_DNA_DAMAGE_RESPONSE	ATM	CCNE1	CCNE2	CDK2	CDKN1A	CDKN1B	COP1	COP1P1	MDM2	PSMA1	PSMA2	PSMA3	PSMA4	PSMA5	PSMA6	PSMA7	PSMA8	PSMB1	PSMB10	PSMB2	PSMB3	PSMB4	PSMB5	PSMB6	PSMB7	PSMB8	PSMB9	PSMC1	PSMC2	PSMC3	PSMC4	PSMC5	PSMC6	PSMD1	PSMD10	PSMD11	PSMD12	PSMD13	PSMD14	PSMD2	PSMD3	PSMD4	PSMD5	PSMD6	PSMD7	PSMD8	PSMD9	PSME1	PSME2	PSME4	PSMF1	RPS27A	RPS27AP11	TP53	UBA52
+REACTOME_P53_INDEPENDENT_G1_S_DNA_DAMAGE_CHECKPOINT	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/REACTOME_P53_INDEPENDENT_G1_S_DNA_DAMAGE_CHECKPOINT	ATM	CDC25A	CHEK1	CHEK2	PSMA1	PSMA2	PSMA3	PSMA4	PSMA5	PSMA6	PSMA7	PSMA8	PSMB1	PSMB10	PSMB2	PSMB3	PSMB4	PSMB5	PSMB6	PSMB7	PSMB8	PSMB9	PSMC1	PSMC2	PSMC3	PSMC4	PSMC5	PSMC6	PSMD1	PSMD10	PSMD11	PSMD12	PSMD13	PSMD14	PSMD2	PSMD3	PSMD4	PSMD5	PSMD6	PSMD7	PSMD8	PSMD9	PSME1	PSME2	PSME4	PSMF1	RPS27A	RPS27AP11	UBA52
+WP_DNA_DAMAGE_RESPONSE	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/WP_DNA_DAMAGE_RESPONSE	ABL1	AKT1	APAF1	ATM	ATR	ATRIP	BAX	BBC3	BID	BRCA1	CASP3	CASP8	CASP9	CCNB1	CCNB2	CCNB3	CCND1	CCND2	CCND3	CCNE1	CCNE2	CDC25A	CDC25C	CDK1	CDK2	CDK4	CDK5	CDK6	CDKN1A	CDKN1B	CHEK1	CHEK2	CREB1	CYCS	DDB2	E2F1	FANCD2	FAS	GADD45A	GADD45B	GADD45G	H2AX	HUS1B	MDM2	MRE11	MYC	NBN	PIDD1	PMAIP1	PML	PRKDC	RAD1	RAD17	RAD50	RAD51	RAD52	RAD9A	RB1	RFC1	RPA2	RRM2B	SESN1	SFN	SMC1A	TLK1	TLK2	TNFRSF10B	TP53	TP53AIP1
+WP_DNA_DAMAGE_RESPONSE_ONLY_ATM_DEPENDENT	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/WP_DNA_DAMAGE_RESPONSE_ONLY_ATM_DEPENDENT	ABL1	AKT1	AKT2	AKT3	APC	ATM	AXIN1	BAD	BAK1	BAX	BBC3	BCL2	BCL2L11	BCL6	BIK	CAT	CCND1	CCND2	CCND3	CCNG2	CDC42	CDKN1A	CDKN1B	CDKN2A	CTNNB1	DVL1	DVL2	DVL3	ERBB2	FASLG	FOSL1	FOXO3	FRAT1	G6PC1	GRB2	GSK3B	HMGB1	HRAS	INSR	IRS1	JUN	KRAS	LDLR	LEF1	MAP3K1	MAP3K4	MAP3K7	MAPK1	MAPK10	MAPK8	MAPK9	MDM2	MLKL	MYC	NFKB1	NFKB2	NRAS	PCK2	PDK1	PIK3C2A	PIK3C2B	PIK3C2G	PIK3C3	PIK3CA	PIK3CB	PIK3CD	PIK3CG	PIK3R1	PIK3R2	PIK3R3	PIK3R4	PIK3R5	PLAU	PMAIP1	PPP2R5C	PPP2R5E	PTEN	RAC1	RAC2	RAC3	RBL2	RHOA	SCP2	SHC1	SMAD3	SMAD4	SOD2	SOS1	SOS2	TCF7	TCF7L1	TCF7L2	TGFB1	TP53	TP73	WNT1	WNT10A	WNT10B	WNT11	WNT16	WNT2	WNT2B	WNT3	WNT3A	WNT4	WNT5A	WNT5B	WNT6	WNT7A	WNT7B
+WP_MIRNAS_INVOLVED_IN_DNA_DAMAGE_RESPONSE	https://www.gsea-msigdb.org/gsea/msigdb/human/geneset/WP_MIRNAS_INVOLVED_IN_DNA_DAMAGE_RESPONSE	ABL1	APAF1	ATM	ATR	ATRIP	BAX	BBC3	BID	BRCA1	CASP3	CASP8	CASP9	CCNB1	CCNB2	CCNB3	CCND1	CCND2	CCND3	CCNE1	CCNE2	CCNG1	CDC20B	CDC25A	CDC25C	CDK1	CDK2	CDK4	CDK5	CDK6	CDKN1A	CDKN1B	CHEK1	CHEK2	CREB1	CYCS	DDB2	E2F1	FANCD2	FAS	GADD45A	GADD45B	GADD45G	H2AX	HUS1B	MCM7	MDM2	MIR106B	MIR145	MIR15A	MIR16-1	MIR17	MIR17HG	MIR181A1	MIR195	MIR203A	MIR20A	MIR21	MIR210	MIR221	MIR222	MIR223	MIR24-1	MIR29A	MIR29B1	MIR29C	MIR330	MIR34B	MIR3591	MIR373	MIR421	MIR424	MIR449A	MIR449B	MRE11	MYC	NBN	PIDD1	PMAIP1	PML	PRKDC	RAD1	RAD17	RAD50	RAD51	RAD52	RAD9A	RB1	RFC1	RPA2	RRM2B	SESN1	SFN	SMC1A	TLK1	TLK2	TNFRSF10B	TP53	TP53AIP1
--- a/DNA_damage_repair.R
+++ b/DNA_damage_repair.R
+library(Seurat)
+library(ggplot2)
+library(dittoSeq)
+library(UCell)
+library(openxlsx)
+library(ggpubr)
+library(dplyr)
+library(tidyr)
+library(purrr)
+library(clusterProfiler)
+library(ComplexHeatmap)
+library(circlize)
+
+outdir <- "HSC_vs_Bulk_Focus_Supplemental_2B/"
+dir.create(outdir)
+
+obj_fig2C <- readRDS("Fig2C_Dataset.rds")
+
+gmt_total_v7.2 <- read.gmt("https://data.broadinstitute.org/gsea-msigdb/msigdb/release/7.2/msigdb.v7.2.symbols.gmt")
+dna_damage_and_repair_A <- read.gmt(gmtfile = "DNA_damage_and_repair_genesets.v2025.1.Hs.gmt")
+dna_damage_and_repair_Av7.2 <- read.gmt(gmtfile = "DNA_damage_and_repair_genesets.v7.2.Hs.alias_aligned.gmt") # by AI 
+
+# da gmt df a list #
+dna_damage_and_repair_A_list <- split(dna_damage_and_repair_Av7.2$gene, dna_damage_and_repair_Av7.2$term)
+dna_damage_and_repair_A_list <- lapply(dna_damage_and_repair_A_list, unique)
+
+# adding custom terms #
+
+dna_damage_and_repair_A_list$FORK_REVERSAL <- c('FBH1','SMARCAL1','ZRANB3','HLTF')
+dna_damage_and_repair_A_list$FORK_RESTART <- c('RECQL','WRN','RNF8','DNA2')
+dna_damage_and_repair_A_list$REPRIMING <- c('BLM','RMI1','TOP3A','RMI2','PRIMPOL')
+
+dna_damage_and_repair_B <- read.gmt(gmtfile = "DNA_Repair_signatures_LoFurnoDellaVolpe.gmt")
+dna_damage_and_repair_B$term <- gsub(pattern = " ", replacement = "_", x = dna_damage_and_repair_B$term)
+dna_damage_and_repair_B$term <- gsub(pattern = "\\)", replacement = "", x = dna_damage_and_repair_B$term)
+dna_damage_and_repair_B$term <- gsub(pattern = "\\(", replacement = "", x = dna_damage_and_repair_B$term)
+dna_damage_and_repair_B$term <- gsub(pattern = "-", replacement = "_", x = dna_damage_and_repair_B$term)
+dna_damage_and_repair_B_list <- split(dna_damage_and_repair_B$gene, dna_damage_and_repair_B$term)
+dna_damage_and_repair_B_list <- lapply(dna_damage_and_repair_B_list, unique)
+
+# combino liste
+
+dna_damage_and_repair_list <- c(dna_damage_and_repair_A_list, dna_damage_and_repair_B_list)
+
+obj_fig2C_Cs <- AddModuleScore_UCell(obj = subset(obj_fig2C, idents = c("C04","C02","C03")),
+                                     features = dna_damage_and_repair_list)
+
+saveRDS(object = obj_fig2C_Cs@meta.data, file = "obj_fig2C_Cs_metadata.rds")
+
+# releveling and rename levels across timepoint ##
+
+obj_fig2C_Cs$orig.ident.f <- factor(obj_fig2C_Cs$orig.ident, levels = c("C04","C02","C03"), labels = c("NC","Day4","Day7"))
+obj_fig2C_Cs$Timepoint.f <- obj_fig2C_Cs$orig.ident.f
+obj_fig2C_Cs$PopTimepoint <- paste0(obj_fig2C_Cs$Population, "_", obj_fig2C_Cs$Timepoint.f)
+obj_fig2C_Cs$PopTimepoint <- factor(obj_fig2C_Cs$PopTimepoint, 
+                                    levels = with(expand.grid(levels(obj_fig2C_Cs$Timepoint.f) , levels(obj_fig2C_Cs$Population)), 
+                                                              paste0(Var2, "_", Var1)))
+
+fig2C_terms <- grep(x = colnames(obj_fig2C_Cs@meta.data), pattern = "UCell", value = T)
+
+# subsetting dataset looking only at HSC or Bulk #
+
+outdir2 <- paste(outdir, "FocusHSC/")
+dir.create(outdir2)
+
+obj_fig2C_Cs$Group <- ifelse(test = obj_fig2C_Cs$Population != "HSC", "Bulk", "HSC")
+obj_fig2C_Cs$Group <- factor(obj_fig2C_Cs$Group, levels = c("HSC","Bulk"))
+
+obj_fig2C_Cs$GroupTimepoint <- paste0(obj_fig2C_Cs$Group, "_", obj_fig2C_Cs$Timepoint.f)
+obj_fig2C_Cs$GroupTimepoint <- factor(obj_fig2C_Cs$GroupTimepoint, 
+                                    levels = c("HSC_NC","Bulk_NC", "HSC_Day4", "Bulk_Day4", "HSC_Day7", "Bulk_Day7"))
+
+datasets <- list(fig2C = list(object = obj_fig2C_Cs, 
+                              var1 = "Timepoint.f",
+                              var2 = "Group",
+                              var3 = "GroupTimepoint",
+                              reduction = "umap.harmony.orig.ident",
+                              sigterms = fig2C_terms
+                              )
+                 )
+
+
+### Custom plot fig2c ###
+
+pdf(file = paste0(outdir2, "FigS2C_Heatmap_DNA_damage_terms_Group_x_TP.pdf"), width = 9, height = 6)
+
+datasetid <- names(datasets)[1]
+idvar <- "var3"
+
+meta_df <- datasets[[datasetid]][["object"]]@meta.data %>%
+  select(all_of(c(datasets[[datasetid]][[idvar]], datasets[[datasetid]][["sigterms"]]))) %>%
+  group_by(!!sym(datasets[[datasetid]][[idvar]])) %>%
+  summarise(across(all_of(datasets[[datasetid]][["sigterms"]]), 
+                   ~ median(.x, na.rm = TRUE),  
+                   .names = "{.col}"), 
+            .groups = 'drop')
+
+meta_df <- as.data.frame(meta_df)
+rownames(meta_df) <- meta_df$GroupTimepoint
+meta_df$GroupTimepoint <- NULL
+meta_df <- meta_df[, colSums(abs(meta_df)) > 0, drop = FALSE]
+#meta_df$GroupTimepoint <- row.names(meta_df)
+
+
+# traspose
+heatmap_mat <- as.matrix(t(meta_df))  # Prima colonna è pop_col
+colnames(heatmap_mat) <- rownames(meta_df)
+
+# Scaling 
+heatmap_mat_t <- t(scale(t(heatmap_mat)))  
+
+# custom palette - soft
+col_fun <- colorRamp2(c(-2, 0, 2), c("#00B4D8", "white", "#FF2E35")) # "#00B4D8" #FF2E35
+
+ncol_total <- ncol(heatmap_mat_t)
+col_split <- c(rep("NC", 2), rep("Day4", 2), rep("Day7", ncol_total - 4))
+
+rownames(heatmap_mat_t) <- gsub(x = rownames(heatmap_mat_t), pattern = "_UCell", replacement = "")
+
+p <- Heatmap(heatmap_mat_t,
+             name = "Median Z-score",
+             col = col_fun, 
+             cluster_rows = TRUE,
+             cluster_columns = FALSE,  
+             show_row_names = TRUE,
+             show_column_names = TRUE,
+             row_names_gp = gpar(fontsize = 6),
+             column_names_gp = gpar(fontsize = 6),
+             width = unit(4, "cm"),
+             column_split = factor(col_split, levels = unique(col_split)),
+             show_heatmap_legend = FALSE)
+
+draw(p, padding = unit(c(2, 2, 2, 100), "mm")) # c(bottom, left, top, right)
+dev.off()
--- a/obj_fig2C_Cs_metadata.rds
+++ b/obj_fig2C_Cs_metadata.rds