Prepare TF Modules 03

Explore and visualize the data

Set environment

suppressMessages(suppressWarnings(source("../run_config_project_sing.R")))
suppressMessages(suppressWarnings(library("pheatmap")))
show_env()

You are working on        Singularity: singularity_proj_encode_fcc 
BASE DIRECTORY (FD_BASE): /data/reddylab/Kuei 
REPO DIRECTORY (FD_REPO): /data/reddylab/Kuei/repo 
WORK DIRECTORY (FD_WORK): /data/reddylab/Kuei/work 
DATA DIRECTORY (FD_DATA): /data/reddylab/Kuei/data 

You are working with      ENCODE FCC 
PATH OF PROJECT (FD_PRJ): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC 
PROJECT RESULTS (FD_RES): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/results 
PROJECT SCRIPTS (FD_EXE): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/scripts 
PROJECT DATA    (FD_DAT): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/data 
PROJECT NOTE    (FD_NBK): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/notebooks 
PROJECT DOCS    (FD_DOC): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/docs 
PROJECT LOG     (FD_LOG): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/log 
PROJECT REF     (FD_REF): /data/reddylab/Kuei/repo/Proj_ENCODE_FCC/references 

Set global variables

TXT_FOLDER_REGION = "module_tf_shannon"

Import data

### set directory
txt_folder = TXT_FOLDER_REGION
txt_fdiry  = file.path(FD_RES, "region", txt_folder, "summary")

vec = dir(txt_fdiry)
for (txt in vec){cat(txt, "\n")}

data.module2TF.tsv 
data.region2module.tsv 
data.region2TF.tsv 
description.tsv 
matrix.module2TF.tsv 
matrix.region2module.tsv 
matrix.region2TF.tsv 
metadata.label.tsv 

### set file path
txt_folder = TXT_FOLDER_REGION
txt_fdiry  = file.path(FD_RES, "region", txt_folder, "summary")
txt_fname  = "matrix.region2module.tsv"
txt_fpath  = file.path(txt_fdiry, txt_fname)

### read table
dat = read_tsv(txt_fpath, show_col_types = FALSE)

### assign and show
dat_region2module_matrix = dat
print(dim(dat))
fun_display_table(head(dat, 3))

[1] 173996     74

Chrom	ChromStart	ChromEnd	Region	Module_01	Module_02	Module_03	Module_04	Module_05	Module_06	Module_07	Module_08	Module_09	Module_10	Module_11	Module_12	Module_13	Module_14	Module_15	Module_16	Module_17	Module_18	Module_19	Module_20	Module_21	Module_22	Module_23	Module_24	Module_25	Module_26	Module_27	Module_28	Module_29	Module_30	Module_31	Module_33	Module_34	Module_35	Module_36	Module_37	Module_39	Module_40	Module_41	Module_42	Module_43	Module_44	Module_45	Module_46	Module_47	Module_48	Module_49	Module_50	Module_51	Module_52	Module_53	Module_54	Module_55	Module_56	Module_57	Module_58	Module_59	Module_61	Module_63	Module_64	Module_65	Module_66	Module_67	Module_68	Module_71	Module_72	Module_73	Module_74	Module_75	Module_77
chr1	115702	115751	chr1:115702-115751	0	1	0	0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
chr1	118585	118665	chr1:118585-118665	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
chr1	136446	136510	chr1:136446-136510	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0

### set file path
txt_folder = TXT_FOLDER_REGION
txt_fdiry  = file.path(FD_RES, "region", txt_folder, "summary")
txt_fname  = "matrix.region2TF.tsv"
txt_fpath  = file.path(txt_fdiry, txt_fname)

### read table
dat = read_tsv(txt_fpath, show_col_types = FALSE)

### assign and show
dat_region2TF_matrix = dat
print(dim(dat))
fun_display_table(head(dat, 3))

[1] 173996    269

Chrom	ChromStart	ChromEnd	Region	ADNP	AGO1	ARHGAP35	ARID2	ARID3A	ARID4B	ARNT	ATF1	ATF2	ATF3	ATF4	ATF6	ATF7	BCL6	BHLHE40	BRD4	BRF2	CAMTA2	CBFB	CBX1	CBX2	CBX5	CCAR2	CEBPB	CEBPG	CEBPZ	CHCHD3	CHD2	CHD4	CREB1	CREB3	CREM	CTCF	DDIT3	DMTF1	DPF2	E2F1	E2F4	E2F5	E2F8	EGR1	EHMT2	ELF1	ELF4	ELK1	EP300	ERF	ESRRA	ETS1	ETV5	ETV6	EZH2	FIP1L1	FOSL1	FOXA1	FOXA3	FOXJ3	FOXK1	FOXK2	FOXM1	FOXP1	FOXP4	FUS	GABPA	GABPB1	GATA2	GATAD2A	GMEB1	GTF2F1	HBP1	HCFC1	HDAC1	HDAC2	HDAC6	HINFP	HIVEP1	HMG20A	HMG20B	HNRNPH1	HNRNPK	HNRNPL	HNRNPLL	HNRNPUL1	HOMEZ	IKZF1	IRF1	IRF2	IRF9	JUN	JUNB	JUND	KAT2B	KAT7	KAT8	KDM1A	KDM5B	KLF13	KLF16	KLF6	LCOR	MAFF	MAFG	MAFK	MAX	MAZ	MBD1	MEF2A	MEF2D	MEIS2	MGA	MLX	MNT	MTA1	MTA3	MTF1	MXD1	MXI1	MYBL2	MYC	MYNN	NBN	NCOA1	NCOA2	NCOR1	NFATC3	NFE2	NFE2L1	NFIC	NFRKB	NFYA	NONO	NR1H2	NR2C2	NR2F1	NR2F2	NR2F6	NR3C1	NRF1	PATZ1	PBX2	PCBP1	PCBP2	PHB2	PHF20	PHF21A	PHF8	POLR2A	POLR2AphosphoS2	POLR2AphosphoS5	POLR2G	PRDM10	PRPF4	PTBP1	RAD21	RAD51	RBFOX2	RBM22	RBM39	RBPJ	RCOR1	RELA	REST	RFX1	RFX5	RNF2	RNF219	RREB1	SAFB2	SETDB1	SFPQ	SIN3A	SIN3B	SKIL	SMAD1	SMAD3	SMAD4	SMARCC2	SMARCE1	SMC3	SNRNP70	SOX6	SP1	SRF	SRSF1	SRSF9	STAG1	STAT5B	SUZ12	TAF15	TARDBP	TBL1XR1	TBP	TCF12	TCF3	TCF7	TCF7L2	TEAD1	TEAD2	TEAD4	TFAP4	TFDP1	TFE3	TGIF2	THRA	THRB	TOE1	TRIM24	U2AF1	U2AF2	UBTF	USF1	USF2	XRCC5	YY1	ZBTB2	ZBTB26	ZBTB33	ZBTB34	ZBTB40	ZBTB49	ZBTB7A	ZBTB8A	ZC3H4	ZC3H8	ZFP1	ZFP36	ZFP91	ZFX	ZHX1	ZKSCAN1	ZKSCAN8	ZMYM3	ZNF12	ZNF121	ZNF124	ZNF143	ZNF146	ZNF217	ZNF224	ZNF232	ZNF24	ZNF253	ZNF263	ZNF274	ZNF280B	ZNF281	ZNF282	ZNF3	ZNF318	ZNF354B	ZNF384	ZNF431	ZNF511	ZNF512	ZNF589	ZNF639	ZNF644	ZNF7	ZNF707	ZNF740	ZNF766	ZNF780A	ZNF83	ZSCAN29	ZZZ3
chr1	115702	115751	chr1:115702-115751	0	0	0	0	1	0	0	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	1	0	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	0	1	1	0	0	0	0	1	0	1	1	0	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	1	1	0	0	0	0	0	0	1	1	0	1	0	1	0	1	1	0	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	1	1	0	0	1	0	0	0	0	0	0	0	0	0	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	1	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
chr1	118585	118665	chr1:118585-118665	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
chr1	136446	136510	chr1:136446-136510	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0

### set file path
txt_folder = TXT_FOLDER_REGION
txt_fdiry  = file.path(FD_RES, "region", txt_folder, "summary")
txt_fname  = "matrix.module2TF.tsv"
txt_fpath  = file.path(txt_fdiry, txt_fname)

### read table
dat = read_tsv(txt_fpath, show_col_types = FALSE)

### assign and show
dat_module2TF_matrix = dat
print(dim(dat))
fun_display_table(head(dat, 3))

[1] 234  71

TF	Module_01	Module_02	Module_03	Module_04	Module_05	Module_06	Module_07	Module_08	Module_09	Module_10	Module_11	Module_12	Module_13	Module_14	Module_15	Module_16	Module_17	Module_18	Module_19	Module_20	Module_21	Module_22	Module_23	Module_24	Module_25	Module_26	Module_27	Module_28	Module_29	Module_30	Module_31	Module_33	Module_34	Module_35	Module_36	Module_37	Module_39	Module_40	Module_41	Module_42	Module_43	Module_44	Module_45	Module_46	Module_47	Module_48	Module_49	Module_50	Module_51	Module_52	Module_53	Module_54	Module_55	Module_56	Module_57	Module_58	Module_59	Module_61	Module_63	Module_64	Module_65	Module_66	Module_67	Module_68	Module_71	Module_72	Module_73	Module_74	Module_75	Module_77
ADNP	0	0	1	0	0	0	0	1	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
AGO1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	1	0	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0
ARHGAP35	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0

Explore data

Region-Module: Module locations across the genome

### arrange the matrix
dat = dat_region2module_matrix
dat = dat %>% 
    dplyr::select(-Chrom, -ChromStart, -ChromEnd) %>% 
    column_to_rownames("Region")

### assign and show
dat = dat_region2module_arrange = dat
print(dim(dat))
head(dat)

[1] 173996     70

A data.frame: 6 × 70

	Module_01	Module_02	Module_03	Module_04	Module_05	Module_06	Module_07	Module_08	Module_09	Module_10	⋯	Module_65	Module_66	Module_67	Module_68	Module_71	Module_72	Module_73	Module_74	Module_75	Module_77
	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
chr1:115702-115751	0	1	0	0	1	0	0	0	0	1	⋯	0	0	0	0	0	0	0	0	0	0
chr1:118585-118665	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:136446-136510	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:139031-139110	0	1	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:268005-268051	0	1	0	0	0	0	0	0	0	1	⋯	0	0	0	0	0	0	0	0	0	0
chr1:586187-586203	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0

Summarize counts of the binary matrix

### count by row
dat = dat = dat_region2module_arrange
vec = apply(dat, 1, sum)
dat = tibble(Region = names(vec), Count = vec)
dat = dat %>% dplyr::arrange(Count)

### assign and summary
dat_region_stats = dat
print(dim(dat))
print(summary(vec))

### show top/bottom of table
fun_display_table(
    bind_rows(
        head(dat, 6), 
        tail(dat, 6)
    )
)

[1] 173996      2
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  1.000   1.000   2.000   2.378   3.000  14.000 

Region	Count
chr1:118585-118665	1
chr1:136446-136510	1
chr1:586187-586203	1
chr1:905285-905486	1
chr1:905662-905685	1
chr1:912602-912614	1
chr17:46795428-46795947	12
chr18:23528512-23530101	12
chr19:6603491-6604311	12
chr8:102809995-102811632	12
chr19:10835074-10837434	13
chr10:71860432-71861688	14

### count by column
dat = dat_region2module_arrange
vec = apply(dat, 2, sum)
dat = tibble(Module = names(vec), Count = vec)
dat = dat %>% dplyr::arrange(Count)

### assign and summary
dat_module_stats = dat
print(dim(dat))
print(summary(vec))

### show top/bottom of table
fun_display_table(
    bind_rows(
        head(dat, 6), 
        tail(dat, 6)
    )
)

[1] 70  2
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    636    2052    4620    5910    8176   24267 

Module	Count
Module_08	636
Module_65	636
Module_53	695
Module_26	802
Module_74	849
Module_09	916
Module_35	13060
Module_27	13750
Module_15	17534
Module_02	18655
Module_06	21510
Module_44	24267

Visualize the summary

dat = dat_region_stats
gpt = ggplot(dat, aes(x=Count)) + 
    geom_histogram(bins = 100) + 
    theme_cowplot() + 
    background_grid()

options(repr.plot.height=4, repr.plot.width=10)
print(gpt)

dat = dat_module_stats         
gpt = ggplot(dat, aes(x=Count)) + 
    geom_histogram(bins = 100) + 
    theme_cowplot() + 
    background_grid() +
    labs(x="#{Region} each module binds)", y = "Count")

options(repr.plot.height=4, repr.plot.width=10)
print(gpt)

Subset and plot the matrix

dat = dat_region_stats
dat = dat %>% dplyr::filter(Count > 5)
idx = dat$Region
idx_region = idx

dat = dat_module_stats
dat = dat %>% dplyr::filter(Count > 10)
idx = dat$Module
idx_module = idx

### init
dat = dat_region2module_arrange
print(dim(dat))

### subset the matrix
dat = dat[idx_region, idx_module]
print(dim(dat))

### subset the matrix
set.seed(123)
idx = sample(1:nrow(dat), size=7000)
dat = dat[idx,]
print(dim(dat))

### assign
dat_region2module_subset = dat

[1] 173996     70
[1] 7574   70
[1] 7000   70

dat = dat_region2module_subset

pheatmap(
    t(dat),
    color = c("white", "black"),
    breaks = c(0, 0.5, 1),
    treeheight_row = 0,
    treeheight_col = 0,
    legend = FALSE,
    show_colnames = FALSE,
    fontsize_row = 7,
    main = "Module annotation across genome"
)

txt_fdiry = "."
txt_fname = "fig.matrix.region2module.png"
txt_fpath = file.path(txt_fdiry, txt_fname)
dat = dat_region2module_subset

options(repr.plot.height=10, repr.plot.width=25)
pheatmap(
    t(dat),
    color = c("white", "black"),
    breaks = c(0, 0.5, 1),
    treeheight_row = 0,
    treeheight_col = 0,
    legend = FALSE,
    show_colnames = FALSE,
    fontsize_row = 7,
    main = "Module annotation across genome",
    height   = 10,
    width    = 10,
    filename = txt_fpath
)

Region-TF: Summarized TF binding sites across the genome

### arrange the matrix
dat = dat_region2TF_matrix
dat = dat %>% 
    dplyr::select(-Chrom, -ChromStart, -ChromEnd) %>% 
    column_to_rownames("Region")

### assign and show
dat = dat_region2TF_arrange = dat
print(dim(dat))
head(dat)

[1] 173996    265

A data.frame: 6 × 265

	ADNP	AGO1	ARHGAP35	ARID2	ARID3A	ARID4B	ARNT	ATF1	ATF2	ATF3	⋯	ZNF639	ZNF644	ZNF7	ZNF707	ZNF740	ZNF766	ZNF780A	ZNF83	ZSCAN29	ZZZ3
	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	⋯	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
chr1:115702-115751	0	0	0	0	1	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:118585-118665	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:136446-136510	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:139031-139110	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:268005-268051	0	0	0	1	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0
chr1:586187-586203	0	0	0	0	0	0	0	0	0	0	⋯	0	0	0	0	0	0	0	0	0	0

Summarize counts of the binary matrix

### count by row
dat = dat_region2TF_arrange
vec = apply(dat, 1, sum)
dat = tibble(Region = names(vec), Count = vec)
dat = dat %>% dplyr::arrange(Count)

### assign and summary
dat_region_stats = dat
print(dim(dat))
print(summary(vec))

### show top/bottom of table
fun_display_table(
    bind_rows(
        head(dat, 6), 
        tail(dat, 6)
    )
)

[1] 173996      2
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   2.00    3.00    6.00   15.74   15.00  214.00 

Region	Count
chr1:1041445-1041646	2
chr1:1081931-1082133	2
chr1:1247497-1247699	2
chr1:1527412-1527616	2
chr1:1548746-1548953	2
chr1:1616720-1616967	2
chr7:139339776-139342125	188
chr6:27131655-27135406	195
chr11:62839262-62842225	205
chr1:44720944-44722487	212
chr1:11907607-11910232	214
chr1:28647570-28649255	214

### count by column
dat = dat_region2TF_arrange
vec = apply(dat, 2, sum)
dat = tibble(TF = names(vec), Count = vec)
dat = dat %>% dplyr::arrange(Count)

### assign and summary
dat_tfs_stats = dat
print(dim(dat))
print(summary(vec))

### show top/bottom of table
fun_display_table(
    bind_rows(
        head(dat, 6), 
        tail(dat, 6)
    )
)

[1] 265   2
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
      3    1694    7159   10333   16695   42737 

TF	Count
SRSF9	3
SAFB2	10
BRF2	14
ZC3H4	15
ZNF217	30
TGIF2	31
RNF2	33892
IKZF1	33910
MEIS2	34477
REST	38175
RCOR1	40914
JUND	42737

Visualize the summary

dat = dat_region_stats
gpt = ggplot(dat, aes(x=Count)) + 
    geom_histogram(bins = 100) + 
    theme_cowplot() + 
    background_grid()

options(repr.plot.height=4, repr.plot.width=10)
print(gpt)

dat = dat_tfs_stats         
gpt = ggplot(dat, aes(x=Count)) + 
    geom_histogram(bins = 100) + 
    theme_cowplot() + 
    background_grid() +
    labs(x="#{Region} each TF binds)", y = "Count")

options(repr.plot.height=4, repr.plot.width=10)
print(gpt)

Subset and plot the matrix

dat = dat_region_stats
dat = dat %>% dplyr::filter(Count > 10)
idx = dat$Region
idx_region = idx

dat = dat_tfs_stats
dat = dat %>% dplyr::filter(Count > 1000) %>% dplyr::filter(!str_detect(TF, "phospho"))
idx = dat$TF
idx_tfs = idx

### init
dat = dat_region2TF_arrange
print(dim(dat))

### subset the matrix
dat = dat[idx_region, idx_tfs]
print(dim(dat))

### subset the matrix
set.seed(123)
idx = sample(1:nrow(dat), size=10000)
dat = dat[idx,]
print(dim(dat))

### assign
dat_region2TF_subset = dat

[1] 173996    265
[1] 56957   208
[1] 10000   208

dat = dat_region2TF_subset

options(repr.plot.height=20, repr.plot.width=10)
pheatmap(
    t(dat),
    color = c("white", "black"),
    breaks = c(0, 0.5, 1),
    treeheight_row = 0,
    treeheight_col = 0,
    legend = FALSE,
    show_colnames = FALSE,
    fontsize_row = 7,
    main = "TF binding sites across genome"
)

txt_fdiry = "."
txt_fname = "fig.matrix.region2TF.png"
txt_fpath = file.path(txt_fdiry, txt_fname)
dat = dat_region2TF_subset

pheatmap(
    t(dat),
    color = c("white", "black"),
    breaks = c(0, 0.5, 1),
    treeheight_row = 0,
    treeheight_col = 0,
    legend = FALSE,
    show_colnames = FALSE,
    fontsize_row = 7,
    main = "TF binding sites across genome",
    height   = 20,
    width    = 10,
    filename = txt_fpath
)

Module-TF: composition of TFs for each modulde

### arrange matrix
dat = dat_module2TF_matrix
dat = dat %>% column_to_rownames("TF")

### assign and show
dat_module2TF_arrange = dat
print(dim(dat))
fun_display_table(head(dat))

[1] 234  70

	Module_01	Module_02	Module_03	Module_04	Module_05	Module_06	Module_07	Module_08	Module_09	Module_10	Module_11	Module_12	Module_13	Module_14	Module_15	Module_16	Module_17	Module_18	Module_19	Module_20	Module_21	Module_22	Module_23	Module_24	Module_25	Module_26	Module_27	Module_28	Module_29	Module_30	Module_31	Module_33	Module_34	Module_35	Module_36	Module_37	Module_39	Module_40	Module_41	Module_42	Module_43	Module_44	Module_45	Module_46	Module_47	Module_48	Module_49	Module_50	Module_51	Module_52	Module_53	Module_54	Module_55	Module_56	Module_57	Module_58	Module_59	Module_61	Module_63	Module_64	Module_65	Module_66	Module_67	Module_68	Module_71	Module_72	Module_73	Module_74	Module_75	Module_77
ADNP	0	0	1	0	0	0	0	1	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
AGO1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	1	0	0	0	0	1	0	1	0	0	0	0	0	0	0	0	0	1	0	0	0	0
ARHGAP35	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0
ARID2	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	1	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	1
ARID3A	1	1	0	0	0	0	0	1	0	1	0	1	0	0	0	0	1	0	0	0	0	0	0	0	1	0	0	1	0	0	0	0	0	0	1	0	1	0	0	0	1	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	1	0	0
ARID4B	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	0	1	0	0

dat = dat_module2TF_arrange

options(repr.plot.height=10, repr.plot.width=25)
pheatmap(
    t(dat), 
    color  = c("white", "black"),
    breaks = c(0, 0.5, 1),
    legend = FALSE,
    fontsize     = 20,
    fontsize_row = 7,
    fontsize_col = 5,
    main = "Module-TF mapping"
)

txt_fdiry = "."
txt_fname = "fig.matrix.module_tf_mapping.png"
txt_fpath = file.path(txt_fdiry, txt_fname)
dat = dat_module2TF_arrange

options(repr.plot.height=10, repr.plot.width=25)
pheatmap(
    t(dat), 
    color  = c("white", "black"),
    breaks = c(0, 0.5, 1),
    legend = FALSE,
    fontsize     = 20,
    fontsize_row = 7,
    fontsize_col = 5,
    main     = "Module-TF mapping",
    height   = 10,
    width    = 25,
    filename = txt_fpath
)