# Parameters
data_name = "LRG_INTSTN;A;CL"
modisco_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_modisco2019"
tomtom_report_root = "http://mitra.stanford.edu/kundaje/msharmin/report/tomtom_outs/cells"
task_dir = "task_53-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_53-naivegw/NaiveauPRC.txt"
homer_root = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/Naive_scans"
reportfile = "/mnt/lab_data/kundaje/msharmin/annotations/filtering samples_MS2.xlsx"
sheetname = "filter23"

from matlas.reports import display_metadata

load data from labcluster

Using TensorFlow backend.
2019-08-30 18:51:28,205 [WARNING] git-lfs not installed

display_metadata(data_name, perf_file, reportfile, sheetname)

from matlas.reports import display_paiwise_pattern_comparison
from matlas.reports import display_denovo_patterns

display_denovo_patterns(data_name, modisco_root=modisco_root)

TF-MoDISco is using the TensorFlow backend.

display_paiwise_pattern_comparison(data_name, modisco_root, homer_root)

MetaData Name	Description
Cell type	Large Intestine
Cell Group	Other Tissues
Experiment Name	ATAC
Experiment Group	Casellas Lab

replicate	Naïve overlap peaks	IDR peaks	TSS enrichment (< 8 is very poor <10 is low)	Final number of unique mapping, dup-filtered, chrM filtered reads	Number of reads in called peak regions	Fraction of reads in called peak regions	Number of reads in promoter regions	Fraction of reads in promoter regions	Number of reads in enhancer regions	Fraction of reads in enhancer regions
rep1	137857	92049	17.4863	6685930	889473	0.1334	1112640	0.1669	2321255	0.3481
rep2	137857	92049	13.2097	14361249	2305769	0.1608	2175580	0.1517	5453375	0.3802
rep3	137857	92049	11.0875	28229693	4726452	0.1675	3715611	0.1317	10685303	0.3788
rep4	137857	92049	12.1545	18107472	3051520	0.1687	2665295	0.1473	6851768	0.3788

Metric	Value
auPRC	0.5934
Calibrated Recall at 50% FDR	0.194
Number of Positive Examples in Test Data	103084
Number of Negative Examples in Test Data	7967767
Imbalance Ratio in Test Data	0.0128
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 5048 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Klf3, Klf6, Sp4, Klf1, Wt1, Klf15, Klf5, Sp5, Zfx, Maz, Egr1, Zbtb17, Klf7, Klf4, Egr2, Klf12, Klf8, Zfp281, Usf2, Mxi1, E2f4, Sall4, Fli1, Rela, Nr1h4, Tfap2c, E2f3, Ctcfl, Tfap2b, Mbd2, Egr3
metacluster_0/pattern_1 # seqlets: 2241 SequenceContrib ScoresHyp_Contrib Scores	Hnf4g, Hnf4a, Nr1h3, Nr2c2, Rxra, Nr2f6, Rxrb, Ppara, Pparg, Nr2f1, Rarg, Nr5a2, Nr2c1, Nr2e3, Nr5a1, Nr4a2
metacluster_0/pattern_2 # seqlets: 1637 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_3 # seqlets: 1337 SequenceContrib ScoresHyp_Contrib Scores	Etv4, Etv2, Spi1, Ehf, Spib, Ets1, Erg, Etv6, Elf3, Elf4, Elf2, Gabpa, Elf5, Elk1, Etv3, Irf8, XP_911724.4, Elk4, Irf4, Elf1, Elk3, Spic, Etv1, Etv5, Spdef, Fev, Prdm1, Irf3, Irf2, Zscan10, Stat3
metacluster_0/pattern_4 # seqlets: 1252 SequenceContrib ScoresHyp_Contrib Scores	Mecp2
metacluster_0/pattern_5 # seqlets: 922 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_6 # seqlets: 828 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_7 # seqlets: 717 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf7, Irf9, Stat1, Stat2, Batf3
metacluster_0/pattern_8 # seqlets: 655 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Jdp2, Atf7, Atf2, Atf1, Crem, Jun, Nfil3, Tef, Mafb, Dbp, Gmeb2, Hlf, Cebpb, Fosl1, Atf3, Cebpa, Gmeb1, Junb, Jund, Cebpd, Cebpg, Fosl2, Esr2
metacluster_0/pattern_9 # seqlets: 652 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_0/pattern_10 # seqlets: 648 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Fos, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa
metacluster_0/pattern_11 # seqlets: 510 SequenceContrib ScoresHyp_Contrib Scores	Cdx2, Evx2, Hoxb9, Hoxa11, Hoxc12, Hoxa9, Hoxd10, Hoxc11, Hoxc10, Cdx1, Hoxd9, Hoxb8, Evx1, Hoxa10, Cdx4, Hoxd11, Hoxd8, Hoxd13, Hoxa13, Hoxa7, Hoxa6, Hoxb13, Hoxb7, Hoxc9, Hoxc13, Hoxc8, Hoxa5, Hoxb4, Hoxb5, Hoxa4, Hoxc4, Hoxa3, Meis1, Hoxb3, Nanog, Meox1, Srf, Vax1, Hoxa2, Barx2
metacluster_0/pattern_12 # seqlets: 505 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata2, Tal1, Gata1, Gata3, Gata6, Mecom, Gata5
metacluster_0/pattern_13 # seqlets: 503 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_0/pattern_14 # seqlets: 502 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_15 # seqlets: 420 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Arntl, Tfec, Mitf, Clock, Bhlhe40, Srebf1, Arnt, Npas2, Mlx, Creb3l2, Srebf2, Mycn, Tcfl5, Max, Myc, Bhlhe41, Xbp1, Mlxip, Hes1
metacluster_0/pattern_16 # seqlets: 396 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_17 # seqlets: 392 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_18 # seqlets: 377 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_19 # seqlets: 94 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_0/pattern_20 # seqlets: 87 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_21 # seqlets: 71 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_22 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_23 # seqlets: 73 SequenceContrib ScoresHyp_Contrib Scores	Foxa2, Foxp2, Foxd1, Foxa1, Foxd3, Foxc1, Foxb1, Foxc2, Foxm1, Foxa3, Foxg1, Foxk1, Foxo1, Foxo3, Foxj3, Foxj2, Foxp1, Foxl1, Maf, Foxo4, Foxj1, Foxq1, Mafg
metacluster_0/pattern_24 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores