# Parameters
data_name = "416B_MP;CD34+;D;En"
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_241-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_241-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 19:34:47,497 [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	myeloid progenitor cells, CD34+ (416B)
Cell Group	Cancer or Immortalized cells
Experiment Name	DHS
Experiment Group	ENCODE

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	195576	149958	7.4739	130255579	34268544	0.2631	13572995	0.1042	54008393	0.4147
rep2	195576	149958	12.1603	18403591	4226985	0.2299	2132609	0.116	7624696	0.4147

Metric	Value
auPRC	0.5393
Calibrated Recall at 50% FDR	0.244
Number of Positive Examples in Test Data	137472
Number of Negative Examples in Test Data	7933379
Imbalance Ratio in Test Data	0.017
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 8904 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 5749 SequenceContrib ScoresHyp_Contrib Scores	Etv2, Etv4, Ets1, Erg, Spi1, Spib, Fli1, Etv6, Gabpa, Etv3, XP_911724.4, Elk1, Elk4, Elf4, Elk3, Elf2, Irf8, Irf4, Ehf, Etv1, Etv5, Elf3, Spic, Elf5, Elf1, Fev, Spdef, Prdm1
metacluster_1/pattern_2 # seqlets: 2034 SequenceContrib ScoresHyp_Contrib Scores	Jun, Bach2, Nfe2, Nfe2l2, Bach1, Fos, Fosl2, Jund, Fosl1, Atf3, Fosb, Junb, Batf, Jdp2, Mafk, Mafa, Mafb, Mafg, Maf, Maff
metacluster_1/pattern_3 # seqlets: 1864 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf1, Klf8, Klf12, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Zfp740, Egr3, Zbtb1
metacluster_1/pattern_4 # seqlets: 1805 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Dbp, Nfil3, Hlf, Cebpe, Ddit3, Atf4, Tef
metacluster_1/pattern_5 # seqlets: 1508 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_6 # seqlets: 1157 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_7 # seqlets: 680 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_8 # seqlets: 570 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Irf7, Irf3, Stat2, Irf9, Batf3
metacluster_1/pattern_9 # seqlets: 565 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfya, Nfyb, Foxi1, Pbx3
metacluster_1/pattern_10 # seqlets: 487 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 451 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Zfx
metacluster_1/pattern_12 # seqlets: 397 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 395 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata6, Tal1, Gata2, Gata1, Gata5, Gata3
metacluster_1/pattern_14 # seqlets: 247 SequenceContrib ScoresHyp_Contrib Scores	Nfatc1, Rorc, Nr1d2
metacluster_1/pattern_15 # seqlets: 244 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf2, Atf7, Atf1, Crem, Creb5, Usf1, Srebf2, Tfe3, Rfx1
metacluster_1/pattern_16 # seqlets: 188 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Arntl, Tfec, Mitf, Clock, Srebf1, Arnt, Bhlhe40, Mlx, Npas2, Tcfl5, Mycn, Creb3l2, Rxrg, Bhlhe41, Mxi1, Max, Rxrb, Myc, Nr1h4, Zic3
metacluster_1/pattern_17 # seqlets: 188 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six4, Six1
metacluster_1/pattern_18 # seqlets: 147 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_19 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_20 # seqlets: 81 SequenceContrib ScoresHyp_Contrib Scores	Esrrb, Rara, Rxra, Nr5a2, Esrra, Rarg, Esrrg, Nr5a1, Nr2f6
metacluster_1/pattern_21 # seqlets: 79 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_22 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_23 # seqlets: 62 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33