# Parameters
data_name = "preB_BMD;A;GEO"
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_140-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_140-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 19:11:21,500 [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	Bone marrow derived pre-B cell
Cell Group	B cells
Experiment Name	ATAC
Experiment Group	GEO

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	157798	129026	18.8433	30832398	10448081	0.3391	6083609	0.1974	11654867	0.3782
rep2	157798	129026	18.6649	30807421	10713779	0.348	6246998	0.2029	11867394	0.3855

Metric	Value
auPRC	0.6207
Calibrated Recall at 50% FDR	0.209
Number of Positive Examples in Test Data	139188
Number of Negative Examples in Test Data	7931663
Imbalance Ratio in Test Data	0.0172
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5830 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4707 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Prdm1, Irf3, Spic, Elf3, Ehf, Irf2, Etv2, Irf1, Ets1, Erg, Etv6, Etv4, Elf5, Gabpa, Elk1, Elf1, Elf4, Etv3, Elf2, Fli1, XP_911724.4, Elk4, Elk3
metacluster_1/pattern_2 # seqlets: 3205 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp1, Klf6, Sp4, Zfx, Wt1, Klf1, Klf15, Klf5, Egr1, Maz, Zbtb17, Klf4, E2f4, Sp5, Klf7, Klf8, Klf12, Zfp281, Tfap2c, Egr2, Usf2, Nr1h4, Sall4, E2f1, Rela, Mxi1, Egr3
metacluster_1/pattern_3 # seqlets: 1420 SequenceContrib ScoresHyp_Contrib Scores	Etv1, Fev, Etv5, Spdef, Mbd2, E2f3
metacluster_1/pattern_4 # seqlets: 1320 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Irf7, Irf5, Irf9, Irf6
metacluster_1/pattern_5 # seqlets: 1251 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Ascl2, Ascl1, Myog, Ptf1a, Myod1, Bhlha15, Tcf7l1, Tcf12, Myf6, Tcf4, Tal1, Myf5, Atoh1, Nhlh2, Lyl1, Olig2, Tgif1, Snai2, Figla, Nhlh1, Tcf21, Snai1, Neurod2, Meis2, Neurog2, Meis3, Pknox2, Neurod1, Hes5, Mnt
metacluster_1/pattern_6 # seqlets: 1180 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 1102 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_8 # seqlets: 1001 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 544 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_1/pattern_10 # seqlets: 531 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Jdp2, Crem, Atf1, Creb5, Atf3, Usf1, Fosl2, Jun, Hlf, Fosl1, Nfil3
metacluster_1/pattern_11 # seqlets: 529 SequenceContrib ScoresHyp_Contrib Scores	Tfec, Arntl, Tfeb, Mitf, Bhlhe40, Srebf1, Tfe3, Mlx, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Dbp, Xbp1, Arnt2, Mlxip
metacluster_1/pattern_12 # seqlets: 484 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_13 # seqlets: 470 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_14 # seqlets: 453 SequenceContrib ScoresHyp_Contrib Scores	Pax5, Pax6
metacluster_1/pattern_15 # seqlets: 445 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_16 # seqlets: 353 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 342 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_18 # seqlets: 236 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_19 # seqlets: 113 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_20 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic