# Parameters
data_name = "WHL_BRN;8wks;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_254-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_254-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 19:37:09,246 [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	Whole Brain(adult-8wks)
Cell Group	Neural Cells and Tissues
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	272842	182883	10.6566	118051699	35961014	0.3047	13707305	0.1161	59421681	0.5034
rep2	272842	182883	22.8079	26875229	8698278	0.3239	3742816	0.1394	13671282	0.5091
rep3	272842	182883	21.5956	27399821	8373866	0.3058	3670097	0.134	13694899	0.5002
rep4	272842	182883	21.6081	23413184	6743769	0.2883	3101676	0.1326	11786846	0.5038
rep5	272842	182883	12.4127	45570776	7023303	0.1542	4452435	0.0977	19184481	0.4211
rep6	272842	182883	15.9948	21143031	3612109	0.1709	2830934	0.134	9219837	0.4363

Metric	Value
auPRC	0.6124
Calibrated Recall at 50% FDR	0.229
Number of Positive Examples in Test Data	228417
Number of Negative Examples in Test Data	7842434
Imbalance Ratio in Test Data	0.0283
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 3428 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3239 SequenceContrib ScoresHyp_Contrib Scores	Egr2, Egr3, Egr1, Zbtb17, Zfp281, Klf1
metacluster_1/pattern_2 # seqlets: 3150 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_3 # seqlets: 2537 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_4 # seqlets: 2463 SequenceContrib ScoresHyp_Contrib Scores	Neurod2, Neurod1, Neurog2, Olig2, Atoh1, Bhlhe22, Msc, Neurog1, Twist2, Msgn1, Tcf21, Bhlha15, Lyl1, Ascl2, Ascl1, Tal1, Myog
metacluster_1/pattern_5 # seqlets: 2128 SequenceContrib ScoresHyp_Contrib Scores	Batf, Fosl2, Jdp2, Jund, Fosb, Fos, Junb, Atf3, Fosl1, Jun, Bach2, Nfe2, Nfe2l2, Bach1, Mafk, Mafa, Mafb
metacluster_1/pattern_6 # seqlets: 1671 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_7 # seqlets: 1570 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Sp3, Sp1, Klf3, E2f4, Klf7, Klf6, Klf4, Klf8, Klf12, E2f1, Zfx, Sp5, Klf5
metacluster_1/pattern_8 # seqlets: 1335 SequenceContrib ScoresHyp_Contrib Scores	Nfil3, Dbp, Hlf, Tef, Cebpb, Sox2, Cebpd, Cebpa, Pou5f1, Cebpg, Ddit3, Nanog, Atf4
metacluster_1/pattern_9 # seqlets: 926 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_10 # seqlets: 778 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Creb5, Atf1, Crem, Gmeb2, Gmeb1
metacluster_1/pattern_11 # seqlets: 656 SequenceContrib ScoresHyp_Contrib Scores	Ptf1a, Tcf12, Myod1, Snai1, Tcf3, Myf6, Tgif1, Tcf7l1, Tfap4, Figla, Tcf4, Myc
metacluster_1/pattern_12 # seqlets: 650 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Ets1, Erg, Elk4, Elf1, Fli1, Etv6, Elk3, Etv3, Etv1, Etv4, Etv5, XP_911724.4, Etv2, Elf4, Elf2, Ehf, Spi1, Elf5, Fev, Spib, Spic, Spdef, Elf3, Irf8, Irf4, Irf2, Prdm1, Irf1
metacluster_1/pattern_13 # seqlets: 623 SequenceContrib ScoresHyp_Contrib Scores	Arntl, Tfe3, Tfeb, Usf1, Usf2, Npas2, Tfec, Clock, Mitf, Bhlhe40, Srebf1, Arnt, Mlx, Bhlhe41, Creb3l2, Xbp1, Max, Hey2, Tcfl5, Srebf2, Mycn, Mlxip, Arnt2, Hes5, Hes1, Epas1, Hes2
metacluster_1/pattern_14 # seqlets: 451 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_15 # seqlets: 373 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox3, Sox4, Sox6, Sox17
metacluster_1/pattern_16 # seqlets: 291 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Nr1d2, Pparg, Nr1d1, Rora, Ppara
metacluster_1/pattern_17 # seqlets: 251 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_18 # seqlets: 102 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Maz