# Parameters
data_name = "wES;Telenchephalon;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_255-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_255-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 19:37:16,970 [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	telencephalon tissue
Cell Group	ES cells and embryonic 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	242651	148955	13.0311	38057733	8163016	0.2145	4170212	0.1096	17229032	0.4528
rep2	242651	148955	13.5146	23226492	4110108	0.177	2340725	0.1008	10593679	0.4562
rep3	242651	148955	14.223	24480536	4392314	0.1795	2597231	0.1061	11010817	0.4499

Metric	Value
auPRC	0.6109
Calibrated Recall at 50% FDR	0.237
Number of Positive Examples in Test Data	191380
Number of Negative Examples in Test Data	7879471
Imbalance Ratio in Test Data	0.0237
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4401 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3220 SequenceContrib ScoresHyp_Contrib Scores	Egr2, Egr3, Egr1, Zbtb17, Zfp281, Gli3, Klf1, Gli1
metacluster_1/pattern_2 # seqlets: 2679 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_3 # seqlets: 2594 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Olig2, Neurog2, Atoh1, Bhlhe22, Msc, Neurog1, Twist2, Tcf21, Msgn1, Lyl1, Bhlha15, Ascl2, Ascl1, Tal1, Myog, Tfap4, Twist1
metacluster_1/pattern_4 # seqlets: 2341 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_1/pattern_5 # seqlets: 2295 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp4, Sp3, Sp2, E2f4, Klf3, Wt1, Sp5, Klf4, Klf7, Klf8, Klf6, Klf12, E2f1, Klf15, Maz, Klf5
metacluster_1/pattern_6 # seqlets: 1645 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx1, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_7 # seqlets: 1542 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fos, Jdp2, Fosb, Junb, Fosl1, Atf3, Batf, Fosl2, Jun, Bach2, Nfe2, Nfe2l2, Bach1
metacluster_1/pattern_8 # seqlets: 1305 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 1108 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Foxi1, Pbx3
metacluster_1/pattern_10 # seqlets: 1081 SequenceContrib ScoresHyp_Contrib Scores	Dbp, Nfil3, Hlf, Tef, Cebpb, Pou5f1, Sox2, Nanog
metacluster_1/pattern_11 # seqlets: 860 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elk4, Fli1, Elk3, Erg, Etv5, Ets1, Etv1, Etv4, Etv6, Elf1, Fev, Etv3, XP_911724.4, Spi1, Elf4, Elf2, Etv2, Elf5, Ehf, Spic, Spib, Spdef, Elf3, Irf8, Irf4
metacluster_1/pattern_12 # seqlets: 549 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb1, Creb5, Crem, Atf1, Mafb, Creb3l2, Cebpg, Tfe3
metacluster_1/pattern_13 # seqlets: 389 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_14 # seqlets: 344 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Tfec, Usf2, Arntl, Mitf, Srebf1, Bhlhe40, Mlx, Arnt, Clock, Srebf2, Npas2, Tcfl5, Mycn, Bhlhe41, Max, Myc, Mlxip
metacluster_1/pattern_15 # seqlets: 325 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_16 # seqlets: 208 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42
metacluster_1/pattern_17 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox3, Sox6, Sox4, Sox17
metacluster_1/pattern_18 # seqlets: 49 SequenceContrib ScoresHyp_Contrib Scores