# Parameters
data_name = "Mammary_BptfKO;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_188-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_188-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 19:23:25,515 [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	BptfKO Mammary Cells
Cell Group	Other Tissues
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	125103	83090	18.7841	24903536	3934275	0.1581	2724148	0.1095	8222993	0.3304
rep2	125103	83090	15.5136	4933855	232551	0.0473	399318	0.0812	1554941	0.3162
rep3	125103	83090	18.0835	25172499	5388444	0.2142	3542956	0.1408	9059925	0.3602
rep4	125103	83090	22.0198	8056501	1161888	0.1445	931523	0.1159	2660018	0.3309
rep5	125103	83090	21.2393	6631293	844055	0.1276	844925	0.1277	2296393	0.3472

Metric	Value
auPRC	0.6299
Calibrated Recall at 50% FDR	0.221
Number of Positive Examples in Test Data	107015
Number of Negative Examples in Test Data	7963836
Imbalance Ratio in Test Data	0.0133
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2610 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp4, Sp1, Sp2, Klf3, Klf7, Egr1, Klf8, Klf12, E2f4, Zbtb17, Egr2, Klf6, E2f1, Klf4, Klf1, Klf5, Sp5, Zfp281, Egr3, Klf15, Zfp740, Wt1, Maz, Sall4, E2f6, Zbtb1, E2f7
metacluster_0/pattern_1 # seqlets: 2319 SequenceContrib ScoresHyp_Contrib Scores	Junb, Fosl1, Fos, Jun, Fosb, Jund, Atf3, Fosl2, Jdp2, Batf, Bach2, Nfe2, Nfe2l2, Bach1, Mafa
metacluster_0/pattern_2 # seqlets: 1953 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_3 # seqlets: 1287 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpd, Cebpa, Cebpe, Cebpg, Nfil3, Dbp, Ddit3, Atf4, Hlf, Tef, Pou3f3
metacluster_0/pattern_4 # seqlets: 1196 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elf1, Elk1, Fli1, Erg, Elk4, Ets1, Elk3, Elf5, Etv5, Fev, Ehf, Etv4, Elf2, Etv1, Elf4, Etv6, Etv3, XP_911724.4, Etv2, Elf3, Spi1, Spdef, Stat6, Stat3, Spib, Spic
metacluster_0/pattern_5 # seqlets: 1056 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_0/pattern_6 # seqlets: 1011 SequenceContrib ScoresHyp_Contrib Scores	Zfx, Mxi1, Usf2, Rfx1, Ctcfl, Ctcf
metacluster_0/pattern_7 # seqlets: 776 SequenceContrib ScoresHyp_Contrib Scores	Trp53, Trp63, Trp73, Tcfcp2l1
metacluster_0/pattern_8 # seqlets: 747 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb5, Creb1, Atf1, Crem, Srebf1, Mafb, Mlx, Tfec, Rxrb
metacluster_0/pattern_9 # seqlets: 739 SequenceContrib ScoresHyp_Contrib Scores	Sox9, Sox10, Sox3, Sox4, Sox2, Sox6, Sox17, Sox12
metacluster_0/pattern_10 # seqlets: 683 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_11 # seqlets: 604 SequenceContrib ScoresHyp_Contrib Scores	Xbp1, Gmeb2, Gmeb1
metacluster_0/pattern_12 # seqlets: 542 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_13 # seqlets: 538 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Prdm1, Irf8, Stat2, Irf4, Stat1, Irf9, Irf3
metacluster_0/pattern_14 # seqlets: 420 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_15 # seqlets: 361 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfeb, Arntl, Mitf, Bhlhe40, Tfe3, Clock, Arnt, Npas2, Srebf2, Creb3l2, Tcfl5, Bhlhe41, Mlxip
metacluster_0/pattern_16 # seqlets: 331 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_17 # seqlets: 299 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_0/pattern_18 # seqlets: 286 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Rela, Relb, Nfkb2, Rel
metacluster_0/pattern_19 # seqlets: 274 SequenceContrib ScoresHyp_Contrib Scores	Tfap2b
metacluster_0/pattern_20 # seqlets: 184 SequenceContrib ScoresHyp_Contrib Scores	Mbd2
metacluster_0/pattern_21 # seqlets: 187 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_22 # seqlets: 92 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Tfap2c, Tfap2e
metacluster_0/pattern_23 # seqlets: 82 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores	Srf
metacluster_0/pattern_25 # seqlets: 74 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_0/pattern_26 # seqlets: 47 SequenceContrib ScoresHyp_Contrib Scores