# Parameters
data_name = "B;B220_CD43;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_141-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_141-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 19:11:22,191 [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	B220+CD43+ B cells
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	155845	119051	10.106	69280898	13116271	0.1894	8252172	0.1191	24769833	0.3576
rep2	155845	119051	11.2553	51624811	8949766	0.1734	6352100	0.1231	18321142	0.355

Metric	Value
auPRC	0.621
Calibrated Recall at 50% FDR	0.209
Number of Positive Examples in Test Data	130774
Number of Negative Examples in Test Data	7940077
Imbalance Ratio in Test Data	0.0162
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5126 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 3291 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp4, Klf3, Sp3, Sp1, Klf6, E2f4, Klf7, Klf4, Klf1, Klf8, Klf12, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Zfx, Zfp740, Zbtb1, Egr3
metacluster_1/pattern_2 # seqlets: 2686 SequenceContrib ScoresHyp_Contrib Scores	Etv2, Erg, Ets1, Elk4, Gabpa, Elk1, Spi1, Elf2, Fli1, Etv6, Etv4, Ehf, Etv3, XP_911724.4, Spib, Elf3, Elk3, Etv1, Elf4, Elf1, Etv5, Fev, Irf8, Elf5, Irf4, Ets2, Spdef, Spic, Stat4
metacluster_1/pattern_3 # seqlets: 1899 SequenceContrib ScoresHyp_Contrib Scores	Prdm1, Irf3, Irf2, Irf1, Rela
metacluster_1/pattern_4 # seqlets: 1429 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Stat1, Zscan10, Irf7
metacluster_1/pattern_5 # seqlets: 1319 SequenceContrib ScoresHyp_Contrib Scores	Irf9, Batf3, Irf5
metacluster_1/pattern_6 # seqlets: 1314 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_1/pattern_7 # seqlets: 1132 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_8 # seqlets: 1030 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_9 # seqlets: 954 SequenceContrib ScoresHyp_Contrib Scores	Tcf3, Ascl2, Ascl1, Tcf7l1, Myog, Ptf1a, Myod1, Bhlha15, Myf6, Tcf4, Tcf12, Myf5, Tal1, Nhlh2, Snai2, Atoh1, Nhlh1, Olig2, Lyl1, Tgif1, Tcf21, Snai1, Meis3, Figla, Pknox2, Neurod2, Meis2, Neurog2, Mnt, Hes5, Neurod1
metacluster_1/pattern_10 # seqlets: 818 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb
metacluster_1/pattern_11 # seqlets: 787 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_12 # seqlets: 572 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Usf2, Crem, Atf1, Jdp2, Creb5, Atf3, Fosl2
metacluster_1/pattern_13 # seqlets: 524 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_14 # seqlets: 521 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2d, Mef2c
metacluster_1/pattern_15 # seqlets: 489 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_16 # seqlets: 439 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 344 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Rfx1, Maz, Mxi1
metacluster_1/pattern_18 # seqlets: 340 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 323 SequenceContrib ScoresHyp_Contrib Scores	Pax5, Pax6
metacluster_1/pattern_20 # seqlets: 295 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfe3, Tfeb, Tfec, Arntl, Mitf, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Srebf2, Npas2, Tcfl5, Creb3l2, Mycn, Max, Bhlhe41, Hlf, Myc, Dbp, Xbp1, Mlxip
metacluster_1/pattern_21 # seqlets: 270 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_22 # seqlets: 181 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_23 # seqlets: 145 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jun, Fosl1, Jund, Batf, Junb, Mafk, Fosb, Bach2, Mafb, Mafg, Nfe2l2, Maff, Nfe2, Bach1, Mafa, Maf
metacluster_1/pattern_24 # seqlets: 127 SequenceContrib ScoresHyp_Contrib Scores	Gata1, Gata6, Gata5, Gata4, Gata2, Gata3
metacluster_1/pattern_25 # seqlets: 99 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_26 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_27 # seqlets: 71 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_28 # seqlets: 43 SequenceContrib ScoresHyp_Contrib Scores	Nfatc1, Rorc, Nr1d2, Pparg