# Parameters
data_name = "NCR+ILC3+IL23;A;CL"
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_85-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_85-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 18:59:23,939 [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	NCR+ILC3+IL23
Cell Group	Other Immune Cells
Experiment Name	ATAC
Experiment Group	Casellas Lab

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	114196	82596	21.3378	12755662	2989441	0.2347	2342638	0.1839	4262474	0.3347
rep2	114196	82596	13.8666	36946603	8391268	0.2272	5323576	0.1442	12180983	0.3299

Metric	Value
auPRC	0.5675
Calibrated Recall at 50% FDR	0.22
Number of Positive Examples in Test Data	98429
Number of Negative Examples in Test Data	7972422
Imbalance Ratio in Test Data	0.0122
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4597 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Etv4, Elk1, Etv2, Gabpa, Fli1, Elk4, Etv6, Spi1, Elf2, Elk3, Etv5, Spib, Ehf, XP_911724.4, Fev, Etv3, Elf1, Elf3, Etv1, Elf4, Stat4, Irf8, Irf4, Elf5, Ets2, Spdef, Spic, Stat3
metacluster_1/pattern_1 # seqlets: 4018 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3028 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf7, Klf4, Klf6, Klf8, Klf12, Klf1, Egr1, Egr2, Zbtb17, Klf5, E2f1, Sp5, Zfp281, Egr3, Zfp740, Zfx
metacluster_1/pattern_3 # seqlets: 2460 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Bach2, Nfe2l2, Nfe2, Fosb, Junb, Fosl1, Jun, Atf3, Jdp2, Fosl2, Bach1, Batf, Mafk, Mafa, Mafb
metacluster_1/pattern_4 # seqlets: 1326 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Cbfb, Runx3
metacluster_1/pattern_5 # seqlets: 1297 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Atf1, Creb1, Crem, Nfil3, Dbp, Tfec, Srebf1, Rxrb, Hlf, Cebpa, Cebpb, Mlx, Tef
metacluster_1/pattern_6 # seqlets: 980 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 934 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Stat1, Prdm1, Irf7, Stat2, Irf3, Irf9, Batf3
metacluster_1/pattern_8 # seqlets: 899 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Foxi1, Nfya, Pbx3
metacluster_1/pattern_9 # seqlets: 683 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Rora, Nr1d2, Ppara, Nr1d1
metacluster_1/pattern_10 # seqlets: 603 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 537 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 460 SequenceContrib ScoresHyp_Contrib Scores	Nfkb2, Nfkb1, Rela, Relb, Rel
metacluster_1/pattern_13 # seqlets: 450 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Wt1, Rfx1
metacluster_1/pattern_14 # seqlets: 409 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfe3, Tfeb, Arntl, Mitf, Clock, Bhlhe40, Arnt, Npas2, Creb3l2, Srebf2, Mycn, Tcfl5, Max, Myc, Bhlhe41, Xbp1, Hes1
metacluster_1/pattern_15 # seqlets: 311 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6, Sox2
metacluster_1/pattern_16 # seqlets: 217 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata2, Gata1, Gata4, Gata6, Tal1, Gata5
metacluster_1/pattern_17 # seqlets: 141 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_18 # seqlets: 118 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_20 # seqlets: 76 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_21 # seqlets: 65 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_22 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_23 # seqlets: 33 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2