# Parameters
data_name = "NK;IL2+IL12+;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_80-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_80-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 18:58:33,647 [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	NK (+IL2+IL12)
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	72685	52858	15.7584	9397828	1188033	0.1267	1041050	0.111	3090135	0.3294
rep2	72685	52858	11.9275	40619930	5193030	0.1279	4035218	0.0994	13424750	0.3307

Metric	Value
auPRC	0.5992
Calibrated Recall at 50% FDR	0.213
Number of Positive Examples in Test Data	59572
Number of Negative Examples in Test Data	8011279
Imbalance Ratio in Test Data	0.0074
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5004 SequenceContrib ScoresHyp_Contrib Scores	Erg, Ets1, Elk1, Gabpa, Fli1, Elk4, Etv2, Etv4, Etv5, Elf2, Elk3, Spi1, Etv6, Elf1, Fev, Ehf, Spib, XP_911724.4, Etv1, Etv3, Elf3, Elf4, Elf5, Stat4, Irf8, Irf4, Ets2, Spdef, Spic
metacluster_1/pattern_1 # seqlets: 4022 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Klf1, Klf12, Egr1, Zbtb17, Egr2, E2f1, Klf5, Sp5, Zfp281, Zfx, Egr3, Zbtb1, Zfp740
metacluster_1/pattern_2 # seqlets: 1848 SequenceContrib ScoresHyp_Contrib Scores	Jun, Jund, Junb, Fosl1, Fosb, Atf3, Fos, Fosl2, Bach2, Jdp2, Batf, Nfe2l2, Nfe2, Bach1, Mafa, Mafk
metacluster_1/pattern_3 # seqlets: 1703 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_4 # seqlets: 1605 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1361 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Atf2, Atf1, Crem, Nfil3, Mafb, Tef, Rxrb, Dbp, Hlf, Cebpb, Gmeb2
metacluster_1/pattern_6 # seqlets: 1156 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_7 # seqlets: 1140 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_8 # seqlets: 998 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Prdm1, Irf9, Irf3, Stat2, Batf3, Irf5
metacluster_1/pattern_9 # seqlets: 853 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1, Wt1, Maz
metacluster_1/pattern_10 # seqlets: 755 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 699 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_12 # seqlets: 344 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Arntl, Tfec, Tfe3, Mitf, Srebf1, Clock, Bhlhe40, Mlx, Arnt, Npas2, Mycn, Max, Creb3l2, Srebf2, Myc, Tcfl5, Bhlhe41, Xbp1, Mlxip
metacluster_1/pattern_13 # seqlets: 153 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_14 # seqlets: 111 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_15 # seqlets: 101 SequenceContrib ScoresHyp_Contrib Scores	Nfkb1, Nfkb2, Rela, Relb, Rel
metacluster_1/pattern_16 # seqlets: 72 SequenceContrib ScoresHyp_Contrib Scores	Mef2a, Mef2c, Mef2d
metacluster_1/pattern_17 # seqlets: 69 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib