# Parameters
data_name = "Adipose;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_57-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_57-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 18:52:56,774 [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	Adipose
Cell Group	Other Tissues
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	59064	36655	10.5352	18574604	1352099	0.0729	1862774	0.1004	6129555	0.3303
rep2	59064	36655	6.36	53206816	1823426	0.0343	2958154	0.0556	16743725	0.3148

Metric	Value
auPRC	0.7077
Calibrated Recall at 50% FDR	0.163
Number of Positive Examples in Test Data	40627
Number of Negative Examples in Test Data	8030224
Imbalance Ratio in Test Data	0.005
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4777 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp1, Sp4, Klf3, E2f4, Klf6, Klf4, Egr1, Zbtb17, Sp5, Klf7, Klf5, Klf8, Klf12, Wt1, Egr2, Zfp281, Klf1, Maz, E2f1, Klf15, Egr3, Srebf2, Ctcfl, Sall4, Zfx
metacluster_1/pattern_1 # seqlets: 4738 SequenceContrib ScoresHyp_Contrib Scores	Ets1, Erg, Etv4, Elk1, Etv2, Gabpa, Fli1, Elk4, Spi1, Elf2, Etv6, Spib, Ehf, Etv5, Elf1, Elk3, Fev, Elf3, Etv3, Etv1, XP_911724.4, Irf8, Irf4, Elf4, Ets2, Stat4, Elf5, Spic
metacluster_1/pattern_2 # seqlets: 4282 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_1/pattern_3 # seqlets: 1890 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_4 # seqlets: 1876 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1038 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf7, Stat1, Irf3, Stat2, Prdm1, Irf9, Zscan10, Batf3
metacluster_1/pattern_6 # seqlets: 950 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_7 # seqlets: 868 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Rfx1, Zfp42
metacluster_1/pattern_8 # seqlets: 812 SequenceContrib ScoresHyp_Contrib Scores	Hes7, Hes1
metacluster_1/pattern_9 # seqlets: 720 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Usf2, Atf7, Atf2, Atf1, Jdp2, Crem, Creb5, Atf3, Hlf, Usf1, Nfil3, Fosl2, Tef, Dbp, Jun
metacluster_1/pattern_10 # seqlets: 567 SequenceContrib ScoresHyp_Contrib Scores	Tfec, Tfeb, Arntl, Mitf, Bhlhe40, Srebf1, Tfe3, Clock, Mlx, Arnt, Npas2, Creb3l2, Tcfl5, Bhlhe41, Xbp1, Mlxip, Max
metacluster_1/pattern_11 # seqlets: 392 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_12 # seqlets: 304 SequenceContrib ScoresHyp_Contrib Scores	Jund, Fos, Fosl1, Fosb, Junb, Batf, Bach2, Bach1, Nfe2, Nfe2l2, Mafa, Mafk
metacluster_1/pattern_13 # seqlets: 243 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_14 # seqlets: 126 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 96 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou2f1