# Parameters
data_name = "STMCH;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_63-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_63-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 18:53:37,953 [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	stomach
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	44310	25214	9.2288	6255655	127790	0.0205	396966	0.0636	1951352	0.3129
rep2	44310	25214	6.9103	46947480	1421716	0.0303	2537222	0.0541	14669330	0.3126

Metric	Value
auPRC	0.6555
Calibrated Recall at 50% FDR	0.142
Number of Positive Examples in Test Data	28687
Number of Negative Examples in Test Data	8042164
Imbalance Ratio in Test Data	0.0036
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4860 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp1, Sp4, Klf6, Zbtb17, Klf1, Wt1, Sp5, Maz, Klf5, Egr1, Zfp281, Klf4, E2f4, Klf7, Zfx, Klf15, Egr2, Klf8, Klf12, E2f1, Fli1, Usf2, Ptf1a, Ctcfl, Sall4, Mxi1, E2f7, Nr1h4, Srebf2
metacluster_1/pattern_1 # seqlets: 2073 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Pbx3, Foxi1
metacluster_1/pattern_2 # seqlets: 1623 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_3 # seqlets: 1515 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Ets1, Elf1, Elk4, Elk1, Erg, Elk3, Ehf, Etv4, Etv1, Etv6, Fev, Etv2, Elf5, Etv3, XP_911724.4, Etv5, Elf4, Elf3, Elf2, Spdef, Spi1, Spib
metacluster_1/pattern_4 # seqlets: 1002 SequenceContrib ScoresHyp_Contrib Scores	Rfx1, Ctcf, Mbd2
metacluster_1/pattern_5 # seqlets: 884 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_6 # seqlets: 848 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_7 # seqlets: 812 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_1/pattern_8 # seqlets: 800 SequenceContrib ScoresHyp_Contrib Scores	Hes1, Hes7
metacluster_1/pattern_9 # seqlets: 646 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf2, Atf7, Atf1, Jdp2, Crem, Creb5, Atf3, Usf1, Fosl2, Hlf, Tfe3, Nfil3
metacluster_1/pattern_10 # seqlets: 507 SequenceContrib ScoresHyp_Contrib Scores	Arntl, Tfeb, Tfec, Mitf, Bhlhe40, Clock, Srebf1, Arnt, Mlx, Npas2, Tcfl5, Myc, Bhlhe41, Creb3l2, Mycn, Max, Rxrg
metacluster_1/pattern_11 # seqlets: 370 SequenceContrib ScoresHyp_Contrib Scores	Jun, Jund, Junb, Fosb, Fosl1, Fos, Bach2, Batf, Nfe2l2, Bach1, Nfe2, Mafa, Nr1d2
metacluster_1/pattern_12 # seqlets: 296 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib
metacluster_1/pattern_13 # seqlets: 216 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_1/pattern_14 # seqlets: 183 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_15 # seqlets: 162 SequenceContrib ScoresHyp_Contrib Scores	Irf2, Irf1, Irf7, Prdm1, Irf8, Irf9, Stat2, Stat1, Irf3, Irf4
metacluster_1/pattern_16 # seqlets: 146 SequenceContrib ScoresHyp_Contrib Scores	Nfic, Hic1
metacluster_1/pattern_17 # seqlets: 149 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_18 # seqlets: 121 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 113 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_1/pattern_20 # seqlets: 96 SequenceContrib ScoresHyp_Contrib Scores	Egr3, Mef2d, Mef2c, Mef2a
metacluster_1/pattern_21 # seqlets: 66 SequenceContrib ScoresHyp_Contrib Scores	Foxd1
metacluster_1/pattern_22 # seqlets: 75 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_23 # seqlets: 53 SequenceContrib ScoresHyp_Contrib Scores	Gata3, Gata2, Gata1, Gata4, Mecom, Gata6