# Parameters
data_name = "MCRPHG_BMD.UnStmltd;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_142-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_142-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 19:11:24,156 [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	bone marrow-derived macrophages (Unstimulated)
Cell Group	Other Immune 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	69293	42357	10.6363	11197064	648349	0.058	846365	0.0757	4092575	0.3661
rep2	69293	42357	9.9308	17610779	1540404	0.0876	1453797	0.0826	6341407	0.3605
rep3	69293	42357	7.6328	26187752	899545	0.0344	1487595	0.0568	8604844	0.3288

Metric	Value
auPRC	0.584
Calibrated Recall at 50% FDR	0.248
Number of Positive Examples in Test Data	50238
Number of Negative Examples in Test Data	8020613
Imbalance Ratio in Test Data	0.0062
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7151 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Spic, Etv2, Ets1, Elf3, Etv6, Ehf, Erg, Etv4, Irf3, Prdm1, Etv3, Elf1, Fli1, Gabpa, Elf4, Elk1, XP_911724.4, Elf2, Irf2, Irf1, Elk4, Elk3, Elf5, Etv1, Etv5
metacluster_1/pattern_1 # seqlets: 2970 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, Klf6, E2f4, Klf7, Klf4, Klf1, Klf8, Klf12, Egr1, Zbtb17, Egr2, E2f1, Sp5, Zfp281, Klf5, Zfx
metacluster_1/pattern_2 # seqlets: 2908 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_3 # seqlets: 2034 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Atf3, Fosl1, Junb, Fos, Jun, Fosl2, Jund, Batf, Jdp2, Bach2, Nfe2l2, Nfe2, Bach1, Mafk, Mafa, Mafb, Mafg, Maf, Maff
metacluster_1/pattern_4 # seqlets: 1580 SequenceContrib ScoresHyp_Contrib Scores	Atf7, Atf2, Creb5, Creb1, Atf1, Crem, Nfil3, Dbp, Cebpb, Hlf, Cebpa, Tef, Srebf1, Tfec, Mlx, Ddit3, Rxrb, Atf4, Gmeb2
metacluster_1/pattern_5 # seqlets: 1480 SequenceContrib ScoresHyp_Contrib Scores	Nfyc, Nfya, Nfyb, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 1311 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_7 # seqlets: 1159 SequenceContrib ScoresHyp_Contrib Scores	Cebpd, Cebpg, Cebpe
metacluster_1/pattern_8 # seqlets: 926 SequenceContrib ScoresHyp_Contrib Scores	Irf7, Stat2, Irf9, Stat1, Zscan10
metacluster_1/pattern_9 # seqlets: 794 SequenceContrib ScoresHyp_Contrib Scores	Mitf, Usf1, Tfeb, Arntl, Usf2, Tfe3, Bhlhe40, Clock, Arnt, Npas2, Srebf2, Tcfl5, Creb3l2, Bhlhe41, Arnt2, Max, Xbp1, Mlxip
metacluster_1/pattern_10 # seqlets: 775 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_11 # seqlets: 474 SequenceContrib ScoresHyp_Contrib Scores	Twist1
metacluster_1/pattern_12 # seqlets: 461 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx3, Runx2, Cbfb
metacluster_1/pattern_13 # seqlets: 341 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Rfx1
metacluster_1/pattern_14 # seqlets: 331 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_15 # seqlets: 184 SequenceContrib ScoresHyp_Contrib Scores	Mef2c, Mef2a, Mef2d
metacluster_1/pattern_16 # seqlets: 133 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33