# Parameters
data_name = "MTR_NRN_MN1;methyl3;D;En"
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_276-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_276-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 19:42:42,328 [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	cholinergic motor neuron cell line MN1 treated with 10 nM methyltrienolone
Cell Group	Cancer or Immortalized cells
Experiment Name	DHS
Experiment Group	ENCODE

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	196358	142074	16.7638	44005294	12940134	0.2942	7569181	0.1721	18380386	0.4179
rep2	196358	142074	10.5977	103274339	25601270	0.2479	13257997	0.1284	41978664	0.4066
rep3	196358	142074	33.5681	5732383	1836121	0.3214	1412390	0.2472	2348845	0.4111
rep4	196358	142074	13.7866	45476793	8888625	0.1955	6008724	0.1322	17297534	0.3805
rep5	196358	142074	8.5762	117117327	21089553	0.1801	11915570	0.1018	43794934	0.374
rep6	196358	142074	23.9495	8103581	1804406	0.2232	1421543	0.1758	3081885	0.3812

Metric	Value
auPRC	0.5612
Calibrated Recall at 50% FDR	0.229
Number of Positive Examples in Test Data	155323
Number of Negative Examples in Test Data	7915528
Imbalance Ratio in Test Data	0.0192
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 3079 SequenceContrib ScoresHyp_Contrib Scores	Sp3, Sp2, Sp1, Klf3, Sp4, Zbtb17, Klf4, Sp5, Klf5, Klf6, Zfp281, Klf7, E2f4, Egr1, Wt1, Klf8, Klf12, Egr2, E2f1, Maz, Sall4, Srebf2, Klf15, Klf1, Zfp740
metacluster_0/pattern_1 # seqlets: 2215 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 1624 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Elk4, Elk1, Ets1, Erg, Elk3, Elf1, Fev, Etv5, Etv4, Etv1, Etv6, Etv2, Etv3, XP_911724.4, Elf2, Ehf, Elf5, Elf4, Spi1, Spdef, Elf3, Spic, Spib
metacluster_0/pattern_3 # seqlets: 1244 SequenceContrib ScoresHyp_Contrib Scores	Prop1, Alx1, Uncx, Phox2a, Arx, Alx4, Alx3, Prrx2, Lhx3, Lhx1, Pax7, Lhx5, Lhx4, Lmx1b, En1, Vsx2, Otx1, Shox2, Msx1, Lhx8, Pax6, Vsx1, Pou2f1, Arid3b, Prrx1, Lhx2, Arid3a, Duxbl1
metacluster_0/pattern_4 # seqlets: 1214 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_5 # seqlets: 1197 SequenceContrib ScoresHyp_Contrib Scores	Ebf1, Prdm16
metacluster_0/pattern_6 # seqlets: 1118 SequenceContrib ScoresHyp_Contrib Scores	Fos, Jund, Fosl2, Junb, Jun, Fosl1, Batf, Fosb, Jdp2, Atf3, Bach2, Bach1, Nfe2, Nfe2l2, Mafa
metacluster_0/pattern_7 # seqlets: 769 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb5, Creb1, Atf1, Crem, Nfil3, Srebf1, Dbp, Cebpb, Cebpa, Tfec, Mlx, Hlf, Tef, Ddit3, Mafb, Rxrb, Atf4
metacluster_0/pattern_8 # seqlets: 694 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_9 # seqlets: 636 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_10 # seqlets: 591 SequenceContrib ScoresHyp_Contrib Scores	Ar, Nr3c1, Pgr, Esr1
metacluster_0/pattern_11 # seqlets: 567 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx6, Rfx4, Rfx7
metacluster_0/pattern_12 # seqlets: 537 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Atoh1, Olig2, Neurog2, Msc, Neurog1, Msgn1, Ascl1, Snai1, Bhlhe22, Ascl2, Yy1, Clock, Twist1, Tfap4, Tcf21
metacluster_0/pattern_13 # seqlets: 522 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Zfx, Zfp42, Mxi1, Usf2
metacluster_0/pattern_14 # seqlets: 516 SequenceContrib ScoresHyp_Contrib Scores	Gata4, Gata3, Gata1, Gata2, Tal1, Mecom, Gata6, Gata5
metacluster_0/pattern_15 # seqlets: 491 SequenceContrib ScoresHyp_Contrib Scores	Hand1
metacluster_0/pattern_16 # seqlets: 486 SequenceContrib ScoresHyp_Contrib Scores	Gmeb2, Cebpg, Gmeb1, Cebpd, Esr2, Xbp1, Rora, Cebpe
metacluster_0/pattern_17 # seqlets: 485 SequenceContrib ScoresHyp_Contrib Scores	Pou5f1, Sox2
metacluster_0/pattern_18 # seqlets: 434 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_19 # seqlets: 373 SequenceContrib ScoresHyp_Contrib Scores	Tfeb, Usf1, Arntl, Mitf, Bhlhe40, Tfe3, Arnt, Npas2, Tcfl5, Creb3l2, Bhlhe41, Mlxip, Arnt2
metacluster_0/pattern_20 # seqlets: 267 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_0/pattern_21 # seqlets: 218 SequenceContrib ScoresHyp_Contrib Scores	Thap11, Zfp143, Tbx2
metacluster_0/pattern_22 # seqlets: 212 SequenceContrib ScoresHyp_Contrib Scores	Irf2, Irf1, Prdm1, Irf7, Irf8, Stat1, Stat2, Irf9, Irf4, Irf3, Batf3
metacluster_0/pattern_23 # seqlets: 85 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_24 # seqlets: 52 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a