# Parameters
data_name = "AML;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_270-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_270-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 19:41:02,053 [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	acute myeloid leukemia
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	198208	149522	5.8136	241539321	44768391	0.1854	19316971	0.08	94331020	0.3906
rep2	198208	149522	18.3448	27812360	7116975	0.256	4485462	0.1613	11538847	0.4151
rep3	198208	149522	12.7962	21655008	2906037	0.1342	2767169	0.1278	8482068	0.3918

Metric	Value
auPRC	0.6384
Calibrated Recall at 50% FDR	0.208
Number of Positive Examples in Test Data	130371
Number of Negative Examples in Test Data	7940480
Imbalance Ratio in Test Data	0.0162
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 7545 SequenceContrib ScoresHyp_Contrib Scores	Spib, Spi1, Irf8, Irf4, Spic, Etv2, Elf3, Irf3, Prdm1, Ehf, Ets1, Etv6, Etv4, Irf2, Irf1, Erg, Elf5, Elf4, Elf1, Etv3, Elf2, XP_911724.4, Gabpa, Fli1, Elk1, Elk4, Elk3
metacluster_1/pattern_1 # seqlets: 7043 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 3351 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Dbp, Nfil3, Hlf, Cebpg, Ddit3, Atf4, Cebpe, Tef
metacluster_1/pattern_3 # seqlets: 1834 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Klf3, Sp2, Sp3, Sp1, Klf6, Klf7, Klf4, E2f4, Klf8, Klf12, Klf1, Egr1, Egr2, Zbtb17, Klf5, Sp5, E2f1, Zfp281, Zfp740, Egr3, Zbtb1
metacluster_1/pattern_4 # seqlets: 1442 SequenceContrib ScoresHyp_Contrib Scores	Stat2, Zscan10, Irf7, Stat1, Irf9
metacluster_1/pattern_5 # seqlets: 829 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_6 # seqlets: 761 SequenceContrib ScoresHyp_Contrib Scores	Etv5, Etv1, Fev, Spdef
metacluster_1/pattern_7 # seqlets: 735 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Fosl1, Fos, Jun, Jund, Bach2, Atf3, Fosb, Junb, Mafk, Nfe2l2, Nfe2, Batf, Bach1, Mafg, Jdp2, Mafb, Maf, Maff, Mafa
metacluster_1/pattern_8 # seqlets: 647 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Runx2, Runx3, Cbfb, Gfi1b
metacluster_1/pattern_9 # seqlets: 626 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_10 # seqlets: 574 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_11 # seqlets: 435 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Atf7, Atf2, Creb5, Atf1, Crem, Creb3l2, Usf1, Tfec, Rxrb, Srebf1, Tfe3
metacluster_1/pattern_12 # seqlets: 405 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Foxi1, Nfyc, Nfya, Pbx3
metacluster_1/pattern_13 # seqlets: 414 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_14 # seqlets: 253 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_15 # seqlets: 207 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_16 # seqlets: 189 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_17 # seqlets: 180 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Tfeb, Arntl, Mitf, Bhlhe40, Clock, Arnt, Mlx, Npas2, Srebf2, Tcfl5, Mycn, Bhlhe41, Max, Myc
metacluster_1/pattern_18 # seqlets: 151 SequenceContrib ScoresHyp_Contrib Scores	Hoxc9, Hoxa9, Evx1, Meis1, Cdx4, Pdx1, Hoxb4, Hoxb7, Pbx2, Hoxa10, Cdx1, Hoxb8, Hoxa2
metacluster_1/pattern_19 # seqlets: 143 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_20 # seqlets: 118 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Wt1, Zfp42, Maz
metacluster_1/pattern_21 # seqlets: 103 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2c, Mef2a
metacluster_1/pattern_22 # seqlets: 92 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Zfp322a, Nfic, Nfib
metacluster_1/pattern_23 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33