# Parameters
data_name = "A20;B-lymphoma;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_269-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_269-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 19:40:43,337 [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	Murine B-lymphoma cell line(A20 cell line)
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	177830	149198	18.0012	10987474	2513748	0.2292	2308867	0.2105	4000423	0.3647
rep10	177830	149198	18.2361	10932212	2524431	0.2313	2309069	0.2116	3980864	0.3647
rep11	177830	149198	18.1804	10974464	2506120	0.2287	2309398	0.2108	3992387	0.3644
rep12	177830	149198	17.831	10898142	2458558	0.226	2265225	0.2082	3971124	0.365
rep13	177830	149198	17.6211	10922703	2451217	0.2248	2270340	0.2082	3977698	0.3648
rep14	177830	149198	18.1906	10808248	2694547	0.2497	2289835	0.2122	3938728	0.365
rep15	177830	149198	15.5067	3300423	510167	0.1549	589932	0.1792	1194854	0.3629
rep16	177830	149198	8.1824	26514251	4658672	0.1758	3162251	0.1193	9497873	0.3584
rep2	177830	149198	17.9871	10987502	2464561	0.2247	2293891	0.2091	4002795	0.3649
rep3	177830	149198	17.8915	10943898	2508845	0.2296	2285917	0.2092	3986710	0.3649
rep4	177830	149198	16.0158	4891333	853020	0.175	933905	0.1916	1795142	0.3682
rep5	177830	149198	18.4378	10475072	2621498	0.2507	2242126	0.2144	3837453	0.367
rep6	177830	149198	18.3476	10402272	2607499	0.2511	2241019	0.2158	3816572	0.3675
rep7	177830	149198	18.9656	9574445	2721278	0.2846	2138643	0.2237	3543635	0.3707
rep8	177830	149198	12.0798	20809534	4378547	0.2106	3316071	0.1595	7664471	0.3687
rep9	177830	149198	20.9909	4469992	949107	0.2131	1013266	0.2275	1612032	0.3619

Metric	Value
auPRC	0.5745
Calibrated Recall at 50% FDR	0.2
Number of Positive Examples in Test Data	163470
Number of Negative Examples in Test Data	7907381
Imbalance Ratio in Test Data	0.0203
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 21092 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 4682 SequenceContrib ScoresHyp_Contrib Scores	Irf8, Irf4, Spib, Irf1, Irf2, Spi1, Irf3, Stat2, Stat1, Zscan10, Prdm1, Irf7, Elf5, Irf9, Spic, Zkscan5
metacluster_1/pattern_2 # seqlets: 2803 SequenceContrib ScoresHyp_Contrib Scores	Elf3, Ehf, Etv2, Ets1, Etv6, Etv4, Gabpa, Elf1, Erg, Elf4, Elf2, Elk1, Etv3
metacluster_1/pattern_3 # seqlets: 2706 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_4 # seqlets: 743 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_5 # seqlets: 371 SequenceContrib ScoresHyp_Contrib Scores	Fli1, Sp2, Zfx, Elk4, Elk3, Sp3, Sp1, Etv5, Etv1, Fev, Usf2, XP_911724.4, Klf3, Klf6, Rfx1, Sp4
metacluster_1/pattern_6 # seqlets: 223 SequenceContrib ScoresHyp_Contrib Scores	Zbtb17, Wt1, Egr1, Sp5, Klf15, Maz, Mxi1, Zfp281, Klf1, Klf5, Egr2, Tfap2b
metacluster_1/pattern_7 # seqlets: 168 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_8 # seqlets: 157 SequenceContrib ScoresHyp_Contrib Scores	Nrf1, Mbd2
metacluster_1/pattern_9 # seqlets: 117 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 79 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2
metacluster_1/pattern_11 # seqlets: 69 SequenceContrib ScoresHyp_Contrib Scores	Nr1h4, Tfap2a
metacluster_1/pattern_12 # seqlets: 36 SequenceContrib ScoresHyp_Contrib Scores