# Parameters
data_name = "LVR;8wks;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_224-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_224-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 19:30:29,751 [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	Liver(adult-8wks)
Cell Group	Other Tissues
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	189092	141583	10.5019	17456519	3823117	0.2192	1593713	0.0914	6980539	0.4002
rep10	189092	141583	9.0657	32667634	6614408	0.2025	3033830	0.0929	12195644	0.3734
rep11	189092	141583	18.336	15179717	5834213	0.3845	2643969	0.1742	6819720	0.4494
rep12	189092	141583	16.7853	22681444	9236183	0.4074	3669106	0.1618	10426106	0.4598
rep13	189092	141583	10.1592	29558474	4476333	0.1515	2304623	0.078	11267615	0.3813
rep14	189092	141583	12.0208	27381052	7358853	0.2689	2687758	0.0982	11334053	0.4141
rep2	189092	141583	7.0062	113906602	34245186	0.3007	10570447	0.0928	47552662	0.4175
rep3	189092	141583	11.7577	19823261	5348148	0.2699	2058410	0.1039	8467563	0.4273
rep4	189092	141583	11.3708	17752601	4238100	0.2389	1874130	0.1056	7408898	0.4176
rep5	189092	141583	15.65	16038825	7047902	0.4396	2508806	0.1565	7917819	0.4939
rep6	189092	141583	13.2908	16127786	6775612	0.4203	2264582	0.1405	7864700	0.4879
rep7	189092	141583	11.1194	17614444	6972538	0.396	2422528	0.1376	8073995	0.4585
rep8	189092	141583	17.6579	19263658	6937639	0.3603	2876396	0.1494	8616200	0.4475
rep9	189092	141583	15.7119	21092484	6312055	0.2994	2745382	0.1302	9126180	0.4329

Metric	Value
auPRC	0.5399
Calibrated Recall at 50% FDR	0.252
Number of Positive Examples in Test Data	179928
Number of Negative Examples in Test Data	7890923
Imbalance Ratio in Test Data	0.0223
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 4545 SequenceContrib ScoresHyp_Contrib Scores	Nr1h3, Hnf4g, Rxra, Nr2c2, Nr2f6, Rxrb, Hnf4a, Ppara, Nr2f1, Pparg, Nr2c1, Nr4a2, Nr5a2, Nr2e3, Nr5a1, Rara, Rarg, Rarb, Nr2f2, Esrrb, Esrra
metacluster_0/pattern_1 # seqlets: 3858 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_0/pattern_2 # seqlets: 3232 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Nfil3, Dbp, Cebpg, Hlf, Ddit3, Atf4, Cebpe, Tef, Pou3f3
metacluster_0/pattern_3 # seqlets: 2314 SequenceContrib ScoresHyp_Contrib Scores	Sp4, Sp2, Sp3, Klf3, Sp1, E2f4, Klf6, Klf7, Klf4, Klf8, Egr1, Klf1, Klf12, Zbtb17, Egr2, Sp5, E2f1, Zfp281, Klf5, Zfx, Egr3
metacluster_0/pattern_4 # seqlets: 1978 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_5 # seqlets: 1172 SequenceContrib ScoresHyp_Contrib Scores	Hnf1b, Hnf1a
metacluster_0/pattern_6 # seqlets: 961 SequenceContrib ScoresHyp_Contrib Scores	Onecut1, Cux2
metacluster_0/pattern_7 # seqlets: 896 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_8 # seqlets: 825 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Elk1, Elf1, Elk4, Fli1, Ets1, Erg, Elk3, Fev, Etv5, Elf5, Etv1, Etv4, Ehf, Etv6, Elf4, Etv3, XP_911724.4, Etv2, Elf2, Spdef, Elf3, Spi1, Stat3
metacluster_0/pattern_9 # seqlets: 803 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_10 # seqlets: 720 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Usf2, Tfeb, Tfec, Mitf, Arntl, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Srebf2, Creb3l2, Tcfl5, Atf1, Bhlhe41, Xbp1, Mlxip, Mycn
metacluster_0/pattern_11 # seqlets: 639 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Jdp2, Atf2, Crem, Jun, Mafb, Atf3, Fosl1, Gmeb2, Jund, Fosl2
metacluster_0/pattern_12 # seqlets: 587 SequenceContrib ScoresHyp_Contrib Scores	Foxa2, Foxm1, Foxd1, Foxc2, Foxa1, Foxc1, Foxb1, Foxj2, Foxa3, Foxl1, Foxd3
metacluster_0/pattern_13 # seqlets: 530 SequenceContrib ScoresHyp_Contrib Scores	Foxg1, Foxp2, Foxl2, Foxk1, Foxo1, Foxp1, Foxo3, Foxj3, Gm5294, Foxj1, Foxq1
metacluster_0/pattern_14 # seqlets: 471 SequenceContrib ScoresHyp_Contrib Scores	Barx1
metacluster_0/pattern_15 # seqlets: 442 SequenceContrib ScoresHyp_Contrib Scores	Yy1, Taf1, Rfx1, Zfp42
metacluster_0/pattern_16 # seqlets: 341 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_17 # seqlets: 334 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf8, Irf7, Prdm1, Stat2, Stat1, Irf9, Irf4, Irf3, Spib, Batf3
metacluster_0/pattern_18 # seqlets: 158 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Nfe2l2, Bach2, Mafk, Bach1, Mafa, Maff, Mafg, Fosb, Junb, Maf, Batf, Fos
metacluster_0/pattern_19 # seqlets: 101 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_20 # seqlets: 50 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33