# Parameters
data_name = "CRBLM;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_236-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_236-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 19:33:29,609 [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	Cerebellum
Cell Group	Neural Cells and 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	118743	79431	14.6458	18866499	3586022	0.1902	2136418	0.1133	7588285	0.4024
rep2	118743	79431	13.2157	18243263	2968818	0.1628	1914079	0.105	6959356	0.3817
rep3	118743	79431	17.5272	28254615	7244862	0.2565	3821190	0.1353	11675589	0.4134

Metric	Value
auPRC	0.4973
Calibrated Recall at 50% FDR	0.265
Number of Positive Examples in Test Data	103311
Number of Negative Examples in Test Data	7967540
Imbalance Ratio in Test Data	0.0128
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 5074 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_1 # seqlets: 2976 SequenceContrib ScoresHyp_Contrib Scores	Neurod1, Neurod2, Olig2, Neurog2, Atoh1, Msgn1, Msc, Bhlhe22, Neurog1, Tcf21, Twist2, Bhlha15, Ascl2, Lyl1, Ascl1, Clock, Snai1
metacluster_1/pattern_2 # seqlets: 2917 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_3 # seqlets: 1719 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Sp4, Sp1, Klf3, E2f4, Klf6, Sp5, Klf4, Zbtb17, Egr1, Klf7, Klf5, Wt1, Klf8, Klf12, Egr2, Maz, Zfp281, Klf1, Klf15, E2f1, Egr3
metacluster_1/pattern_4 # seqlets: 1342 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_5 # seqlets: 1294 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfya, Nfyc, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 973 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Atf7, Jdp2, Atf2, Atf1, Crem, Nfil3, Jun, Mafb, Tef, Rxrb, Dbp, Atf3, Hlf, Fosl1, Gmeb2
metacluster_1/pattern_7 # seqlets: 875 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Fli1, Ets1, Elk4, Elk3, Erg, Elk1, Elf1, Etv4, Etv1, Etv5, Etv2, Fev, Etv3, Etv6, XP_911724.4, Elf4, Ehf, Elf5, Elf2, Spdef, Spi1, Elf3
metacluster_1/pattern_8 # seqlets: 522 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Cebpg, Ddit3, Atf4
metacluster_1/pattern_9 # seqlets: 515 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_10 # seqlets: 472 SequenceContrib ScoresHyp_Contrib Scores	Usf2, Usf1, Tfeb, Arntl, Tfe3, Tfec, Mitf, Srebf1, Bhlhe40, Arnt, Mlx, Srebf2, Npas2, Tcfl5, Mycn, Max, Myc, Bhlhe41, Creb3l2, Rxrg
metacluster_1/pattern_11 # seqlets: 458 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_1/pattern_12 # seqlets: 330 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx1, Rfx2, Rfx4, Rfx6, Rfx7
metacluster_1/pattern_13 # seqlets: 318 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfx, Zfp42
metacluster_1/pattern_14 # seqlets: 196 SequenceContrib ScoresHyp_Contrib Scores	Rorc, Pparg, Rora, Nr1d2, Esr2
metacluster_1/pattern_15 # seqlets: 167 SequenceContrib ScoresHyp_Contrib Scores	Zic3, Zic2
metacluster_1/pattern_16 # seqlets: 145 SequenceContrib ScoresHyp_Contrib Scores	Fosl2, Fos, Jund, Junb, Fosb, Batf, Bach2, Nfe2, Nfe2l2, Mafk, Mafa, Mafg, Bach1, Maf, Maff
metacluster_1/pattern_17 # seqlets: 140 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33
metacluster_1/pattern_18 # seqlets: 101 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_19 # seqlets: 78 SequenceContrib ScoresHyp_Contrib Scores