# Parameters
data_name = "ES;ZhBTc4;1;D;GEO"
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_198-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_198-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 19:25:17,769 [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	Undifferentiated mouse embryonic stem cells (ZhBTc4)
Cell Group	ES cells and embryonic tissues
Experiment Name	DHS
Experiment Group	GEO

Metric	Value
auPRC	0.6826
Calibrated Recall at 50% FDR	0.168
Number of Positive Examples in Test Data	133495
Number of Negative Examples in Test Data	7937356
Imbalance Ratio in Test Data	0.0165
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_1/pattern_0 # seqlets: 4584 SequenceContrib ScoresHyp_Contrib Scores	Sp1, Sp2, Sp3, Klf3, Sp4, Sp5, Maz, Zfp281, Zbtb17, Wt1, Klf15, Klf6, Klf1, Rela, Egr1, Klf5, Klf4, Klf7, Sall4, Egr2, Klf12, Bcl6, Klf8, E2f4, Ptf1a, E2f6, Nr1h4, Mbd2, Zfx, Fli1, Srebf2
metacluster_1/pattern_1 # seqlets: 3251 SequenceContrib ScoresHyp_Contrib Scores	Ctcf, Ctcfl
metacluster_1/pattern_2 # seqlets: 2960 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_3 # seqlets: 1547 SequenceContrib ScoresHyp_Contrib Scores	Tfap2a, Tfap2c, Tfap2b, Tfap2e
metacluster_1/pattern_4 # seqlets: 1515 SequenceContrib ScoresHyp_Contrib Scores	Elk1, Gabpa, Elf1, Ets1, Erg, Elk4, Elk3, Elf5, Etv5, Fev, Ehf, Etv4, Elf2, Etv1, Elf4, Etv6, XP_911724.4, Etv3, Etv2, Elf3, Spi1, Spdef, Stat6, Stat3, Spib, Spic
metacluster_1/pattern_5 # seqlets: 1220 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_1/pattern_6 # seqlets: 983 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead2, Tead1
metacluster_1/pattern_7 # seqlets: 917 SequenceContrib ScoresHyp_Contrib Scores	Sox4, Sox17, Sox3, Sox2, Sox9, Sox6, Nanog, Lef1, Tcf7, Sox12, Sry
metacluster_1/pattern_8 # seqlets: 911 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_1/pattern_9 # seqlets: 821 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_10 # seqlets: 686 SequenceContrib ScoresHyp_Contrib Scores	Tfec, Tfeb, Usf1, Srebf1, Mitf, Arntl, Tfe3, Bhlhe40, Usf2, Mlx, Clock, Arnt, Npas2, Tcfl5, Creb3l2, Bhlhe41, Atf1, Hlf, Dbp, Xbp1, Mlxip
metacluster_1/pattern_11 # seqlets: 643 SequenceContrib ScoresHyp_Contrib Scores	Rara, Esrrb, Nr5a2, Rxrg, Rxra, Esrra, Nr5a1, Esrrg, Rarg, Nr2f6, Rxrb, Nr2c2, Nr4a2, Nkx2-9
metacluster_1/pattern_12 # seqlets: 544 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_13 # seqlets: 401 SequenceContrib ScoresHyp_Contrib Scores	Nfe2, Bach2, Nfe2l2, Bach1, Mafk, Mafa, Mafb, Mafg, Jun, Maff, Maf, Atf3, Fosb, Fosl2, Junb, Batf, Fosl1, Jund, Fos, Jdp2
metacluster_1/pattern_14 # seqlets: 400 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42, Mxi1
metacluster_1/pattern_15 # seqlets: 231 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_1/pattern_16 # seqlets: 206 SequenceContrib ScoresHyp_Contrib Scores	Rfx3, Rfx2, Rfx1, Rfx4, Rfx7, Rfx6
metacluster_1/pattern_17 # seqlets: 203 SequenceContrib ScoresHyp_Contrib Scores	Six2, Six1, Six4
metacluster_1/pattern_18 # seqlets: 172 SequenceContrib ScoresHyp_Contrib Scores	Pou2f2, Pou5f1, Pou2f1
metacluster_1/pattern_19 # seqlets: 130 SequenceContrib ScoresHyp_Contrib Scores	Tcfcp2l1
metacluster_1/pattern_20 # seqlets: 118 SequenceContrib ScoresHyp_Contrib Scores	Atf2, Atf7, Creb1, Crem, Creb5, Nfil3, Tef
metacluster_1/pattern_21 # seqlets: 99 SequenceContrib ScoresHyp_Contrib Scores	Nfia, Nfib, Nfic
metacluster_1/pattern_22 # seqlets: 95 SequenceContrib ScoresHyp_Contrib Scores	Trp53, Trp63, Trp73
metacluster_1/pattern_23 # seqlets: 90 SequenceContrib ScoresHyp_Contrib Scores	Rest
metacluster_1/pattern_24 # seqlets: 48 SequenceContrib ScoresHyp_Contrib Scores
metacluster_1/pattern_25 # seqlets: 39 SequenceContrib ScoresHyp_Contrib Scores