# Parameters
data_name = "LNG;8wks;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_203-naivegw"
perf_file = "/srv/scratch/msharmin/mouse_hem/with_tfd/full_mouse50/fineFactorized/task_203-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 19:27:35,694 [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	Lung (adult-8wks)
Cell Group	Other Tissues
Experiment Name	DHS
Experiment Group	GEO

Metric	Value
auPRC	0.5162
Calibrated Recall at 50% FDR	0.263
Number of Positive Examples in Test Data	91988
Number of Negative Examples in Test Data	7978863
Imbalance Ratio in Test Data	0.0114
Test Chromosomes	chr2, chr3, chr19

Pattern Name	TF Name(s)	Modisco
metacluster_0/pattern_0 # seqlets: 2160 SequenceContrib ScoresHyp_Contrib Scores	Sp2, Sp3, Klf3, Sp4, Sp1, Klf6, E2f4, Klf4, Klf5, Sp5, Klf7, Egr1, Zbtb17, Klf8, Wt1, Klf12, Egr2, Klf1, Maz, Zfp281, E2f1, Klf15, Sall4, Srebf2
metacluster_0/pattern_1 # seqlets: 2046 SequenceContrib ScoresHyp_Contrib Scores	Gabpa, Erg, Spi1, Elk1, Etv2, Etv4, Ets1, Fli1, Mxi1, Ehf, Etv6, Usf2, Elf2, Elk4, Etv5, Elk3, Etv3, XP_911724.4, Elf1, Fev, Etv1, Spib, Elf3, Elf4, Nr1h4, Spic, Zfx, Elf5, Zfp335, Myc, Spdef, Ctcfl, Nr1d2
metacluster_0/pattern_2 # seqlets: 1946 SequenceContrib ScoresHyp_Contrib Scores	Cebpb, Cebpa, Cebpd, Dbp, Nfil3, Hlf, Cebpg, Ddit3, Atf4, Cebpe, Tef, Pou3f3
metacluster_0/pattern_3 # seqlets: 1830 SequenceContrib ScoresHyp_Contrib Scores	Ctcf
metacluster_0/pattern_4 # seqlets: 1630 SequenceContrib ScoresHyp_Contrib Scores	Nfib, Nfia, Nfic
metacluster_0/pattern_5 # seqlets: 1249 SequenceContrib ScoresHyp_Contrib Scores	Foxm1, Foxa2, Foxa1, Foxd3, Foxa3, Foxd1, Foxc1, Foxc2, Foxb1, Foxj2, Foxl1, Foxl2, Foxg1, Foxk1, Foxp2, Gm5294, Foxj3, Foxj1, Foxp1, Foxo3, Foxo1, Foxq1, Pou2f1
metacluster_0/pattern_6 # seqlets: 1106 SequenceContrib ScoresHyp_Contrib Scores	Creb1, Creb5, Jdp2, Atf7, Atf1, Atf2, Crem, Jun, Mafb, Gmeb2, Fosl1, Rxrb, Atf3, Junb, Jund, Gmeb1
metacluster_0/pattern_7 # seqlets: 1045 SequenceContrib ScoresHyp_Contrib Scores	Nrf1
metacluster_0/pattern_8 # seqlets: 853 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_9 # seqlets: 743 SequenceContrib ScoresHyp_Contrib Scores	Nkx2-5, Nkx2-1, Nkx2-6, Nkx2-4, Nkx2-9, Nkx2-2, Nkx2-3, Nkx3-1, Nkx3-2, Hmx1, Hmx2
metacluster_0/pattern_10 # seqlets: 684 SequenceContrib ScoresHyp_Contrib Scores
metacluster_0/pattern_11 # seqlets: 678 SequenceContrib ScoresHyp_Contrib Scores	Nfyb, Nfyc, Nfya, Foxi1, Pbx3
metacluster_0/pattern_12 # seqlets: 624 SequenceContrib ScoresHyp_Contrib Scores	Irf1, Irf2, Irf8, Irf4, Irf7, Prdm1, Stat2, Irf9, Stat1, Irf5, Irf3
metacluster_0/pattern_13 # seqlets: 520 SequenceContrib ScoresHyp_Contrib Scores	Fosb, Fosl2, Fos, Bach2, Bach1, Nfe2l2, Nfe2, Batf, Mafa, Mafk
metacluster_0/pattern_14 # seqlets: 511 SequenceContrib ScoresHyp_Contrib Scores	Rfx2, Rfx3, Rfx1, Rfx4, Rfx6, Rfx7
metacluster_0/pattern_15 # seqlets: 505 SequenceContrib ScoresHyp_Contrib Scores	Usf1, Tfec, Tfeb, Mitf, Arntl, Tfe3, Srebf1, Bhlhe40, Clock, Mlx, Arnt, Npas2, Creb3l2, Tcfl5, Bhlhe41, Xbp1, Mycn, Max, Mlxip
metacluster_0/pattern_16 # seqlets: 402 SequenceContrib ScoresHyp_Contrib Scores	Taf1, Yy1, Zfp42
metacluster_0/pattern_17 # seqlets: 343 SequenceContrib ScoresHyp_Contrib Scores	Zfp143, Thap11, Tbx2
metacluster_0/pattern_18 # seqlets: 335 SequenceContrib ScoresHyp_Contrib Scores	Tead4, Tead1, Tead2
metacluster_0/pattern_19 # seqlets: 255 SequenceContrib ScoresHyp_Contrib Scores	Grhl2
metacluster_0/pattern_20 # seqlets: 197 SequenceContrib ScoresHyp_Contrib Scores	Mef2d, Mef2a, Mef2c
metacluster_0/pattern_21 # seqlets: 177 SequenceContrib ScoresHyp_Contrib Scores	Olig2, Twist1, Ptf1a, Lyl1, Atoh1, Tcf3, Neurod1, Neurod2, Tgif1, Ascl2, Myog, Snai1, Tfap4
metacluster_0/pattern_22 # seqlets: 138 SequenceContrib ScoresHyp_Contrib Scores	Gata2, Gata1, Tal1, Gata4, Gata6, Gata3, Gata5
metacluster_0/pattern_23 # seqlets: 90 SequenceContrib ScoresHyp_Contrib Scores	Runx1, Cbfb, Runx2
metacluster_0/pattern_24 # seqlets: 83 SequenceContrib ScoresHyp_Contrib Scores	Zbtb33