TF-MoDISco results

Summary of motifs

TOMTOM matches to motifs

In [1]:
import os
import sys
sys.path.append(os.path.abspath("/users/amtseng/tfmodisco/src/"))
from tfmodisco.run_tfmodisco import import_shap_scores, import_tfmodisco_results
from motif.read_motifs import pfm_info_content, pfm_to_pwm, trim_motif_by_ic
from motif.match_motifs import match_motifs_to_database
from util import figure_to_vdom_image
import plot.viz_sequence as viz_sequence
import numpy as np
import h5py
import matplotlib.pyplot as plt
import vdom.helpers as vdomh
from IPython.display import display

Define constants and paths

In [2]:
# Define parameters/fetch arguments
tf_name = os.environ["TFM_TF_NAME"]
shap_scores_path = os.environ["TFM_SHAP_PATH"]
tfm_results_path = os.environ["TFM_TFM_PATH"]
hyp_score_key = os.environ["TFM_HYP_SCORE_KEY"]
if "TFM_MOTIF_CACHE" in os.environ:
    tfm_motifs_cache_dir = os.environ["TFM_MOTIF_CACHE"]
else:
    tfm_motifs_cache_dir = None

print("TF name: %s" % tf_name)
print("DeepSHAP scores path: %s" % shap_scores_path)
print("TF-MoDISco results path: %s" % tfm_results_path)
print("Importance score key: %s" % hyp_score_key)
print("Saved TF-MoDISco-derived motifs cache: %s" % tfm_motifs_cache_dir)

TF name: CEBPB
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/CEBPB_multitask_profile_fold3/CEBPB_multitask_profile_fold3_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/CEBPB_multitask_profile_fold3/CEBPB_multitask_profile_fold3_count_tfm.h5
Importance score key: count_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/CEBPB_multitask_profile_fold3/CEBPB_multitask_profile_fold3_count
In [3]:
# Define paths and constants
input_length = 2114
shap_score_center_size = 400
In [4]:
if tfm_motifs_cache_dir:
    os.makedirs(tfm_motifs_cache_dir, exist_ok=True)

Import SHAP scores and TF-MoDISco results

In [5]:
# Import SHAP coordinates and one-hot sequences
hyp_scores, _, one_hot_seqs, shap_coords = import_shap_scores(shap_scores_path, hyp_score_key, center_cut_size=shap_score_center_size)
# This cuts the sequences/scores off just as how TF-MoDISco saw them, but the coordinates are uncut

Importing SHAP scores: 100%|██████████| 273/273 [08:26<00:00,  1.86s/it]
In [6]:
# Import the TF-MoDISco results object
tfm_obj = import_tfmodisco_results(tfm_results_path, hyp_scores, one_hot_seqs, shap_score_center_size)

Plot some SHAP score tracks

Plot the central region of some randomly selected actual importance scores

In [7]:
plot_slice = slice(int(shap_score_center_size / 4), int(3 * shap_score_center_size / 4))
for index in np.random.choice(hyp_scores.shape[0], size=5, replace=False):
    viz_sequence.plot_weights((hyp_scores[index] * one_hot_seqs[index])[plot_slice], subticks_frequency=100)

Plot TF-MoDISco results

Plot all motifs by metacluster

In [8]:
motif_pfms, motif_hcwms, motif_cwms = [], [], []  # Save the trimmed PFMs, hCWMs, and CWMs
motif_pfms_short = []  # PFMs that are even more trimmed (for TOMTOM)
num_seqlets = []  # Number of seqlets for each motif
motif_seqlets = []  # Save seqlets of each motif
metaclusters = tfm_obj.metacluster_idx_to_submetacluster_results
num_metaclusters = len(metaclusters.keys())
if tfm_motifs_cache_dir:
    motif_hdf5 = h5py.File(os.path.join(tfm_motifs_cache_dir, "all_motifs.h5"), "w")
for metacluster_i, metacluster_key in enumerate(metaclusters.keys()):
    metacluster = metaclusters[metacluster_key]
    display(vdomh.h3("Metacluster %d/%d" % (metacluster_i + 1, num_metaclusters)))
    patterns = metacluster.seqlets_to_patterns_result.patterns
    if not patterns:
        break
    motif_pfms.append([])
    motif_hcwms.append([])
    motif_cwms.append([])
    motif_pfms_short.append([])
    num_seqlets.append([])
    motif_seqlets.append([])
    num_patterns = len(patterns)
    for pattern_i, pattern in enumerate(patterns):
        seqlets = pattern.seqlets
        display(vdomh.h4("Pattern %d/%d" % (pattern_i + 1, num_patterns)))
        display(vdomh.p("%d seqlets" % len(seqlets)))
        
        pfm = pattern["sequence"].fwd
        hcwm = pattern["task0_hypothetical_contribs"].fwd
        cwm = pattern["task0_contrib_scores"].fwd
        
        pfm_fig = viz_sequence.plot_weights(pfm, subticks_frequency=10, return_fig=True)
        hcwm_fig = viz_sequence.plot_weights(hcwm, subticks_frequency=10, return_fig=True)
        cwm_fig = viz_sequence.plot_weights(cwm, subticks_frequency=10, return_fig=True)
        pfm_fig.tight_layout()
        hcwm_fig.tight_layout()
        cwm_fig.tight_layout()
        
        motif_table = vdomh.table(
            vdomh.tr(
                vdomh.td("Sequence (PFM)"),
                vdomh.td(figure_to_vdom_image(pfm_fig))
            ),
            vdomh.tr(
                vdomh.td("Hypothetical contributions (hCWM)"),
                vdomh.td(figure_to_vdom_image(hcwm_fig))
            ),
            vdomh.tr(
                vdomh.td("Actual contributions (CWM)"),
                vdomh.td(figure_to_vdom_image(cwm_fig))
            )
        )
        display(motif_table)
        plt.close("all")  # Remove all standing figures
        
        # Trim motif based on information content
        short_trimmed_pfm = trim_motif_by_ic(pfm, pfm)
        motif_pfms_short[-1].append(short_trimmed_pfm)
        
        # Expand trimming to +/- 4bp on either side
        trimmed_pfm = trim_motif_by_ic(pfm, pfm, pad=4)
        trimmed_hcwm = trim_motif_by_ic(pfm, hcwm, pad=4)
        trimmed_cwm = trim_motif_by_ic(pfm, cwm, pad=4)
        
        motif_pfms[-1].append(trimmed_pfm)
        motif_hcwms[-1].append(trimmed_hcwm)
        motif_cwms[-1].append(trimmed_cwm)
        
        num_seqlets[-1].append(len(seqlets))
        
        if tfm_motifs_cache_dir:
            # Save results and figures
            motif_id = "%d_%d" % (metacluster_i, pattern_i)
            pfm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_pfm_full.png"))
            hcwm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_full.png"))
            cwm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_cwm_full.png"))
            motif_dset = motif_hdf5.create_group(motif_id)
            motif_dset.create_dataset("pfm_full", data=pfm, compression="gzip")
            motif_dset.create_dataset("hcwm_full", data=hcwm, compression="gzip")
            motif_dset.create_dataset("cwm_full", data=cwm, compression="gzip")
            motif_dset.create_dataset("pfm_trimmed", data=trimmed_pfm, compression="gzip")
            motif_dset.create_dataset("hcwm_trimmed", data=trimmed_hcwm, compression="gzip")
            motif_dset.create_dataset("cwm_trimmed", data=trimmed_cwm, compression="gzip")
            motif_dset.create_dataset("pfm_short_trimmed", data=short_trimmed_pfm, compression="gzip")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

Metacluster 1/2

Pattern 1/11

12360 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 2/11

908 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 3/11

733 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 4/11

280 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 5/11

253 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 6/11

146 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 7/11

130 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 8/11

92 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 9/11

44 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 10/11

36 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 11/11

34 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Metacluster 2/2

Pattern 1/6

286 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 2/6

250 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 3/6

244 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 4/6

234 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 5/6

233 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Pattern 6/6

75 seqlets

Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)

Summary of motifs

Motifs are trimmed based on information content, and presented in descending order by number of supporting seqlets. The motifs are separated by metacluster. The motifs are presented as hCWMs. The forward orientation is defined as the orientation that is richer in purines.

In [9]:
colgroup = vdomh.colgroup(
    vdomh.col(style={"width": "5%"}),
    vdomh.col(style={"width": "5%"}),
    vdomh.col(style={"width": "45%"}),
    vdomh.col(style={"width": "45%"})
)
header = vdomh.thead(
    vdomh.tr(
        vdomh.th("#", style={"text-align": "center"}),
        vdomh.th("Seqlets", style={"text-align": "center"}),
        vdomh.th("Forward", style={"text-align": "center"}),
        vdomh.th("Reverse", style={"text-align": "center"})
    )
)

for i in range(len(motif_hcwms)):
    display(vdomh.h3("Metacluster %d/%d" % (i + 1, num_metaclusters)))
    body = []
    for j in range(len(motif_hcwms[i])):
        motif = motif_hcwms[i][j]
        if np.sum(motif[:, [0, 2]]) > 0.5 * np.sum(motif):
            # Forward is purine-rich, reverse-complement is pyrimidine-rich
            f, rc = motif, np.flip(motif, axis=(0, 1))
        else:
            f, rc = np.flip(motif, axis=(0, 1)), motif
            
        f_fig = viz_sequence.plot_weights(f, figsize=(20, 4), return_fig=True)
        f_fig.tight_layout()
        rc_fig = viz_sequence.plot_weights(rc, figsize=(20, 4), return_fig=True)
        rc_fig.tight_layout()
        
        if tfm_motifs_cache_dir:
            # Save results and figures
            motif_id = "%d_%d" % (i, j)
            f_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_trimmed_fwd.png"))
            rc_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_trimmed_rev.png"))

        body.append(
            vdomh.tr(
                vdomh.td(str(j + 1)),
                vdomh.td(str(num_seqlets[i][j])),
                vdomh.td(figure_to_vdom_image(f_fig)),
                vdomh.td(figure_to_vdom_image(rc_fig))
            )
        )
    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")

Metacluster 1/2

/users/amtseng/tfmodisco/src/plot/viz_sequence.py:152: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  fig = plt.figure(figsize=figsize)
#SeqletsForwardReverse
112360
2908
3733
4280
5253
6146
7130
892
944
1036
1134

Metacluster 2/2

#SeqletsForwardReverse
1286
2250
3244
4234
5233
675

Top TOMTOM matches for each motif

Here, the TF-MoDISco motifs are plotted as hCWMs, but the TOMTOM matches are shown as PWMs.

In [10]:
num_matches_to_keep = 10
num_matches_to_show = 5

header = vdomh.thead(
    vdomh.tr(
        vdomh.th("Motif ID", style={"text-align": "center"}),
        vdomh.th("q-val", style={"text-align": "center"}),
        vdomh.th("PWM", style={"text-align": "center"})
    )
)

for i in range(len(motif_pfms)):
    display(vdomh.h3("Metacluster %d/%d" % (i + 1, num_metaclusters)))
    
    # Compute TOMTOM matches for all motifs in the metacluster at once
    out_dir = os.path.join(tfm_motifs_cache_dir, "tomtom", "metacluster_%d" % i) if tfm_motifs_cache_dir else None
    tomtom_matches = match_motifs_to_database(motif_pfms_short[i], top_k=num_matches_to_keep, temp_dir=out_dir)
    
    for j in range(len(motif_pfms[i])):
        display(vdomh.h4("Motif %d/%d" % (j + 1, len(motif_pfms[i]))))
        viz_sequence.plot_weights(motif_hcwms[i][j])
    
        body = []
        for k, (match_name, match_pfm, match_qval) in enumerate(tomtom_matches[j]):
            fig = viz_sequence.plot_weights(pfm_to_pwm(match_pfm), return_fig=True)
            fig.tight_layout()
            if k < num_matches_to_show:
                body.append(
                    vdomh.tr(
                        vdomh.td(match_name),
                        vdomh.td(str(match_qval)),
                        vdomh.td(figure_to_vdom_image(fig))
                    )
                )
                if tfm_motifs_cache_dir:
                    # Save results and figures
                    motif_id = "%d_%d" % (i, j)
                    fig.savefig(os.path.join(out_dir, motif_id + ("_hit-%d.png" % (k + 1))))
            else:
                body.append(
                    vdomh.tr(
                        vdomh.td(match_name),
                        vdomh.td(str(match_qval)),
                        vdomh.td("Not shown")
                    )
                )
        if not body:
            display(vdomh.p("No TOMTOM matches passing threshold"))
        else:
            display(vdomh.table(header, vdomh.tbody(*body)))
        plt.close("all")

Metacluster 1/2

Motif 1/11

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A7.618960000000001e-10
CEBPD_HUMAN.H11MO.0.C3.58374e-09
CEBPA_HUMAN.H11MO.0.A5.19032e-07
MA0836.2_CEBPD1.70503e-05
MA0102.4_CEBPA0.000140298
MA0837.1_CEBPE0.000384489Not shown
MA0466.2_CEBPB0.000467352Not shown
MA0838.1_CEBPG0.0007583830000000001Not shown
MA0025.2_NFIL30.00128133Not shown
NFIL3_HUMAN.H11MO.0.D0.00234254Not shown

Motif 2/11

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A5.8661999999999995e-05
FOSL2_HUMAN.H11MO.0.A5.8661999999999995e-05
MA1622.1_Smad2::Smad35.8661999999999995e-05
MA1141.1_FOS::JUND7.11047e-05
NFE2_HUMAN.H11MO.0.A7.11047e-05
MA1128.1_FOSL1::JUN7.11047e-05Not shown
FOSL1_HUMAN.H11MO.0.A7.11047e-05Not shown
MA1130.1_FOSL2::JUN7.11047e-05Not shown
BACH2_HUMAN.H11MO.0.A7.11047e-05Not shown
MA0099.3_FOS::JUN7.11047e-05Not shown

Motif 3/11

Motif IDq-valPWM
MA0139.1_CTCF3.3534099999999996e-16
CTCF_HUMAN.H11MO.0.A9.63603e-13
CTCFL_HUMAN.H11MO.0.A2.2784099999999998e-07
MA1102.2_CTCFL0.000127594
MA1568.1_TCF21(var.2)0.13378199999999998
MA1638.1_HAND20.150917Not shown
ZIC3_HUMAN.H11MO.0.B0.22924699999999998Not shown
SNAI1_HUMAN.H11MO.0.C0.281523Not shown
ZIC2_HUMAN.H11MO.0.D0.316973Not shown
MA0155.1_INSM10.363845Not shown

Motif 4/11

Motif IDq-valPWM
TAL1_HUMAN.H11MO.0.A0.00042706
GATA1_HUMAN.H11MO.0.A0.00123501
GATA2_HUMAN.H11MO.0.A0.00123501
GATA4_HUMAN.H11MO.0.A0.00269241
MA0140.2_GATA1::TAL10.00316914
GATA1_HUMAN.H11MO.1.A0.00316914Not shown
GATA2_HUMAN.H11MO.1.A0.00316914Not shown
MA0036.3_GATA20.00862807Not shown
MA0482.2_GATA40.0152306Not shown
GATA3_HUMAN.H11MO.0.A0.0152306Not shown

Motif 5/11

Motif IDq-valPWM
FOXA2_HUMAN.H11MO.0.A1.0413500000000001e-07
FOXA1_HUMAN.H11MO.0.A1.32481e-07
FOXA3_HUMAN.H11MO.0.B5.65063e-07
FOXF2_HUMAN.H11MO.0.D1.3173699999999999e-06
FOXD3_HUMAN.H11MO.0.D3.16168e-06
MA0846.1_FOXC28.30743e-06Not shown
FOXM1_HUMAN.H11MO.0.A2.17378e-05Not shown
FOXC1_HUMAN.H11MO.0.C2.6727399999999998e-05Not shown
MA0847.2_FOXD23.15551e-05Not shown
FOXD1_HUMAN.H11MO.0.D0.000142165Not shown

Motif 6/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A7.76698e-07
SP3_HUMAN.H11MO.0.B7.74193e-06
PATZ1_HUMAN.H11MO.0.C0.000360727
TBX15_HUMAN.H11MO.0.D0.000360727
ZN148_HUMAN.H11MO.0.D0.000360727
KLF3_HUMAN.H11MO.0.B0.000360727Not shown
SP4_HUMAN.H11MO.0.A0.000360727Not shown
MAZ_HUMAN.H11MO.0.A0.000415515Not shown
ZN467_HUMAN.H11MO.0.C0.000507951Not shown
VEZF1_HUMAN.H11MO.0.C0.000507951Not shown

Motif 7/11

Motif IDq-valPWM
FOXB1_HUMAN.H11MO.0.D0.0008763660000000001
FOXD2_HUMAN.H11MO.0.D0.00782793
MA0845.1_FOXB10.0185118
MA0032.2_FOXC10.0185118
MA0846.1_FOXC20.0892364
MA0148.4_FOXA10.10228200000000001Not shown
MA1683.1_FOXA30.15478Not shown
FOXA2_HUMAN.H11MO.0.A0.171783Not shown
MA0047.3_FOXA20.171783Not shown
MA0481.3_FOXP10.171783Not shown

Motif 8/11

Motif IDq-valPWM
HNF4A_HUMAN.H11MO.0.A4.68566e-06
HNF4G_HUMAN.H11MO.0.B6.246e-06
MA0856.1_RXRG0.000235981
MA0855.1_RXRB0.000235981
MA0512.2_Rxra0.000235981
MA1574.1_THRB0.000259956Not shown
MA1550.1_PPARD0.000282713Not shown
MA0677.1_Nr2f60.000282713Not shown
MA1537.1_NR2F1(var.2)0.000502972Not shown
MA1148.1_PPARA::RXRA0.000576471Not shown

Motif 9/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B0.00559162
HNF4A_HUMAN.H11MO.0.A0.00559162
RXRG_HUMAN.H11MO.0.B0.00559162
NR1H2_HUMAN.H11MO.0.D0.0100029
MA0512.2_Rxra0.0100029
MA0855.1_RXRB0.0100029Not shown
MA0856.1_RXRG0.0100029Not shown
MA0677.1_Nr2f60.0104685Not shown
MA0115.1_NR1H2::RXRA0.0108693Not shown
MA1537.1_NR2F1(var.2)0.012812100000000002Not shown

Motif 10/11

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A4.28653e-07
MA0139.1_CTCF4.28653e-07
CTCFL_HUMAN.H11MO.0.A2.004e-06
MA1102.2_CTCFL0.000220137
SP1_HUMAN.H11MO.0.A0.00949196
SP2_HUMAN.H11MO.1.B0.00949196Not shown
MA1513.1_KLF150.010690100000000001Not shown
ZFX_HUMAN.H11MO.1.A0.011850399999999999Not shown
SP3_HUMAN.H11MO.0.B0.011850399999999999Not shown
PATZ1_HUMAN.H11MO.0.C0.011850399999999999Not shown

Motif 11/11

Motif IDq-valPWM
MA0833.2_ATF40.00827186
MA1636.1_CEBPG(var.2)0.00863928
DDIT3_HUMAN.H11MO.0.D0.00863928
CEBPG_HUMAN.H11MO.0.B0.00863928
CEBPB_HUMAN.H11MO.0.A0.00863928
ATF4_HUMAN.H11MO.0.A0.00969773Not shown
NFIL3_HUMAN.H11MO.0.D0.013009399999999999Not shown
CEBPD_HUMAN.H11MO.0.C0.0150072Not shown
DBP_HUMAN.H11MO.0.B0.0150072Not shown
CEBPA_HUMAN.H11MO.0.A0.0164965Not shown

Metacluster 2/2

Motif 1/6

No TOMTOM matches passing threshold

Motif 2/6

No TOMTOM matches passing threshold

Motif 3/6

No TOMTOM matches passing threshold

Motif 4/6

No TOMTOM matches passing threshold

Motif 5/6

Motif IDq-valPWM
MA0466.2_CEBPB0.0005662169999999999
MA0837.1_CEBPE0.0005662169999999999
CEBPB_HUMAN.H11MO.0.A0.000789357
CEBPD_HUMAN.H11MO.0.C0.000789357
MA0838.1_CEBPG0.00120733
MA0025.2_NFIL30.00825084Not shown
CEBPG_HUMAN.H11MO.0.B0.00825084Not shown
CEBPE_HUMAN.H11MO.0.A0.00825084Not shown
DDIT3_HUMAN.H11MO.0.D0.00825084Not shown
ATF4_HUMAN.H11MO.0.A0.00825084Not shown

Motif 6/6

No TOMTOM matches passing threshold