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: MAFK
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/MAFK_multitask_profile_fold9/MAFK_multitask_profile_fold9_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAFK_multitask_profile_fold9/MAFK_multitask_profile_fold9_profile_tfm.h5
Importance score key: profile_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/MAFK_multitask_profile_fold9/MAFK_multitask_profile_fold9_profile
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%|██████████| 311/311 [03:56<00:00,  1.32it/s]
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

9912 seqlets

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

Pattern 2/11

621 seqlets

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

Pattern 3/11

579 seqlets

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

Pattern 4/11

360 seqlets

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

Pattern 5/11

329 seqlets

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

Pattern 6/11

325 seqlets

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

Pattern 7/11

98 seqlets

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

Pattern 8/11

87 seqlets

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

Pattern 9/11

72 seqlets

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

Pattern 10/11

61 seqlets

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

Pattern 11/11

41 seqlets

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

Metacluster 2/2

Pattern 1/4

95 seqlets

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

Pattern 2/4

37 seqlets

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

Pattern 3/4

36 seqlets

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

Pattern 4/4

31 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
19912
2621
3579
4360
5329
6325
798
887
972
1061
1141

Metacluster 2/2

#SeqletsForwardReverse
195
237
336
431

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
MAFB_HUMAN.H11MO.0.B2.21356e-09
MA0496.3_MAFK2.21356e-09
MAFK_HUMAN.H11MO.0.A2.21356e-09
MA1520.1_MAF3.14599e-09
MAFG_HUMAN.H11MO.0.A3.2074099999999998e-09
MAFK_HUMAN.H11MO.1.A1.44299e-08Not shown
MAF_HUMAN.H11MO.0.A3.77619e-08Not shown
MA1521.1_MAFA7.45455e-08Not shown
MAFF_HUMAN.H11MO.0.B1.93753e-07Not shown
MAF_HUMAN.H11MO.1.B8.19416e-06Not shown

Motif 2/11

Motif IDq-valPWM
MA0478.1_FOSL20.000230699
MA0150.2_Nfe2l20.000230699
BACH2_HUMAN.H11MO.0.A0.000230699
FOSL1_HUMAN.H11MO.0.A0.000230699
MA0089.2_NFE2L10.000230699
FOSB_HUMAN.H11MO.0.A0.000230699Not shown
MA1633.1_BACH10.000230699Not shown
MA0501.1_MAF::NFE20.000230699Not shown
NF2L2_HUMAN.H11MO.0.A0.000230699Not shown
NFE2_HUMAN.H11MO.0.A0.000230699Not shown

Motif 3/11

Motif IDq-valPWM
MA0139.1_CTCF4.50517e-19
CTCF_HUMAN.H11MO.0.A5.61951e-13
CTCFL_HUMAN.H11MO.0.A8.09465e-08
MA1102.2_CTCFL0.000316898
MA1568.1_TCF21(var.2)0.0696614
MA1638.1_HAND20.10793699999999999Not shown
SNAI1_HUMAN.H11MO.0.C0.19077Not shown
ZIC3_HUMAN.H11MO.0.B0.43387600000000004Not shown
MA1648.1_TCF12(var.2)0.447201Not shown
BHA15_HUMAN.H11MO.0.B0.447201Not shown

Motif 4/11

Motif IDq-valPWM
MA0117.2_Mafb9.52701e-06
MAFG_HUMAN.H11MO.0.A4.18338e-05
MA0659.2_MAFG4.18338e-05
MA0495.3_MAFF7.97188e-05
MAFK_HUMAN.H11MO.0.A0.000229388
MAFF_HUMAN.H11MO.0.B0.0062063000000000005Not shown
MA0842.2_NRL0.0117063Not shown
MA0501.1_MAF::NFE20.014149700000000001Not shown
NF2L2_HUMAN.H11MO.0.A0.014149700000000001Not shown
MAF_HUMAN.H11MO.1.B0.014149700000000001Not shown

Motif 5/11

Motif IDq-valPWM
MAF_HUMAN.H11MO.1.B0.00176119
MAF_HUMAN.H11MO.0.A0.00801348
MAFK_HUMAN.H11MO.1.A0.00996404
MA1520.1_MAF0.0106167
MAFF_HUMAN.H11MO.0.B0.0106167
MA1521.1_MAFA0.0106167Not shown
MAFG_HUMAN.H11MO.0.A0.0106167Not shown
MA0496.3_MAFK0.012169200000000002Not shown
MAFK_HUMAN.H11MO.0.A0.012169200000000002Not shown
MAFB_HUMAN.H11MO.0.B0.0128644Not shown

Motif 6/11

Motif IDq-valPWM
PTF1A_HUMAN.H11MO.1.B0.0414963
BHA15_HUMAN.H11MO.0.B0.0466448
ASCL2_HUMAN.H11MO.0.D0.0826838
ITF2_HUMAN.H11MO.0.C0.0826838
MA0521.1_Tcf120.0826838
MYOD1_HUMAN.H11MO.1.A0.0826838Not shown
ATOH1_HUMAN.H11MO.0.B0.0826838Not shown
MYF6_HUMAN.H11MO.0.C0.0826838Not shown
TFE2_HUMAN.H11MO.0.A0.0895938Not shown
MA1638.1_HAND20.0895938Not shown

Motif 7/11

Motif IDq-valPWM
MA0139.1_CTCF0.0201032
CTCF_HUMAN.H11MO.0.A0.026069
CTCFL_HUMAN.H11MO.0.A0.0272003
MA0748.2_YY20.161437
MA0095.2_YY10.17269
TYY1_HUMAN.H11MO.0.A0.17269Not shown
SNAI1_HUMAN.H11MO.0.C0.18695799999999999Not shown
MA1638.1_HAND20.308983Not shown
MA1102.2_CTCFL0.39876100000000003Not shown
MA0743.2_SCRT10.39876100000000003Not shown

Motif 8/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D7.166019999999999e-06
MA1125.1_ZNF3840.0005063859999999999
LMX1A_HUMAN.H11MO.0.D0.010737100000000001
HXC10_HUMAN.H11MO.0.D0.010737100000000001
FOXG1_HUMAN.H11MO.0.D0.0121802
PO3F3_HUMAN.H11MO.0.D0.0142476Not shown
MA0679.2_ONECUT10.0157761Not shown
FOXL1_HUMAN.H11MO.0.D0.0157761Not shown
PRDM6_HUMAN.H11MO.0.C0.0223372Not shown
FOXD2_HUMAN.H11MO.0.D0.0302039Not shown

Motif 9/11

Motif IDq-valPWM
MA0496.3_MAFK2.2283000000000003e-06
BACH2_HUMAN.H11MO.0.A1.3884000000000001e-05
MA0150.2_Nfe2l22.2881399999999997e-05
MA1633.1_BACH12.2881399999999997e-05
MA0501.1_MAF::NFE22.2881399999999997e-05
MA0591.1_Bach1::Mafk2.2881399999999997e-05Not shown
MAFK_HUMAN.H11MO.1.A2.2881399999999997e-05Not shown
NFE2_HUMAN.H11MO.0.A3.12283e-05Not shown
NF2L2_HUMAN.H11MO.0.A3.46982e-05Not shown
BACH1_HUMAN.H11MO.0.A3.63703e-05Not shown

Motif 10/11

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A0.00325537
MA0139.1_CTCF0.0103867
TYY1_HUMAN.H11MO.0.A0.05685
ZN121_HUMAN.H11MO.0.C0.05685
MITF_HUMAN.H11MO.0.A0.05685
PAX5_HUMAN.H11MO.0.A0.062309800000000005Not shown
TFE3_HUMAN.H11MO.0.B0.062309800000000005Not shown
MA0095.2_YY10.062309800000000005Not shown
MA0860.1_Rarg(var.2)0.0799785Not shown
CTCFL_HUMAN.H11MO.0.A0.0799785Not shown

Motif 11/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A5.3005000000000004e-08
SP1_HUMAN.H11MO.0.A5.52721e-08
KLF16_HUMAN.H11MO.0.D5.52721e-08
SP3_HUMAN.H11MO.0.B1.2232999999999998e-07
TBX15_HUMAN.H11MO.0.D2.04108e-07
PATZ1_HUMAN.H11MO.0.C1.1564e-06Not shown
MAZ_HUMAN.H11MO.0.A1.8493099999999999e-06Not shown
ZN467_HUMAN.H11MO.0.C2.29525e-06Not shown
WT1_HUMAN.H11MO.0.C6.4220600000000005e-06Not shown
VEZF1_HUMAN.H11MO.0.C2.36603e-05Not shown

Metacluster 2/2

Motif 1/4

Motif IDq-valPWM
MA0495.3_MAFF9.14425e-06
MA0659.2_MAFG1.7024300000000002e-05
MA0117.2_Mafb6.09267e-05
MAFB_HUMAN.H11MO.0.B0.000436111
MAF_HUMAN.H11MO.1.B0.000436111
MAFK_HUMAN.H11MO.0.A0.00531029Not shown
MA0842.2_NRL0.00634251Not shown
MAFG_HUMAN.H11MO.0.A0.0066961Not shown
NRL_HUMAN.H11MO.0.D0.00688886Not shown
MA0501.1_MAF::NFE20.00688886Not shown

Motif 2/4

Motif IDq-valPWM
MAF_HUMAN.H11MO.0.A0.00946805
MAFK_HUMAN.H11MO.0.A0.00946805
MAFG_HUMAN.H11MO.0.A0.00946805
MA0496.3_MAFK0.00946805
MAFK_HUMAN.H11MO.1.A0.00946805
MA0495.3_MAFF0.00946805Not shown
MA0117.2_Mafb0.015268799999999999Not shown
MA0681.2_PHOX2B0.0195783Not shown
RX_HUMAN.H11MO.0.D0.0230983Not shown
ESX1_HUMAN.H11MO.0.D0.0247079Not shown

Motif 3/4

No TOMTOM matches passing threshold

Motif 4/4

No TOMTOM matches passing threshold