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: E2F6
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/E2F6_multitask_profile_fold6/E2F6_multitask_profile_fold6_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/E2F6_multitask_profile_fold6/E2F6_multitask_profile_fold6_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/E2F6_multitask_profile_fold6/E2F6_multitask_profile_fold6_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%|██████████| 52/52 [00:28<00:00,  1.80it/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")

Metacluster 1/1

Pattern 1/14

5241 seqlets

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

Pattern 2/14

3141 seqlets

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

Pattern 3/14

1961 seqlets

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

Pattern 4/14

1467 seqlets

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

Pattern 5/14

456 seqlets

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

Pattern 6/14

412 seqlets

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

Pattern 7/14

206 seqlets

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

Pattern 8/14

193 seqlets

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

Pattern 9/14

144 seqlets

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

Pattern 10/14

87 seqlets

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

Pattern 11/14

78 seqlets

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

Pattern 12/14

61 seqlets

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

Pattern 13/14

45 seqlets

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

Pattern 14/14

45 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 1/1

/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
15241
23141
31961
41467
5456
6412
7206
8193
9144
1087
1178
1261
1345
1445

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 1/1

Motif 1/14

Motif IDq-valPWM
MAX_HUMAN.H11MO.0.A0.0006885560000000001
MA0147.3_MYC0.0006885560000000001
MXI1_HUMAN.H11MO.1.A0.00209588
MYC_HUMAN.H11MO.0.A0.00209588
MA0058.3_MAX0.00371653
MA0059.1_MAX::MYC0.00674503Not shown
MXI1_HUMAN.H11MO.0.A0.00707906Not shown
MA0825.1_MNT0.00713633Not shown
MA0004.1_Arnt0.00713633Not shown
HEY2_HUMAN.H11MO.0.D0.014875399999999999Not shown

Motif 2/14

Motif IDq-valPWM
E2F1_HUMAN.H11MO.0.A8.697750000000001e-07
E2F6_HUMAN.H11MO.0.A6.5238900000000005e-06
E2F3_HUMAN.H11MO.0.A7.62174e-06
MA0471.2_E2F69.527180000000001e-06
E2F4_HUMAN.H11MO.0.A1.9294100000000002e-05
TFDP1_HUMAN.H11MO.0.C1.9294100000000002e-05Not shown
E2F7_HUMAN.H11MO.0.B0.000169814Not shown
MA1122.1_TFDP10.00105367Not shown
E2F4_HUMAN.H11MO.1.A0.017314700000000002Not shown
MA0865.1_E2F80.017314700000000002Not shown

Motif 3/14

Motif IDq-valPWM
MA1650.1_ZBTB140.27724499999999996

Motif 4/14

Motif IDq-valPWM
MA0147.3_MYC0.0946903
MYCN_HUMAN.H11MO.0.A0.0946903
MA0104.4_MYCN0.15845499999999998
HES1_HUMAN.H11MO.0.D0.2914
MYC_HUMAN.H11MO.0.A0.306998
ZIC3_HUMAN.H11MO.0.B0.306998Not shown
MA0871.2_TFEC0.306998Not shown
ZIC2_HUMAN.H11MO.0.D0.319791Not shown
HEY2_HUMAN.H11MO.0.D0.322866Not shown

Motif 5/14

Motif IDq-valPWM
BACH2_HUMAN.H11MO.0.A0.000186045
BACH1_HUMAN.H11MO.0.A0.000186045
MA0150.2_Nfe2l20.000376415
NF2L2_HUMAN.H11MO.0.A0.000376415
MA0501.1_MAF::NFE20.000376415
JUND_HUMAN.H11MO.0.A0.000376415Not shown
JUN_HUMAN.H11MO.0.A0.000376415Not shown
JUNB_HUMAN.H11MO.0.A0.000376415Not shown
MA0591.1_Bach1::Mafk0.000376415Not shown
MA1633.1_BACH10.000376415Not shown

Motif 6/14

Motif IDq-valPWM
CTCFL_HUMAN.H11MO.0.A2.14444e-09
CTCF_HUMAN.H11MO.0.A1.35764e-08
MA0139.1_CTCF4.27815e-07
MA1102.2_CTCFL1.3856800000000001e-05
PLAL1_HUMAN.H11MO.0.D0.12435299999999999
KLF8_HUMAN.H11MO.0.C0.140476Not shown
MA0155.1_INSM10.140476Not shown
MA1548.1_PLAGL20.150885Not shown
SNAI1_HUMAN.H11MO.0.C0.163425Not shown
AP2B_HUMAN.H11MO.0.B0.195798Not shown

Motif 7/14

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00012096100000000001
SP1_HUMAN.H11MO.0.A0.000157388
SP3_HUMAN.H11MO.0.B0.00204884
MA1650.1_ZBTB140.00679068
THAP1_HUMAN.H11MO.0.C0.00679068
MXI1_HUMAN.H11MO.0.A0.00793957Not shown
SP1_HUMAN.H11MO.1.A0.00839924Not shown
CTCF_HUMAN.H11MO.0.A0.0181683Not shown
ZFX_HUMAN.H11MO.1.A0.0184868Not shown
MA0146.2_Zfx0.0222422Not shown

Motif 8/14

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.0048708
SP1_HUMAN.H11MO.0.A0.00543164
SP3_HUMAN.H11MO.0.B0.00543164
MXI1_HUMAN.H11MO.0.A0.00926931
MA1650.1_ZBTB140.0112961
CTCFL_HUMAN.H11MO.0.A0.0118935Not shown
AP2D_HUMAN.H11MO.0.D0.012434299999999999Not shown
ZBT14_HUMAN.H11MO.0.C0.030635500000000003Not shown
MA1099.2_HES10.0423933Not shown
THAP1_HUMAN.H11MO.0.C0.0423933Not shown

Motif 9/14

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A5.85189e-06
SP1_HUMAN.H11MO.0.A4.4714799999999994e-05
SP3_HUMAN.H11MO.0.B9.932129999999999e-05
MXI1_HUMAN.H11MO.0.A0.00032877199999999996
SP1_HUMAN.H11MO.1.A0.00510296
PATZ1_HUMAN.H11MO.0.C0.00541891Not shown
ZFX_HUMAN.H11MO.1.A0.00541891Not shown
KLF3_HUMAN.H11MO.0.B0.00541891Not shown
THAP1_HUMAN.H11MO.0.C0.00541891Not shown
MA1650.1_ZBTB140.00877193Not shown

Motif 10/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.24758e-05
MA1125.1_ZNF3840.0260452
PRDM6_HUMAN.H11MO.0.C0.0260452
FOXL1_HUMAN.H11MO.0.D0.04125209999999999
FOXG1_HUMAN.H11MO.0.D0.07947219999999999
ANDR_HUMAN.H11MO.0.A0.140466Not shown
MA0679.2_ONECUT10.140466Not shown
FOXJ3_HUMAN.H11MO.0.A0.140466Not shown
HXC10_HUMAN.H11MO.0.D0.140466Not shown
ONEC2_HUMAN.H11MO.0.D0.181312Not shown

Motif 11/14

Motif IDq-valPWM
CTCFL_HUMAN.H11MO.0.A1.86079e-05
MA1102.2_CTCFL5.37792e-05
CTCF_HUMAN.H11MO.0.A0.000135358
SP2_HUMAN.H11MO.0.A0.00128456
MA0139.1_CTCF0.00128456
SP3_HUMAN.H11MO.0.B0.00289045Not shown
THAP1_HUMAN.H11MO.0.C0.0176759Not shown
SP1_HUMAN.H11MO.0.A0.0176759Not shown
USF2_HUMAN.H11MO.0.A0.0183423Not shown
SNAI1_HUMAN.H11MO.0.C0.022564599999999997Not shown

Motif 12/14

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00618776
USF2_HUMAN.H11MO.0.A0.0122249
SP1_HUMAN.H11MO.0.A0.013639400000000001
SP3_HUMAN.H11MO.0.B0.041864
MA1650.1_ZBTB140.041864
MXI1_HUMAN.H11MO.0.A0.041864Not shown
THAP1_HUMAN.H11MO.0.C0.041864Not shown
ZFX_HUMAN.H11MO.1.A0.0567231Not shown
MA0104.4_MYCN0.07687669999999999Not shown
CTCFL_HUMAN.H11MO.0.A0.07760030000000001Not shown

Motif 13/14

Motif IDq-valPWM
TBX15_HUMAN.H11MO.0.D1.3319100000000002e-07
KLF16_HUMAN.H11MO.0.D1.3319100000000002e-07
MAZ_HUMAN.H11MO.0.A1.3319100000000002e-07
ZN467_HUMAN.H11MO.0.C1.48012e-07
SP1_HUMAN.H11MO.0.A2.31744e-07
SP2_HUMAN.H11MO.0.A3.38313e-07Not shown
WT1_HUMAN.H11MO.0.C5.75756e-07Not shown
PATZ1_HUMAN.H11MO.0.C5.75756e-07Not shown
SP3_HUMAN.H11MO.0.B6.31238e-07Not shown
VEZF1_HUMAN.H11MO.0.C8.5697e-07Not shown

Motif 14/14

Motif IDq-valPWM
CTCFL_HUMAN.H11MO.0.A2.58473e-05
CTCF_HUMAN.H11MO.0.A0.000515747
SP2_HUMAN.H11MO.0.A0.000746325
SP1_HUMAN.H11MO.0.A0.00242
SP3_HUMAN.H11MO.0.B0.00368335
MA0139.1_CTCF0.00368335Not shown
KLF16_HUMAN.H11MO.0.D0.00403004Not shown
MA1102.2_CTCFL0.00513103Not shown
MA1513.1_KLF150.0158155Not shown
AP2B_HUMAN.H11MO.0.B0.0190914Not shown