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: MAX
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/MAX_multitask_profile_fold7/MAX_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAX_multitask_profile_fold7/MAX_multitask_profile_fold7_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/MAX_multitask_profile_fold7/MAX_multitask_profile_fold7_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%|██████████| 204/204 [01:38<00:00,  2.07it/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 1/2

Pattern 1/13

4492 seqlets

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

Pattern 2/13

3510 seqlets

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

Pattern 3/13

2331 seqlets

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

Pattern 4/13

2220 seqlets

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

Pattern 5/13

775 seqlets

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

Pattern 6/13

81 seqlets

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

Pattern 7/13

74 seqlets

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

Pattern 8/13

58 seqlets

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

Pattern 9/13

52 seqlets

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

Pattern 10/13

42 seqlets

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

Pattern 11/13

37 seqlets

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

Pattern 12/13

33 seqlets

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

Pattern 13/13

31 seqlets

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

Metacluster 2/2

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
14492
23510
32331
42220
5775
681
774
858
952
1042
1137
1233
1331

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 1/13

Motif IDq-valPWM
MA0104.4_MYCN0.000710117
MYCN_HUMAN.H11MO.0.A0.000710117
MA0147.3_MYC0.000710117
MXI1_HUMAN.H11MO.0.A0.0008876460000000001
MA0059.1_MAX::MYC0.00213183
MAX_HUMAN.H11MO.0.A0.00309682Not shown
CR3L1_HUMAN.H11MO.0.D0.00309682Not shown
BMAL1_HUMAN.H11MO.0.A0.00309682Not shown
MXI1_HUMAN.H11MO.1.A0.00309682Not shown
MA0004.1_Arnt0.00386059Not shown

Motif 2/13

Motif IDq-valPWM
MA1108.2_MXI10.00995814
MAX_HUMAN.H11MO.0.A0.050048699999999995
MA0058.3_MAX0.050048699999999995
MA0147.3_MYC0.050048699999999995
MXI1_HUMAN.H11MO.1.A0.050048699999999995
MYCN_HUMAN.H11MO.0.A0.050048699999999995Not shown
MYC_HUMAN.H11MO.0.A0.050048699999999995Not shown
MA0059.1_MAX::MYC0.050048699999999995Not shown
MA0825.1_MNT0.050048699999999995Not shown
MA0668.1_NEUROD20.050048699999999995Not shown

Motif 3/13

Motif IDq-valPWM
MA1099.2_HES10.235103
MA0626.1_Npas20.235103
MA0822.1_HES70.235103
HES7_HUMAN.H11MO.0.D0.235103
AHR_HUMAN.H11MO.0.B0.235103
MA0059.1_MAX::MYC0.235103Not shown
NRF1_HUMAN.H11MO.0.A0.235103Not shown
MA0825.1_MNT0.235103Not shown
MA0823.1_HEY10.235103Not shown
MA0147.3_MYC0.235103Not shown

Motif 4/13

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A8.341280000000001e-16
MA0139.1_CTCF1.85246e-15
CTCFL_HUMAN.H11MO.0.A1.9722900000000002e-08
MA1102.2_CTCFL4.3689499999999996e-05
MA1568.1_TCF21(var.2)0.163306
SNAI1_HUMAN.H11MO.0.C0.163306Not shown
MA1638.1_HAND20.163306Not shown
ZIC3_HUMAN.H11MO.0.B0.331368Not shown
MA0155.1_INSM10.331368Not shown
KLF8_HUMAN.H11MO.0.C0.331368Not shown

Motif 5/13

Motif IDq-valPWM
MA1512.1_KLF110.10308599999999998
KLF14_HUMAN.H11MO.0.D0.10308599999999998
MA0746.2_SP30.10308599999999998
MA0685.1_SP40.10308599999999998
MA0079.4_SP10.10308599999999998
MA0740.1_KLF140.10308599999999998Not shown
MA0747.1_SP80.10635Not shown
MA0014.3_PAX50.10635Not shown
MA1516.1_KLF30.10635Not shown
MA0741.1_KLF160.10635Not shown

Motif 6/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A4.70731e-08
SP3_HUMAN.H11MO.0.B6.164940000000001e-08
SP1_HUMAN.H11MO.0.A6.164940000000001e-08
KLF16_HUMAN.H11MO.0.D1.27848e-07
TBX15_HUMAN.H11MO.0.D2.3252400000000002e-07
MAZ_HUMAN.H11MO.0.A1.1234700000000001e-06Not shown
PATZ1_HUMAN.H11MO.0.C1.1234700000000001e-06Not shown
WT1_HUMAN.H11MO.0.C1.23459e-06Not shown
ZN467_HUMAN.H11MO.0.C2.08218e-06Not shown
VEZF1_HUMAN.H11MO.0.C1.15897e-05Not shown

Motif 7/13

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.012671799999999999
MA0076.2_ELK40.012671799999999999
MA0765.2_ETV50.025797000000000004
ELK4_HUMAN.H11MO.0.A0.025797000000000004
FEV_HUMAN.H11MO.0.B0.0302623
ETV1_HUMAN.H11MO.0.A0.0303822Not shown
MA0750.2_ZBTB7A0.0487839Not shown
ELF1_HUMAN.H11MO.0.A0.057275099999999995Not shown
ELK1_HUMAN.H11MO.0.B0.07295560000000001Not shown
ETS1_HUMAN.H11MO.0.A0.136224Not shown

Motif 8/13

Motif IDq-valPWM
ZN770_HUMAN.H11MO.0.C3.7059800000000005e-08
MA1596.1_ZNF4601.75544e-07
ZN770_HUMAN.H11MO.1.C0.000506426
MA1587.1_ZNF1350.0167402
ZBT17_HUMAN.H11MO.0.A0.07377610000000001
ZSC22_HUMAN.H11MO.0.C0.10460599999999999Not shown
ZFX_HUMAN.H11MO.1.A0.10460599999999999Not shown
KLF6_HUMAN.H11MO.0.A0.14716600000000002Not shown
EGR2_HUMAN.H11MO.0.A0.14716600000000002Not shown
PTF1A_HUMAN.H11MO.1.B0.312585Not shown

Motif 9/13

Motif IDq-valPWM
MA1108.2_MXI10.195776
MA0147.3_MYC0.203459
MA1568.1_TCF21(var.2)0.203459
PTF1A_HUMAN.H11MO.0.B0.203459
MYC_HUMAN.H11MO.0.A0.203459
MA0748.2_YY20.203459Not shown
TYY1_HUMAN.H11MO.0.A0.203459Not shown
TBX1_HUMAN.H11MO.0.D0.203459Not shown
MA1648.1_TCF12(var.2)0.203459Not shown
CR3L1_HUMAN.H11MO.0.D0.203459Not shown

Motif 10/13

Motif IDq-valPWM
MXI1_HUMAN.H11MO.0.A0.0192761
SP2_HUMAN.H11MO.0.A0.0192761
SP1_HUMAN.H11MO.0.A0.0192761
PATZ1_HUMAN.H11MO.0.C0.0192761
SP3_HUMAN.H11MO.0.B0.0192761
USF2_HUMAN.H11MO.0.A0.0192761Not shown
SP4_HUMAN.H11MO.0.A0.0192761Not shown
MA0147.3_MYC0.0192761Not shown
KLF3_HUMAN.H11MO.0.B0.053427699999999995Not shown
ZN467_HUMAN.H11MO.0.C0.0640329Not shown

Motif 11/13

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A2.10981e-05
MA0139.1_CTCF0.00016441400000000002
CTCFL_HUMAN.H11MO.0.A0.000380197
TYY1_HUMAN.H11MO.0.A0.04153830000000001
MA1102.2_CTCFL0.0432942
MA1568.1_TCF21(var.2)0.0432942Not shown
MA1638.1_HAND20.0456198Not shown
MA0095.2_YY10.0500361Not shown
SNAI1_HUMAN.H11MO.0.C0.0554212Not shown
MXI1_HUMAN.H11MO.0.A0.0677377Not shown

Motif 12/13

Motif IDq-valPWM
ZN770_HUMAN.H11MO.0.C4.5768700000000004e-07
MA1596.1_ZNF4600.00713526
ZN770_HUMAN.H11MO.1.C0.0102475
MA1587.1_ZNF1350.0117865
ZN219_HUMAN.H11MO.0.D0.042038099999999995
ZFX_HUMAN.H11MO.1.A0.233514Not shown
MA0146.2_Zfx0.283572Not shown
IKZF1_HUMAN.H11MO.0.C0.295901Not shown
WT1_HUMAN.H11MO.0.C0.295901Not shown
TBX1_HUMAN.H11MO.0.D0.295901Not shown

Motif 13/13

Motif IDq-valPWM
MA1125.1_ZNF3840.00757715
PAX5_HUMAN.H11MO.0.A0.112508
ZN121_HUMAN.H11MO.0.C0.112508
GLI1_HUMAN.H11MO.0.D0.471263