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_fold3/E2F6_multitask_profile_fold3_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/E2F6_multitask_profile_fold3/E2F6_multitask_profile_fold3_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_fold3/E2F6_multitask_profile_fold3_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 [00:31<00:00,  1.64it/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 1/11

4536 seqlets

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

Pattern 2/11

2964 seqlets

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

Pattern 3/11

2564 seqlets

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

Pattern 4/11

1591 seqlets

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

Pattern 5/11

878 seqlets

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

Pattern 6/11

159 seqlets

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

Pattern 7/11

72 seqlets

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

Pattern 8/11

58 seqlets

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

Pattern 9/11

56 seqlets

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

Pattern 10/11

31 seqlets

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

Pattern 11/11

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 1/1

/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
14536
22964
32564
41591
5878
6159
772
858
956
1031
1131

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 1/11

Motif IDq-valPWM
MA0147.3_MYC0.000292844
MAX_HUMAN.H11MO.0.A0.000292844
MXI1_HUMAN.H11MO.1.A0.000453605
MA0059.1_MAX::MYC0.0008981410000000001
MXI1_HUMAN.H11MO.0.A0.00143703
MYC_HUMAN.H11MO.0.A0.00190105Not shown
MA0058.3_MAX0.00206502Not shown
MA0004.1_Arnt0.00654828Not shown
MYCN_HUMAN.H11MO.0.A0.00654828Not shown
MA0825.1_MNT0.00777285Not shown

Motif 2/11

Motif IDq-valPWM
E2F1_HUMAN.H11MO.0.A2.3517e-05
MA0471.2_E2F60.0002836
E2F3_HUMAN.H11MO.0.A0.000302925
MA0865.1_E2F80.000466502
E2F6_HUMAN.H11MO.0.A0.000466502
E2F4_HUMAN.H11MO.1.A0.000466502Not shown
TFDP1_HUMAN.H11MO.0.C0.000466502Not shown
E2F4_HUMAN.H11MO.0.A0.000680209Not shown
MA0758.1_E2F70.0007054019999999999Not shown
MA1122.1_TFDP10.00127151Not shown

Motif 3/11

Motif IDq-valPWM
MA0632.2_TCFL50.175303
MA0006.1_Ahr::Arnt0.175303
MA1560.1_SOHLH20.175303
MA0059.1_MAX::MYC0.175303
MYC_HUMAN.H11MO.0.A0.175303
MA0506.1_NRF10.175303Not shown
MA0259.1_ARNT::HIF1A0.175303Not shown
MA0147.3_MYC0.175303Not shown
MA1099.2_HES10.175303Not shown
MA0058.3_MAX0.175303Not shown

Motif 4/11

No TOMTOM matches passing threshold

Motif 5/11

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A2.74729e-08
CTCFL_HUMAN.H11MO.0.A2.93133e-08
MA0139.1_CTCF2.64413e-07
MA1102.2_CTCFL9.38253e-06
SNAI1_HUMAN.H11MO.0.C0.119531
PLAL1_HUMAN.H11MO.0.D0.119531Not shown
KLF8_HUMAN.H11MO.0.C0.12182899999999999Not shown
MA0155.1_INSM10.169266Not shown
MA0830.2_TCF40.17766500000000002Not shown
MA1548.1_PLAGL20.17766500000000002Not shown

Motif 6/11

Motif IDq-valPWM
MXI1_HUMAN.H11MO.0.A0.0005044380000000001
SP2_HUMAN.H11MO.0.A0.000523492
MA1650.1_ZBTB140.000523492
USF2_HUMAN.H11MO.0.A0.000523492
SP1_HUMAN.H11MO.0.A0.0037544000000000006
MA0147.3_MYC0.00442869Not shown
SP3_HUMAN.H11MO.0.B0.00699762Not shown
THAP1_HUMAN.H11MO.0.C0.00699762Not shown
MYCN_HUMAN.H11MO.0.A0.0176672Not shown
MA0104.4_MYCN0.0221079Not shown

Motif 7/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D3.0470500000000002e-05
MA1125.1_ZNF3840.023861
PRDM6_HUMAN.H11MO.0.C0.023861
FOXL1_HUMAN.H11MO.0.D0.0355043
FOXG1_HUMAN.H11MO.0.D0.04303819999999999
MA0679.2_ONECUT10.062055099999999995Not shown
FOXJ3_HUMAN.H11MO.0.A0.09726280000000001Not shown
ANDR_HUMAN.H11MO.0.A0.120957Not shown
HXC10_HUMAN.H11MO.0.D0.155618Not shown
FUBP1_HUMAN.H11MO.0.D0.155618Not shown

Motif 8/11

Motif IDq-valPWM
TBX15_HUMAN.H11MO.0.D3.20576e-07
MAZ_HUMAN.H11MO.0.A3.20576e-07
KLF16_HUMAN.H11MO.0.D3.20576e-07
SP2_HUMAN.H11MO.0.A3.20576e-07
SP1_HUMAN.H11MO.0.A3.20576e-07
ZN467_HUMAN.H11MO.0.C3.20576e-07Not shown
SP3_HUMAN.H11MO.0.B4.87119e-07Not shown
PATZ1_HUMAN.H11MO.0.C1.2273e-06Not shown
VEZF1_HUMAN.H11MO.0.C1.23286e-06Not shown
WT1_HUMAN.H11MO.0.C2.26098e-06Not shown

Motif 9/11

Motif IDq-valPWM
MA0805.1_TBX17.471930000000001e-05
MA1565.1_TBX180.00013567899999999999
MA0803.1_TBX150.000229847
MA0801.1_MGA0.00033306
MA1566.1_TBX30.00033306
MA1567.1_TBX60.00033306Not shown
MA0806.1_TBX40.00042367699999999996Not shown
MA0807.1_TBX50.00042367699999999996Not shown
TBX21_HUMAN.H11MO.0.A0.00045237300000000005Not shown
MA0689.1_TBX200.00047013800000000004Not shown

Motif 10/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00219599
SP1_HUMAN.H11MO.0.A0.0235794
SP3_HUMAN.H11MO.0.B0.042858600000000004
KLF3_HUMAN.H11MO.0.B0.044030400000000004
USF2_HUMAN.H11MO.0.A0.0685525
MXI1_HUMAN.H11MO.0.A0.20056Not shown
MA0146.2_Zfx0.24419699999999997Not shown
RFX1_HUMAN.H11MO.0.B0.24419699999999997Not shown
PATZ1_HUMAN.H11MO.0.C0.24419699999999997Not shown
MA1650.1_ZBTB140.24419699999999997Not shown

Motif 11/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00757243
USF2_HUMAN.H11MO.0.A0.020552
SP3_HUMAN.H11MO.0.B0.0230535
MA0147.3_MYC0.0479145
MA0104.4_MYCN0.049507499999999996
SP1_HUMAN.H11MO.0.A0.049507499999999996Not shown
MXI1_HUMAN.H11MO.0.A0.0803553Not shown
MA1650.1_ZBTB140.0908889Not shown
MA1513.1_KLF150.138899Not shown
SP1_HUMAN.H11MO.1.A0.138899Not shown