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: FOXA2
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_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/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_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%|██████████| 174/174 [03:26<00:00,  1.19s/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")

Metacluster 1/1

Pattern 1/11

7385 seqlets

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

Pattern 2/11

3031 seqlets

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

Pattern 3/11

956 seqlets

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

Pattern 4/11

869 seqlets

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

Pattern 5/11

837 seqlets

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

Pattern 6/11

162 seqlets

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

Pattern 7/11

141 seqlets

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

Pattern 8/11

127 seqlets

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

Pattern 9/11

119 seqlets

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

Pattern 10/11

107 seqlets

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

Pattern 11/11

36 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
17385
23031
3956
4869
5837
6162
7141
8127
9119
10107
1136

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
FOXA3_HUMAN.H11MO.0.B4.39795e-08
MA0846.1_FOXC25.6973199999999994e-08
FOXA1_HUMAN.H11MO.0.A1.1163299999999999e-07
FOXA2_HUMAN.H11MO.0.A4.910309999999999e-07
MA0032.2_FOXC15.39707e-07
FOXF2_HUMAN.H11MO.0.D8.94813e-06Not shown
MA0847.2_FOXD21.02722e-05Not shown
FOXD3_HUMAN.H11MO.0.D1.34822e-05Not shown
MA1607.1_Foxl22.18237e-05Not shown
MA0845.1_FOXB13.01568e-05Not shown

Motif 2/11

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A0.000146476
FOXJ2_HUMAN.H11MO.0.C0.00166545
MA1487.1_FOXE10.00207895
FOXA1_HUMAN.H11MO.0.A0.00633576
FOXF2_HUMAN.H11MO.0.D0.00730002
MA0847.2_FOXD20.00747166Not shown
MA0846.1_FOXC20.00747166Not shown
FOXA2_HUMAN.H11MO.0.A0.00747166Not shown
MA0041.1_Foxd30.00747166Not shown
FOXF1_HUMAN.H11MO.0.D0.00747166Not shown

Motif 3/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B3.3033099999999996e-06
HNF4A_HUMAN.H11MO.0.A3.3033099999999996e-06
MA0677.1_Nr2f60.00038559
MA0856.1_RXRG0.00038559
MA1574.1_THRB0.00038559
MA1550.1_PPARD0.00038559Not shown
MA0512.2_Rxra0.00038559Not shown
MA1537.1_NR2F1(var.2)0.000439292Not shown
MA0855.1_RXRB0.000499125Not shown
MA0115.1_NR1H2::RXRA0.000499125Not shown

Motif 4/11

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.00039789999999999997
FOXB1_HUMAN.H11MO.0.D0.0076244
MA0845.1_FOXB10.0978989
MA0032.2_FOXC10.0978989
MA0846.1_FOXC20.292133
PO4F3_HUMAN.H11MO.0.D0.340998Not shown
MA0148.4_FOXA10.340998Not shown
FOXJ2_HUMAN.H11MO.0.C0.41766400000000004Not shown
LMX1A_HUMAN.H11MO.0.D0.41766400000000004Not shown
MA0683.1_POU4F20.458809Not shown

Motif 5/11

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A4.14864e-08
MA0836.2_CEBPD1.83919e-06
CEBPA_HUMAN.H11MO.0.A2.79118e-06
CEBPD_HUMAN.H11MO.0.C7.449010000000001e-06
MA0102.4_CEBPA5.2293800000000004e-05
MA0837.1_CEBPE0.00114482Not shown
MA0466.2_CEBPB0.00127021Not shown
MA0838.1_CEBPG0.00127021Not shown
MA0025.2_NFIL30.00175361Not shown
DBP_HUMAN.H11MO.0.B0.00283799Not shown

Motif 6/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B7.2601199999999995e-09
HNF4A_HUMAN.H11MO.0.A7.2601199999999995e-09
MA0677.1_Nr2f63.4573e-05
MA1550.1_PPARD8.327e-05
MA0512.2_Rxra0.000103026
MA0856.1_RXRG0.000103026Not shown
MA1537.1_NR2F1(var.2)0.000103026Not shown
MA1494.1_HNF4A(var.2)0.000103026Not shown
MA0855.1_RXRB0.000118249Not shown
MA1574.1_THRB0.00016071100000000001Not shown

Motif 7/11

Motif IDq-valPWM
MA0655.1_JDP24.64323e-06
FOSL2_HUMAN.H11MO.0.A1.52926e-05
JUN_HUMAN.H11MO.0.A3.02124e-05
MA0477.2_FOSL13.02124e-05
MA0489.1_JUN(var.2)4.9408500000000006e-05
JUND_HUMAN.H11MO.0.A4.9408500000000006e-05Not shown
MA0841.1_NFE26.38446e-05Not shown
FOSL1_HUMAN.H11MO.0.A8.379600000000001e-05Not shown
MA1130.1_FOSL2::JUN9.02202e-05Not shown
MA0491.2_JUND0.00010826399999999999Not shown

Motif 8/11

Motif IDq-valPWM
HNF1B_HUMAN.H11MO.0.A6.993e-10
HNF1A_HUMAN.H11MO.0.C6.558410000000001e-07
MA0046.2_HNF1A3.7447900000000003e-06
MA0153.2_HNF1B3.7447900000000003e-06
HNF1B_HUMAN.H11MO.1.A0.00010786799999999999
MA0853.1_Alx40.0520189Not shown
ZFHX3_HUMAN.H11MO.0.D0.0520189Not shown
MA0854.1_Alx10.11213499999999998Not shown
FOXJ3_HUMAN.H11MO.1.B0.122063Not shown
MA0755.1_CUX20.17168Not shown

Motif 9/11

Motif IDq-valPWM
MA0466.2_CEBPB1.35694e-06
MA0837.1_CEBPE1.35694e-06
MA0838.1_CEBPG2.75642e-06
CEBPB_HUMAN.H11MO.0.A0.00324564
DBP_HUMAN.H11MO.0.B0.00324564
MA0639.1_DBP0.00324564Not shown
MA0836.2_CEBPD0.00364501Not shown
CEBPE_HUMAN.H11MO.0.A0.00364501Not shown
MA0843.1_TEF0.00695625Not shown
CEBPD_HUMAN.H11MO.0.C0.00713965Not shown

Motif 10/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B0.00010926100000000001
HNF4A_HUMAN.H11MO.0.A0.000110583
MA0115.1_NR1H2::RXRA0.00107072
MA0677.1_Nr2f60.00158155
MA1550.1_PPARD0.00209328
MA0114.4_HNF4A0.00209328Not shown
RXRG_HUMAN.H11MO.0.B0.00209328Not shown
MA0484.2_HNF4G0.00209328Not shown
MA0512.2_Rxra0.00273678Not shown
MA0856.1_RXRG0.00273678Not shown

Motif 11/11

Motif IDq-valPWM
CEBPD_HUMAN.H11MO.0.C0.000101555
CEBPB_HUMAN.H11MO.0.A0.00011832
CEBPA_HUMAN.H11MO.0.A0.00012140299999999999
MA0837.1_CEBPE0.000556753
MA0466.2_CEBPB0.000556753
MA0838.1_CEBPG0.000570557Not shown
CEBPE_HUMAN.H11MO.0.A0.00131757Not shown
MA0025.2_NFIL30.00131757Not shown
MA0836.2_CEBPD0.00407517Not shown
MA0102.4_CEBPA0.00426308Not shown