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: CEBPB
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/CEBPB_multitask_profile_fold7/CEBPB_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/CEBPB_multitask_profile_fold7/CEBPB_multitask_profile_fold7_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/CEBPB_multitask_profile_fold7/CEBPB_multitask_profile_fold7_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%|██████████| 273/273 [05:12<00:00,  1.14s/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")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

Metacluster 1/2

Pattern 1/9

11828 seqlets

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

Pattern 2/9

824 seqlets

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

Pattern 3/9

653 seqlets

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

Pattern 4/9

464 seqlets

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

Pattern 5/9

387 seqlets

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

Pattern 6/9

248 seqlets

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

Pattern 7/9

159 seqlets

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

Pattern 8/9

95 seqlets

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

Pattern 9/9

48 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

#SeqletsForwardReverse
111828
2824
3653
4464
5387
6248
7159
895
948

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 1/9

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A3.2878600000000003e-10
CEBPD_HUMAN.H11MO.0.C2.0361e-09
CEBPA_HUMAN.H11MO.0.A2.13507e-07
MA0836.2_CEBPD2.21721e-05
MA0102.4_CEBPA0.000126728
MA0837.1_CEBPE0.000433605Not shown
MA0466.2_CEBPB0.000441657Not shown
MA0838.1_CEBPG0.000831186Not shown
MA0025.2_NFIL30.00121334Not shown
NFIL3_HUMAN.H11MO.0.D0.0028462Not shown

Motif 2/9

Motif IDq-valPWM
JUND_HUMAN.H11MO.0.A1.91317e-06
FOSL1_HUMAN.H11MO.0.A1.91317e-06
FOSB_HUMAN.H11MO.0.A1.91317e-06
FOS_HUMAN.H11MO.0.A1.91317e-06
JUN_HUMAN.H11MO.0.A4.59161e-06
FOSL2_HUMAN.H11MO.0.A9.35376e-06Not shown
MA0099.3_FOS::JUN1.1128699999999999e-05Not shown
MA0478.1_FOSL21.2078199999999999e-05Not shown
MA1138.1_FOSL2::JUNB1.2078199999999999e-05Not shown
MA1144.1_FOSL2::JUND1.2078199999999999e-05Not shown

Motif 3/9

Motif IDq-valPWM
MA0139.1_CTCF7.46518e-17
CTCF_HUMAN.H11MO.0.A5.23259e-15
CTCFL_HUMAN.H11MO.0.A1.44201e-08
MA1102.2_CTCFL9.264600000000001e-05
MA1568.1_TCF21(var.2)0.133364
MA1638.1_HAND20.188584Not shown
ZIC3_HUMAN.H11MO.0.B0.291377Not shown
SNAI1_HUMAN.H11MO.0.C0.291377Not shown
MA0155.1_INSM10.39663400000000004Not shown
ZIC2_HUMAN.H11MO.0.D0.39663400000000004Not shown

Motif 4/9

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A7.674960000000001e-07
FOXA2_HUMAN.H11MO.0.A7.674960000000001e-07
FOXM1_HUMAN.H11MO.0.A3.93776e-06
FOXF2_HUMAN.H11MO.0.D3.93776e-06
FOXD3_HUMAN.H11MO.0.D5.25035e-06
FOXA3_HUMAN.H11MO.0.B5.25035e-06Not shown
MA0846.1_FOXC28.00948e-06Not shown
MA0847.2_FOXD22.01085e-05Not shown
FOXC1_HUMAN.H11MO.0.C2.68114e-05Not shown
FOXD1_HUMAN.H11MO.0.D0.000275602Not shown

Motif 5/9

Motif IDq-valPWM
HNF4A_HUMAN.H11MO.0.A9.74727e-12
HNF4G_HUMAN.H11MO.0.B9.74727e-12
MA1494.1_HNF4A(var.2)0.000953484
MA0484.2_HNF4G0.000990227
MA0114.4_HNF4A0.000990227
MA0856.1_RXRG0.00220844Not shown
MA0512.2_Rxra0.00220844Not shown
MA1550.1_PPARD0.00220844Not shown
MA1574.1_THRB0.00220844Not shown
MA0855.1_RXRB0.00223959Not shown

Motif 6/9

Motif IDq-valPWM
CTCFL_HUMAN.H11MO.0.A0.00161522
CTCF_HUMAN.H11MO.0.A0.00991261
MA1102.2_CTCFL0.015629
MA0139.1_CTCF0.015629
SP2_HUMAN.H11MO.0.A0.0202917
SP3_HUMAN.H11MO.0.B0.0202917Not shown
KLF9_HUMAN.H11MO.0.C0.0202917Not shown
SP4_HUMAN.H11MO.0.A0.0202917Not shown
SP4_HUMAN.H11MO.1.A0.053354Not shown
KLF12_HUMAN.H11MO.0.C0.060740300000000004Not shown

Motif 7/9

Motif IDq-valPWM
GATA1_HUMAN.H11MO.1.A6.21897e-06
GATA4_HUMAN.H11MO.0.A6.21897e-06
GATA1_HUMAN.H11MO.0.A6.21897e-06
TAL1_HUMAN.H11MO.0.A6.21897e-06
GATA2_HUMAN.H11MO.1.A6.26405e-06
GATA2_HUMAN.H11MO.0.A4.12885e-05Not shown
GATA6_HUMAN.H11MO.0.A8.484950000000001e-05Not shown
MA0140.2_GATA1::TAL10.00042331300000000003Not shown
MA0766.2_GATA50.00758078Not shown
MA0036.3_GATA20.00758078Not shown

Motif 8/9

Motif IDq-valPWM
FOXB1_HUMAN.H11MO.0.D0.00509682
FOXD2_HUMAN.H11MO.0.D0.00509682
MA0845.1_FOXB10.036622800000000004
MA0032.2_FOXC10.036622800000000004
MA0148.4_FOXA10.104299
MA0846.1_FOXC20.104299Not shown
MA1683.1_FOXA30.24231599999999998Not shown
FOXA2_HUMAN.H11MO.0.A0.30298400000000003Not shown
MA0481.3_FOXP10.30298400000000003Not shown
MA0047.3_FOXA20.30298400000000003Not shown

Motif 9/9

Motif IDq-valPWM
MA0114.4_HNF4A0.000748605
MA0484.2_HNF4G0.000748605
HNF4G_HUMAN.H11MO.0.B0.00131381
HNF4A_HUMAN.H11MO.0.A0.00131381
NR2E3_HUMAN.H11MO.0.C0.0112691
COT2_HUMAN.H11MO.0.A0.0112691Not shown
MA0856.1_RXRG0.016339799999999998Not shown
MA0512.2_Rxra0.0181075Not shown
MA0855.1_RXRB0.0181075Not shown
MA1494.1_HNF4A(var.2)0.0181075Not shown