Direct links to results¶

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¶

# 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_fold7/FOXA2_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold7/FOXA2_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/FOXA2_multitask_profile_fold7/FOXA2_multitask_profile_fold7_count

# Define paths and constants
input_length = 2114
shap_score_center_size = 400

if tfm_motifs_cache_dir:
    os.makedirs(tfm_motifs_cache_dir, exist_ok=True)

Import SHAP scores and TF-MoDISco results¶

# 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 [01:32<00:00,  1.88it/s]

# 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

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

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")

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.

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")

Top TOMTOM matches for each motif¶

Here, the TF-MoDISco motifs are plotted as hCWMs, but the TOMTOM matches are shown as PWMs.

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")

#	Seqlets	Forward	Reverse
1	11164
2	1433
3	572
4	181
5	104
6	84
7	53

Motif ID	q-val	PWM
FOXA1_HUMAN.H11MO.0.A	5.26905e-10
FOXA2_HUMAN.H11MO.0.A	1.61967e-09
MA0846.1_FOXC2	4.81403e-09
FOXA3_HUMAN.H11MO.0.B	4.81403e-09
FOXF2_HUMAN.H11MO.0.D	5.29215e-07
MA0032.2_FOXC1	7.560219999999999e-07	Not shown
MA0847.2_FOXD2	7.560219999999999e-07	Not shown
FOXD3_HUMAN.H11MO.0.D	1.83958e-06	Not shown
FOXC1_HUMAN.H11MO.0.C	2.86601e-06	Not shown
FOXM1_HUMAN.H11MO.0.A	3.67243e-05	Not shown

Motif ID	q-val	PWM
HNF4G_HUMAN.H11MO.0.B	3.01618e-05
HNF4A_HUMAN.H11MO.0.A	3.01618e-05
MA0677.1_Nr2f6	0.000436055
MA0856.1_RXRG	0.000436055
MA1550.1_PPARD	0.000436055
MA0512.2_Rxra	0.000436055	Not shown
MA1537.1_NR2F1(var.2)	0.000436055	Not shown
MA1574.1_THRB	0.000436055	Not shown
MA0115.1_NR1H2::RXRA	0.000436055	Not shown
NR1H2_HUMAN.H11MO.0.D	0.000545591	Not shown

Motif ID	q-val	PWM
CEBPB_HUMAN.H11MO.0.A	7.741239999999999e-06
CEBPA_HUMAN.H11MO.0.A	1.55298e-05
MA0836.2_CEBPD	1.55298e-05
CEBPD_HUMAN.H11MO.0.C	1.55298e-05
MA0102.4_CEBPA	0.00020919799999999998
MA0837.1_CEBPE	0.000912597	Not shown
MA0466.2_CEBPB	0.0009282339999999999	Not shown
MA0838.1_CEBPG	0.0009282339999999999	Not shown
MA0043.3_HLF	0.00167848	Not shown
MA0025.2_NFIL3	0.00167848	Not shown

Motif ID	q-val	PWM
HNF1B_HUMAN.H11MO.0.A	3.1882e-08
MA0046.2_HNF1A	6.36551e-07
MA0153.2_HNF1B	7.05618e-07
HNF1A_HUMAN.H11MO.0.C	1.80351e-06
HNF1B_HUMAN.H11MO.1.A	1.96072e-05
ZFHX3_HUMAN.H11MO.0.D	0.0681838	Not shown
MA0853.1_Alx4	0.0717315	Not shown
MA0854.1_Alx1	0.155651	Not shown
MEOX2_HUMAN.H11MO.0.D	0.20467	Not shown
FOXJ3_HUMAN.H11MO.1.B	0.20467	Not shown

Direct links to results¶

Define constants and paths¶

Import SHAP scores and TF-MoDISco results¶

Plot some SHAP score tracks¶

Plot TF-MoDISco results¶

Metacluster 1/1

Pattern 1/7

Pattern 2/7

Pattern 3/7

Pattern 4/7

Pattern 5/7

Pattern 6/7

Pattern 7/7

Summary of motifs¶

Metacluster 1/1

Top TOMTOM matches for each motif¶

Metacluster 1/1

Motif 1/7

Motif 2/7

Motif 3/7

Motif 4/7

Motif 5/7

Motif 6/7

Motif 7/7

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

Motif ID	q-val	PWM
JUN_HUMAN.H11MO.0.A	5.31128e-05
MA0477.2_FOSL1	5.31128e-05
FOSL2_HUMAN.H11MO.0.A	5.61173e-05
MA0491.2_JUND	5.61173e-05
MA1137.1_FOSL1::JUNB	8.62492e-05
MA1142.1_FOSL1::JUND	0.000166564	Not shown
MA1622.1_Smad2::Smad3	0.000166564	Not shown
MA1144.1_FOSL2::JUND	0.000166564	Not shown
MA1130.1_FOSL2::JUN	0.000166564	Not shown
MA1141.1_FOS::JUND	0.000166564	Not shown

Motif ID	q-val	PWM
MA0677.1_Nr2f6	2.74418e-05
MA1550.1_PPARD	2.74418e-05
MA1537.1_NR2F1(var.2)	2.74418e-05
HNF4G_HUMAN.H11MO.0.B	2.74418e-05
MA0856.1_RXRG	2.74418e-05
MA0512.2_Rxra	2.74418e-05	Not shown
MA0115.1_NR1H2::RXRA	2.74418e-05	Not shown
MA1574.1_THRB	2.98792e-05	Not shown
NR1H2_HUMAN.H11MO.0.D	2.98792e-05	Not shown
MA0855.1_RXRB	4.2156999999999996e-05	Not shown

Motif ID	q-val	PWM
HNF4G_HUMAN.H11MO.0.B	0.000115847
HNF4A_HUMAN.H11MO.0.A	0.000115847
MA0677.1_Nr2f6	0.00137386
MA0856.1_RXRG	0.00169422
MA0512.2_Rxra	0.00169422
MA0114.4_HNF4A	0.0019662	Not shown
MA0855.1_RXRB	0.00217607	Not shown
MA0484.2_HNF4G	0.00300555	Not shown
MA1550.1_PPARD	0.00300555	Not shown
RXRG_HUMAN.H11MO.0.B	0.00300555	Not shown