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: NR3C1-reddytime
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/NR3C1-reddytime_multitask_profile_fold8/NR3C1-reddytime_multitask_profile_fold8_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/NR3C1-reddytime_multitask_profile_fold8/NR3C1-reddytime_multitask_profile_fold8_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/NR3C1-reddytime_multitask_profile_fold8/NR3C1-reddytime_multitask_profile_fold8_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%|██████████| 186/186 [01:30<00:00,  2.05it/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")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

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	5932
2	3262
3	1667
4	1139
5	445
6	394
7	271
8	226
9	153

Motif ID	q-val	PWM
GCR_HUMAN.H11MO.0.A	2.36031e-09
PRGR_HUMAN.H11MO.0.A	7.79811e-07
ANDR_HUMAN.H11MO.1.A	7.79811e-07
MA0727.1_NR3C2	8.737549999999999e-05
MA0113.3_NR3C1	0.00023452099999999999
PRGR_HUMAN.H11MO.1.A	0.00851173	Not shown
MA0007.3_Ar	0.0160857	Not shown
GCR_HUMAN.H11MO.1.A	0.034278199999999995	Not shown
RARG_HUMAN.H11MO.0.B	0.428939	Not shown
MA1508.1_IKZF1	0.428939	Not shown

Motif ID	q-val	PWM
JUN_HUMAN.H11MO.0.A	4.04932e-07
FOSB_HUMAN.H11MO.0.A	4.04932e-07
FOSL2_HUMAN.H11MO.0.A	4.04932e-07
FOSL1_HUMAN.H11MO.0.A	9.6514e-07
MA1130.1_FOSL2::JUN	9.6514e-07
MA0099.3_FOS::JUN	1.0340799999999998e-06	Not shown
MA1622.1_Smad2::Smad3	1.0340799999999998e-06	Not shown
MA1137.1_FOSL1::JUNB	3.7729099999999998e-06	Not shown
MA1128.1_FOSL1::JUN	3.7729099999999998e-06	Not shown
MA1141.1_FOS::JUND	3.7729099999999998e-06	Not shown

Motif ID	q-val	PWM
CEBPB_HUMAN.H11MO.0.A	6.98839e-10
CEBPD_HUMAN.H11MO.0.C	2.89374e-06
MA0836.2_CEBPD	1.2329500000000001e-05
CEBPA_HUMAN.H11MO.0.A	1.2329500000000001e-05
MA0102.4_CEBPA	2.66264e-05
MA0837.1_CEBPE	0.0006198169999999999	Not shown
MA0025.2_NFIL3	0.0006198169999999999	Not shown
MA0466.2_CEBPB	0.0006198169999999999	Not shown
MA0838.1_CEBPG	0.000920357	Not shown
NFIL3_HUMAN.H11MO.0.D	0.00225456	Not shown

Motif ID	q-val	PWM
FOXA1_HUMAN.H11MO.0.A	1.83899e-06
FOXA2_HUMAN.H11MO.0.A	1.83899e-06
FOXM1_HUMAN.H11MO.0.A	5.60362e-06
FOXF2_HUMAN.H11MO.0.D	9.77385e-06
FOXA3_HUMAN.H11MO.0.B	2.52448e-05
MA0847.2_FOXD2	2.52448e-05	Not shown
MA0846.1_FOXC2	2.52448e-05	Not shown
FOXC1_HUMAN.H11MO.0.C	2.77065e-05	Not shown
FOXD3_HUMAN.H11MO.0.D	2.77065e-05	Not shown
FOXJ2_HUMAN.H11MO.0.C	0.00104545	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 1/9

Pattern 2/9

Pattern 3/9

Pattern 4/9

Pattern 5/9

Pattern 6/9

Pattern 7/9

Pattern 8/9

Pattern 9/9

Summary of motifs¶

Metacluster 1/1

Top TOMTOM matches for each motif¶

Metacluster 1/1

Motif 1/9

Motif 2/9

Motif 3/9

Motif 4/9

Motif 5/9

Motif 6/9

Motif 7/9

Motif 8/9

Motif 9/9

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

Motif ID	q-val	PWM
PRGR_HUMAN.H11MO.0.A	0.00514982
GCR_HUMAN.H11MO.0.A	0.00855941
ANDR_HUMAN.H11MO.1.A	0.037991500000000004
MA0808.1_TEAD3	0.0481774
ZN394_HUMAN.H11MO.1.D	0.0523408
MA0727.1_NR3C2	0.144426	Not shown
HSF1_HUMAN.H11MO.0.A	0.144426	Not shown
MA0113.3_NR3C1	0.161834	Not shown
HSF2_HUMAN.H11MO.0.A	0.161834	Not shown
SMCA5_HUMAN.H11MO.0.C	0.22321300000000002	Not shown

Motif ID	q-val	PWM
MA1127.1_FOSB::JUN	1.4860899999999999e-05
MA1136.1_FOSB::JUNB(var.2)	3.23263e-05
ATF2_HUMAN.H11MO.2.C	3.23263e-05
ATF7_HUMAN.H11MO.0.D	3.23263e-05
MA0840.1_Creb5	3.23263e-05
MA1133.1_JUN::JUNB(var.2)	3.23263e-05	Not shown
MA1139.1_FOSL2::JUNB(var.2)	3.23263e-05	Not shown
JDP2_HUMAN.H11MO.0.D	3.23263e-05	Not shown
MA1126.1_FOS::JUN(var.2)	3.76506e-05	Not shown
MA0609.2_CREM	3.76506e-05	Not shown

Motif ID	q-val	PWM
FOXD2_HUMAN.H11MO.0.D	0.00908909
FOXB1_HUMAN.H11MO.0.D	0.11860699999999999
MA0791.1_POU4F3	0.40799
MA0683.1_POU4F2	0.419227
MA0032.2_FOXC1	0.419227
MA0845.1_FOXB1	0.419227	Not shown
PO4F3_HUMAN.H11MO.0.D	0.45840699999999995	Not shown
FOXJ2_HUMAN.H11MO.0.C	0.45840699999999995	Not shown

Motif ID	q-val	PWM
PRGR_HUMAN.H11MO.0.A	0.026316200000000005
GCR_HUMAN.H11MO.0.A	0.0361124
ANDR_HUMAN.H11MO.1.A	0.0361124
MA0727.1_NR3C2	0.0957936
MA0113.3_NR3C1	0.101773
PRGR_HUMAN.H11MO.1.A	0.112049	Not shown

Motif ID	q-val	PWM
TEAD4_HUMAN.H11MO.0.A	2.8217900000000004e-06
TEAD1_HUMAN.H11MO.0.A	0.00113675
TEAD2_HUMAN.H11MO.0.D	0.0012300999999999998
MA0090.3_TEAD1	0.0012300999999999998
MA1121.1_TEAD2	0.00309424
MA0809.2_TEAD4	0.00888052	Not shown
MA0808.1_TEAD3	0.00965784	Not shown
P53_HUMAN.H11MO.1.A	0.0405481	Not shown
P73_HUMAN.H11MO.1.A	0.044046499999999995	Not shown
P63_HUMAN.H11MO.0.A	0.22519	Not shown