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: NR3C1-reddytime
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/NR3C1-reddytime_multitask_profile_fold10/NR3C1-reddytime_multitask_profile_fold10_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/NR3C1-reddytime_multitask_profile_fold10/NR3C1-reddytime_multitask_profile_fold10_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_fold10/NR3C1-reddytime_multitask_profile_fold10_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%|██████████| 186/186 [01:31<00:00,  2.03it/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")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

Metacluster 1/1

Pattern 1/10

6275 seqlets

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

Pattern 2/10

2938 seqlets

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

Pattern 3/10

1696 seqlets

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

Pattern 4/10

786 seqlets

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

Pattern 5/10

418 seqlets

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

Pattern 6/10

416 seqlets

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

Pattern 7/10

292 seqlets

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

Pattern 8/10

143 seqlets

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

Pattern 9/10

129 seqlets

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

Pattern 10/10

43 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

#SeqletsForwardReverse
16275
22938
31696
4786
5418
6416
7292
8143
9129
1043

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 1/10

Motif IDq-valPWM
GCR_HUMAN.H11MO.0.A2.8726799999999996e-09
PRGR_HUMAN.H11MO.0.A7.87826e-07
ANDR_HUMAN.H11MO.1.A7.87826e-07
MA0727.1_NR3C26.75506e-05
MA0113.3_NR3C10.00015613200000000002
PRGR_HUMAN.H11MO.1.A0.00861995Not shown
MA0007.3_Ar0.0158351Not shown
GCR_HUMAN.H11MO.1.A0.0311205Not shown
MA1508.1_IKZF10.44886899999999996Not shown
ANDR_HUMAN.H11MO.2.A0.460674Not shown

Motif 2/10

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A7.106310000000001e-06
FOSB_HUMAN.H11MO.0.A7.106310000000001e-06
FOSL1_HUMAN.H11MO.0.A7.106310000000001e-06
FOSL2_HUMAN.H11MO.0.A7.106310000000001e-06
MA0099.3_FOS::JUN7.106310000000001e-06
MA1130.1_FOSL2::JUN9.720260000000001e-06Not shown
MA1137.1_FOSL1::JUNB9.720260000000001e-06Not shown
MA1141.1_FOS::JUND9.720260000000001e-06Not shown
JUND_HUMAN.H11MO.0.A9.720260000000001e-06Not shown
MA1622.1_Smad2::Smad39.720260000000001e-06Not shown

Motif 3/10

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A5.44507e-11
CEBPD_HUMAN.H11MO.0.C2.95338e-07
CEBPA_HUMAN.H11MO.0.A4.92584e-06
MA0836.2_CEBPD4.92584e-06
MA0102.4_CEBPA3.84659e-05
MA0837.1_CEBPE0.00015395399999999998Not shown
MA0466.2_CEBPB0.000281122Not shown
MA0838.1_CEBPG0.000337599Not shown
MA0025.2_NFIL30.00104464Not shown
DBP_HUMAN.H11MO.0.B0.00327963Not shown

Motif 4/10

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A6.68075e-08
FOXA2_HUMAN.H11MO.0.A1.05558e-07
FOXF2_HUMAN.H11MO.0.D6.558110000000001e-06
MA0846.1_FOXC26.558110000000001e-06
FOXA3_HUMAN.H11MO.0.B6.558110000000001e-06
MA0847.2_FOXD26.558110000000001e-06Not shown
FOXC1_HUMAN.H11MO.0.C8.43186e-06Not shown
FOXM1_HUMAN.H11MO.0.A9.60205e-06Not shown
FOXD3_HUMAN.H11MO.0.D1.07411e-05Not shown
MA0032.2_FOXC10.00039425Not shown

Motif 5/10

Motif IDq-valPWM
MA1129.1_FOSL1::JUN(var.2)2.18119e-05
MA1133.1_JUN::JUNB(var.2)2.18119e-05
MA1140.2_JUNB(var.2)2.18119e-05
MA0840.1_Creb52.18119e-05
MA0656.1_JDP2(var.2)2.18119e-05
MA1139.1_FOSL2::JUNB(var.2)2.18119e-05Not shown
JDP2_HUMAN.H11MO.0.D2.18119e-05Not shown
ATF7_HUMAN.H11MO.0.D2.18119e-05Not shown
ATF2_HUMAN.H11MO.2.C2.18119e-05Not shown
MA1136.1_FOSB::JUNB(var.2)2.18119e-05Not shown

Motif 6/10

Motif IDq-valPWM
PRGR_HUMAN.H11MO.0.A0.00617718
GCR_HUMAN.H11MO.0.A0.0115553
MA0808.1_TEAD30.0207385
ANDR_HUMAN.H11MO.1.A0.0520331
HXB2_HUMAN.H11MO.0.D0.0549317
HSF1_HUMAN.H11MO.0.A0.0549317Not shown
MA0113.3_NR3C10.0549317Not shown
MA0727.1_NR3C20.0549317Not shown
HSF4_HUMAN.H11MO.0.D0.0667047Not shown
ZN394_HUMAN.H11MO.1.D0.0812558Not shown

Motif 7/10

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.010149
FOXB1_HUMAN.H11MO.0.D0.0639314
MA0791.1_POU4F30.33587100000000003
MA0683.1_POU4F20.33587100000000003
MA0845.1_FOXB10.33587100000000003
MA0032.2_FOXC10.33587100000000003Not shown
PO4F3_HUMAN.H11MO.0.D0.33587100000000003Not shown
MA0847.2_FOXD20.33587100000000003Not shown
FOXJ2_HUMAN.H11MO.0.C0.33587100000000003Not shown
FOXA2_HUMAN.H11MO.0.A0.389823Not shown

Motif 8/10

Motif IDq-valPWM
PRGR_HUMAN.H11MO.0.A0.0184482
GCR_HUMAN.H11MO.0.A0.07887360000000002
MA0113.3_NR3C10.22271300000000002
ANDR_HUMAN.H11MO.1.A0.22271300000000002
MA0727.1_NR3C20.22271300000000002
MA0808.1_TEAD30.227292Not shown
PRGR_HUMAN.H11MO.1.A0.298298Not shown
MA0007.3_Ar0.342991Not shown
NR1I3_HUMAN.H11MO.0.C0.496345Not shown
MA1553.1_RARG(var.3)0.496345Not shown

Motif 9/10

Motif IDq-valPWM
MA1132.1_JUN::JUNB0.04573769999999999
MA1633.1_BACH10.04573769999999999
MA1137.1_FOSL1::JUNB0.04573769999999999
MA1128.1_FOSL1::JUN0.04573769999999999
MA1142.1_FOSL1::JUND0.04573769999999999
MA0655.1_JDP20.04573769999999999Not shown
MA1138.1_FOSL2::JUNB0.04573769999999999Not shown
FOSL2_HUMAN.H11MO.0.A0.04573769999999999Not shown
MA1144.1_FOSL2::JUND0.04573769999999999Not shown
MA1135.1_FOSB::JUNB0.04573769999999999Not shown

Motif 10/10

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A0.0301264
MA0846.1_FOXC20.0301264
FOXJ2_HUMAN.H11MO.0.C0.0301264
FOXF1_HUMAN.H11MO.0.D0.030274799999999998
MA0041.1_Foxd30.030274799999999998
FOXA3_HUMAN.H11MO.0.B0.030994599999999997Not shown
FOXA2_HUMAN.H11MO.0.A0.051670299999999995Not shown
FOXF2_HUMAN.H11MO.0.D0.051670299999999995Not shown
FOXL1_HUMAN.H11MO.0.D0.06283949999999999Not shown
FOXO4_HUMAN.H11MO.0.C0.0682328Not shown