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_fold7/NR3C1-reddytime_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/NR3C1-reddytime_multitask_profile_fold7/NR3C1-reddytime_multitask_profile_fold7_profile_tfm.h5
Importance score key: profile_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/NR3C1-reddytime_multitask_profile_fold7/NR3C1-reddytime_multitask_profile_fold7_profile
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 [01:30<00:00,  2.06it/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 1/12

5315 seqlets

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

Pattern 2/12

3095 seqlets

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

Pattern 3/12

1819 seqlets

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

Pattern 4/12

1095 seqlets

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

Pattern 5/12

804 seqlets

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

Pattern 6/12

313 seqlets

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

Pattern 7/12

204 seqlets

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

Pattern 8/12

186 seqlets

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

Pattern 9/12

146 seqlets

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

Pattern 10/12

56 seqlets

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

Pattern 11/12

50 seqlets

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

Pattern 12/12

34 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
15315
23095
31819
41095
5804
6313
7204
8186
9146
1056
1150
1234

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 1/12

Motif IDq-valPWM
GCR_HUMAN.H11MO.0.A1.29646e-09
PRGR_HUMAN.H11MO.0.A8.90355e-07
ANDR_HUMAN.H11MO.1.A8.90355e-07
MA0727.1_NR3C25.7668900000000006e-05
MA0113.3_NR3C19.87835e-05
PRGR_HUMAN.H11MO.1.A0.00775449Not shown
MA0007.3_Ar0.012263799999999998Not shown
GCR_HUMAN.H11MO.1.A0.0291485Not shown
MA1508.1_IKZF10.42656700000000003Not shown
RARG_HUMAN.H11MO.0.B0.42656700000000003Not shown

Motif 2/12

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A6.0178e-05
FOSL2_HUMAN.H11MO.0.A6.0178e-05
MA1622.1_Smad2::Smad36.0178e-05
MA1141.1_FOS::JUND7.0531e-05
NFE2_HUMAN.H11MO.0.A7.0531e-05
MA1128.1_FOSL1::JUN7.0531e-05Not shown
FOSB_HUMAN.H11MO.0.A7.0531e-05Not shown
MA1137.1_FOSL1::JUNB7.0531e-05Not shown
JUND_HUMAN.H11MO.0.A7.0531e-05Not shown
BACH2_HUMAN.H11MO.0.A7.0531e-05Not shown

Motif 3/12

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A1.9936099999999997e-09
CEBPA_HUMAN.H11MO.0.A2.9709800000000003e-06
CEBPD_HUMAN.H11MO.0.C2.9709800000000003e-06
MA0836.2_CEBPD1.93376e-05
MA0102.4_CEBPA8.72689e-05
MA0025.2_NFIL30.000530395Not shown
MA0837.1_CEBPE0.00121483Not shown
MA0466.2_CEBPB0.00147522Not shown
DBP_HUMAN.H11MO.0.B0.00147522Not shown
NFIL3_HUMAN.H11MO.0.D0.00147522Not shown

Motif 4/12

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A2.14671e-06
FOXM1_HUMAN.H11MO.0.A2.14671e-06
FOXA2_HUMAN.H11MO.0.A2.43164e-06
FOXF2_HUMAN.H11MO.0.D1.38775e-05
FOXA3_HUMAN.H11MO.0.B2.2204e-05
MA0846.1_FOXC22.73159e-05Not shown
FOXD3_HUMAN.H11MO.0.D3.35459e-05Not shown
MA0847.2_FOXD23.77348e-05Not shown
FOXC1_HUMAN.H11MO.0.C5.0313100000000005e-05Not shown
FOXJ2_HUMAN.H11MO.0.C0.00113081Not shown

Motif 5/12

Motif IDq-valPWM
ATF2_HUMAN.H11MO.2.C7.39407e-05
ATF7_HUMAN.H11MO.0.D7.39407e-05
MA1127.1_FOSB::JUN7.39407e-05
JDP2_HUMAN.H11MO.0.D7.39407e-05
MA1133.1_JUN::JUNB(var.2)7.39407e-05
MA0834.1_ATF78.45036e-05Not shown
MA1145.1_FOSL2::JUND(var.2)8.45036e-05Not shown
MA1475.1_CREB3L4(var.2)0.00012126799999999999Not shown
MA1140.2_JUNB(var.2)0.00012126799999999999Not shown
MA1139.1_FOSL2::JUNB(var.2)0.00012126799999999999Not shown

Motif 6/12

Motif IDq-valPWM
MA1121.1_TEAD24.85586e-05
TEAD2_HUMAN.H11MO.0.D5.8001700000000004e-05
TEAD4_HUMAN.H11MO.0.A0.000254669
TEAD1_HUMAN.H11MO.0.A0.000254669
MA0809.2_TEAD40.000284568
MA0090.3_TEAD10.000296424Not shown
MA0808.1_TEAD30.00156347Not shown
P63_HUMAN.H11MO.1.A0.22049899999999997Not shown
TEAD3_HUMAN.H11MO.0.D0.320792Not shown
P73_HUMAN.H11MO.1.A0.320792Not shown

Motif 7/12

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.00131293
FOXB1_HUMAN.H11MO.0.D0.012084600000000001
MA0032.2_FOXC10.159696
MA0791.1_POU4F30.159696
MA0845.1_FOXB10.159696
MA0683.1_POU4F20.159696Not shown
MA0847.2_FOXD20.24046700000000001Not shown
PO4F3_HUMAN.H11MO.0.D0.24046700000000001Not shown
MA0148.4_FOXA10.242758Not shown
MA0846.1_FOXC20.242758Not shown

Motif 8/12

Motif IDq-valPWM
GCR_HUMAN.H11MO.0.A0.378101
HSF2_HUMAN.H11MO.0.A0.378101
HSF1_HUMAN.H11MO.0.A0.378101
MA0107.1_RELA0.378101
MA0808.1_TEAD30.378101
NFKB1_HUMAN.H11MO.1.B0.438134Not shown

Motif 9/12

Motif IDq-valPWM
PRGR_HUMAN.H11MO.0.A0.00284359
GCR_HUMAN.H11MO.0.A0.00907649
PRGR_HUMAN.H11MO.1.A0.0365418
ANDR_HUMAN.H11MO.1.A0.0365418
MA0727.1_NR3C20.23703000000000002
MA0113.3_NR3C10.255078Not shown
TEAD3_HUMAN.H11MO.0.D0.471413Not shown
MA1508.1_IKZF10.471413Not shown

Motif 10/12

Motif IDq-valPWM
MA0466.2_CEBPB1.26083e-05
MA0837.1_CEBPE1.26083e-05
MA0838.1_CEBPG1.26083e-05
CEBPB_HUMAN.H11MO.0.A4.02272e-05
CEBPE_HUMAN.H11MO.0.A4.02272e-05
MA0836.2_CEBPD0.00074564Not shown
CEBPA_HUMAN.H11MO.0.A0.00129114Not shown
CEBPD_HUMAN.H11MO.0.C0.00174049Not shown
MA1636.1_CEBPG(var.2)0.00191616Not shown
MA0102.4_CEBPA0.00227893Not shown

Motif 11/12

Motif IDq-valPWM
MA0837.1_CEBPE2.10168e-07
MA0466.2_CEBPB2.43304e-07
MA0838.1_CEBPG1.22105e-06
CEBPB_HUMAN.H11MO.0.A8.61357e-05
CEBPE_HUMAN.H11MO.0.A0.00184411
CEBPA_HUMAN.H11MO.0.A0.00184411Not shown
MA0836.2_CEBPD0.00184411Not shown
MA0102.4_CEBPA0.0019125999999999998Not shown
CEBPD_HUMAN.H11MO.0.C0.00195077Not shown
MA0025.2_NFIL30.00266061Not shown

Motif 12/12

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A4.217630000000001e-08
FOXA1_HUMAN.H11MO.0.A6.23361e-08
FOXA2_HUMAN.H11MO.0.A6.42842e-07
FOXD3_HUMAN.H11MO.0.D7.27005e-05
FOXF2_HUMAN.H11MO.0.D0.00022969400000000001
FOXA3_HUMAN.H11MO.0.B0.00022969400000000001Not shown
MA0846.1_FOXC20.0005244469999999999Not shown
MA1683.1_FOXA30.000680198Not shown
MA0593.1_FOXP20.000680198Not shown
MA0847.2_FOXD20.000729377Not shown