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: MAFK
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/MAFK_multitask_profile_fold1/MAFK_multitask_profile_fold1_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAFK_multitask_profile_fold1/MAFK_multitask_profile_fold1_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/MAFK_multitask_profile_fold1/MAFK_multitask_profile_fold1_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%|██████████| 311/311 [10:33<00:00,  2.04s/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 1/14

5010 seqlets

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

Pattern 2/14

3679 seqlets

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

Pattern 3/14

2272 seqlets

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

Pattern 4/14

739 seqlets

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

Pattern 5/14

262 seqlets

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

Pattern 6/14

203 seqlets

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

Pattern 7/14

172 seqlets

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

Pattern 8/14

150 seqlets

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

Pattern 9/14

67 seqlets

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

Pattern 10/14

58 seqlets

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

Pattern 11/14

55 seqlets

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

Pattern 12/14

47 seqlets

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

Pattern 13/14

36 seqlets

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

Pattern 14/14

34 seqlets

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

Metacluster 2/2

Pattern 1/1

31 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 1/2

/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
15010
23679
32272
4739
5262
6203
7172
8150
967
1058
1155
1247
1336
1434

Metacluster 2/2

#SeqletsForwardReverse
131

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 1/14

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A9.95233e-10
MA0501.1_MAF::NFE28.334030000000001e-08
NF2L2_HUMAN.H11MO.0.A3.64202e-07
MAFG_HUMAN.H11MO.0.A3.6458799999999996e-07
MA0496.3_MAFK1.9327e-06
MA1633.1_BACH15.46087e-06Not shown
MA0089.2_NFE2L15.6534e-06Not shown
MAFF_HUMAN.H11MO.1.B7.13195e-06Not shown
BACH2_HUMAN.H11MO.0.A1.4433499999999998e-05Not shown
MAFF_HUMAN.H11MO.0.B8.05029e-05Not shown

Motif 2/14

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A5.1252e-06
MAFG_HUMAN.H11MO.0.A5.1252e-06
MAF_HUMAN.H11MO.0.A5.1252e-06
MA1520.1_MAF1.2283599999999999e-05
MA0496.3_MAFK1.3534700000000001e-05
MAF_HUMAN.H11MO.1.B1.3534700000000001e-05Not shown
MA0117.2_Mafb2.99823e-05Not shown
MA1521.1_MAFA4.7479e-05Not shown
MAFF_HUMAN.H11MO.0.B4.7479e-05Not shown
MAFK_HUMAN.H11MO.1.A4.7479e-05Not shown

Motif 3/14

Motif IDq-valPWM
MA0117.2_Mafb0.000743197
MAFK_HUMAN.H11MO.0.A0.000743197
MA0495.3_MAFF0.000743197
MA0659.2_MAFG0.000743197
MAFG_HUMAN.H11MO.0.A0.0008142539999999999
MAF_HUMAN.H11MO.0.A0.0008142539999999999Not shown
MAF_HUMAN.H11MO.1.B0.0008142539999999999Not shown
ATF2_HUMAN.H11MO.1.B0.000973233Not shown
MAFB_HUMAN.H11MO.0.B0.00159167Not shown
MAFF_HUMAN.H11MO.0.B0.00309125Not shown

Motif 4/14

Motif IDq-valPWM
MA0139.1_CTCF2.4959e-16
CTCF_HUMAN.H11MO.0.A3.3519699999999996e-13
CTCFL_HUMAN.H11MO.0.A3.30552e-07
MA1102.2_CTCFL0.000139491
MA1568.1_TCF21(var.2)0.0925367
MA1638.1_HAND20.138167Not shown
SNAI1_HUMAN.H11MO.0.C0.159618Not shown
ZIC3_HUMAN.H11MO.0.B0.253918Not shown
ZIC2_HUMAN.H11MO.0.D0.425489Not shown
MA1648.1_TCF12(var.2)0.43420299999999995Not shown

Motif 5/14

Motif IDq-valPWM
MAFG_HUMAN.H11MO.0.A0.000961834
MA0659.2_MAFG0.000961834
MA0117.2_Mafb0.000961834
MA0495.3_MAFF0.000961834
MAFF_HUMAN.H11MO.0.B0.00485729
MAFK_HUMAN.H11MO.0.A0.0120511Not shown
MAF_HUMAN.H11MO.0.A0.0127466Not shown
NF2L2_HUMAN.H11MO.0.A0.016383Not shown
MAF_HUMAN.H11MO.1.B0.0225876Not shown
MA0842.2_NRL0.0225876Not shown

Motif 6/14

Motif IDq-valPWM
MA1587.1_ZNF1350.053797000000000005
MA1596.1_ZNF4600.140202
MA0116.1_Znf4230.140202
RARA_HUMAN.H11MO.0.A0.140202
USF2_HUMAN.H11MO.0.A0.140202
TYY1_HUMAN.H11MO.0.A0.300509Not shown
BHE41_HUMAN.H11MO.0.D0.37194499999999997Not shown
ZSC22_HUMAN.H11MO.0.C0.44196599999999997Not shown
MA0095.2_YY10.44196599999999997Not shown
EHF_HUMAN.H11MO.0.B0.469258Not shown

Motif 7/14

Motif IDq-valPWM
MAF_HUMAN.H11MO.1.B0.00488145
MAFK_HUMAN.H11MO.1.A0.014585299999999997
MAF_HUMAN.H11MO.0.A0.014585299999999997
MA0839.1_CREB3L10.0212183
MA0496.3_MAFK0.0212183
MAFF_HUMAN.H11MO.0.B0.0212183Not shown
MAFG_HUMAN.H11MO.0.A0.0212183Not shown
CR3L2_HUMAN.H11MO.0.D0.0212183Not shown
MA1520.1_MAF0.0212183Not shown
MA1521.1_MAFA0.0212183Not shown

Motif 8/14

Motif IDq-valPWM
MA0139.1_CTCF0.320747
CTCF_HUMAN.H11MO.0.A0.34733200000000003
TYY1_HUMAN.H11MO.0.A0.43059200000000003
MA0095.2_YY10.43059200000000003
MA1638.1_HAND20.43059200000000003
MA1568.1_TCF21(var.2)0.43059200000000003Not shown

Motif 9/14

Motif IDq-valPWM
MA0591.1_Bach1::Mafk2.56716e-06
NFE2_HUMAN.H11MO.0.A1.22925e-05
BACH2_HUMAN.H11MO.0.A1.22925e-05
BACH1_HUMAN.H11MO.0.A6.65573e-05
MA1633.1_BACH19.52452e-05
MA0150.2_Nfe2l20.000125103Not shown
MAFF_HUMAN.H11MO.1.B0.000415801Not shown
MA0501.1_MAF::NFE20.0007712000000000001Not shown
MA0089.2_NFE2L10.0009577030000000001Not shown
MA0478.1_FOSL20.00116918Not shown

Motif 10/14

Motif IDq-valPWM
PAX5_HUMAN.H11MO.0.A0.00939007
ZN121_HUMAN.H11MO.0.C0.0477513

Motif 11/14

Motif IDq-valPWM
TBX15_HUMAN.H11MO.0.D1.13868e-07
KLF16_HUMAN.H11MO.0.D2.4903300000000003e-07
MAZ_HUMAN.H11MO.0.A4.62032e-07
ZN467_HUMAN.H11MO.0.C4.62032e-07
SP1_HUMAN.H11MO.0.A1.30351e-06
SP3_HUMAN.H11MO.0.B1.77423e-06Not shown
SP2_HUMAN.H11MO.0.A2.03762e-06Not shown
PATZ1_HUMAN.H11MO.0.C2.11552e-06Not shown
VEZF1_HUMAN.H11MO.0.C2.425e-06Not shown
WT1_HUMAN.H11MO.0.C4.57246e-06Not shown

Motif 12/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D6.35213e-05
MA1125.1_ZNF3840.0265237
PRDM6_HUMAN.H11MO.0.C0.0265237
FOXL1_HUMAN.H11MO.0.D0.0518379
FOXG1_HUMAN.H11MO.0.D0.0895437
ANDR_HUMAN.H11MO.0.A0.156775Not shown
FOXJ3_HUMAN.H11MO.0.A0.156775Not shown
MA0679.2_ONECUT10.17415999999999998Not shown
ONEC2_HUMAN.H11MO.0.D0.22130300000000003Not shown
FUBP1_HUMAN.H11MO.0.D0.22359600000000002Not shown

Motif 13/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D3.03227e-06
MA0679.2_ONECUT10.000886045
MA1125.1_ZNF3840.00180971
FOXG1_HUMAN.H11MO.0.D0.0035851
HXC10_HUMAN.H11MO.0.D0.0035851
LMX1A_HUMAN.H11MO.0.D0.0035851Not shown
FOXL1_HUMAN.H11MO.0.D0.0035851Not shown
ARI3A_HUMAN.H11MO.0.D0.0035851Not shown
MA0757.1_ONECUT30.0074513999999999995Not shown
ONEC2_HUMAN.H11MO.0.D0.0158703Not shown

Motif 14/14

No TOMTOM matches passing threshold

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
NF2L2_HUMAN.H11MO.0.A0.0453724
MA0501.1_MAF::NFE20.0453724
MA0495.3_MAFF0.0453724
MAF_HUMAN.H11MO.1.B0.047803500000000006
MA0089.2_NFE2L10.05504439999999999
MA0659.2_MAFG0.0662768Not shown
HXC10_HUMAN.H11MO.0.D0.0662768Not shown
MAFG_HUMAN.H11MO.0.A0.0866799Not shown
MAFK_HUMAN.H11MO.0.A0.0881525Not shown
MAFG_HUMAN.H11MO.1.A0.090245Not shown