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: REST
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/REST_multitask_profile_fold7/REST_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/REST_multitask_profile_fold7/REST_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/REST_multitask_profile_fold7/REST_multitask_profile_fold7_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%|██████████| 287/287 [03:02<00:00,  1.58it/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 1/2

Pattern 1/18

3958 seqlets

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

Pattern 2/18

3507 seqlets

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

Pattern 3/18

3415 seqlets

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

Pattern 4/18

658 seqlets

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

Pattern 5/18

630 seqlets

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

Pattern 6/18

510 seqlets

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

Pattern 7/18

463 seqlets

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

Pattern 8/18

428 seqlets

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

Pattern 9/18

320 seqlets

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

Pattern 10/18

206 seqlets

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

Pattern 11/18

176 seqlets

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

Pattern 12/18

173 seqlets

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

Pattern 13/18

135 seqlets

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

Pattern 14/18

71 seqlets

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

Pattern 15/18

71 seqlets

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

Pattern 16/18

59 seqlets

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

Pattern 17/18

50 seqlets

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

Pattern 18/18

31 seqlets

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

Metacluster 2/2

Pattern 1/7

142 seqlets

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

Pattern 2/7

72 seqlets

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

Pattern 3/7

63 seqlets

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

Pattern 4/7

60 seqlets

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

Pattern 5/7

43 seqlets

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

Pattern 6/7

42 seqlets

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

Pattern 7/7

40 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
13958
23507
33415
4658
5630
6510
7463
8428
9320
10206
11176
12173
13135
1471
1571
1659
1750
1831

Metacluster 2/2

#SeqletsForwardReverse
1142
272
363
460
543
642
740

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 1/18

Motif IDq-valPWM
MA0138.2_REST1.90345e-22
REST_HUMAN.H11MO.0.A1.50685e-17

Motif 2/18

Motif IDq-valPWM
MA0138.2_REST0.0579251
REST_HUMAN.H11MO.0.A0.0663734

Motif 3/18

Motif IDq-valPWM
MA0138.2_REST1.2264200000000001e-12
REST_HUMAN.H11MO.0.A4.20998e-11

Motif 4/18

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.000170536
MA0138.2_REST0.00018440400000000002

Motif 5/18

Motif IDq-valPWM
MA0138.2_REST0.393376
REST_HUMAN.H11MO.0.A0.398931

Motif 6/18

Motif IDq-valPWM
MA0139.1_CTCF1.20284e-26
CTCF_HUMAN.H11MO.0.A7.03255e-21
CTCFL_HUMAN.H11MO.0.A1.43629e-08
MA1102.2_CTCFL0.000176656
MA1568.1_TCF21(var.2)0.243558
MA1638.1_HAND20.287371Not shown
SNAI1_HUMAN.H11MO.0.C0.370487Not shown

Motif 7/18

Motif IDq-valPWM
ZN549_HUMAN.H11MO.0.C0.057681600000000006

Motif 8/18

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.36225300000000005

Motif 9/18

No TOMTOM matches passing threshold

Motif 10/18

No TOMTOM matches passing threshold

Motif 11/18

Motif IDq-valPWM
MA1513.1_KLF150.030708799999999998
SP1_HUMAN.H11MO.1.A0.04819469999999999
SP2_HUMAN.H11MO.1.B0.04819469999999999
MA0516.2_SP20.062197699999999995
SP4_HUMAN.H11MO.1.A0.062197699999999995
EGR4_HUMAN.H11MO.0.D0.062197699999999995Not shown
MA0506.1_NRF10.062197699999999995Not shown
SP1_HUMAN.H11MO.0.A0.062197699999999995Not shown
MA0830.2_TCF40.062197699999999995Not shown
KLF12_HUMAN.H11MO.0.C0.062197699999999995Not shown

Motif 12/18

Motif IDq-valPWM
MA1631.1_ASCL1(var.2)0.0524298
MA0830.2_TCF40.129686
MYOD1_HUMAN.H11MO.0.A0.409269

Motif 13/18

Motif IDq-valPWM
TBX20_HUMAN.H11MO.0.D0.353977
MA0138.2_REST0.353977
REST_HUMAN.H11MO.0.A0.374654
MAFA_HUMAN.H11MO.0.D0.374654
MYOD1_HUMAN.H11MO.0.A0.374654
ZSC16_HUMAN.H11MO.0.D0.49410699999999996Not shown

Motif 14/18

Motif IDq-valPWM
ATF6A_HUMAN.H11MO.0.B0.155468
ZN549_HUMAN.H11MO.0.C0.155468

Motif 15/18

Motif IDq-valPWM
MA0139.1_CTCF0.000555805
CTCF_HUMAN.H11MO.0.A0.000654419
CTCFL_HUMAN.H11MO.0.A0.00237827
MA0138.2_REST0.014604399999999998
REST_HUMAN.H11MO.0.A0.018734400000000002
MA1102.2_CTCFL0.0332687Not shown
ASCL1_HUMAN.H11MO.0.A0.203242Not shown

Motif 16/18

Motif IDq-valPWM
ZN549_HUMAN.H11MO.0.C0.0511806

Motif 17/18

Motif IDq-valPWM
MA0527.1_ZBTB331.19366e-05
KAISO_HUMAN.H11MO.0.A1.60845e-05
KAISO_HUMAN.H11MO.1.A0.00251786
THAP1_HUMAN.H11MO.0.C0.382758

Motif 18/18

No TOMTOM matches passing threshold

Metacluster 2/2

Motif 1/7

No TOMTOM matches passing threshold

Motif 2/7

No TOMTOM matches passing threshold

Motif 3/7

Motif IDq-valPWM
ZFX_HUMAN.H11MO.0.A0.0135282
HAND1_HUMAN.H11MO.1.D0.200709
MA0146.2_Zfx0.200709
MA1102.2_CTCFL0.200709
MA1615.1_Plagl10.22140700000000002
SP1_HUMAN.H11MO.0.A0.336704Not shown

Motif 4/7

No TOMTOM matches passing threshold

Motif 5/7

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.00539236
SP2_HUMAN.H11MO.0.A0.00539236
SP3_HUMAN.H11MO.0.B0.018968000000000002
THAP1_HUMAN.H11MO.0.C0.031917900000000006
NR1H4_HUMAN.H11MO.0.B0.031917900000000006
USF2_HUMAN.H11MO.0.A0.031917900000000006Not shown
MA0146.2_Zfx0.037802800000000004Not shown
MA1102.2_CTCFL0.037802800000000004Not shown
CTCFL_HUMAN.H11MO.0.A0.0539221Not shown
COT1_HUMAN.H11MO.0.C0.056480899999999994Not shown

Motif 6/7

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.0209282
CTCFL_HUMAN.H11MO.0.A0.0209282
SP1_HUMAN.H11MO.0.A0.0209282
MBD2_HUMAN.H11MO.0.B0.0209282
HAND1_HUMAN.H11MO.1.D0.0209282
SP3_HUMAN.H11MO.0.B0.0259801Not shown
ZFX_HUMAN.H11MO.1.A0.0259801Not shown
MXI1_HUMAN.H11MO.0.A0.0345794Not shown
MA1650.1_ZBTB140.0605664Not shown
MA0146.2_Zfx0.0607818Not shown

Motif 7/7

Motif IDq-valPWM
COT1_HUMAN.H11MO.1.C0.00467673
SP2_HUMAN.H11MO.0.A0.08831030000000001
ZFX_HUMAN.H11MO.1.A0.195927
MA0155.1_INSM10.195927
INSM1_HUMAN.H11MO.0.C0.195927
SP3_HUMAN.H11MO.0.B0.195927Not shown
MYOD1_HUMAN.H11MO.0.A0.195927Not shown
COT2_HUMAN.H11MO.1.A0.195927Not shown
SP4_HUMAN.H11MO.0.A0.195927Not shown
COT1_HUMAN.H11MO.0.C0.195927Not shown