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_fold5/REST_multitask_profile_fold5_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/REST_multitask_profile_fold5/REST_multitask_profile_fold5_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/REST_multitask_profile_fold5/REST_multitask_profile_fold5_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%|██████████| 287/287 [04:50<00:00,  1.01s/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 1/13

4566 seqlets

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

Pattern 2/13

1940 seqlets

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

Pattern 3/13

1128 seqlets

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

Pattern 4/13

619 seqlets

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

Pattern 5/13

203 seqlets

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

Pattern 6/13

161 seqlets

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

Pattern 7/13

142 seqlets

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

Pattern 8/13

59 seqlets

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

Pattern 9/13

54 seqlets

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

Pattern 10/13

51 seqlets

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

Pattern 11/13

51 seqlets

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

Pattern 12/13

51 seqlets

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

Pattern 13/13

45 seqlets

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

Metacluster 2/2

Pattern 1/7

71 seqlets

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

Pattern 2/7

61 seqlets

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

Pattern 3/7

45 seqlets

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

Pattern 4/7

41 seqlets

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

Pattern 5/7

40 seqlets

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

Pattern 6/7

38 seqlets

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

Pattern 7/7

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
14566
21940
31128
4619
5203
6161
7142
859
954
1051
1151
1251
1345

Metacluster 2/2

#SeqletsForwardReverse
171
261
345
441
540
638
731

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 1/13

Motif IDq-valPWM
MA0138.2_REST6.815619999999999e-20
REST_HUMAN.H11MO.0.A2.0578e-16

Motif 2/13

Motif IDq-valPWM
MA0138.2_REST0.0447985
REST_HUMAN.H11MO.0.A0.0447985

Motif 3/13

No TOMTOM matches passing threshold

Motif 4/13

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A9.50986e-18
MA0139.1_CTCF1.89933e-17
CTCFL_HUMAN.H11MO.0.A5.201649999999999e-10
MA1102.2_CTCFL5.39841e-05
MA1568.1_TCF21(var.2)0.14505
MA1638.1_HAND20.157397Not shown
SNAI1_HUMAN.H11MO.0.C0.170067Not shown
MA1629.1_Zic20.45651099999999994Not shown
AP2B_HUMAN.H11MO.0.B0.45651099999999994Not shown
ZIC2_HUMAN.H11MO.0.D0.45651099999999994Not shown

Motif 5/13

No TOMTOM matches passing threshold

Motif 6/13

No TOMTOM matches passing threshold

Motif 7/13

No TOMTOM matches passing threshold

Motif 8/13

No TOMTOM matches passing threshold

Motif 9/13

Motif IDq-valPWM
MA1631.1_ASCL1(var.2)0.0446117
MA0499.2_MYOD10.0681125
MA0830.2_TCF40.0947793
MYOD1_HUMAN.H11MO.0.A0.42218

Motif 10/13

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.284524
ZBTB6_HUMAN.H11MO.0.C0.284524
MA1102.2_CTCFL0.284524
MA0138.2_REST0.284524
REST_HUMAN.H11MO.0.A0.322968

Motif 11/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A1.20931e-09
SP1_HUMAN.H11MO.0.A2.88053e-09
SP3_HUMAN.H11MO.0.B4.60209e-09
KLF16_HUMAN.H11MO.0.D4.1069e-07
TBX15_HUMAN.H11MO.0.D5.1100400000000005e-06
PATZ1_HUMAN.H11MO.0.C5.328430000000001e-06Not shown
WT1_HUMAN.H11MO.0.C2.2897800000000003e-05Not shown
KLF3_HUMAN.H11MO.0.B2.44669e-05Not shown
ZN467_HUMAN.H11MO.0.C2.44669e-05Not shown
MAZ_HUMAN.H11MO.0.A2.44669e-05Not shown

Motif 12/13

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.0563383
MA0138.2_REST0.0563383

Motif 13/13

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.030925400000000002
MA0138.2_REST0.030925400000000002

Metacluster 2/2

Motif 1/7

Motif IDq-valPWM
MA1631.1_ASCL1(var.2)0.0303149
MA0830.2_TCF40.05913380000000001
MA0138.2_REST0.114845
SP2_HUMAN.H11MO.0.A0.114845
REST_HUMAN.H11MO.0.A0.199656
SP3_HUMAN.H11MO.0.B0.199656Not shown
THAP1_HUMAN.H11MO.0.C0.199656Not shown
MA1529.1_NHLH20.199656Not shown
SP1_HUMAN.H11MO.0.A0.199656Not shown
PATZ1_HUMAN.H11MO.0.C0.199656Not shown

Motif 2/7

No TOMTOM matches passing threshold

Motif 3/7

No TOMTOM matches passing threshold

Motif 4/7

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A2.5239800000000002e-05
SP3_HUMAN.H11MO.0.B7.9973e-05
SP1_HUMAN.H11MO.0.A0.00017775400000000002
PATZ1_HUMAN.H11MO.0.C0.00111962
KLF16_HUMAN.H11MO.0.D0.00111962
KLF3_HUMAN.H11MO.0.B0.00323189Not shown
CTCFL_HUMAN.H11MO.0.A0.00558834Not shown
MA1513.1_KLF150.00749288Not shown
MXI1_HUMAN.H11MO.0.A0.00901645Not shown
SP1_HUMAN.H11MO.1.A0.011374299999999999Not shown

Motif 5/7

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.0164
KLF16_HUMAN.H11MO.0.D0.0164
TBX15_HUMAN.H11MO.0.D0.0164
SP2_HUMAN.H11MO.0.A0.0449228
PATZ1_HUMAN.H11MO.0.C0.0449228
THAP1_HUMAN.H11MO.0.C0.0449228Not shown
SP3_HUMAN.H11MO.0.B0.05546280000000001Not shown
TBX1_HUMAN.H11MO.0.D0.0618365Not shown
AP2D_HUMAN.H11MO.0.D0.0618365Not shown
WT1_HUMAN.H11MO.0.C0.0618365Not shown

Motif 6/7

Motif IDq-valPWM
KLF9_HUMAN.H11MO.0.C0.0195263
MA0753.2_ZNF7400.0195263
SP1_HUMAN.H11MO.1.A0.0202636
MA0741.1_KLF160.0202636
SP1_HUMAN.H11MO.0.A0.0202636
MA0039.4_KLF40.0202636Not shown
SP2_HUMAN.H11MO.0.A0.0202636Not shown
TBX15_HUMAN.H11MO.0.D0.0228362Not shown
KLF16_HUMAN.H11MO.0.D0.0228362Not shown
SP3_HUMAN.H11MO.0.B0.024345500000000003Not shown

Motif 7/7

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00772534
TBX15_HUMAN.H11MO.0.D0.00772534
PATZ1_HUMAN.H11MO.0.C0.00846284
WT1_HUMAN.H11MO.0.C0.0160328
SP3_HUMAN.H11MO.0.B0.0160328
SP1_HUMAN.H11MO.0.A0.0160328Not shown
KLF15_HUMAN.H11MO.0.A0.026378500000000003Not shown
MA1650.1_ZBTB140.0292252Not shown
KLF16_HUMAN.H11MO.0.D0.0389251Not shown
MAZ_HUMAN.H11MO.0.A0.0431218Not shown