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_fold8/REST_multitask_profile_fold8_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/REST_multitask_profile_fold8/REST_multitask_profile_fold8_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_fold8/REST_multitask_profile_fold8_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 [03:01<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 1/14

3697 seqlets

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

Pattern 2/14

2727 seqlets

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

Pattern 3/14

580 seqlets

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

Pattern 4/14

551 seqlets

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

Pattern 5/14

346 seqlets

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

Pattern 6/14

248 seqlets

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

Pattern 7/14

184 seqlets

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

Pattern 8/14

180 seqlets

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

Pattern 9/14

111 seqlets

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

Pattern 10/14

108 seqlets

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

Pattern 11/14

70 seqlets

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

Pattern 12/14

53 seqlets

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

Pattern 13/14

48 seqlets

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

Pattern 14/14

35 seqlets

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

Metacluster 2/2

Pattern 1/6

54 seqlets

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

Pattern 2/6

47 seqlets

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

Pattern 3/6

43 seqlets

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

Pattern 4/6

42 seqlets

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

Pattern 5/6

39 seqlets

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

Pattern 6/6

30 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
13697
22727
3580
4551
5346
6248
7184
8180
9111
10108
1170
1253
1348
1435

Metacluster 2/2

#SeqletsForwardReverse
154
247
343
442
539
630

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
MA0138.2_REST7.72653e-07
REST_HUMAN.H11MO.0.A4.06517e-06

Motif 2/14

Motif IDq-valPWM
MA0138.2_REST3.0083400000000004e-20
REST_HUMAN.H11MO.0.A2.7817900000000004e-17

Motif 3/14

Motif IDq-valPWM
MA0138.2_REST0.267121
REST_HUMAN.H11MO.0.A0.323751

Motif 4/14

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A3.31075e-19
MA0139.1_CTCF2.27199e-17
CTCFL_HUMAN.H11MO.0.A3.66034e-10
MA1102.2_CTCFL6.63143e-05
MA1568.1_TCF21(var.2)0.151893
MA1638.1_HAND20.17615Not shown
SNAI1_HUMAN.H11MO.0.C0.192636Not shown
MA0155.1_INSM10.477433Not shown

Motif 5/14

Motif IDq-valPWM
MA0138.2_REST0.0868023
REST_HUMAN.H11MO.0.A0.11518900000000001

Motif 6/14

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.26618

Motif 7/14

Motif IDq-valPWM
REST_HUMAN.H11MO.0.A0.0185418
MA0138.2_REST0.0185418
TBX20_HUMAN.H11MO.0.D0.19844900000000001

Motif 8/14

No TOMTOM matches passing threshold

Motif 9/14

Motif IDq-valPWM
MA1631.1_ASCL1(var.2)0.0688933
MA0830.2_TCF40.148476
MA0139.1_CTCF0.208393
CTCF_HUMAN.H11MO.0.A0.270931

Motif 10/14

No TOMTOM matches passing threshold

Motif 11/14

Motif IDq-valPWM
TBX20_HUMAN.H11MO.0.D0.338032
MAFA_HUMAN.H11MO.0.D0.374641
MA0138.2_REST0.374641
MYOD1_HUMAN.H11MO.0.A0.374641

Motif 12/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.98981e-05
PRDM6_HUMAN.H11MO.0.C0.0172636
FOXL1_HUMAN.H11MO.0.D0.0273337
MA1125.1_ZNF3840.0273337
FOXG1_HUMAN.H11MO.0.D0.0669546
ANDR_HUMAN.H11MO.0.A0.09224539999999999Not shown
FOXJ3_HUMAN.H11MO.0.A0.103801Not shown
MA0679.2_ONECUT10.103801Not shown
ONEC2_HUMAN.H11MO.0.D0.14829Not shown
FUBP1_HUMAN.H11MO.0.D0.170163Not shown

Motif 13/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D2.2334799999999997e-06
MA1125.1_ZNF3840.00722165
MA0679.2_ONECUT10.0185735
FOXL1_HUMAN.H11MO.0.D0.0185735
FOXG1_HUMAN.H11MO.0.D0.0185735
PRDM6_HUMAN.H11MO.0.C0.023851900000000002Not shown
ONEC2_HUMAN.H11MO.0.D0.0324531Not shown
HXC10_HUMAN.H11MO.0.D0.0324531Not shown
ARI3A_HUMAN.H11MO.0.D0.050844400000000005Not shown
LMX1A_HUMAN.H11MO.0.D0.051944399999999995Not shown

Motif 14/14

Motif IDq-valPWM
ZN549_HUMAN.H11MO.0.C0.273798
REST_HUMAN.H11MO.0.A0.299077
MA0138.2_REST0.299077

Metacluster 2/2

Motif 1/6

No TOMTOM matches passing threshold

Motif 2/6

Motif IDq-valPWM
CTCFL_HUMAN.H11MO.0.A0.00278858
CTCF_HUMAN.H11MO.0.A0.00493551
REST_HUMAN.H11MO.0.A0.016445500000000002
MA0139.1_CTCF0.0183428
SP2_HUMAN.H11MO.0.A0.018741
MA0138.2_REST0.019916099999999996Not shown
MBD2_HUMAN.H11MO.0.B0.0241465Not shown
MA0003.4_TFAP2A0.07119860000000001Not shown
MA0814.2_TFAP2C(var.2)0.251064Not shown
AP2B_HUMAN.H11MO.0.B0.324944Not shown

Motif 3/6

Motif IDq-valPWM
SP1_HUMAN.H11MO.1.A0.253328
SP2_HUMAN.H11MO.1.B0.253328
EGR4_HUMAN.H11MO.0.D0.253328
MA0814.2_TFAP2C(var.2)0.253328
BACH1_HUMAN.H11MO.0.A0.253328
SP2_HUMAN.H11MO.0.A0.253328Not shown
MA1513.1_KLF150.25566300000000003Not shown
MA0599.1_KLF50.289223Not shown
SP3_HUMAN.H11MO.0.B0.289223Not shown
MA0741.1_KLF160.39112600000000003Not shown

Motif 4/6

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00026195200000000003
SP3_HUMAN.H11MO.0.B0.00064452
THAP1_HUMAN.H11MO.0.C0.00201129
SP1_HUMAN.H11MO.0.A0.00291904
ZFX_HUMAN.H11MO.1.A0.00878015
SP1_HUMAN.H11MO.1.A0.0100946Not shown
KLF3_HUMAN.H11MO.0.B0.0133865Not shown
RFX1_HUMAN.H11MO.0.B0.014015600000000001Not shown
MA1650.1_ZBTB140.0161337Not shown
USF2_HUMAN.H11MO.0.A0.0225795Not shown

Motif 5/6

Motif IDq-valPWM
AP2B_HUMAN.H11MO.0.B0.396313
THAP1_HUMAN.H11MO.0.C0.396313
MA0524.2_TFAP2C0.396313
MA1615.1_Plagl10.396313
MA0811.1_TFAP2B0.396313
AP2C_HUMAN.H11MO.0.A0.396313Not shown
MXI1_HUMAN.H11MO.0.A0.396313Not shown
RARA_HUMAN.H11MO.1.A0.396313Not shown
COT2_HUMAN.H11MO.1.A0.396313Not shown
COT1_HUMAN.H11MO.0.C0.396313Not shown

Motif 6/6

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00169802
SP1_HUMAN.H11MO.0.A0.0019343
MA0131.2_HINFP0.010460700000000002
SP3_HUMAN.H11MO.0.B0.010460700000000002
MA1513.1_KLF150.016151699999999998
PATZ1_HUMAN.H11MO.0.C0.030997900000000005Not shown
SP1_HUMAN.H11MO.1.A0.0311789Not shown
MXI1_HUMAN.H11MO.0.A0.035491Not shown
AP2D_HUMAN.H11MO.0.D0.0368366Not shown
KLF1_HUMAN.H11MO.0.A0.0615582Not shown