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: JUND
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/JUND_multitask_profile_fold5/JUND_multitask_profile_fold5_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/JUND_multitask_profile_fold5/JUND_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/JUND_multitask_profile_fold5/JUND_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%|██████████| 350/350 [03:27<00:00,  1.68it/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 1/7

5892 seqlets

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

Pattern 2/7

1798 seqlets

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

Pattern 3/7

495 seqlets

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

Pattern 4/7

360 seqlets

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

Pattern 5/7

108 seqlets

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

Pattern 6/7

108 seqlets

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

Pattern 7/7

61 seqlets

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

Metacluster 2/2

Pattern 1/12

134 seqlets

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

Pattern 2/12

106 seqlets

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

Pattern 3/12

98 seqlets

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

Pattern 4/12

83 seqlets

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

Pattern 5/12

66 seqlets

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

Pattern 6/12

64 seqlets

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

Pattern 7/12

51 seqlets

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

Pattern 8/12

49 seqlets

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

Pattern 9/12

45 seqlets

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

Pattern 10/12

40 seqlets

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

Pattern 11/12

36 seqlets

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

Pattern 12/12

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

#SeqletsForwardReverse
15892
21798
3495
4360
5108
6108
761

Metacluster 2/2

/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
1134
2106
398
483
566
664
751
849
945
1040
1136
1230

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 1/7

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A4.80146e-07
FOSL2_HUMAN.H11MO.0.A1.95785e-06
MA1130.1_FOSL2::JUN3.65213e-06
MA1141.1_FOS::JUND3.65213e-06
MA0099.3_FOS::JUN3.65213e-06
FOSB_HUMAN.H11MO.0.A3.67561e-06Not shown
MA1144.1_FOSL2::JUND5.0724e-06Not shown
MA1128.1_FOSL1::JUN5.0724e-06Not shown
FOSL1_HUMAN.H11MO.0.A5.0724e-06Not shown
MA1622.1_Smad2::Smad35.47819e-06Not shown

Motif 2/7

Motif IDq-valPWM
ATF2_HUMAN.H11MO.0.B2.17206e-06
MA0605.2_ATF32.17206e-06
MA1136.1_FOSB::JUNB(var.2)2.5977099999999996e-06
MA1129.1_FOSL1::JUN(var.2)5.10634e-06
MA1145.1_FOSL2::JUND(var.2)5.6279899999999995e-06
MA1131.1_FOSL2::JUN(var.2)5.6279899999999995e-06Not shown
MA1139.1_FOSL2::JUNB(var.2)5.6279899999999995e-06Not shown
MA1475.1_CREB3L4(var.2)5.6279899999999995e-06Not shown
JDP2_HUMAN.H11MO.0.D5.6279899999999995e-06Not shown
MA1133.1_JUN::JUNB(var.2)6.9641899999999995e-06Not shown

Motif 3/7

Motif IDq-valPWM
MA1132.1_JUN::JUNB0.180608
MA0841.1_NFE20.180608
MA1138.1_FOSL2::JUNB0.180608
MA1144.1_FOSL2::JUND0.180608
MA0150.2_Nfe2l20.180608
MA0501.1_MAF::NFE20.180608Not shown
MA0591.1_Bach1::Mafk0.180608Not shown
MA0477.2_FOSL10.180608Not shown
MA0490.2_JUNB0.180608Not shown
MA0491.2_JUND0.180608Not shown

Motif 4/7

No TOMTOM matches passing threshold

Motif 5/7

Motif IDq-valPWM
MA0466.2_CEBPB0.024876099999999998
MA0837.1_CEBPE0.024876099999999998
MA0838.1_CEBPG0.024876099999999998
BATF_HUMAN.H11MO.1.A0.024876099999999998
CEBPD_HUMAN.H11MO.0.C0.0362807
MA1143.1_FOSL1::JUND(var.2)0.0362807Not shown
MA1636.1_CEBPG(var.2)0.0421073Not shown
CEBPB_HUMAN.H11MO.0.A0.0421073Not shown
MA0639.1_DBP0.049519099999999996Not shown
NFIL3_HUMAN.H11MO.0.D0.049519099999999996Not shown

Motif 6/7

Motif IDq-valPWM
MAF_HUMAN.H11MO.0.A0.0143308
MAFB_HUMAN.H11MO.0.B0.0158547
MAFK_HUMAN.H11MO.1.A0.0158547
MA0496.3_MAFK0.0158547
MA0591.1_Bach1::Mafk0.0211613
NF2L2_HUMAN.H11MO.0.A0.0261177Not shown
MAFG_HUMAN.H11MO.0.A0.0261177Not shown
BACH2_HUMAN.H11MO.0.A0.026878899999999997Not shown
MAFK_HUMAN.H11MO.0.A0.032266Not shown
NRL_HUMAN.H11MO.0.D0.0389657Not shown

Motif 7/7

Motif IDq-valPWM
MA1143.1_FOSL1::JUND(var.2)0.00244551
BATF_HUMAN.H11MO.1.A0.00244551
MA1131.1_FOSL2::JUN(var.2)0.00244551
MA1127.1_FOSB::JUN0.00244551
CREB5_HUMAN.H11MO.0.D0.00244551
CEBPG_HUMAN.H11MO.0.B0.0053295Not shown
MA1136.1_FOSB::JUNB(var.2)0.0053295Not shown
ATF7_HUMAN.H11MO.0.D0.0053295Not shown
ATF2_HUMAN.H11MO.0.B0.0053295Not shown
MA1129.1_FOSL1::JUN(var.2)0.0053295Not shown

Metacluster 2/2

Motif 1/12

No TOMTOM matches passing threshold

Motif 2/12

No TOMTOM matches passing threshold

Motif 3/12

No TOMTOM matches passing threshold

Motif 4/12

No TOMTOM matches passing threshold

Motif 5/12

Motif IDq-valPWM
BHA15_HUMAN.H11MO.0.B0.142924
RFX5_HUMAN.H11MO.0.A0.142924
MA1635.1_BHLHE22(var.2)0.142924
ZN563_HUMAN.H11MO.0.C0.142924
MA1100.2_ASCL10.142924
HTF4_HUMAN.H11MO.0.A0.142924Not shown
ZN547_HUMAN.H11MO.0.C0.142924Not shown
ASCL2_HUMAN.H11MO.0.D0.142924Not shown
MA0521.1_Tcf120.142924Not shown
MA0816.1_Ascl20.142924Not shown

Motif 6/12

Motif IDq-valPWM
ZFX_HUMAN.H11MO.1.A0.0623419
SP3_HUMAN.H11MO.0.B0.0623419
PATZ1_HUMAN.H11MO.0.C0.0623419
SP2_HUMAN.H11MO.0.A0.0623419
KLF1_HUMAN.H11MO.0.A0.0703298
KLF3_HUMAN.H11MO.0.B0.075265Not shown
KLF6_HUMAN.H11MO.0.A0.08233389999999999Not shown
VEZF1_HUMAN.H11MO.0.C0.0853962Not shown
KLF9_HUMAN.H11MO.0.C0.0853962Not shown
SP1_HUMAN.H11MO.0.A0.09417089999999999Not shown

Motif 7/12

No TOMTOM matches passing threshold

Motif 8/12

Motif IDq-valPWM
BACH1_HUMAN.H11MO.0.A0.07297569999999999
FOS_HUMAN.H11MO.0.A0.07297569999999999
MAFB_HUMAN.H11MO.0.B0.0752426
FOSB_HUMAN.H11MO.0.A0.0752426
MA0476.1_FOS0.08003510000000001
MA0478.1_FOSL20.08003510000000001Not shown
MAFF_HUMAN.H11MO.1.B0.08003510000000001Not shown
JUND_HUMAN.H11MO.0.A0.08003510000000001Not shown
MA0655.1_JDP20.08003510000000001Not shown
MA1633.1_BACH10.08003510000000001Not shown

Motif 9/12

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.000279935
SP1_HUMAN.H11MO.0.A0.00038701800000000004
PATZ1_HUMAN.H11MO.0.C0.00113401
SP3_HUMAN.H11MO.0.B0.0067286
MA1513.1_KLF150.010406700000000001
SP1_HUMAN.H11MO.1.A0.010406700000000001Not shown
SP2_HUMAN.H11MO.1.B0.0118575Not shown
MA0162.4_EGR10.0129422Not shown
KLF12_HUMAN.H11MO.0.C0.0218913Not shown
EGR4_HUMAN.H11MO.0.D0.0218913Not shown

Motif 10/12

Motif IDq-valPWM
JUND_HUMAN.H11MO.0.A0.22075999999999998
MA0841.1_NFE20.22075999999999998
MA1135.1_FOSB::JUNB0.22075999999999998
JUN_HUMAN.H11MO.0.A0.22075999999999998
MA1134.1_FOS::JUNB0.22075999999999998
MA1101.2_BACH20.22075999999999998Not shown
MA1138.1_FOSL2::JUNB0.22075999999999998Not shown
MAFG_HUMAN.H11MO.1.A0.22075999999999998Not shown
NR1H4_HUMAN.H11MO.1.B0.22075999999999998Not shown
MA1130.1_FOSL2::JUN0.251538Not shown

Motif 11/12

Motif IDq-valPWM
MA0814.2_TFAP2C(var.2)0.49831400000000003

Motif 12/12

No TOMTOM matches passing threshold