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_fold10/MAFK_multitask_profile_fold10_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAFK_multitask_profile_fold10/MAFK_multitask_profile_fold10_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_fold10/MAFK_multitask_profile_fold10_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 [05:54<00:00,  1.14s/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 1/11

10781 seqlets

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

Pattern 2/11

684 seqlets

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

Pattern 3/11

289 seqlets

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

Pattern 4/11

171 seqlets

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

Pattern 5/11

81 seqlets

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

Pattern 6/11

76 seqlets

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

Pattern 7/11

69 seqlets

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

Pattern 8/11

47 seqlets

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

Pattern 9/11

46 seqlets

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

Pattern 10/11

36 seqlets

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

Pattern 11/11

33 seqlets

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

Metacluster 2/2

Pattern 1/3

50 seqlets

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

Pattern 2/3

45 seqlets

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

Pattern 3/3

35 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
110781
2684
3289
4171
581
676
769
847
946
1036
1133

Metacluster 2/2

#SeqletsForwardReverse
150
245
335

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 1/11

Motif IDq-valPWM
MA0496.3_MAFK1.11544e-09
MAFK_HUMAN.H11MO.0.A1.11544e-09
MA1520.1_MAF1.11544e-09
MAFB_HUMAN.H11MO.0.B2.85813e-09
MAFG_HUMAN.H11MO.0.A2.85813e-09
MAFK_HUMAN.H11MO.1.A3.21035e-08Not shown
MAF_HUMAN.H11MO.0.A4.3044199999999996e-08Not shown
MA1521.1_MAFA5.0739900000000004e-08Not shown
MAFF_HUMAN.H11MO.0.B1.3330600000000002e-07Not shown
MAF_HUMAN.H11MO.1.B1.1494400000000001e-05Not shown

Motif 2/11

Motif IDq-valPWM
MA0139.1_CTCF9.421039999999999e-14
CTCF_HUMAN.H11MO.0.A8.06696e-12
CTCFL_HUMAN.H11MO.0.A1.3828700000000002e-06
MA1102.2_CTCFL0.000602867
MA1568.1_TCF21(var.2)0.06390509999999999
MA1638.1_HAND20.08627510000000001Not shown
SNAI1_HUMAN.H11MO.0.C0.191583Not shown
MA1648.1_TCF12(var.2)0.475389Not shown
NDF1_HUMAN.H11MO.0.A0.475389Not shown
BHA15_HUMAN.H11MO.0.B0.475389Not shown

Motif 3/11

Motif IDq-valPWM
MA0495.3_MAFF0.00065865
MA0117.2_Mafb0.00065865
MAF_HUMAN.H11MO.1.B0.00065865
MA0659.2_MAFG0.0008572310000000001
MAFG_HUMAN.H11MO.0.A0.0016830999999999999
MAFK_HUMAN.H11MO.0.A0.00329449Not shown
MA0501.1_MAF::NFE20.024247499999999998Not shown
MAFG_HUMAN.H11MO.1.A0.024247499999999998Not shown
MAFF_HUMAN.H11MO.0.B0.024247499999999998Not shown
NF2L2_HUMAN.H11MO.0.A0.024247499999999998Not shown

Motif 4/11

Motif IDq-valPWM
PATZ1_HUMAN.H11MO.0.C0.12137300000000001
E2F1_HUMAN.H11MO.0.A0.12137300000000001
SP2_HUMAN.H11MO.0.A0.12137300000000001
TFDP1_HUMAN.H11MO.0.C0.12137300000000001
ZN770_HUMAN.H11MO.0.C0.140489
WT1_HUMAN.H11MO.0.C0.187647Not shown
MXI1_HUMAN.H11MO.0.A0.200991Not shown
SP3_HUMAN.H11MO.0.B0.200991Not shown
MA1102.2_CTCFL0.200991Not shown
CTCF_HUMAN.H11MO.0.A0.200991Not shown

Motif 5/11

Motif IDq-valPWM
NF2L2_HUMAN.H11MO.0.A8.84822e-06
MA0591.1_Bach1::Mafk8.84822e-06
MA0089.2_NFE2L18.84822e-06
MA1633.1_BACH11.42693e-05
MA0150.2_Nfe2l21.42693e-05
MA0501.1_MAF::NFE21.42693e-05Not shown
NFE2_HUMAN.H11MO.0.A1.82807e-05Not shown
BACH2_HUMAN.H11MO.0.A2.1445500000000003e-05Not shown
BACH1_HUMAN.H11MO.0.A0.000139529Not shown
JUN_HUMAN.H11MO.0.A0.00218594Not shown

Motif 6/11

Motif IDq-valPWM
MA0139.1_CTCF0.014059799999999999
CTCF_HUMAN.H11MO.0.A0.027295299999999998
MA1568.1_TCF21(var.2)0.0986438

Motif 7/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D8.02852e-06
MA1125.1_ZNF3840.00433734
FOXL1_HUMAN.H11MO.0.D0.018402500000000002
FOXG1_HUMAN.H11MO.0.D0.02597
MA0679.2_ONECUT10.02597
PRDM6_HUMAN.H11MO.0.C0.02597Not shown
HXC10_HUMAN.H11MO.0.D0.0525619Not shown
ARI3A_HUMAN.H11MO.0.D0.0704557Not shown
ANDR_HUMAN.H11MO.0.A0.10264100000000001Not shown
FOXJ3_HUMAN.H11MO.0.A0.10264100000000001Not shown

Motif 8/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D3.7793800000000004e-05
MA1125.1_ZNF3840.0234253
PRDM6_HUMAN.H11MO.0.C0.0234253
FOXL1_HUMAN.H11MO.0.D0.0638123
FOXG1_HUMAN.H11MO.0.D0.0733091
ANDR_HUMAN.H11MO.0.A0.08778999999999999Not shown
MA0679.2_ONECUT10.08778999999999999Not shown
FOXJ3_HUMAN.H11MO.0.A0.11311600000000001Not shown
HXC10_HUMAN.H11MO.0.D0.11311600000000001Not shown
ONEC2_HUMAN.H11MO.0.D0.12830899999999998Not shown

Motif 9/11

Motif IDq-valPWM
KLF16_HUMAN.H11MO.0.D1.35698e-07
TBX15_HUMAN.H11MO.0.D1.35698e-07
SP1_HUMAN.H11MO.0.A5.0025e-07
MAZ_HUMAN.H11MO.0.A5.4309e-07
SP2_HUMAN.H11MO.0.A6.25546e-07
ZN467_HUMAN.H11MO.0.C6.83055e-07Not shown
SP3_HUMAN.H11MO.0.B1.35995e-06Not shown
PATZ1_HUMAN.H11MO.0.C2.26077e-06Not shown
VEZF1_HUMAN.H11MO.0.C3.61202e-06Not shown
WT1_HUMAN.H11MO.0.C4.138619999999999e-06Not shown

Motif 10/11

Motif IDq-valPWM
RREB1_HUMAN.H11MO.0.D0.0125891
MA0073.1_RREB10.0418592
FOXL1_HUMAN.H11MO.0.D0.0457383
FUBP1_HUMAN.H11MO.0.D0.0457383
FOXG1_HUMAN.H11MO.0.D0.0457383
RUNX2_HUMAN.H11MO.0.A0.0457383Not shown
MA1107.2_KLF90.165148Not shown

Motif 11/11

Motif IDq-valPWM
MA0139.1_CTCF0.00717245
CTCF_HUMAN.H11MO.0.A0.018140200000000002
MA1638.1_HAND20.031769599999999995
MA1568.1_TCF21(var.2)0.06571360000000001
ATOH1_HUMAN.H11MO.0.B0.279271
CTCFL_HUMAN.H11MO.0.A0.285646Not shown
NDF1_HUMAN.H11MO.0.A0.285646Not shown
SNAI1_HUMAN.H11MO.0.C0.285646Not shown
MYC_HUMAN.H11MO.0.A0.285646Not shown
ZIC3_HUMAN.H11MO.0.B0.285646Not shown

Metacluster 2/2

Motif 1/3

Motif IDq-valPWM
MA0495.3_MAFF0.000202527
MA0659.2_MAFG0.000202527
MAFK_HUMAN.H11MO.0.A0.00025372599999999996
MAFG_HUMAN.H11MO.0.A0.00025372599999999996
MA0117.2_Mafb0.00040366400000000003
MAF_HUMAN.H11MO.0.A0.000413615Not shown
MAF_HUMAN.H11MO.1.B0.00341955Not shown
MA1520.1_MAF0.00730477Not shown
MA0496.3_MAFK0.00780879Not shown
MA0842.2_NRL0.00893028Not shown

Motif 2/3

Motif IDq-valPWM
GATA3_HUMAN.H11MO.0.A0.10878099999999999
GATA4_HUMAN.H11MO.0.A0.10878099999999999
GATA1_HUMAN.H11MO.1.A0.10878099999999999
GATA2_HUMAN.H11MO.1.A0.110693
TBX3_HUMAN.H11MO.0.C0.147
MA0036.3_GATA20.147Not shown
RARA_HUMAN.H11MO.1.A0.15047Not shown
SMAD3_HUMAN.H11MO.0.B0.22841Not shown
GATA6_HUMAN.H11MO.0.A0.281864Not shown
ZNF85_HUMAN.H11MO.0.C0.281864Not shown

Motif 3/3

No TOMTOM matches passing threshold