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: MAX
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/MAX_multitask_profile_fold9/MAX_multitask_profile_fold9_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAX_multitask_profile_fold9/MAX_multitask_profile_fold9_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/MAX_multitask_profile_fold9/MAX_multitask_profile_fold9_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%|██████████| 204/204 [01:57<00:00,  1.73it/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")

Metacluster 1/2

Pattern 1/8

5665 seqlets

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

Pattern 2/8

1289 seqlets

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

Pattern 3/8

1037 seqlets

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

Pattern 4/8

598 seqlets

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

Pattern 5/8

225 seqlets

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

Pattern 6/8

158 seqlets

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

Pattern 7/8

71 seqlets

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

Pattern 8/8

37 seqlets

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

Metacluster 2/2

Pattern 1/1

47 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
15665
21289
31037
4598
5225
6158
771
837

Metacluster 2/2

#SeqletsForwardReverse
147

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 1/8

Motif IDq-valPWM
BMAL1_HUMAN.H11MO.0.A0.0102542
MYC_HUMAN.H11MO.0.A0.0102542
MXI1_HUMAN.H11MO.0.A0.014996299999999999
MYCN_HUMAN.H11MO.0.A0.014996299999999999
MAX_HUMAN.H11MO.0.A0.014996299999999999
MA0871.2_TFEC0.014996299999999999Not shown
MA0059.1_MAX::MYC0.014996299999999999Not shown
MA0147.3_MYC0.014996299999999999Not shown
MA0058.3_MAX0.014996299999999999Not shown
MXI1_HUMAN.H11MO.1.A0.014996299999999999Not shown

Motif 2/8

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A2.44372e-12
MA0139.1_CTCF1.18236e-09
CTCFL_HUMAN.H11MO.0.A5.82953e-08
MA1102.2_CTCFL1.94895e-05
SNAI1_HUMAN.H11MO.0.C0.050255
MA1568.1_TCF21(var.2)0.1211Not shown
MA1638.1_HAND20.12806800000000002Not shown
MA0830.2_TCF40.172568Not shown
MA1648.1_TCF12(var.2)0.172568Not shown
KLF8_HUMAN.H11MO.0.C0.19223800000000002Not shown

Motif 3/8

Motif IDq-valPWM
MA0632.2_TCFL50.178041
MA1099.2_HES10.178041
MA0058.3_MAX0.178041
MAX_HUMAN.H11MO.0.A0.178041
MA0825.1_MNT0.178041
MXI1_HUMAN.H11MO.1.A0.178041Not shown
MA0059.1_MAX::MYC0.178041Not shown
MA0147.3_MYC0.178041Not shown
MYC_HUMAN.H11MO.0.A0.178041Not shown
MA0506.1_NRF10.178041Not shown

Motif 4/8

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A0.0386709
MA0139.1_CTCF0.0386709
CTCFL_HUMAN.H11MO.0.A0.0591786
MYC_HUMAN.H11MO.0.A0.0841056
MA1568.1_TCF21(var.2)0.0841056
MAX_HUMAN.H11MO.0.A0.134537Not shown
MA0668.1_NEUROD20.134537Not shown
MA0147.3_MYC0.175136Not shown
MA1108.2_MXI10.23126Not shown
MA0827.1_OLIG30.247556Not shown

Motif 5/8

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A3.95011e-08
SP1_HUMAN.H11MO.0.A4.74817e-08
SP3_HUMAN.H11MO.0.B1.12258e-07
KLF16_HUMAN.H11MO.0.D1.43144e-07
TBX15_HUMAN.H11MO.0.D5.4887e-07
PATZ1_HUMAN.H11MO.0.C3.5935000000000004e-06Not shown
MAZ_HUMAN.H11MO.0.A4.7476e-06Not shown
ZN467_HUMAN.H11MO.0.C7.1673e-06Not shown
WT1_HUMAN.H11MO.0.C7.94466e-06Not shown
VEZF1_HUMAN.H11MO.0.C5.3523900000000004e-05Not shown

Motif 6/8

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D2.429e-05
MA1125.1_ZNF3840.010225299999999998
PRDM6_HUMAN.H11MO.0.C0.010225299999999998
FOXL1_HUMAN.H11MO.0.D0.013997999999999998
FOXJ3_HUMAN.H11MO.0.A0.0149386
FOXG1_HUMAN.H11MO.0.D0.0149386Not shown
ANDR_HUMAN.H11MO.0.A0.015555200000000002Not shown
FOXJ3_HUMAN.H11MO.1.B0.0432474Not shown
ONEC2_HUMAN.H11MO.0.D0.057753599999999995Not shown
ARI3A_HUMAN.H11MO.0.D0.0619365Not shown

Motif 7/8

Motif IDq-valPWM
ZN770_HUMAN.H11MO.0.C2.3325199999999997e-09
MA1596.1_ZNF4602.8186800000000002e-08
ZN770_HUMAN.H11MO.1.C2.3579699999999997e-05
ZFX_HUMAN.H11MO.1.A0.010437799999999999
MA1587.1_ZNF1350.0159003
MA0814.2_TFAP2C(var.2)0.13176500000000002Not shown
MA0146.2_Zfx0.151871Not shown
ZSC22_HUMAN.H11MO.0.C0.151871Not shown
KLF6_HUMAN.H11MO.0.A0.20405299999999998Not shown
MA1107.2_KLF90.27038Not shown

Motif 8/8

Motif IDq-valPWM
MA1108.2_MXI10.00276175
MA0668.1_NEUROD20.0443495
MA0147.3_MYC0.0443495
MA0104.4_MYCN0.0443495
CR3L1_HUMAN.H11MO.0.D0.0449318
MYC_HUMAN.H11MO.0.A0.061767499999999996Not shown
MA1568.1_TCF21(var.2)0.0633082Not shown
MA1638.1_HAND20.0633082Not shown
MA0626.1_Npas20.0645423Not shown
MA1524.1_MSGN10.0645423Not shown

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
CR3L1_HUMAN.H11MO.0.D0.00199874
MA0823.1_HEY10.00199874
MA0616.2_HES20.00278564
MA1099.2_HES10.00278564
MA0626.1_Npas20.00278564
MA0649.1_HEY20.00293364Not shown
HEY2_HUMAN.H11MO.0.D0.00312225Not shown
MA0004.1_Arnt0.00417741Not shown
MA0058.3_MAX0.00417741Not shown
HEY1_HUMAN.H11MO.0.D0.00417741Not shown