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: GABPA
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_count_tfm.h5
Importance score key: count_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_count
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%|██████████| 104/104 [01:39<00:00,  1.04it/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 1/11

7189 seqlets

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

Pattern 2/11

919 seqlets

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

Pattern 3/11

551 seqlets

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

Pattern 4/11

353 seqlets

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

Pattern 5/11

71 seqlets

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

Pattern 6/11

41 seqlets

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

Pattern 7/11

38 seqlets

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

Pattern 8/11

33 seqlets

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

Pattern 9/11

33 seqlets

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

Pattern 10/11

32 seqlets

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

Pattern 11/11

31 seqlets

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

Metacluster 2/2

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
17189
2919
3551
4353
571
641
738
833
933
1032
1131

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
ETV1_HUMAN.H11MO.0.A5.01332e-06
MA0750.2_ZBTB7A5.01332e-06
MA0076.2_ELK41.85456e-05
ELK4_HUMAN.H11MO.0.A1.85456e-05
ELF2_HUMAN.H11MO.0.C1.85456e-05
GABPA_HUMAN.H11MO.0.A1.85456e-05Not shown
MA0028.2_ELK13.15071e-05Not shown
MA0765.2_ETV53.2674e-05Not shown
ELK1_HUMAN.H11MO.0.B3.2674e-05Not shown
MA1483.1_ELF23.67583e-05Not shown

Motif 2/11

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.0785663
MA0076.2_ELK40.0785663
MA0772.1_IRF70.0785663
MA0640.2_ELF30.13804
ELK1_HUMAN.H11MO.0.B0.13804
ELK4_HUMAN.H11MO.0.A0.13804Not shown
MA0765.2_ETV50.13804Not shown
LYL1_HUMAN.H11MO.0.A0.159926Not shown
MA0760.1_ERF0.159926Not shown
MA0763.1_ETV30.159926Not shown

Motif 3/11

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C3.37645e-23
ZN143_HUMAN.H11MO.0.A4.7798299999999995e-22
THA11_HUMAN.H11MO.0.B5.320030000000001e-18
MA1573.1_THAP112.90429e-09
MA0088.2_ZNF1430.0139208
STAT3_HUMAN.H11MO.0.A0.06034069999999999Not shown
P63_HUMAN.H11MO.0.A0.0948745Not shown
MA1625.1_Stat5b0.110049Not shown
MA0519.1_Stat5a::Stat5b0.127139Not shown
MA0525.2_TP630.22098299999999998Not shown

Motif 4/11

Motif IDq-valPWM
MA0765.2_ETV50.206875
ETV1_HUMAN.H11MO.0.A0.41312600000000005
MA0076.2_ELK40.41312600000000005
GABPA_HUMAN.H11MO.0.A0.41312600000000005
ELF2_HUMAN.H11MO.0.C0.41312600000000005
ELK4_HUMAN.H11MO.0.A0.41312600000000005Not shown
MA0750.2_ZBTB7A0.41312600000000005Not shown
MA0645.1_ETV60.485888Not shown

Motif 5/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00363465
SP1_HUMAN.H11MO.0.A0.0180963
ZFX_HUMAN.H11MO.1.A0.0180963
MA1122.1_TFDP10.0213696
SP3_HUMAN.H11MO.0.B0.0213696
THAP1_HUMAN.H11MO.0.C0.04816380000000001Not shown
ETV1_HUMAN.H11MO.0.A0.0563893Not shown
MBD2_HUMAN.H11MO.0.B0.0651947Not shown
MA0146.2_Zfx0.0746004Not shown
MA0750.2_ZBTB7A0.0818312Not shown

Motif 6/11

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C1.13207e-12
ZN143_HUMAN.H11MO.0.A1.7843099999999999e-12
THA11_HUMAN.H11MO.0.B8.6163e-12
MA1573.1_THAP118.11299e-11
STAT3_HUMAN.H11MO.0.A0.03610719999999999
MA0525.2_TP630.05564740000000001Not shown
MA1625.1_Stat5b0.0653226Not shown
P63_HUMAN.H11MO.0.A0.0906957Not shown
MA0088.2_ZNF1430.0906957Not shown
MA0519.1_Stat5a::Stat5b0.10280399999999999Not shown

Motif 7/11

Motif IDq-valPWM
MA1122.1_TFDP10.00279518
ELK4_HUMAN.H11MO.0.A0.00279518
ETV1_HUMAN.H11MO.0.A0.00279518
MA0076.2_ELK40.00279518
GABPA_HUMAN.H11MO.0.A0.00279518
PATZ1_HUMAN.H11MO.0.C0.00279518Not shown
MA0765.2_ETV50.00279518Not shown
MA0750.2_ZBTB7A0.00511988Not shown
SP2_HUMAN.H11MO.0.A0.00777287Not shown
SP1_HUMAN.H11MO.0.A0.00777287Not shown

Motif 8/11

Motif IDq-valPWM
ELK4_HUMAN.H11MO.0.A0.00335886
SP2_HUMAN.H11MO.0.A0.00335886
MA0076.2_ELK40.00335886
MA0765.2_ETV50.00363159
SP1_HUMAN.H11MO.0.A0.00363159
ETV1_HUMAN.H11MO.0.A0.00363159Not shown
ZFX_HUMAN.H11MO.1.A0.00453052Not shown
WT1_HUMAN.H11MO.0.C0.00506519Not shown
PATZ1_HUMAN.H11MO.0.C0.00512343Not shown
MA0750.2_ZBTB7A0.00512343Not shown

Motif 9/11

Motif IDq-valPWM
MA1418.1_IRF30.00014795
ETV2_HUMAN.H11MO.0.B0.00014795
GABPA_HUMAN.H11MO.0.A0.00014795
ELF2_HUMAN.H11MO.0.C0.000585629
MA0598.3_EHF0.0005961030000000001
ELF1_HUMAN.H11MO.0.A0.0005961030000000001Not shown
MA0076.2_ELK40.000651123Not shown
MA0473.3_ELF10.000933681Not shown
ELF5_HUMAN.H11MO.0.A0.000933681Not shown
ELK1_HUMAN.H11MO.0.B0.00095312Not shown

Motif 10/11

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.121531
MA0765.2_ETV50.146108
MA0750.2_ZBTB7A0.146108
MA0076.2_ELK40.16941099999999998
ELF2_HUMAN.H11MO.0.C0.16941099999999998
MA0528.2_ZNF2630.16941099999999998Not shown
MECP2_HUMAN.H11MO.0.C0.16941099999999998Not shown
THAP1_HUMAN.H11MO.0.C0.16941099999999998Not shown
MA1596.1_ZNF4600.16941099999999998Not shown
FEV_HUMAN.H11MO.0.B0.16941099999999998Not shown

Motif 11/11

Motif IDq-valPWM
FLI1_HUMAN.H11MO.0.A0.0536239
GABPA_HUMAN.H11MO.0.A0.0536239
ETV1_HUMAN.H11MO.0.A0.0536239
SP2_HUMAN.H11MO.0.A0.0536239
ELK4_HUMAN.H11MO.0.A0.0536239
FLI1_HUMAN.H11MO.1.A0.0632427Not shown
ERG_HUMAN.H11MO.0.A0.0632427Not shown
MA0765.2_ETV50.0632427Not shown
MA0076.2_ELK40.0632427Not shown
MA1513.1_KLF150.0632427Not shown