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_fold5/GABPA_multitask_profile_fold5_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/GABPA_multitask_profile_fold5/GABPA_multitask_profile_fold5_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_fold5/GABPA_multitask_profile_fold5_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 [01:02<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 1/12

6509 seqlets

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

Pattern 2/12

1023 seqlets

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

Pattern 3/12

658 seqlets

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

Pattern 4/12

246 seqlets

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

Pattern 5/12

222 seqlets

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

Pattern 6/12

66 seqlets

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

Pattern 7/12

66 seqlets

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

Pattern 8/12

56 seqlets

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

Pattern 9/12

42 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

39 seqlets

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

Pattern 12/12

35 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
16509
21023
3658
4246
5222
666
766
856
942
1040
1139
1235

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 1/12

Motif IDq-valPWM
MA0750.2_ZBTB7A1.00357e-06
MA0076.2_ELK43.65668e-06
ETV1_HUMAN.H11MO.0.A3.65668e-06
ELF2_HUMAN.H11MO.0.C4.11377e-06
ELK1_HUMAN.H11MO.0.B1.4670799999999999e-05
ELK4_HUMAN.H11MO.0.A1.4670799999999999e-05Not shown
MA0641.1_ELF41.4670799999999999e-05Not shown
ELF1_HUMAN.H11MO.0.A1.59749e-05Not shown
GABPA_HUMAN.H11MO.0.A1.59749e-05Not shown
MA0759.1_ELK32.9346799999999998e-05Not shown

Motif 2/12

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.0016143000000000002
MA0645.1_ETV60.00845406
MA0474.2_ERG0.00845406
MA0475.2_FLI10.00845406
MA0098.3_ETS10.00906271
ELF2_HUMAN.H11MO.0.C0.00906271Not shown
MA0763.1_ETV30.00906271Not shown
MA0760.1_ERF0.00906271Not shown
MA0156.2_FEV0.00930983Not shown
ELF1_HUMAN.H11MO.0.A0.00930983Not shown

Motif 3/12

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C1.02714e-23
ZN143_HUMAN.H11MO.0.A1.59166e-22
THA11_HUMAN.H11MO.0.B1.1002299999999999e-17
MA1573.1_THAP113.55458e-09
MA0088.2_ZNF1430.00636562
STAT3_HUMAN.H11MO.0.A0.042756Not shown
MA1625.1_Stat5b0.08364930000000001Not shown
P63_HUMAN.H11MO.0.A0.08364930000000001Not shown
MA0519.1_Stat5a::Stat5b0.0929492Not shown
HSF1_HUMAN.H11MO.1.A0.176319Not shown

Motif 4/12

Motif IDq-valPWM
MA0471.2_E2F60.25278
E2F4_HUMAN.H11MO.1.A0.25278
E2F1_HUMAN.H11MO.0.A0.25278
MA0516.2_SP20.25278
E2F7_HUMAN.H11MO.0.B0.25278
E2F6_HUMAN.H11MO.0.A0.25278Not shown
SP2_HUMAN.H11MO.0.A0.25278Not shown
MA0758.1_E2F70.25278Not shown
TFDP1_HUMAN.H11MO.0.C0.25278Not shown
TYY1_HUMAN.H11MO.0.A0.25278Not shown

Motif 5/12

Motif IDq-valPWM
MA0028.2_ELK10.13756500000000002
MA0760.1_ERF0.13756500000000002
MA0759.1_ELK30.13756500000000002
MA0475.2_FLI10.13756500000000002
MA0750.2_ZBTB7A0.13756500000000002
ELF2_HUMAN.H11MO.0.C0.13756500000000002Not shown
MA1483.1_ELF20.13756500000000002Not shown
GABPA_HUMAN.H11MO.0.A0.13756500000000002Not shown
ELK4_HUMAN.H11MO.0.A0.13756500000000002Not shown
MA0765.2_ETV50.13756500000000002Not shown

Motif 6/12

Motif IDq-valPWM
THAP1_HUMAN.H11MO.0.C0.030698900000000005
MA0830.2_TCF40.0496034
SP1_HUMAN.H11MO.0.A0.0496034
SP2_HUMAN.H11MO.0.A0.0496034
USF2_HUMAN.H11MO.0.A0.136998
MA1615.1_Plagl10.17670999999999998Not shown
ETV1_HUMAN.H11MO.0.A0.18883699999999998Not shown
MA1122.1_TFDP10.18883699999999998Not shown
GLIS2_HUMAN.H11MO.0.D0.200943Not shown
AP2B_HUMAN.H11MO.0.B0.200943Not shown

Motif 7/12

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00301885
SP1_HUMAN.H11MO.0.A0.00709097
SP3_HUMAN.H11MO.0.B0.011445299999999999
TBX15_HUMAN.H11MO.0.D0.011445299999999999
KLF16_HUMAN.H11MO.0.D0.025370300000000002
ZFX_HUMAN.H11MO.1.A0.025370300000000002Not shown
KLF3_HUMAN.H11MO.0.B0.0273442Not shown
PATZ1_HUMAN.H11MO.0.C0.0369268Not shown
MA0146.2_Zfx0.0387315Not shown
SP1_HUMAN.H11MO.1.A0.0387315Not shown

Motif 8/12

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.05992190000000001
SP3_HUMAN.H11MO.0.B0.05992190000000001
KLF3_HUMAN.H11MO.0.B0.113598
MA1650.1_ZBTB140.113598
E2F6_HUMAN.H11MO.0.A0.113598
SP2_HUMAN.H11MO.0.A0.113598Not shown
MA1122.1_TFDP10.113598Not shown
WT1_HUMAN.H11MO.0.C0.11598599999999999Not shown
ZN263_HUMAN.H11MO.0.A0.219678Not shown
MA0814.2_TFAP2C(var.2)0.253459Not shown

Motif 9/12

Motif IDq-valPWM
ELF2_HUMAN.H11MO.0.C0.0102794
ELK4_HUMAN.H11MO.0.A0.0158147
GABPA_HUMAN.H11MO.0.A0.0158147
ELK1_HUMAN.H11MO.0.B0.0158147
ETV1_HUMAN.H11MO.0.A0.0158147
MA1484.1_ETS20.0158147Not shown
MA0076.2_ELK40.0158147Not shown
MA0136.2_ELF50.0158147Not shown
MA0765.2_ETV50.016515900000000003Not shown
MA0641.1_ELF40.016515900000000003Not shown

Motif 10/12

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C1.1753599999999999e-13
ZN143_HUMAN.H11MO.0.A4.568770000000001e-13
THA11_HUMAN.H11MO.0.B1.31826e-11
MA1573.1_THAP115.45454e-09
STAT3_HUMAN.H11MO.0.A0.0147352
MA0519.1_Stat5a::Stat5b0.018481900000000002Not shown
MA0088.2_ZNF1430.0282704Not shown
MA1625.1_Stat5b0.0321099Not shown
MA0144.2_STAT30.07959680000000001Not shown
STA5A_HUMAN.H11MO.0.A0.18463800000000002Not shown

Motif 11/12

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.0234153
SP3_HUMAN.H11MO.0.B0.039782099999999994
MBD2_HUMAN.H11MO.0.B0.039782099999999994
SP1_HUMAN.H11MO.0.A0.039782099999999994
MA1122.1_TFDP10.039782099999999994
THAP1_HUMAN.H11MO.0.C0.0461736Not shown
FLI1_HUMAN.H11MO.0.A0.0788102Not shown
MXI1_HUMAN.H11MO.0.A0.0788102Not shown
USF2_HUMAN.H11MO.0.A0.0788102Not shown
PATZ1_HUMAN.H11MO.0.C0.0788102Not shown

Motif 12/12

Motif IDq-valPWM
ZFX_HUMAN.H11MO.1.A0.0219502
MXI1_HUMAN.H11MO.0.A0.34542399999999995
MA0830.2_TCF40.393311
MA1650.1_ZBTB140.393311
ETV1_HUMAN.H11MO.0.A0.393311
SP1_HUMAN.H11MO.0.A0.414858Not shown
MBD2_HUMAN.H11MO.0.B0.414858Not shown
MA0146.2_Zfx0.414858Not shown