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_fold2/GABPA_multitask_profile_fold2_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/GABPA_multitask_profile_fold2/GABPA_multitask_profile_fold2_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_fold2/GABPA_multitask_profile_fold2_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 [01:23<00:00,  1.25it/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 1/1

Pattern 1/13

6552 seqlets

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

Pattern 2/13

1047 seqlets

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

Pattern 3/13

538 seqlets

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

Pattern 4/13

390 seqlets

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

Pattern 5/13

128 seqlets

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

Pattern 6/13

94 seqlets

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

Pattern 7/13

87 seqlets

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

Pattern 8/13

86 seqlets

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

Pattern 9/13

84 seqlets

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

Pattern 10/13

80 seqlets

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

Pattern 11/13

63 seqlets

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

Pattern 12/13

62 seqlets

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

Pattern 13/13

60 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 1/1

/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
16552
21047
3538
4390
5128
694
787
886
984
1080
1163
1262
1360

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 1/1

Motif 1/13

Motif IDq-valPWM
MA0076.2_ELK41.66574e-06
ETV1_HUMAN.H11MO.0.A1.66574e-06
MA0750.2_ZBTB7A1.66574e-06
GABPA_HUMAN.H11MO.0.A1.66574e-06
ELF2_HUMAN.H11MO.0.C8.57697e-06
MA0765.2_ETV51.99677e-05Not shown
ELK1_HUMAN.H11MO.0.B1.99677e-05Not shown
ELK4_HUMAN.H11MO.0.A1.99677e-05Not shown
MA1483.1_ELF21.99677e-05Not shown
ELF1_HUMAN.H11MO.0.A2.5159299999999998e-05Not shown

Motif 2/13

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.07802260000000001
MA0076.2_ELK40.07802260000000001
MA0772.1_IRF70.07802260000000001
MA0640.2_ELF30.131839
MA0765.2_ETV50.131839
ELK1_HUMAN.H11MO.0.B0.131839Not shown
ELK4_HUMAN.H11MO.0.A0.131839Not shown
MA0763.1_ETV30.147297Not shown
MA0098.3_ETS10.147297Not shown
MA0028.2_ELK10.147297Not shown

Motif 3/13

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C2.1218500000000002e-21
ZN143_HUMAN.H11MO.0.A1.9073799999999999e-19
THA11_HUMAN.H11MO.0.B4.2594699999999995e-16
MA1573.1_THAP111.70165e-09
MA0088.2_ZNF1430.015054699999999999
STAT3_HUMAN.H11MO.0.A0.0349586Not shown
MA1625.1_Stat5b0.0709818Not shown
P63_HUMAN.H11MO.0.A0.0709818Not shown
MA0519.1_Stat5a::Stat5b0.0749971Not shown
MA0525.2_TP630.152523Not shown

Motif 4/13

Motif IDq-valPWM
MA0765.2_ETV50.489468
MA0645.1_ETV60.489468
E2F7_HUMAN.H11MO.0.B0.489468
ETV1_HUMAN.H11MO.0.A0.489468
MA0733.1_EGR40.489468
E2F4_HUMAN.H11MO.0.A0.489468Not shown
E2F3_HUMAN.H11MO.0.A0.489468Not shown
MA0865.1_E2F80.489468Not shown
GABPA_HUMAN.H11MO.0.A0.489468Not shown
MA0076.2_ELK40.489468Not shown

Motif 5/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00725514
SP1_HUMAN.H11MO.0.A0.00725514
MA0076.2_ELK40.00818315
SP3_HUMAN.H11MO.0.B0.00905581
MA0750.2_ZBTB7A0.00955973
ELK4_HUMAN.H11MO.0.A0.00955973Not shown
MA0765.2_ETV50.0135202Not shown
GABPA_HUMAN.H11MO.0.A0.0135202Not shown
ETV1_HUMAN.H11MO.0.A0.0164738Not shown
FEV_HUMAN.H11MO.0.B0.0227114Not shown

Motif 6/13

Motif IDq-valPWM
MA0840.1_Creb50.0099862
CREB5_HUMAN.H11MO.0.D0.0099862
MA1139.1_FOSL2::JUNB(var.2)0.0099862
MA1131.1_FOSL2::JUN(var.2)0.0099862
CTCF_HUMAN.H11MO.0.A0.0099862
CTCFL_HUMAN.H11MO.0.A0.0099862Not shown
MA1127.1_FOSB::JUN0.0099862Not shown
ATF7_HUMAN.H11MO.0.D0.0099862Not shown
MA0605.2_ATF30.0099862Not shown
MA1140.2_JUNB(var.2)0.0099862Not shown

Motif 7/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.0159031
ETV1_HUMAN.H11MO.0.A0.0159031
SP3_HUMAN.H11MO.0.B0.0404795
ELK4_HUMAN.H11MO.0.A0.0404795
MA0765.2_ETV50.0404795
SP1_HUMAN.H11MO.0.A0.0404795Not shown
MA0076.2_ELK40.0419603Not shown
USF2_HUMAN.H11MO.0.A0.06438300000000001Not shown
FEV_HUMAN.H11MO.0.B0.06438300000000001Not shown
GABPA_HUMAN.H11MO.0.A0.0716067Not shown

Motif 8/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.0597232
MAFA_HUMAN.H11MO.0.D0.071122
MA1529.1_NHLH20.071122
OSR2_HUMAN.H11MO.0.C0.071122
ETV1_HUMAN.H11MO.0.A0.09472380000000001
ELK4_HUMAN.H11MO.0.A0.09472380000000001Not shown
ZN770_HUMAN.H11MO.0.C0.09472380000000001Not shown
MBD2_HUMAN.H11MO.0.B0.09472380000000001Not shown
MA1122.1_TFDP10.108775Not shown
MYOD1_HUMAN.H11MO.0.A0.108775Not shown

Motif 9/13

Motif IDq-valPWM
USF2_HUMAN.H11MO.0.A0.24530500000000002
SP1_HUMAN.H11MO.0.A0.329419
AP2D_HUMAN.H11MO.0.D0.43014300000000005
MA1122.1_TFDP10.43014300000000005
MA1583.1_ZFP570.43014300000000005
MA0003.4_TFAP2A0.43014300000000005Not shown
MXI1_HUMAN.H11MO.0.A0.43014300000000005Not shown
MA1650.1_ZBTB140.43014300000000005Not shown
MA1513.1_KLF150.43014300000000005Not shown
MA1114.1_PBX30.43014300000000005Not shown

Motif 10/13

Motif IDq-valPWM
ETV1_HUMAN.H11MO.0.A0.010468799999999999
MA0076.2_ELK40.010468799999999999
SP2_HUMAN.H11MO.0.A0.010468799999999999
ELK4_HUMAN.H11MO.0.A0.010468799999999999
THAP1_HUMAN.H11MO.0.C0.010468799999999999
MA0765.2_ETV50.010468799999999999Not shown
FEV_HUMAN.H11MO.0.B0.010468799999999999Not shown
SP3_HUMAN.H11MO.0.B0.0109771Not shown
MA0750.2_ZBTB7A0.0119345Not shown
KLF6_HUMAN.H11MO.0.A0.0173708Not shown

Motif 11/13

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.273911
MA1650.1_ZBTB140.273911
MA0076.2_ELK40.273911
MXI1_HUMAN.H11MO.0.A0.273911
MBD2_HUMAN.H11MO.0.B0.273911
MA0645.1_ETV60.273911Not shown
MA0765.2_ETV50.273911Not shown
MA0759.1_ELK30.273911Not shown
ELK4_HUMAN.H11MO.0.A0.273911Not shown
ZN219_HUMAN.H11MO.0.D0.273911Not shown

Motif 12/13

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00896477
SP3_HUMAN.H11MO.0.B0.0276515
NR1H4_HUMAN.H11MO.0.B0.0276515
GABPA_HUMAN.H11MO.0.A0.0276515
ETV1_HUMAN.H11MO.0.A0.0276515
SP1_HUMAN.H11MO.0.A0.0276515Not shown
PATZ1_HUMAN.H11MO.0.C0.0276515Not shown
MA0765.2_ETV50.0276515Not shown
MA0750.2_ZBTB7A0.0344225Not shown
KLF6_HUMAN.H11MO.0.A0.0349176Not shown

Motif 13/13

Motif IDq-valPWM
ETV1_HUMAN.H11MO.0.A0.000533427
MA0765.2_ETV50.00198125
ELK4_HUMAN.H11MO.0.A0.00198125
GABPA_HUMAN.H11MO.0.A0.00231357
MA0076.2_ELK40.00487932
ELK1_HUMAN.H11MO.0.B0.00702757Not shown
MA0475.2_FLI10.015059600000000001Not shown
MA0156.2_FEV0.015059600000000001Not shown
MA0098.3_ETS10.015059600000000001Not shown
FEV_HUMAN.H11MO.0.B0.015059600000000001Not shown