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_fold4/GABPA_multitask_profile_fold4_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/GABPA_multitask_profile_fold4/GABPA_multitask_profile_fold4_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_fold4/GABPA_multitask_profile_fold4_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 [01:18<00:00,  1.32it/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

7428 seqlets

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

Pattern 2/11

900 seqlets

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

Pattern 3/11

715 seqlets

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

Pattern 4/11

613 seqlets

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

Pattern 5/11

130 seqlets

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

Pattern 6/11

82 seqlets

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

Pattern 7/11

66 seqlets

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

Pattern 8/11

58 seqlets

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

Pattern 9/11

38 seqlets

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

Pattern 10/11

35 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

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
17428
2900
3715
4613
5130
682
766
858
938
1035
1133

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
MA0076.2_ELK43.19302e-07
ETV1_HUMAN.H11MO.0.A3.19302e-07
MA0750.2_ZBTB7A3.19302e-07
ELK4_HUMAN.H11MO.0.A1.2746700000000001e-05
ELF2_HUMAN.H11MO.0.C1.2746700000000001e-05
GABPA_HUMAN.H11MO.0.A1.2746700000000001e-05Not shown
MA0759.1_ELK31.95129e-05Not shown
ELK1_HUMAN.H11MO.0.B2.2765100000000003e-05Not shown
MA1483.1_ELF22.52946e-05Not shown
ELF1_HUMAN.H11MO.0.A3.18711e-05Not shown

Motif 2/11

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.00131374
MA0645.1_ETV60.0070113
MA0474.2_ERG0.0070113
MA0475.2_FLI10.0070113
MA0098.3_ETS10.0070113
MA0763.1_ETV30.0070113Not shown
ELF2_HUMAN.H11MO.0.C0.0070113Not shown
MA0760.1_ERF0.0070113Not shown
MA0028.2_ELK10.00742597Not shown
MA1484.1_ETS20.00742597Not shown

Motif 3/11

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.100369
MA0759.1_ELK30.100369
MA0475.2_FLI10.100369
MA0474.2_ERG0.100369
MA0156.2_FEV0.100369
MA0028.2_ELK10.100369Not shown
MA1483.1_ELF20.100369Not shown
MA0641.1_ELF40.100369Not shown
MA0098.3_ETS10.100369Not shown
ETV1_HUMAN.H11MO.0.A0.100369Not shown

Motif 4/11

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C9.261410000000001e-24
ZN143_HUMAN.H11MO.0.A3.3163300000000003e-21
THA11_HUMAN.H11MO.0.B1.40352e-17
MA1573.1_THAP112.38018e-09
MA0088.2_ZNF1430.011866100000000001
STAT3_HUMAN.H11MO.0.A0.0440066Not shown
P63_HUMAN.H11MO.0.A0.0682035Not shown
MA1625.1_Stat5b0.0682035Not shown
MA0519.1_Stat5a::Stat5b0.0748653Not shown
MA0525.2_TP630.18041Not shown

Motif 5/11

Motif IDq-valPWM
USF2_HUMAN.H11MO.0.A0.059058000000000006
MA1129.1_FOSL1::JUN(var.2)0.059058000000000006
MA1127.1_FOSB::JUN0.059058000000000006
ATF7_HUMAN.H11MO.0.D0.059058000000000006
CTCFL_HUMAN.H11MO.0.A0.059058000000000006
JDP2_HUMAN.H11MO.0.D0.059058000000000006Not shown
ATF1_HUMAN.H11MO.0.B0.059058000000000006Not shown
ATF3_HUMAN.H11MO.0.A0.059058000000000006Not shown
CREB1_HUMAN.H11MO.0.A0.059058000000000006Not shown
MA0605.2_ATF30.059058000000000006Not shown

Motif 6/11

No TOMTOM matches passing threshold

Motif 7/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00658266
SP3_HUMAN.H11MO.0.B0.0104633
SP1_HUMAN.H11MO.0.A0.0104633
MA0830.2_TCF40.0104633
PATZ1_HUMAN.H11MO.0.C0.0107884
MYOD1_HUMAN.H11MO.0.A0.0176054Not shown
KLF6_HUMAN.H11MO.0.A0.0176054Not shown
SP1_HUMAN.H11MO.1.A0.0176054Not shown
MA1631.1_ASCL1(var.2)0.0176054Not shown
WT1_HUMAN.H11MO.0.C0.025366299999999998Not shown

Motif 8/11

Motif IDq-valPWM
ETV2_HUMAN.H11MO.0.B7.79436e-05
ERG_HUMAN.H11MO.0.A8.545510000000001e-05
ETS1_HUMAN.H11MO.0.A8.545510000000001e-05
MA0473.3_ELF18.545510000000001e-05
FLI1_HUMAN.H11MO.1.A0.000107551
MA0598.3_EHF0.000107551Not shown
GABPA_HUMAN.H11MO.0.A0.000109962Not shown
MA0764.2_ETV40.00014987100000000002Not shown
MA0062.3_GABPA0.000386611Not shown
MA0761.2_ETV10.000426683Not shown

Motif 9/11

Motif IDq-valPWM
ETV2_HUMAN.H11MO.0.B6.00056e-06
MA0598.3_EHF6.00056e-06
MA0062.3_GABPA2.7729e-05
MA0473.3_ELF12.7729e-05
MA0761.2_ETV12.7729e-05
ETS1_HUMAN.H11MO.0.A2.8906500000000002e-05Not shown
ERG_HUMAN.H11MO.0.A6.0720299999999995e-05Not shown
FLI1_HUMAN.H11MO.1.A9.524200000000001e-05Not shown
MA0764.2_ETV40.00016465Not shown
FLI1_HUMAN.H11MO.0.A0.000251657Not shown

Motif 10/11

Motif IDq-valPWM
ETV2_HUMAN.H11MO.0.B0.00048629300000000006
GABPA_HUMAN.H11MO.0.A0.00048629300000000006
ELF2_HUMAN.H11MO.0.C0.000961739
ELF1_HUMAN.H11MO.0.A0.000961739
MA0076.2_ELK40.0009914519999999999
ELF5_HUMAN.H11MO.0.A0.00207112Not shown
MA0598.3_EHF0.00207112Not shown
MA0750.2_ZBTB7A0.00207112Not shown
MA0765.2_ETV50.00207112Not shown
MA0473.3_ELF10.00310766Not shown

Motif 11/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.000283946
SP1_HUMAN.H11MO.0.A0.000283946
SP3_HUMAN.H11MO.0.B0.00107353
ZFX_HUMAN.H11MO.1.A0.00313415
SP1_HUMAN.H11MO.1.A0.0097816
KLF16_HUMAN.H11MO.0.D0.0149452Not shown
THAP1_HUMAN.H11MO.0.C0.0149452Not shown
KLF3_HUMAN.H11MO.0.B0.0197534Not shown
MA0146.2_Zfx0.026291700000000005Not shown
SP4_HUMAN.H11MO.0.A0.0321382Not shown