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: FOXA2
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/FOXA2_multitask_profile_fold10/FOXA2_multitask_profile_fold10_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold10/FOXA2_multitask_profile_fold10_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/FOXA2_multitask_profile_fold10/FOXA2_multitask_profile_fold10_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%|██████████| 174/174 [01:38<00:00,  1.77it/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 1/9

7320 seqlets

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

Pattern 2/9

2468 seqlets

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

Pattern 3/9

1521 seqlets

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

Pattern 4/9

1095 seqlets

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

Pattern 5/9

296 seqlets

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

Pattern 6/9

215 seqlets

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

Pattern 7/9

104 seqlets

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

Pattern 8/9

84 seqlets

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

Pattern 9/9

69 seqlets

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

Metacluster 2/2

Pattern 1/1

68 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
17320
22468
31521
41095
5296
6215
7104
884
969

Metacluster 2/2

#SeqletsForwardReverse
168

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 1/9

Motif IDq-valPWM
FOXA3_HUMAN.H11MO.0.B1.9816400000000002e-08
FOXA1_HUMAN.H11MO.0.A7.66116e-08
FOXA2_HUMAN.H11MO.0.A9.58357e-08
MA0846.1_FOXC29.58357e-08
MA0032.2_FOXC11.1624e-07
MA0847.2_FOXD28.97757e-06Not shown
FOXF2_HUMAN.H11MO.0.D8.97757e-06Not shown
MA0845.1_FOXB19.98882e-06Not shown
FOXD3_HUMAN.H11MO.0.D9.98882e-06Not shown
FOXC1_HUMAN.H11MO.0.C1.88529e-05Not shown

Motif 2/9

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A6.760550000000001e-05
FOXJ2_HUMAN.H11MO.0.C0.00427179
MA1487.1_FOXE10.00620829
FOXA1_HUMAN.H11MO.0.A0.00681821
FOXF2_HUMAN.H11MO.0.D0.007015899999999999
FOXA2_HUMAN.H11MO.0.A0.00823817Not shown
MA0846.1_FOXC20.00823817Not shown
MA0847.2_FOXD20.00823817Not shown
FOXD3_HUMAN.H11MO.0.D0.010197399999999999Not shown
MA0041.1_Foxd30.010197399999999999Not shown

Motif 3/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B4.29679e-06
HNF4A_HUMAN.H11MO.0.A4.29679e-06
MA0677.1_Nr2f60.00017702200000000001
MA0856.1_RXRG0.00017702200000000001
MA1550.1_PPARD0.00017702200000000001
MA0512.2_Rxra0.00017702200000000001Not shown
MA1537.1_NR2F1(var.2)0.00017702200000000001Not shown
MA0115.1_NR1H2::RXRA0.00018445200000000002Not shown
MA1574.1_THRB0.000187442Not shown
MA0855.1_RXRB0.000187442Not shown

Motif 4/9

Motif IDq-valPWM
MA0837.1_CEBPE1.42257e-06
CEBPB_HUMAN.H11MO.0.A1.42257e-06
MA0466.2_CEBPB1.92903e-06
CEBPD_HUMAN.H11MO.0.C4.29523e-06
MA0838.1_CEBPG9.713380000000001e-06
CEBPA_HUMAN.H11MO.0.A3.83734e-05Not shown
MA0836.2_CEBPD4.7661400000000004e-05Not shown
MA0102.4_CEBPA0.000492195Not shown
HLF_HUMAN.H11MO.0.C0.0009187469999999999Not shown
MA0043.3_HLF0.0009187469999999999Not shown

Motif 5/9

Motif IDq-valPWM
MA0478.1_FOSL25.0004700000000006e-05
BACH2_HUMAN.H11MO.0.A0.000105158
MA0489.1_JUN(var.2)0.00011352799999999999
MA1138.1_FOSL2::JUNB0.00011352799999999999
MA1135.1_FOSB::JUNB0.000127496
MA1144.1_FOSL2::JUND0.000127496Not shown
BACH1_HUMAN.H11MO.0.A0.000127496Not shown
JUND_HUMAN.H11MO.0.A0.000127496Not shown
MA0099.3_FOS::JUN0.000127496Not shown
FOSL1_HUMAN.H11MO.0.A0.000127496Not shown

Motif 6/9

Motif IDq-valPWM
NR4A3_HUMAN.H11MO.0.D0.00143313
HNF4G_HUMAN.H11MO.0.B0.00143313
MA0856.1_RXRG0.00143313
MA0855.1_RXRB0.00143313
MA0512.2_Rxra0.00143313
MA0677.1_Nr2f60.00143313Not shown
RXRG_HUMAN.H11MO.0.B0.00143313Not shown
HNF4A_HUMAN.H11MO.0.A0.00143313Not shown
RXRA_HUMAN.H11MO.1.A0.00153098Not shown
PPARG_HUMAN.H11MO.1.A0.00184364Not shown

Motif 7/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B7.09758e-05
HNF4A_HUMAN.H11MO.0.A7.09758e-05
MA0677.1_Nr2f60.00122287
MA0856.1_RXRG0.00136215
MA0512.2_Rxra0.00136215
MA0855.1_RXRB0.00226677Not shown
MA0115.1_NR1H2::RXRA0.00351588Not shown
MA1574.1_THRB0.00357584Not shown
NR1H2_HUMAN.H11MO.0.D0.00357584Not shown
MA0504.1_NR2C20.00556157Not shown

Motif 8/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B0.00031057599999999996
HNF4A_HUMAN.H11MO.0.A0.00031609
MA0856.1_RXRG0.00031609
MA0512.2_Rxra0.00031609
MA0677.1_Nr2f60.00031609
MA0855.1_RXRB0.000365027Not shown
MA0504.1_NR2C20.00177175Not shown
MA1574.1_THRB0.00182898Not shown
MA1550.1_PPARD0.00182898Not shown
MA0114.4_HNF4A0.00191963Not shown

Motif 9/9

Motif IDq-valPWM
CEBPD_HUMAN.H11MO.0.C1.24125e-05
CEBPE_HUMAN.H11MO.0.A0.00037302099999999996
CEBPB_HUMAN.H11MO.0.A0.000658515
CEBPA_HUMAN.H11MO.0.A0.00153373
MA0837.1_CEBPE0.0020058
MA0466.2_CEBPB0.00286362Not shown
MA0838.1_CEBPG0.00465015Not shown
NFIL3_HUMAN.H11MO.0.D0.00864098Not shown
MA0836.2_CEBPD0.0087003Not shown
MA0043.3_HLF0.0149437Not shown

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
FOXA2_HUMAN.H11MO.0.A9.80218e-07
FOXA3_HUMAN.H11MO.0.B2.316e-05
FOXA1_HUMAN.H11MO.0.A2.316e-05
MA0846.1_FOXC22.8484299999999998e-05
MA0032.2_FOXC14.9753199999999997e-05
MA1607.1_Foxl24.9753199999999997e-05Not shown
FOXF2_HUMAN.H11MO.0.D0.00013799Not shown
FOXD3_HUMAN.H11MO.0.D0.000143309Not shown
MA0847.2_FOXD20.000159588Not shown
FOXC1_HUMAN.H11MO.0.C0.000159588Not shown