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_fold5/FOXA2_multitask_profile_fold5_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold5/FOXA2_multitask_profile_fold5_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_fold5/FOXA2_multitask_profile_fold5_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 [01:53<00:00,  1.53it/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

9749 seqlets

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

Pattern 2/9

1654 seqlets

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

Pattern 3/9

907 seqlets

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

Pattern 4/9

223 seqlets

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

Pattern 5/9

145 seqlets

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

Pattern 6/9

129 seqlets

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

Pattern 7/9

127 seqlets

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

Pattern 8/9

36 seqlets

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

Pattern 9/9

34 seqlets

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

Metacluster 2/2

Pattern 1/2

105 seqlets

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

Pattern 2/2

103 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
19749
21654
3907
4223
5145
6129
7127
836
934

Metacluster 2/2

#SeqletsForwardReverse
1105
2103

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
FOXA1_HUMAN.H11MO.0.A9.00317e-10
FOXA3_HUMAN.H11MO.0.B4.08893e-09
FOXA2_HUMAN.H11MO.0.A9.904389999999999e-09
MA0846.1_FOXC22.80709e-08
FOXD3_HUMAN.H11MO.0.D3.70978e-07
FOXF2_HUMAN.H11MO.0.D5.0411e-07Not shown
MA0847.2_FOXD28.641889999999999e-07Not shown
FOXC1_HUMAN.H11MO.0.C3.81282e-06Not shown
MA0032.2_FOXC14.43486e-06Not shown
MA0848.1_FOXO48.34503e-05Not shown

Motif 2/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B4.59086e-06
HNF4A_HUMAN.H11MO.0.A4.59086e-06
MA0677.1_Nr2f60.00010680000000000001
MA0856.1_RXRG0.00010680000000000001
MA0512.2_Rxra0.00010680000000000001
MA1550.1_PPARD0.00010680000000000001Not shown
MA1537.1_NR2F1(var.2)0.00010680000000000001Not shown
MA1574.1_THRB0.000118074Not shown
MA0855.1_RXRB0.000125716Not shown
MA0115.1_NR1H2::RXRA0.000138914Not shown

Motif 3/9

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A1.74799e-07
CEBPD_HUMAN.H11MO.0.C1.99911e-06
CEBPA_HUMAN.H11MO.0.A1.10043e-05
MA0837.1_CEBPE2.9176e-05
MA0836.2_CEBPD3.42593e-05
MA0466.2_CEBPB3.42593e-05Not shown
MA0838.1_CEBPG0.00010234299999999999Not shown
MA0102.4_CEBPA0.000274572Not shown
MA0043.3_HLF0.00046426800000000005Not shown
MA0025.2_NFIL30.000517132Not shown

Motif 4/9

Motif IDq-valPWM
MA0478.1_FOSL24.90246e-05
MA0489.1_JUN(var.2)4.90246e-05
MA1135.1_FOSB::JUNB7.995e-05
MA1138.1_FOSL2::JUNB7.995e-05
MA1144.1_FOSL2::JUND7.995e-05
MA1134.1_FOS::JUNB0.00017869700000000001Not shown
BACH2_HUMAN.H11MO.0.A0.000206259Not shown
MA0476.1_FOS0.000206259Not shown
MA1101.2_BACH20.000206259Not shown
MA0099.3_FOS::JUN0.000206259Not shown

Motif 5/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B0.000282697
HNF4A_HUMAN.H11MO.0.A0.000369533
MA0677.1_Nr2f60.000405321
MA0856.1_RXRG0.000405321
MA0512.2_Rxra0.00044842199999999997
MA0855.1_RXRB0.000631772Not shown
MA1537.1_NR2F1(var.2)0.00152668Not shown
MA0114.4_HNF4A0.00168445Not shown
MA0484.2_HNF4G0.00168445Not shown
MA0504.1_NR2C20.00168445Not shown

Motif 6/9

Motif IDq-valPWM
PPARG_HUMAN.H11MO.1.A0.0015085
MA0856.1_RXRG0.0015085
MA0512.2_Rxra0.0015085
MA0677.1_Nr2f60.0015085
MA0855.1_RXRB0.0015085
NR4A3_HUMAN.H11MO.0.D0.0016029Not shown
RXRG_HUMAN.H11MO.0.B0.0016029Not shown
HNF4G_HUMAN.H11MO.0.B0.00219166Not shown
PPARA_HUMAN.H11MO.1.B0.00219166Not shown
RXRA_HUMAN.H11MO.1.A0.00219166Not shown

Motif 7/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B4.20824e-06
HNF4A_HUMAN.H11MO.0.A9.46133e-06
RXRG_HUMAN.H11MO.0.B0.00020382900000000002
MA0677.1_Nr2f60.00030345299999999997
MA0856.1_RXRG0.000344003
MA1550.1_PPARD0.000344003Not shown
MA0512.2_Rxra0.000344003Not shown
MA1537.1_NR2F1(var.2)0.000344003Not shown
MA1574.1_THRB0.000466451Not shown
MA0855.1_RXRB0.00046676599999999997Not shown

Motif 8/9

Motif IDq-valPWM
MA0466.2_CEBPB0.00024775599999999996
MA0837.1_CEBPE0.00024775599999999996
MA0838.1_CEBPG0.00110731
DBP_HUMAN.H11MO.0.B0.00150926
CEBPB_HUMAN.H11MO.0.A0.00280449
MA0639.1_DBP0.00461785Not shown
MA0843.1_TEF0.00792977Not shown
CEBPD_HUMAN.H11MO.0.C0.0100911Not shown
HLF_HUMAN.H11MO.0.C0.0102272Not shown
CEBPA_HUMAN.H11MO.0.A0.0111664Not shown

Motif 9/9

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.25219e-05
MA1125.1_ZNF3840.0308526
PRDM6_HUMAN.H11MO.0.C0.0308526
FOXL1_HUMAN.H11MO.0.D0.0315413
FOXG1_HUMAN.H11MO.0.D0.05715599999999999
FOXJ3_HUMAN.H11MO.0.A0.11200299999999999Not shown
ANDR_HUMAN.H11MO.0.A0.112679Not shown
MA0679.2_ONECUT10.12150899999999999Not shown
ONEC2_HUMAN.H11MO.0.D0.14502400000000001Not shown
FUBP1_HUMAN.H11MO.0.D0.149775Not shown

Metacluster 2/2

Motif 1/2

No TOMTOM matches passing threshold

Motif 2/2

Motif IDq-valPWM
FOXF2_HUMAN.H11MO.0.D1.36572e-05
FOXA3_HUMAN.H11MO.0.B1.36572e-05
FOXA1_HUMAN.H11MO.0.A1.36572e-05
FOXA2_HUMAN.H11MO.0.A1.36572e-05
MA0852.2_FOXK11.82097e-05
FOXD3_HUMAN.H11MO.0.D2.82749e-05Not shown
MA1607.1_Foxl26.31199e-05Not shown
MA0846.1_FOXC26.31199e-05Not shown
MA0032.2_FOXC10.00027989599999999996Not shown
MA1683.1_FOXA30.000310837Not shown