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_fold7/FOXA2_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold7/FOXA2_multitask_profile_fold7_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_fold7/FOXA2_multitask_profile_fold7_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 [01:32<00:00,  1.88it/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

9758 seqlets

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

Pattern 2/9

1323 seqlets

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

Pattern 3/9

769 seqlets

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

Pattern 4/9

613 seqlets

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

Pattern 5/9

290 seqlets

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

Pattern 6/9

195 seqlets

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

Pattern 7/9

53 seqlets

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

Pattern 8/9

47 seqlets

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

Pattern 9/9

33 seqlets

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

Metacluster 2/2

Pattern 1/1

55 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
19758
21323
3769
4613
5290
6195
753
847
933

Metacluster 2/2

#SeqletsForwardReverse
155

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.A9.01785e-11
FOXA2_HUMAN.H11MO.0.A3.4894000000000004e-09
MA0846.1_FOXC23.3928e-08
FOXA3_HUMAN.H11MO.0.B3.3928e-08
FOXD3_HUMAN.H11MO.0.D1.17994e-06
FOXF2_HUMAN.H11MO.0.D1.17994e-06Not shown
MA0847.2_FOXD21.17994e-06Not shown
FOXC1_HUMAN.H11MO.0.C2.7594599999999997e-06Not shown
MA0032.2_FOXC13.52065e-06Not shown
FOXM1_HUMAN.H11MO.0.A6.19314e-05Not shown

Motif 2/9

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B1.2135e-05
HNF4A_HUMAN.H11MO.0.A1.2135e-05
MA0677.1_Nr2f60.00019134
MA0856.1_RXRG0.00019134
MA1550.1_PPARD0.00019134
MA1574.1_THRB0.00019134Not shown
MA0512.2_Rxra0.00019134Not shown
MA1537.1_NR2F1(var.2)0.00019134Not shown
MA0115.1_NR1H2::RXRA0.000226081Not shown
MA1148.1_PPARA::RXRA0.000236575Not shown

Motif 3/9

Motif IDq-valPWM
CEBPA_HUMAN.H11MO.0.A1.5818699999999998e-05
CEBPB_HUMAN.H11MO.0.A1.5818699999999998e-05
MA0836.2_CEBPD3.461e-05
CEBPD_HUMAN.H11MO.0.C4.3012e-05
MA0102.4_CEBPA0.000800377
MA0837.1_CEBPE0.00131671Not shown
MA0043.3_HLF0.00131671Not shown
MA0466.2_CEBPB0.00162871Not shown
MA0838.1_CEBPG0.00175283Not shown
DBP_HUMAN.H11MO.0.B0.00175283Not shown

Motif 4/9

No TOMTOM matches passing threshold

Motif 5/9

Motif IDq-valPWM
NFE2_HUMAN.H11MO.0.A0.00016503400000000002
MA0478.1_FOSL20.00016503400000000002
JUND_HUMAN.H11MO.0.A0.00016503400000000002
JUN_HUMAN.H11MO.0.A0.00016503400000000002
FOSL2_HUMAN.H11MO.0.A0.00016503400000000002
MA0099.3_FOS::JUN0.00018861Not shown
MA0501.1_MAF::NFE20.00018861Not shown
BACH2_HUMAN.H11MO.0.A0.000195774Not shown
MA1144.1_FOSL2::JUND0.000198352Not shown
FOSL1_HUMAN.H11MO.0.A0.000198352Not shown

Motif 6/9

Motif IDq-valPWM
FOXA2_HUMAN.H11MO.0.A0.228804
MA0849.1_FOXO60.228804
MA1602.1_ZSCAN290.228804
MA0845.1_FOXB10.228804
FOXA1_HUMAN.H11MO.0.A0.228804
MA0795.1_SMAD30.228804Not shown
MA0042.2_FOXI10.228804Not shown
MA1557.1_SMAD50.228804Not shown
MA0032.2_FOXC10.228804Not shown
MA1607.1_Foxl20.228804Not shown

Motif 7/9

Motif IDq-valPWM
HNF1B_HUMAN.H11MO.0.A1.7308299999999998e-08
HNF1A_HUMAN.H11MO.0.C1.7012099999999998e-06
MA0046.2_HNF1A2.7472500000000003e-06
MA0153.2_HNF1B2.7472500000000003e-06
HNF1B_HUMAN.H11MO.1.A3.48995e-05
ZFHX3_HUMAN.H11MO.0.D0.06790750000000001Not shown
MA0853.1_Alx40.06790750000000001Not shown
MA0854.1_Alx10.176506Not shown
FOXJ3_HUMAN.H11MO.1.B0.18698499999999998Not shown
MA0755.1_CUX20.20310599999999998Not shown

Motif 8/9

Motif IDq-valPWM
MA0043.3_HLF0.0625952
DBP_HUMAN.H11MO.0.B0.0625952
MA0102.4_CEBPA0.0625952
MA0836.2_CEBPD0.0625952
MA0025.2_NFIL30.0643926
NFIL3_HUMAN.H11MO.0.D0.0646867Not shown
MA0466.2_CEBPB0.0846327Not shown
MA0837.1_CEBPE0.0846327Not shown
MA0838.1_CEBPG0.111088Not shown
CEBPA_HUMAN.H11MO.0.A0.111088Not shown

Motif 9/9

Motif IDq-valPWM
HNF4A_HUMAN.H11MO.0.A4.7624700000000005e-05
HNF4G_HUMAN.H11MO.0.B0.000105399
MA1494.1_HNF4A(var.2)0.0023491
MA0855.1_RXRB0.0103741
MA0856.1_RXRG0.0103741
MA0512.2_Rxra0.0139846Not shown
MA1574.1_THRB0.0141582Not shown
MA1550.1_PPARD0.0141582Not shown
MA0484.2_HNF4G0.015659100000000002Not shown
MA0114.4_HNF4A0.0247054Not shown

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
MA0593.1_FOXP20.000100378
MA0846.1_FOXC20.000100378
FOXD1_HUMAN.H11MO.0.D0.000100378
MA1606.1_Foxf10.00011841899999999999
FOXC1_HUMAN.H11MO.0.C0.000236963
MA0042.2_FOXI10.000236963Not shown
MA0849.1_FOXO60.000236963Not shown
FOXF2_HUMAN.H11MO.0.D0.000243201Not shown
FOXD3_HUMAN.H11MO.0.D0.000243201Not shown
MA0852.2_FOXK10.000582081Not shown