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_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/FOXA2_multitask_profile_fold5/FOXA2_multitask_profile_fold5_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%|██████████| 174/174 [01:53<00:00,  1.54it/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 1/1

Pattern 1/11

8064 seqlets

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

Pattern 2/11

2735 seqlets

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

Pattern 3/11

1406 seqlets

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

Pattern 4/11

746 seqlets

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

Pattern 5/11

199 seqlets

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

Pattern 6/11

167 seqlets

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

Pattern 7/11

92 seqlets

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

Pattern 8/11

89 seqlets

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

Pattern 9/11

56 seqlets

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

Pattern 10/11

53 seqlets

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

Pattern 11/11

39 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
18064
22735
31406
4746
5199
6167
792
889
956
1053
1139

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 1/11

Motif IDq-valPWM
MA0846.1_FOXC27.5708e-08
FOXA1_HUMAN.H11MO.0.A1.0148400000000001e-07
FOXA3_HUMAN.H11MO.0.B1.0148400000000001e-07
MA0032.2_FOXC12.2316400000000003e-07
FOXA2_HUMAN.H11MO.0.A2.67796e-07
MA0847.2_FOXD23.50196e-06Not shown
FOXF2_HUMAN.H11MO.0.D5.81495e-06Not shown
FOXD3_HUMAN.H11MO.0.D1.0036e-05Not shown
MA0845.1_FOXB11.38394e-05Not shown
FOXC1_HUMAN.H11MO.0.C1.81006e-05Not shown

Motif 2/11

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A9.48133e-05
FOXJ2_HUMAN.H11MO.0.C0.0047779
MA1487.1_FOXE10.00655144
FOXA1_HUMAN.H11MO.0.A0.00655144
FOXF2_HUMAN.H11MO.0.D0.00674556
MA0846.1_FOXC20.00751415Not shown
MA0847.2_FOXD20.00751415Not shown
FOXA2_HUMAN.H11MO.0.A0.00751415Not shown
FOXC1_HUMAN.H11MO.0.C0.011367100000000002Not shown
FOXD3_HUMAN.H11MO.0.D0.011367100000000002Not shown

Motif 3/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B2.06851e-06
HNF4A_HUMAN.H11MO.0.A2.6282200000000002e-06
MA0677.1_Nr2f60.00034667599999999997
MA0856.1_RXRG0.00034667599999999997
MA0512.2_Rxra0.00034667599999999997
MA1550.1_PPARD0.00034667599999999997Not shown
MA1574.1_THRB0.00034667599999999997Not shown
MA1537.1_NR2F1(var.2)0.00034667599999999997Not shown
MA0855.1_RXRB0.00036618Not shown
MA1494.1_HNF4A(var.2)0.000446924Not shown

Motif 4/11

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A3.10319e-07
CEBPD_HUMAN.H11MO.0.C6.5112000000000004e-06
MA0836.2_CEBPD6.5112000000000004e-06
CEBPA_HUMAN.H11MO.0.A1.04399e-05
MA0102.4_CEBPA7.1612e-05
MA0837.1_CEBPE0.000277699Not shown
MA0466.2_CEBPB0.000340576Not shown
MA0838.1_CEBPG0.00041241300000000004Not shown
MA0025.2_NFIL30.00170625Not shown
DBP_HUMAN.H11MO.0.B0.00209364Not shown

Motif 5/11

Motif IDq-valPWM
HNF4A_HUMAN.H11MO.0.A2.5940999999999998e-05
HNF4G_HUMAN.H11MO.0.B2.5940999999999998e-05
MA0677.1_Nr2f60.000140593
MA0856.1_RXRG0.000140593
MA1550.1_PPARD0.000140593
MA1537.1_NR2F1(var.2)0.000140593Not shown
MA0512.2_Rxra0.000140593Not shown
MA1574.1_THRB0.000140593Not shown
MA0115.1_NR1H2::RXRA0.00018571Not shown
MA0855.1_RXRB0.000202163Not shown

Motif 6/11

Motif IDq-valPWM
MA1128.1_FOSL1::JUN0.000993855
MA1137.1_FOSL1::JUNB0.000993855
MA1134.1_FOS::JUNB0.000993855
MA1144.1_FOSL2::JUND0.000993855
MA0491.2_JUND0.000993855
MA1622.1_Smad2::Smad30.000993855Not shown
MA0478.1_FOSL20.000993855Not shown
MA0099.3_FOS::JUN0.000993855Not shown
MA1135.1_FOSB::JUNB0.000993855Not shown
MA1138.1_FOSL2::JUNB0.000993855Not shown

Motif 7/11

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B4.45924e-05
HNF4A_HUMAN.H11MO.0.A0.000133036
MA0114.4_HNF4A0.00379857
MA0484.2_HNF4G0.00379857
MA1550.1_PPARD0.00586506
MA0856.1_RXRG0.00586506Not shown
RXRG_HUMAN.H11MO.0.B0.00586506Not shown
MA1148.1_PPARA::RXRA0.00586506Not shown
MA0677.1_Nr2f60.00586506Not shown
MA0512.2_Rxra0.00586506Not shown

Motif 8/11

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A0.0105875
FOXA2_HUMAN.H11MO.0.A0.0105875
FOXF2_HUMAN.H11MO.0.D0.0228742
MAFB_HUMAN.H11MO.0.B0.0316204
MA0847.2_FOXD20.0316204
MA0032.2_FOXC10.0316204Not shown
MA0846.1_FOXC20.0414922Not shown
FOXA3_HUMAN.H11MO.0.B0.0640872Not shown
FOXD3_HUMAN.H11MO.0.D0.0760438Not shown
MA0845.1_FOXB10.0760438Not shown

Motif 9/11

Motif IDq-valPWM
HNF1B_HUMAN.H11MO.0.A2.59396e-07
HNF1A_HUMAN.H11MO.0.C5.095230000000001e-07
MA0046.2_HNF1A2.4116099999999998e-06
MA0153.2_HNF1B7.072180000000001e-06
HNF1B_HUMAN.H11MO.1.A0.00019309200000000001
ZFHX3_HUMAN.H11MO.0.D0.0911011Not shown
MA0853.1_Alx40.12953800000000001Not shown
FOXJ3_HUMAN.H11MO.1.B0.203378Not shown
MA0755.1_CUX20.24259899999999998Not shown
MA0854.1_Alx10.253909Not shown

Motif 10/11

Motif IDq-valPWM
MA0845.1_FOXB10.00110842
MA0032.2_FOXC10.00113287
MA0846.1_FOXC20.00780971
MA0047.3_FOXA20.0126809
MA0481.3_FOXP10.0126809
FOXD2_HUMAN.H11MO.0.D0.016824099999999998Not shown
MA1683.1_FOXA30.016824099999999998Not shown
FOXB1_HUMAN.H11MO.0.D0.0226895Not shown
FOXA2_HUMAN.H11MO.0.A0.035569800000000006Not shown
FOXA1_HUMAN.H11MO.0.A0.035569800000000006Not shown

Motif 11/11

Motif IDq-valPWM
MA0837.1_CEBPE0.000372696
MA0466.2_CEBPB0.000372696
CEBPB_HUMAN.H11MO.0.A0.000873395
MA0838.1_CEBPG0.000873395
CEBPD_HUMAN.H11MO.0.C0.000955727
DBP_HUMAN.H11MO.0.B0.000955727Not shown
CEBPA_HUMAN.H11MO.0.A0.00303634Not shown
MA0025.2_NFIL30.00378862Not shown
MA0043.3_HLF0.00389779Not shown
MA0836.2_CEBPD0.00429207Not shown