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: SPI1
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/SPI1_multitask_profile_fold1/SPI1_multitask_profile_fold1_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/SPI1_multitask_profile_fold1/SPI1_multitask_profile_fold1_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/SPI1_multitask_profile_fold1/SPI1_multitask_profile_fold1_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%|██████████| 194/194 [03:31<00:00,  1.09s/it]
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 1/5

15622 seqlets

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

Pattern 2/5

326 seqlets

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

Pattern 3/5

58 seqlets

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

Pattern 4/5

55 seqlets

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

Pattern 5/5

39 seqlets

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

Metacluster 2/2

Pattern 1/5

239 seqlets

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

Pattern 2/5

119 seqlets

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

Pattern 3/5

61 seqlets

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

Pattern 4/5

33 seqlets

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

Pattern 5/5

32 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
115622
2326
358
455
539

Metacluster 2/2

#SeqletsForwardReverse
1239
2119
361
433
532

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 1/5

Motif IDq-valPWM
SPI1_HUMAN.H11MO.0.A2.4282699999999998e-14
SPIB_HUMAN.H11MO.0.A2.47719e-13
MA0081.2_SPIB1.46036e-12
BC11A_HUMAN.H11MO.0.A2.58208e-09
MA0080.5_SPI18.82622e-09
IRF8_HUMAN.H11MO.0.B1.7552e-08Not shown
IRF4_HUMAN.H11MO.0.A2.45302e-08Not shown
MA0598.3_EHF0.000118975Not shown
MA0761.2_ETV10.000209167Not shown
MA0062.3_GABPA0.00032261599999999996Not shown

Motif 2/5

Motif IDq-valPWM
MA0081.2_SPIB0.00289037
MA0080.5_SPI10.00289037
SPI1_HUMAN.H11MO.0.A0.00372447
SPIB_HUMAN.H11MO.0.A0.00520207
MA0687.1_SPIC0.014914600000000002
BC11A_HUMAN.H11MO.0.A0.0149422Not shown
ELF5_HUMAN.H11MO.0.A0.0163687Not shown
ELF3_HUMAN.H11MO.0.A0.026329900000000003Not shown
IRF8_HUMAN.H11MO.0.B0.032875Not shown
IRF4_HUMAN.H11MO.0.A0.036018699999999994Not shown

Motif 3/5

No TOMTOM matches passing threshold

Motif 4/5

Motif IDq-valPWM
IRF4_HUMAN.H11MO.0.A3.3503699999999996e-05
IRF8_HUMAN.H11MO.0.B3.3503699999999996e-05
BC11A_HUMAN.H11MO.0.A0.000818197
SPI1_HUMAN.H11MO.0.A0.00226487
SPIB_HUMAN.H11MO.0.A0.00226487
MA0081.2_SPIB0.00307875Not shown
MA1508.1_IKZF10.0048854Not shown
MA0640.2_ELF30.00581724Not shown
MA0080.5_SPI10.00583984Not shown
IRF2_HUMAN.H11MO.0.A0.020162799999999998Not shown

Motif 5/5

Motif IDq-valPWM
MA0081.2_SPIB1.9188900000000002e-05
BC11A_HUMAN.H11MO.0.A1.9188900000000002e-05
SPI1_HUMAN.H11MO.0.A7.31453e-05
SPIB_HUMAN.H11MO.0.A0.000180423
MA0598.3_EHF0.000418265
MA0080.5_SPI10.000418265Not shown
MA0062.3_GABPA0.000515312Not shown
MA1652.1_ZKSCAN50.000554155Not shown
MA0761.2_ETV10.000554155Not shown
ETV5_HUMAN.H11MO.0.C0.0014035999999999999Not shown

Metacluster 2/2

Motif 1/5

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.0235484
PO3F3_HUMAN.H11MO.0.D0.0235484
LMX1A_HUMAN.H11MO.0.D0.0624666
HXC10_HUMAN.H11MO.0.D0.0624666
FOXG1_HUMAN.H11MO.0.D0.0624666
MA0679.2_ONECUT10.0787542Not shown
MA0845.1_FOXB10.0882702Not shown
MA0032.2_FOXC10.12424400000000001Not shown
PO3F4_HUMAN.H11MO.0.D0.12679200000000002Not shown
CPEB1_HUMAN.H11MO.0.D0.12679200000000002Not shown

Motif 2/5

No TOMTOM matches passing threshold

Motif 3/5

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.17886400000000002
FOXG1_HUMAN.H11MO.0.D0.289005
MA0845.1_FOXB10.289005
LMX1A_HUMAN.H11MO.0.D0.289005
FOXL1_HUMAN.H11MO.0.D0.289005
PO3F3_HUMAN.H11MO.0.D0.289005Not shown
MA0032.2_FOXC10.304685Not shown
HXC10_HUMAN.H11MO.0.D0.404631Not shown
MA1607.1_Foxl20.404631Not shown
MA0627.2_POU2F30.404631Not shown

Motif 4/5

Motif IDq-valPWM
LMX1A_HUMAN.H11MO.0.D0.00101194
HXC10_HUMAN.H11MO.0.D0.00101194
CPEB1_HUMAN.H11MO.0.D0.00296623
FOXG1_HUMAN.H11MO.0.D0.0040812
PO3F3_HUMAN.H11MO.0.D0.00778861
FOXD2_HUMAN.H11MO.0.D0.0159266Not shown
MA1125.1_ZNF3840.031674Not shown
MA0681.2_PHOX2B0.08175039999999999Not shown
FOXL1_HUMAN.H11MO.0.D0.08175039999999999Not shown
LMX1B_HUMAN.H11MO.0.D0.08175039999999999Not shown

Motif 5/5

Motif IDq-valPWM
HXC10_HUMAN.H11MO.0.D0.153498
LMX1A_HUMAN.H11MO.0.D0.22105300000000003
FOXD2_HUMAN.H11MO.0.D0.242623
ARI3A_HUMAN.H11MO.0.D0.242623
MA0687.1_SPIC0.30894
MA1125.1_ZNF3840.30894Not shown
MA0681.2_PHOX2B0.30894Not shown
PO3F3_HUMAN.H11MO.0.D0.362009Not shown
LHX9_HUMAN.H11MO.0.D0.362009Not shown
SHOX_HUMAN.H11MO.0.D0.370122Not shown