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)
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
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)
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")
| Sequence (PFM) |  |
| Hypothetical contributions (hCWM) |  |
| Actual contributions (CWM) |  |
| Sequence (PFM) |  |
| Hypothetical contributions (hCWM) |  |
| Actual contributions (CWM) |  |
| Sequence (PFM) |  |
| Hypothetical contributions (hCWM) |  |
| Actual contributions (CWM) |  |
| Sequence (PFM) |  |
| Hypothetical contributions (hCWM) |  |
| Actual contributions (CWM) |  |
| 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")
| # | Seqlets | Forward | Reverse |
|---|---|---|---|
| 1 | 5311 |  |  |
| 2 | 4173 |  |  |
| 3 | 3182 |  |  |
| 4 | 2440 |  |  |
| 5 | 291 |  |  |
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")
| Motif ID | q-val | PWM |
|---|---|---|
| MA0104.4_MYCN | 0.000365323 |  |
| MYCN_HUMAN.H11MO.0.A | 0.000365323 |  |
| CR3L1_HUMAN.H11MO.0.D | 0.000617383 |  |
| MA0147.3_MYC | 0.00190819 |  |
| MYC_HUMAN.H11MO.0.A | 0.00241784 |  |
| MA0608.1_Creb3l2 | 0.00431983 | Not shown |
| MA0004.1_Arnt | 0.00711176 | Not shown |
| BMAL1_HUMAN.H11MO.0.A | 0.00942644 | Not shown |
| MA1099.2_HES1 | 0.0127363 | Not shown |
| HEY2_HUMAN.H11MO.0.D | 0.0127363 | Not shown |
| Motif ID | q-val | PWM |
|---|---|---|
| CTCFL_HUMAN.H11MO.0.A | 1.96712e-07 |  |
| MA1102.2_CTCFL | 1.86857e-06 |  |
| CTCF_HUMAN.H11MO.0.A | 6.79225e-06 |  |
| MA0139.1_CTCF | 4.78754e-05 |  |
| MA0830.2_TCF4 | 0.0346763 |  |
| SP2_HUMAN.H11MO.0.A | 0.052885400000000006 | Not shown |
| MA0155.1_INSM1 | 0.052885400000000006 | Not shown |
| KLF8_HUMAN.H11MO.0.C | 0.052885400000000006 | Not shown |
| PLAL1_HUMAN.H11MO.0.D | 0.052885400000000006 | Not shown |
| AP2B_HUMAN.H11MO.0.B | 0.053736400000000004 | Not shown |
| Motif ID | q-val | PWM |
|---|---|---|
| MA0632.2_TCFL5 | 0.16930599999999998 |  |
| MA1099.2_HES1 | 0.16930599999999998 |  |
| MA0506.1_NRF1 | 0.16930599999999998 |  |
| MA1560.1_SOHLH2 | 0.16930599999999998 |  |
| MA0616.2_HES2 | 0.16930599999999998 |  |
| MA0825.1_MNT | 0.16930599999999998 | Not shown |
| MA0259.1_ARNT::HIF1A | 0.16930599999999998 | Not shown |
| MA0822.1_HES7 | 0.16930599999999998 | Not shown |
| MA0058.3_MAX | 0.16930599999999998 | Not shown |
| HES7_HUMAN.H11MO.0.D | 0.16930599999999998 | Not shown |
| Motif ID | q-val | PWM |
|---|---|---|
| MA1108.2_MXI1 | 0.00136268 |  |
| MA0104.4_MYCN | 0.0183803 | |
| MA0668.1_NEUROD2 | 0.0183803 |  |
| MA0147.3_MYC | 0.0183803 | |
| MYC_HUMAN.H11MO.0.A | 0.0200685 | |
| MA0058.3_MAX | 0.0248434 | Not shown |
| MA0059.1_MAX::MYC | 0.027085700000000004 | Not shown |
| MA1568.1_TCF21(var.2) | 0.027085700000000004 | Not shown |
| MA1638.1_HAND2 | 0.027085700000000004 | Not shown |
| MA1524.1_MSGN1 | 0.0300075 | Not shown |
| Motif ID | q-val | PWM |
|---|---|---|
| MA0139.1_CTCF | 3.78859e-09 | |
| CTCF_HUMAN.H11MO.0.A | 3.78859e-09 | |
| CTCFL_HUMAN.H11MO.0.A | 7.194060000000001e-05 | |
| MA1102.2_CTCFL | 0.00504387 | |
| SNAI1_HUMAN.H11MO.0.C | 0.0380903 |  |
| MA1638.1_HAND2 | 0.158864 | Not shown |
| MA1568.1_TCF21(var.2) | 0.158864 | Not shown |
| ZIC3_HUMAN.H11MO.0.B | 0.19274000000000002 | Not shown |
| ZIC2_HUMAN.H11MO.0.D | 0.219427 | Not shown |
| MA1648.1_TCF12(var.2) | 0.275124 | Not shown |