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_fold3/SPI1_multitask_profile_fold3_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/SPI1_multitask_profile_fold3/SPI1_multitask_profile_fold3_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/SPI1_multitask_profile_fold3/SPI1_multitask_profile_fold3_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%|██████████| 194/194 [04:24<00:00,  1.36s/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 1/7

12688 seqlets

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

Pattern 2/7

287 seqlets

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

Pattern 3/7

273 seqlets

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

Pattern 4/7

244 seqlets

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

Pattern 5/7

86 seqlets

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

Pattern 6/7

73 seqlets

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

Pattern 7/7

32 seqlets

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

Metacluster 2/2

Pattern 1/11

149 seqlets

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

Pattern 2/11

98 seqlets

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

Pattern 3/11

90 seqlets

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

Pattern 4/11

77 seqlets

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

Pattern 5/11

72 seqlets

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

Pattern 6/11

62 seqlets

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

Pattern 7/11

60 seqlets

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

Pattern 8/11

46 seqlets

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

Pattern 9/11

38 seqlets

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

Pattern 10/11

34 seqlets

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

Pattern 11/11

33 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
112688
2287
3273
4244
586
673
732

Metacluster 2/2

/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
1149
298
390
477
572
662
760
846
938
1034
1133

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 1/7

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A3.99215e-17
MA0081.2_SPIB1.9036900000000003e-14
SPI1_HUMAN.H11MO.0.A5.08536e-13
BC11A_HUMAN.H11MO.0.A4.8508800000000004e-12
MA0080.5_SPI12.9462099999999997e-10
IRF4_HUMAN.H11MO.0.A3.29395e-10Not shown
IRF8_HUMAN.H11MO.0.B3.86044e-09Not shown
MA0761.2_ETV16.9193e-05Not shown
MA0062.3_GABPA0.00010594100000000001Not shown
ETV5_HUMAN.H11MO.0.C0.0005740519999999999Not shown

Motif 2/7

Motif IDq-valPWM
MA0483.1_Gfi1b0.18443099999999998
GFI1_HUMAN.H11MO.0.C0.18443099999999998
MA0038.2_GFI10.18443099999999998

Motif 3/7

Motif IDq-valPWM
SPDEF_HUMAN.H11MO.0.D0.262254
MA0765.2_ETV50.262254
ETV1_HUMAN.H11MO.0.A0.262254
MA0640.2_ELF30.262254
MA0062.3_GABPA0.262254
MA0473.3_ELF10.262254Not shown
MA0760.1_ERF0.262254Not shown
MA0156.2_FEV0.262254Not shown
MA0641.1_ELF40.262254Not shown
ELK4_HUMAN.H11MO.0.A0.262254Not shown

Motif 4/7

Motif IDq-valPWM
MA0081.2_SPIB4.25691e-06
BC11A_HUMAN.H11MO.0.A4.25691e-06
SPIB_HUMAN.H11MO.0.A4.25691e-06
SPI1_HUMAN.H11MO.0.A9.22246e-06
MA0080.5_SPI10.000130753
IRF4_HUMAN.H11MO.0.A0.000960725Not shown
IRF8_HUMAN.H11MO.0.B0.0022215Not shown
MA0687.1_SPIC0.00283513Not shown
MA0508.3_PRDM10.025763799999999996Not shown
ETV5_HUMAN.H11MO.0.C0.025763799999999996Not shown

Motif 5/7

Motif IDq-valPWM
ZFP82_HUMAN.H11MO.0.C0.0404069
CPEB1_HUMAN.H11MO.0.D0.0404069
MA0080.5_SPI10.0864266
ONEC2_HUMAN.H11MO.0.D0.0864266
IRF8_HUMAN.H11MO.0.B0.08855969999999999
BC11A_HUMAN.H11MO.0.A0.21793099999999999Not shown
IRF5_HUMAN.H11MO.0.D0.21793099999999999Not shown
MA0081.2_SPIB0.21793099999999999Not shown
IRF4_HUMAN.H11MO.0.A0.34609Not shown
SPIB_HUMAN.H11MO.0.A0.358189Not shown

Motif 6/7

Motif IDq-valPWM
MA0645.1_ETV60.00258627
ELK1_HUMAN.H11MO.0.B0.00258627
MA0763.1_ETV30.00258627
MA0474.2_ERG0.00258627
MA0028.2_ELK10.00258627
MA0760.1_ERF0.00258627Not shown
MA0081.2_SPIB0.00258627Not shown
MA0098.3_ETS10.00258627Not shown
MA0475.2_FLI10.00258627Not shown
MA0156.2_FEV0.00263006Not shown

Motif 7/7

Motif IDq-valPWM
IRF8_HUMAN.H11MO.0.B0.000198706
IRF4_HUMAN.H11MO.0.A0.000576017
BC11A_HUMAN.H11MO.0.A0.000576017
SPI1_HUMAN.H11MO.0.A0.000625611
SPIB_HUMAN.H11MO.0.A0.000625611
MA0081.2_SPIB0.00090889Not shown
MA0080.5_SPI10.00092354Not shown
IRF3_HUMAN.H11MO.0.B0.0014548Not shown
ETS2_HUMAN.H11MO.0.B0.00175791Not shown
GABPA_HUMAN.H11MO.0.A0.00286724Not shown

Metacluster 2/2

Motif 1/11

No TOMTOM matches passing threshold

Motif 2/11

Motif IDq-valPWM
MA0659.2_MAFG0.41221199999999997

Motif 3/11

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A1.9224299999999997e-08
MA0081.2_SPIB1.9224299999999997e-08
BC11A_HUMAN.H11MO.0.A3.20228e-08
SPI1_HUMAN.H11MO.0.A4.7779300000000004e-08
IRF4_HUMAN.H11MO.0.A2.7421e-07
MA0080.5_SPI12.93796e-07Not shown
IRF8_HUMAN.H11MO.0.B7.01841e-07Not shown
MA0598.3_EHF0.000154986Not shown
MA0062.3_GABPA0.000154986Not shown
MA0761.2_ETV10.00017687400000000001Not shown

Motif 4/11

Motif IDq-valPWM
TLX1_HUMAN.H11MO.0.D0.455003
IRX2_HUMAN.H11MO.0.D0.455003

Motif 5/11

Motif IDq-valPWM
SPI1_HUMAN.H11MO.0.A4.873810000000001e-09
SPIB_HUMAN.H11MO.0.A4.873810000000001e-09
BC11A_HUMAN.H11MO.0.A3.6175699999999996e-08
MA0081.2_SPIB6.04974e-08
IRF4_HUMAN.H11MO.0.A3.55865e-07
IRF8_HUMAN.H11MO.0.B3.81284e-07Not shown
MA0080.5_SPI11.19266e-06Not shown
MA0598.3_EHF0.0011110999999999998Not shown
MA0062.3_GABPA0.00128809Not shown
MA0761.2_ETV10.00129145Not shown

Motif 6/11

No TOMTOM matches passing threshold

Motif 7/11

No TOMTOM matches passing threshold

Motif 8/11

No TOMTOM matches passing threshold

Motif 9/11

No TOMTOM matches passing threshold

Motif 10/11

No TOMTOM matches passing threshold

Motif 11/11

Motif IDq-valPWM
MA0814.2_TFAP2C(var.2)0.015040799999999998
MA0146.2_Zfx0.015040799999999998
PLAL1_HUMAN.H11MO.0.D0.23864499999999997
SP2_HUMAN.H11MO.0.A0.247336
KLF5_HUMAN.H11MO.0.A0.256173
ZF64A_HUMAN.H11MO.0.D0.256173Not shown
CTCFL_HUMAN.H11MO.0.A0.256173Not shown
MA1628.1_Zic1::Zic20.256173Not shown
MA0163.1_PLAG10.256173Not shown
ZFX_HUMAN.H11MO.1.A0.256173Not shown