Link to results

DiChIPMunk: on peaks and on multi-task seqlets and on single-task seqlets

HOMER: on peaks and on multi-task seqlets and on single-task seqlets

MEME: on peaks and on multitask seqlets and on single-task seqlets

import sys
import os
sys.path.append(os.path.abspath("/users/amtseng/tfmodisco/src/"))
from util import figure_to_vdom_image
import motif.read_motifs as read_motifs
from motif.read_motifs import pfm_to_pwm
import plot.viz_sequence as viz_sequence
import numpy as np
import matplotlib.pyplot as plt
import vdom.helpers as vdomh
from IPython.display import display

# Define parameters/fetch arguments
tf_name = os.environ["TFM_TF_NAME"]
multitask_fold = int(os.environ["TFM_MULTITASK_FOLD"])

if "TFM_TASK_INDEX" in os.environ:
    task_index = int(os.environ["TFM_TASK_INDEX"])
    singletask_fold = int(os.environ["TFM_SINGLETASK_FOLD"])
else:
    task_index = None
    singletask_fold = None
    
print("TF name: %s" % tf_name)
print("Multi-task fold: %s" % multitask_fold)
print("Task index: %s" % task_index)
print("Single-task fold: %s" % singletask_fold)

TF name: JUND
Multi-task fold: 7
Task index: 10
Single-task fold: 7

# Define paths and constants
base_path = "/users/amtseng/tfmodisco/results/classic_motifs/"

multitask_seqlets_dir = os.path.join(
    base_path, "seqlets", "multitask_profile_finetune",
    "%s_multitask_profile_finetune_fold%s" % (tf_name, multitask_fold)
)

if task_index is None:
    peaks_path = os.path.join(base_path, "peaks", tf_name, "%s_peaks_taskall" % tf_name)
    multitask_profile_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_profile_taskall" % tf_name
    )
    multitask_count_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_count_taskall" % tf_name
    )
else:
    peaks_path = os.path.join(base_path, "peaks", tf_name, "%s_peaks_task%d" % (tf_name, task_index))
    multitask_profile_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_profile_task%d" % (tf_name, task_index)
    )
    multitask_count_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_count_task%d" % (tf_name, task_index)
    )
    
    singletask_seqlets_dir = os.path.join(
        base_path, "seqlets", "singletask_profile_finetune",
        "%s_singletask_profile_finetune_fold%s" % (tf_name, singletask_fold),
        "task_%d" % task_index
    )
    singletask_profile_seqlets_path = os.path.join(
        singletask_seqlets_dir,
        "%s_seqlets_profile_task%d" % (tf_name, task_index)
    )
    singletask_count_seqlets_path = os.path.join(
        singletask_seqlets_dir,
        "%s_seqlets_count_task%d" % (tf_name, task_index)
    )

Helper functions

def show_peaks_motif_table(results_path, mode):
    """
    Shows a table of motifs from the given results path.
    `mode` is either `dichipmunk`, `homer`, `meme`, or `memechip`.
    """
    assert mode in ("dichipmunk", "homer", "meme", "memechip")
    if mode == "dichipmunk":
        score_name = "Supporting sequences"
        pfms, score_vals = read_motifs.import_dichipmunk_pfms(results_path)
    elif mode == "homer":
        score_name = "Log enrichment"
        pfms, score_vals = read_motifs.import_homer_pfms(results_path)
    elif mode == "meme":
        score_name = "E-value"
        pfms, score_vals = read_motifs.import_meme_pfms(results_path)
    else:
        score_name = "E-value"
        pfms, score_vals = read_motifs.import_meme_pfms(
            os.path.join(results_path, "meme_out")
        )
        
    colgroup = vdomh.colgroup(
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"})
    )
    header = vdomh.thead(
        vdomh.tr(
            vdomh.th("Motif", style={"text-align": "center"}),
            vdomh.th(score_name, style={"text-align": "center"}),
            vdomh.th("PWM", style={"text-align": "center"})
        )
    )

    body = []
    for i, pfm in enumerate(pfms):
        pwm = pfm_to_pwm(pfm)
        if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
            # Flip to purine-rich version
            pwm = np.flip(pwm, axis=(0, 1))
        fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
        fig.tight_layout()

        body.append(
            vdomh.tr(
                vdomh.td(str(i + 1)),
                vdomh.td(str(score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            )
        )

    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")

def show_seqlets_motif_table(profile_results_path, count_results_path, mode):
    """
    Shows a table of motifs from the given results path.
    `mode` is either `dichipmunk`, `homer`, `meme`, or `memechip`
    """
    assert mode in ("dichipmunk", "homer", "meme", "memechip")
    if mode == "dichipmunk":
        score_name = "Supporting sequences"
        p_pfms, p_score_vals = read_motifs.import_dichipmunk_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_dichipmunk_pfms(count_results_path)
    elif mode == "homer":
        score_name = "Log enrichment"
        p_pfms, p_score_vals = read_motifs.import_homer_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_homer_pfms(count_results_path)
    elif mode == "meme":
        score_name = "E-value"
        p_pfms, p_score_vals = read_motifs.import_meme_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_meme_pfms(count_results_path)
    else:
        score_name = "E-value"
        p_pfms, p_score_vals = read_motifs.import_meme_pfms(
            os.path.join(profile_results_path, "meme_out")
        )
        c_pfms, c_score_vals = read_motifs.import_meme_pfms(
            os.path.join(count_results_path, "meme_out")
        )
        
    colgroup = vdomh.colgroup(
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"})
    )
    header = vdomh.thead(
        vdomh.tr(
            vdomh.th("Motif", style={"text-align": "center"}),
            vdomh.th(score_name + " (profile)", style={"text-align": "center"}),
            vdomh.th("PWM (profile)", style={"text-align": "center"}),
            vdomh.th(score_name + " (count)", style={"text-align": "center"}),
            vdomh.th("PWM (count)", style={"text-align": "center"})
        )
    )

    body = []
    for i in range(max(len(p_pfms), len(c_pfms))):
        rows = [vdomh.td(str(i + 1))]
        if i < len(p_pfms):
            pwm = pfm_to_pwm(p_pfms[i])
            if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
                # Flip to purine-rich version
                pwm = np.flip(pwm, axis=(0, 1))
            fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
            fig.tight_layout()
            rows.extend([
                vdomh.td(str(p_score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            ])
        else:
            rows.extend([vdomh.td(), vdomh.td()])
            
        if i < len(c_pfms):
            pwm = pfm_to_pwm(c_pfms[i])
            if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
                # Flip to purine-rich version
                pwm = np.flip(pwm, axis=(0, 1))
            fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
            fig.tight_layout()
            rows.extend([
                vdomh.td(str(c_score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            ])
        else:
            rows.extend([vdomh.td(), vdomh.td()])
            

        body.append(vdomh.tr(*rows))

    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")

Show benchmark motifs

DiChIPMunk on peaks

show_peaks_motif_table(os.path.join(peaks_path, "dichipmunk"), "dichipmunk")

Motif	Supporting sequences	PWM
1	1572
2	2000
3	2000
4	1993
5	1538
6	801
7	426
8	248
9	145
10	108

DiChIPMunk on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "dichipmunk"),
    os.path.join(multitask_count_seqlets_path, "dichipmunk"),
    "dichipmunk"
)

Motif	Supporting sequences (profile)	PWM (profile)	Supporting sequences (count)	PWM (count)
1	10524		12256
2	2885		3781
3	2169		675
4	247		801
5	281

DiChIPMunk on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "dichipmunk"),
        os.path.join(singletask_count_seqlets_path, "dichipmunk"),
        "dichipmunk"
    )

Motif	Supporting sequences (profile)	PWM (profile)	Supporting sequences (count)	PWM (count)
1	9230		8768
2	4645		2568
3	1572		1588
4	118		785
5			172
6			7

HOMER on peaks

show_peaks_motif_table(os.path.join(peaks_path, "homer"), "homer")

/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)

Motif	Log enrichment	PWM
1	-33431.862277
2	-7748.855121
3	-6911.534137
4	-6759.316903
5	-5464.633324
6	-5133.331434
7	-4663.247782
8	-4075.377896
9	-4007.010862
10	-3759.692744
11	-3182.729898
12	-1975.783862
13	-1855.272085
14	-1480.221571
15	-1103.739211
16	-1053.620198
17	-1036.873272
18	-955.406692
19	-662.317328
20	-622.34558
21	-449.078735

HOMER on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "homer"),
    os.path.join(multitask_count_seqlets_path, "homer"),
    "homer"
)

Motif	Log enrichment (profile)	PWM (profile)	Log enrichment (count)	PWM (count)
1	-22448.844485		-45271.425767
2	-4244.889183		-8033.96078
3	-2013.429126		-2754.109725
4	-1773.289566		-932.024704
5	-1106.154325		-636.489599
6	-1065.805418		-499.140517
7	-676.227752		-400.91218
8	-657.719715		-215.56665
9	-651.566075		-200.128746
10	-560.253323		-132.066791
11	-500.491219		-102.672688
12	-460.279873		-98.10726
13	-440.829849		-55.513807
14	-361.319607		-34.720473
15	-333.1987
16	-313.185037
17	-269.429523
18	-99.429484
19	-81.851326
20	-35.87852

HOMER on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "homer"),
        os.path.join(singletask_count_seqlets_path, "homer"),
        "homer"
    )

Motif	Log enrichment (profile)	PWM (profile)	Log enrichment (count)	PWM (count)
1	-16487.155929		-21072.43457
2	-3347.705304		-5157.940464
3	-2732.820504		-4864.95966
4	-2535.829202		-3755.813728
5	-2087.131005		-1039.180116
6	-1064.017553		-551.320927
7	-933.36679		-411.485525
8	-798.759436		-299.90311
9	-795.105694		-138.033952
10	-426.810689		-126.705459
11	-368.94054		-118.232926
12	-368.94054
13	-257.840537
14	-247.074638
15	-226.247217
16	-220.476244
17	-162.103461
18	-156.50986
19	-28.630218

MEMEChIP on peaks

show_peaks_motif_table(os.path.join(peaks_path, "memechip"), "memechip")

Motif	E-value	PWM
1	0.0
2	1.1e-169
3	4.4e-64
4	2.3e-45
5	5e-45
6	1.8e-40
7	6.6e-21
8	2.5e-14
9	1.6e-05
10	0.0091

MEME on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "meme"),
    os.path.join(multitask_count_seqlets_path, "meme"),
    "meme"
)

Motif	E-value (profile)	PWM (profile)	E-value (count)	PWM (count)
1	0.0		0.0
2	3.3e-116		3.7e-205
3	6e-83		0.00036
4	2.5e-34		15000.0
5	5.4e-20		150000.0
6	2.6e-17		2100000.0
7	0.0001		2100000.0
8	10.0		2700000.0
9	26.0		4100000.0
10	170.0		4600000.0

MEME on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "meme"),
        os.path.join(singletask_count_seqlets_path, "meme"),
        "meme"
    )

Motif	E-value (profile)	PWM (profile)	E-value (count)	PWM (count)
1	0.0		0.0
2	1e-118		4.2e-164
3	5.8e-78		7.2e-152
4	9.2e-78		1.3e-138
5	5e-37		2.1e-13
6	8.9e-32		0.17
7	4.9e-09		2.5
8	0.48		2200.0
9	44.0		30000.0
10	60.0		160000.0