Spaces:
Runtime error
Runtime error
File size: 31,099 Bytes
bcd1195 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 | """
Gene Process Dependency Explorer
"""
import pathlib
import textwrap
import matplotlib.pyplot as plt
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go
import streamlit as st
from app_utils import (
latent_load_data,
make_radar,
spider_load_data,
)
BASE_DIR = pathlib.Path(__file__).parent
# ββ Page config βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
st.set_page_config(
page_title="Gene Process Dependency Explorer",
page_icon="π§¬",
layout="wide",
initial_sidebar_state="collapsed",
)
# ββ Styling βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
st.markdown(
"""
<style>
@import url('https://fonts.googleapis.com/css2?family=IBM+Plex+Mono:wght@400;600&family=IBM+Plex+Sans:wght@300;400;600&display=swap');
html, body, [class*="css"] { font-family: 'IBM Plex Sans', sans-serif; }
.stApp { background: #0d1117; color: #e6edf3; }
.metric-card {
background: #161b22;
border: 1px solid #30363d;
border-radius: 8px;
padding: 16px 20px;
margin-bottom: 8px;
}
.metric-label { font-size: 11px; color: #8b949e; text-transform: uppercase; letter-spacing: 1px; }
.metric-value { font-size: 28px; font-weight: 600; color: #58a6ff; font-family: 'IBM Plex Mono', monospace; }
.control-panel {
background: #161b22;
border: 1px solid #21262d;
border-radius: 8px;
padding: 16px 20px;
margin-bottom: 20px;
}
.control-label {
font-size: 11px;
color: #8b949e;
font-family: 'IBM Plex Mono', monospace;
text-transform: uppercase;
letter-spacing: 0.5px;
margin-bottom: 4px;
}
h1, h2, h3 { font-family: 'IBM Plex Mono', monospace !important; }
h1 { color: #58a6ff !important; font-size: 1.6rem !important; }
h2 { color: #79c0ff !important; font-size: 1.1rem !important; }
h3 { color: #cdd9e5 !important; font-size: 0.95rem !important; }
.section-tag {
display: inline-block;
background: #1f2937;
border: 1px solid #30363d;
border-radius: 4px;
padding: 2px 8px;
font-size: 11px;
font-family: 'IBM Plex Mono', monospace;
color: #8b949e;
margin-bottom: 12px;
}
.stTabs [data-baseweb="tab-list"] { gap: 8px; }
.stTabs [data-baseweb="tab"] {
background: #161b22;
border: 1px solid #30363d;
border-radius: 6px;
color: #8b949e;
font-family: 'IBM Plex Mono', monospace;
font-size: 12px;
padding: 6px 16px;
}
.stTabs [aria-selected="true"] {
background: #1f6feb !important;
border-color: #1f6feb !important;
color: #ffffff !important;
}
</style>
""",
unsafe_allow_html=True,
)
# ββ Header ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
st.markdown("# Gene Process Dependency Explorer")
st.markdown(
'<span class="section-tag">DepMap Β· BioBombe Β· WayScience</span>',
unsafe_allow_html=True,
)
# ββ Load only the tiny model metadata file at startup (188 KB) ββββββββββββββββ
_model_meta = pd.read_parquet(
BASE_DIR / "data" / "Model.parquet",
columns=["ModelID", "OncotreePrimaryDisease"],
)
ALL_DISEASES = sorted(_model_meta["OncotreePrimaryDisease"].dropna().unique().tolist())
ALL_MODEL_IDS = sorted(_model_meta["ModelID"].dropna().unique().tolist())
DEFAULT_MODEL_IDS = ["ACH-000323", "ACH-002083", "ACH-002228"]
single_gene_pca_df = pd.read_parquet(
BASE_DIR / "data" / "pca_embeddings_single_dependencies.parquet"
)
latent_reactome_pca_df = pd.read_parquet(
BASE_DIR / "data" / "pca_embeddings_latent_reactome.parquet"
)
latent_corum_pca_df = pd.read_parquet(
BASE_DIR / "data" / "pca_embeddings_latent_corum.parquet"
)
latent_drug_pca_df = pd.read_parquet(
BASE_DIR / "data" / "pca_embeddings_latent_drug.parquet"
)
# ββ Tabs ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
(
tab_welcome,
tab_single,
tab_latent,
tab_spider,
tab_scores,
tab_table,
) = st.tabs(
[
"π Welcome",
"π Single dependency plots",
"π Latent plots",
"π· Spider plots",
"π Top scores",
"π Data table",
]
)
# ββ Helpers βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def disease_controls(key_prefix: str, default_all: bool = True) -> list[str]:
"""Render an All / None button pair + multiselect for disease filtering."""
st.markdown(
'<div class="control-label">Primary diseases</div>', unsafe_allow_html=True
)
ca, cn = st.columns(2)
if ca.button("All", key=f"{key_prefix}_dis_all", use_container_width=True):
st.session_state[f"{key_prefix}_diseases"] = ALL_DISEASES
if cn.button("None", key=f"{key_prefix}_dis_none", use_container_width=True):
st.session_state[f"{key_prefix}_diseases"] = []
return st.multiselect(
"Primary diseases",
ALL_DISEASES,
default=st.session_state.get(
f"{key_prefix}_diseases", ALL_DISEASES if default_all else []
),
label_visibility="collapsed",
key=f"{key_prefix}_diseases",
)
def model_id_controls(key_prefix: str) -> list[str]:
"""Render All / None / Default buttons + multiselect for ModelID filtering."""
st.markdown('<div class="control-label">Model IDs</div>', unsafe_allow_html=True)
ca, cn, cd = st.columns(3)
if ca.button("All", key=f"{key_prefix}_mod_all", use_container_width=True):
st.session_state[f"{key_prefix}_model_ids"] = ALL_MODEL_IDS
if cn.button("None", key=f"{key_prefix}_mod_none", use_container_width=True):
st.session_state[f"{key_prefix}_model_ids"] = []
if cd.button("Default", key=f"{key_prefix}_mod_default", use_container_width=True):
st.session_state[f"{key_prefix}_model_ids"] = DEFAULT_MODEL_IDS
return st.multiselect(
"Model IDs",
ALL_MODEL_IDS,
default=st.session_state.get(f"{key_prefix}_model_ids", DEFAULT_MODEL_IDS),
label_visibility="collapsed",
key=f"{key_prefix}_model_ids",
)
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 0 β Intro text
# ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_welcome:
st.markdown("## Welcome to the Gene Process Dependency Explorer")
st.markdown(
"This app allows you to explore gene process dependencies across different cancer types and model IDs."
)
st.markdown(
"We are visualizing latent representations of gene dependencies learned by a compression model trained on DepMap data, with biological processes as features."
)
st.markdown(
"For more details on the data and methods, please see our github repository: https://github.com/WayScience/gene-process-dependencies"
)
st.markdown(
"For more information about the group, please visit the WayScience website: https://wayscience.com"
)
st.markdown("---")
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 1 β Single dependency plots
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_single:
st.markdown("### Latent Space PCA β single dependency")
st.markdown(
"PCA projection of raw gene dependency scores. "
"Each point is a cancer cell line; colour encodes primary disease."
)
with st.container():
st.markdown('<div class="control-panel">', unsafe_allow_html=True)
selected_diseases_single = disease_controls("single")
st.markdown("</div>", unsafe_allow_html=True)
cancer_types = single_gene_pca_df["OncotreePrimaryDisease"].unique()
color_map = (
px.colors.qualitative.Plotly
+ px.colors.qualitative.Light24
+ px.colors.qualitative.Dark24
)
highlight_color_map = {
c: color_map[i % len(color_map)] for i, c in enumerate(cancer_types)
}
traces = []
for cancer in cancer_types:
df_sub = single_gene_pca_df[
single_gene_pca_df["OncotreePrimaryDisease"] == cancer
]
is_selected = cancer in selected_diseases_single
traces.append(
go.Scatter(
x=df_sub["PCA1"],
y=df_sub["PCA2"],
mode="markers",
name=cancer,
marker=dict(
size=7,
color=highlight_color_map[cancer] if is_selected else "#3d444d",
opacity=1.0 if is_selected else 0.3,
),
text=[f"{cancer} | {m}" for m in df_sub["ModelID"]],
hoverinfo="text" if is_selected else "skip",
showlegend=is_selected,
)
)
# Render grayed traces behind colored ones
traces.sort(key=lambda t: t.name in selected_diseases_single, reverse=True)
fig_single = go.Figure(data=traces)
fig_single.update_layout(
paper_bgcolor="#0d1117",
plot_bgcolor="#0d1117",
font=dict(color="#e6edf3"),
xaxis=dict(gridcolor="#21262d"),
yaxis=dict(gridcolor="#21262d"),
legend=dict(bgcolor="#161b22", bordercolor="#30363d", borderwidth=1),
height=1200,
margin=dict(l=40, r=40, t=40, b=40),
width=800,
)
st.plotly_chart(fig_single, use_container_width=True)
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 2 β Latent plots
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_latent:
st.markdown("### Latent Space PCA Projections")
st.markdown(
"PCA projection of latent representations learned by the selected compression model. "
"Each point is a cancer cell line; clusters indicate similar gene dependency profiles."
)
with st.container():
st.markdown('<div class="control-panel">', unsafe_allow_html=True)
selected_diseases_latent = disease_controls("latent")
st.markdown("</div>", unsafe_allow_html=True)
for title, pca_df in [
("Reactome", latent_reactome_pca_df),
("CORUM", latent_corum_pca_df),
("Drug", latent_drug_pca_df),
]:
st.markdown(f"#### PCA: {title} Subset")
cancer_types = pca_df["OncotreePrimaryDisease"].unique()
color_map = (
px.colors.qualitative.Plotly
+ px.colors.qualitative.Light24
+ px.colors.qualitative.Dark24
)
highlight_color_map = {
c: color_map[i % len(color_map)] for i, c in enumerate(cancer_types)
}
traces = []
for cancer in cancer_types:
df_sub = pca_df[pca_df["OncotreePrimaryDisease"] == cancer]
is_selected = cancer in selected_diseases_latent
traces.append(
go.Scatter(
x=df_sub["PCA1"],
y=df_sub["PCA2"],
mode="markers",
name=cancer,
marker=dict(
size=7,
color=highlight_color_map[cancer] if is_selected else "#3d444d",
opacity=1.0 if is_selected else 0.3,
),
text=[f"{cancer} | {m}" for m in df_sub["ModelID"]],
hoverinfo="text" if is_selected else "skip",
showlegend=is_selected,
)
)
traces.sort(key=lambda t: t.name in selected_diseases_latent, reverse=True)
fig = go.Figure(data=traces)
fig.update_layout(
paper_bgcolor="#0d1117",
plot_bgcolor="#0d1117",
font=dict(color="#e6edf3"),
xaxis=dict(gridcolor="#21262d"),
yaxis=dict(gridcolor="#21262d"),
legend=dict(bgcolor="#161b22", bordercolor="#30363d", borderwidth=1),
height=600,
margin=dict(l=40, r=40, t=40, b=40),
)
st.plotly_chart(fig, use_container_width=True)
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 3 β Spider plots
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_spider:
st.markdown("### Biological Process Dependency Profiles β Spider Plots")
st.markdown(
"Mean dependency score per biological process category for selected cell lines. "
"Negative scores indicate stronger dependencies (essential genes)."
)
with st.container():
st.markdown('<div class="control-panel">', unsafe_allow_html=True)
sp_c1, sp_c2, sp_c3 = st.columns(3)
with sp_c1:
spider_filter_mode = st.radio(
"Filter by",
["Model IDs", "Cancer Types"],
horizontal=True,
key="spider_filter_mode",
)
with sp_c2:
if spider_filter_mode == "Model IDs":
st.markdown(
'<div class="control-label">Model IDs (max 10)</div>',
unsafe_allow_html=True,
)
spider_model_ids = st.multiselect(
"Model IDs",
ALL_MODEL_IDS,
default=st.session_state.get("spider_model_ids", DEFAULT_MODEL_IDS),
max_selections=10,
label_visibility="collapsed",
key="spider_model_ids",
)
else:
st.markdown(
'<div class="control-label">Cancer Types (max 5)</div>',
unsafe_allow_html=True,
)
spider_cancer_types = st.multiselect(
"Cancer Types",
ALL_DISEASES,
default=st.session_state.get(
"spider_cancer_types", ALL_DISEASES[:2]
),
max_selections=5,
label_visibility="collapsed",
key="spider_cancer_types",
)
st.markdown(
'<div class="control-label">Aggregation</div>',
unsafe_allow_html=True,
)
spider_agg = st.radio(
"Aggregation",
["Mean", "Min", "Max"],
horizontal=True,
key="spider_agg",
label_visibility="collapsed",
)
with sp_c3:
st.markdown(
'<div class="control-label">Process limit</div>', unsafe_allow_html=True
)
limit_processes = st.toggle(
"Limit axes", value=False, key="spider_limit_toggle"
)
if limit_processes:
max_processes = st.slider(
"Max processes per plot",
min_value=3,
max_value=50,
value=20,
step=1,
key="spider_max_proc",
label_visibility="collapsed",
)
else:
max_processes = None
st.markdown("</div>", unsafe_allow_html=True)
dfs, global_max, feature_colnames = spider_load_data()
if spider_filter_mode == "Model IDs":
selected_ids = spider_model_ids
id_col = "ModelID"
else:
selected_ids = (
spider_cancer_types
if "spider_cancer_types" in st.session_state or True
else []
)
id_col = "OncotreePrimaryDisease"
agg_func = {"Mean": "mean", "Min": "min", "Max": "max"}[spider_agg]
if len(selected_ids) == 0:
st.warning(
"Please select at least one model ID or cancer type to display the plots."
)
else:
fig_spider, axes = plt.subplots(
3, 1, figsize=(18, 12), subplot_kw=dict(polar=True)
)
for ax, (title, df) in zip(axes, dfs.items()):
cols = feature_colnames[title]
if spider_filter_mode == "Cancer Types":
df_filtered = df[df["OncotreePrimaryDisease"].isin(selected_ids)].copy()
# cols from feature_colnames[title] is the correct feature column list
feature_cols = list(cols) if not isinstance(cols, list) else cols
st.write("feature_colnames:", feature_colnames)
df_agg = (
df_filtered.groupby("OncotreePrimaryDisease")[feature_cols]
.agg(agg_func)
.reset_index()
.rename(columns={"OncotreePrimaryDisease": "ModelID"})
)
# Melt to long format β use a fixed string for var_name
df_long = df_agg.melt(
id_vars="ModelID",
value_vars=feature_cols,
var_name="feature", # fixed string, not cols
value_name="agg_score",
)
make_radar(
ax,
df_long,
"feature", # must match var_name above
f"{title} ({spider_agg})",
global_max,
score_col="agg_score",
model_ids=selected_ids,
max_processes=max_processes,
)
else:
df_filtered = df[df["ModelID"].isin(selected_ids)].copy()
make_radar(
ax,
df_filtered,
cols,
title,
global_max,
model_ids=selected_ids,
max_processes=max_processes,
)
handles, labels = axes[0].get_legend_handles_labels()
fig_spider.legend(
handles,
labels,
loc="lower center",
ncol=3,
fontsize=12,
frameon=False,
bbox_to_anchor=(0.5, -0.05),
)
plt.tight_layout(rect=[0, 0, 1, 0.95])
st.pyplot(fig_spider)
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 4 β Top scores
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_scores:
st.markdown("### Top Dependency Scores")
st.markdown(
"Highest-scoring biological processes across cancer types and individual cell lines."
)
reactome_matrix, corum_matrix, drug_matrix = latent_load_data()
all_matrices = {
"Reactome": reactome_matrix,
"CORUM": corum_matrix,
"Drug": drug_matrix,
}
with st.container():
st.markdown('<div class="control-panel">', unsafe_allow_html=True)
ctl1, ctl2, ctl3, ctl4, ctl5 = st.columns(5)
with ctl1:
selected_diseases_scores = disease_controls("scores")
with ctl2:
scores_dataset = st.selectbox(
"Dataset",
options=["Reactome", "CORUM", "Drug"],
key="scores_dataset",
)
with ctl3:
top_n_scores = st.slider(
"Top N processes",
min_value=3,
max_value=50,
value=15,
step=1,
key="scores_top_n",
)
with ctl4:
top_m_types = st.slider(
"Top M cancer types",
min_value=1,
max_value=len(selected_diseases_scores),
value=8,
step=1,
key="scores_top_m",
)
with ctl5:
top_i_models = st.slider(
"Top I model IDs",
min_value=1,
max_value=30,
value=8,
step=1,
key="scores_top_i",
)
st.markdown("</div>", unsafe_allow_html=True)
score_df = all_matrices[scores_dataset].copy()
score_df = score_df[
score_df["OncotreePrimaryDisease"].isin(selected_diseases_scores)
]
meta_cols = ["ModelID", "OncotreePrimaryDisease"]
score_cols = [c for c in score_df.columns if c not in meta_cols]
# ββ Heatmap: cancer types βββββββββββββββββββββββββββββββββββββββββ
st.markdown("---")
st.markdown("#### By cancer type")
st.markdown(
"Mean dependency score per process averaged across all cell lines in each cancer type. "
"Top N processes by max mean score across shown cancer types."
)
disease_means = (
score_df.groupby("OncotreePrimaryDisease")[score_cols].mean().reset_index()
)
disease_means["_max"] = disease_means[score_cols].max(axis=1)
top_diseases = disease_means.nlargest(top_m_types, "_max")[
"OncotreePrimaryDisease"
].tolist()
disease_means = disease_means[
disease_means["OncotreePrimaryDisease"].isin(top_diseases)
].drop(columns=["_max"])
top_processes = (
disease_means[score_cols].max(axis=0).nlargest(top_n_scores).index.tolist()
)
heatmap_disease = disease_means.set_index("OncotreePrimaryDisease")[top_processes]
fig_disease = go.Figure(
go.Heatmap(
z=heatmap_disease.values,
x=[
textwrap.shorten(p, width=30, placeholder="β¦")
for p in heatmap_disease.columns
],
y=heatmap_disease.index.tolist(),
colorscale="Blues",
hovertemplate="Disease: %{y}<br>Process: %{x}<br>Score: %{z:.3f}<extra></extra>",
colorbar=dict(title="Mean score", thickness=14, len=0.6),
)
)
fig_disease.update_layout(
height=max(300, top_m_types * 36 + 120),
margin=dict(l=20, r=20, t=30, b=120),
paper_bgcolor="#0d1117",
plot_bgcolor="#0d1117",
font=dict(color="#e6edf3", size=11),
xaxis=dict(tickangle=-40, gridcolor="#21262d"),
yaxis=dict(gridcolor="#21262d"),
)
st.plotly_chart(fig_disease, use_container_width=True)
# ββ Heatmap: model IDs ββββββββββββββββββββββββββββββββββββββββββββ
st.markdown("---")
st.markdown("#### By model ID")
st.markdown(
"Raw dependency score per process for individual cell lines ranked by peak score."
)
score_df["_max"] = score_df[score_cols].max(axis=1)
top_models = score_df.nlargest(top_i_models, "_max")["ModelID"].tolist()
score_df = score_df.drop(columns=["_max"])
model_df = score_df[score_df["ModelID"].isin(top_models)].set_index("ModelID")[
top_processes
]
fig_model = go.Figure(
go.Heatmap(
z=model_df.values,
x=[
textwrap.shorten(p, width=30, placeholder="β¦") for p in model_df.columns
],
y=model_df.index.tolist(),
colorscale="Purples",
hovertemplate="Model: %{y}<br>Process: %{x}<br>Score: %{z:.3f}<extra></extra>",
colorbar=dict(title="Score", thickness=14, len=0.6),
)
)
fig_model.update_layout(
height=max(300, top_i_models * 36 + 120),
margin=dict(l=20, r=20, t=30, b=120),
paper_bgcolor="#0d1117",
plot_bgcolor="#0d1117",
font=dict(color="#e6edf3", size=11),
xaxis=dict(tickangle=-40, gridcolor="#21262d"),
yaxis=dict(gridcolor="#21262d"),
)
st.plotly_chart(fig_model, use_container_width=True)
# ββ Bar charts ββββββββββββββββββββββββββββββββββββββββββββββββββββ
st.markdown("---")
st.markdown("#### Overall top processes")
st.markdown("Global mean score per process across all filtered cell lines, ranked.")
overall_means = score_df[score_cols].mean().nlargest(top_n_scores).reset_index()
overall_means.columns = ["Process", "Mean Score"]
overall_means["Process"] = overall_means["Process"].apply(
lambda p: textwrap.shorten(p, width=40, placeholder="β¦")
)
bar1, bar2 = st.columns(2)
_bar_layout = dict(
margin=dict(l=10, r=10, t=40, b=20),
paper_bgcolor="#0d1117",
plot_bgcolor="#0d1117",
font=dict(color="#e6edf3", size=11),
yaxis=dict(autorange="reversed", gridcolor="#21262d"),
xaxis=dict(gridcolor="#21262d"),
coloraxis_showscale=False,
showlegend=False,
)
with bar1:
fig_bar_all = px.bar(
overall_means,
x="Mean Score",
y="Process",
orientation="h",
title="Top processes β all cell lines",
color="Mean Score",
color_continuous_scale="Blues",
)
fig_bar_all.update_layout(
height=max(300, top_n_scores * 24 + 80), **_bar_layout
)
st.plotly_chart(fig_bar_all, use_container_width=True)
with bar2:
top_disease_means = (
score_df[score_df["OncotreePrimaryDisease"].isin(top_diseases)][score_cols]
.mean()
.nlargest(top_n_scores)
.reset_index()
)
top_disease_means.columns = ["Process", "Mean Score"]
top_disease_means["Process"] = top_disease_means["Process"].apply(
lambda p: textwrap.shorten(p, width=40, placeholder="β¦")
)
fig_bar_top = px.bar(
top_disease_means,
x="Mean Score",
y="Process",
orientation="h",
title=f"Top processes β top {top_m_types} cancer types",
color="Mean Score",
color_continuous_scale="Purples",
)
fig_bar_top.update_layout(
height=max(300, top_n_scores * 24 + 80), **_bar_layout
)
st.plotly_chart(fig_bar_top, use_container_width=True)
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# TAB 5 β Data table
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
with tab_table:
st.markdown("### Cancer Types & Primary Diseases")
st.markdown("Summary of all cancer types and their associated primary diseases.")
with st.container():
st.markdown('<div class="control-panel">', unsafe_allow_html=True)
selected_diseases_table = disease_controls("table")
st.markdown("</div>", unsafe_allow_html=True)
reactome_matrix, _, _ = latent_load_data()
full_df = reactome_matrix[
reactome_matrix["OncotreePrimaryDisease"].isin(selected_diseases_table)
]
summary = (
full_df.groupby(["OncotreePrimaryDisease", "ModelID"], dropna=False)
.size()
.reset_index(name="_n")
.drop(columns=["_n"])
.drop_duplicates()
.rename(columns={"OncotreePrimaryDisease": "Primary Disease"})
.sort_values(["Primary Disease", "ModelID"])
)
m1, m2 = st.columns(2)
m1.markdown(
f'<div class="metric-card"><div class="metric-label">Primary diseases</div><div class="metric-value">{summary["Primary Disease"].nunique()}</div></div>',
unsafe_allow_html=True,
)
m2.markdown(
f'<div class="metric-card"><div class="metric-label">Total cell lines</div><div class="metric-value">{int(summary["ModelID"].nunique())}</div></div>',
unsafe_allow_html=True,
)
st.markdown("")
sc1, sc2 = st.columns([3, 1])
with sc1:
sort_by = st.selectbox(
"Sort by", options=summary.columns.tolist(), index=0, key="table_sort_col"
)
with sc2:
sort_asc = st.radio(
"Order",
["Ascending", "Descending"],
index=0,
horizontal=True,
key="table_sort_dir",
)
summary = summary.sort_values(sort_by, ascending=(sort_asc == "Ascending"))
st.dataframe(
summary.reset_index(drop=True),
use_container_width=True,
height=560,
column_config={
"Primary Disease": st.column_config.TextColumn(width="large"),
"ModelID": st.column_config.TextColumn("Model ID", width="large"),
},
hide_index=True,
)
st.download_button(
label="β¬ Download as CSV",
data=summary.to_csv(index=False).encode("utf-8"),
file_name="cancer_types_diseases.csv",
mime="text/csv",
key="table_download",
)
|