Skip to content

Commit 6948900

Browse files
committed
Update sidechainnet data storage URLs.
1 parent 0f573ae commit 6948900

File tree

2 files changed

+45
-81
lines changed

2 files changed

+45
-81
lines changed

sidechainnet/utils/download.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -646,9 +646,9 @@ def download_complete_proteinnet(user_dir=None):
646646
"sidechainnet", "resources/proteinnet_parsed.zip")
647647

648648
if not os.path.isdir(os.path.join(dir_path, "proteinnet_parsed", "targets")):
649-
print("Downloading pre-parsed ProteinNet data from Box (~3.5 GB compressed).")
649+
print("Downloading pre-parsed ProteinNet data (~3.5 GB compressed).")
650650
_download(
651-
"https://pitt.box.com/shared/static/nzsglfxdetnrpd4d6lomqh5102upa65a.zip",
651+
"http://bits.csb.pitt.edu/~jok120/sidechainnet_data/resources/proteinnet_parsed.zip",
652652
zip_file_path)
653653

654654
with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:

sidechainnet/utils/load.py

Lines changed: 43 additions & 79 deletions
Original file line numberDiff line numberDiff line change
@@ -66,15 +66,15 @@ def _download(url, file_name):
6666
def _download_sidechainnet(casp_version, thinning, scn_dir):
6767
"""Download the specified version of Sidechainnet."""
6868
# Prepare destination paths for downloading
69-
if format_sidechainnet_path(casp_version, thinning) not in BOXURLS:
69+
if format_sidechainnet_path(casp_version, thinning) not in SCN_URLS:
7070
raise FileNotFoundError(
7171
"The requested file is currently unavailable. Please check back later.")
7272
outfile_path = os.path.join(scn_dir, format_sidechainnet_path(casp_version, thinning))
7373
os.makedirs(os.path.dirname(outfile_path), exist_ok=True)
74-
print("Downloading from", BOXURLS[format_sidechainnet_path(casp_version, thinning)])
74+
print("Downloading from", SCN_URLS[format_sidechainnet_path(casp_version, thinning)])
7575

76-
# Use a data-agnostic tool for downloading URL data from Box to a specified local file
77-
_download(BOXURLS[format_sidechainnet_path(casp_version, thinning)], outfile_path)
76+
# Use a data-agnostic tool for downloading URL data from web to a specified local file
77+
_download(SCN_URLS[format_sidechainnet_path(casp_version, thinning)], outfile_path)
7878
print(f"Downloaded SidechainNet to {outfile_path}.")
7979

8080
return outfile_path
@@ -397,92 +397,56 @@ def filter_dictionary_by_missing_residues(raw_data):
397397
return raw_data
398398

399399

400-
BOXURLS = {
400+
_base_url = "http://bits.csb.pitt.edu/~jok120/sidechainnet_data/"
401+
SCN_URLS = {
401402
# CASP 12
402-
"sidechainnet_casp12_30.pkl":
403-
"https://pitt.box.com/shared/static/hbatd2a750tx8e27yizwinc3hsceeeui.pkl",
404-
"sidechainnet_casp12_50.pkl":
405-
"https://pitt.box.com/shared/static/7cng5zdi2s4doruh1m512d281w2cmk0z.pkl",
406-
"sidechainnet_casp12_70.pkl":
407-
"https://pitt.box.com/shared/static/xfaktrj8ole0eqktxi5fa4qp9efum8f2.pkl",
408-
"sidechainnet_casp12_90.pkl":
409-
"https://pitt.box.com/shared/static/nh7vybjjm224m1nezrgmnywxsa4st2uk.pkl",
410-
"sidechainnet_casp12_95.pkl":
411-
"https://pitt.box.com/shared/static/wcz1kex8idnpy8zx7a59r3h6e216tlq1.pkl",
412-
"sidechainnet_casp12_100.pkl":
413-
"https://pitt.box.com/shared/static/ey5xh6l4p8iwzrxtxwpxt7oeg70eayl4.pkl",
403+
"sidechainnet_casp12_30.pkl": _base_url + "sidechainnet_casp12_30.pkl",
404+
"sidechainnet_casp12_50.pkl": _base_url + "sidechainnet_casp12_50.pkl",
405+
"sidechainnet_casp12_70.pkl": _base_url + "sidechainnet_casp12_70.pkl",
406+
"sidechainnet_casp12_90.pkl": _base_url + "sidechainnet_casp12_90.pkl",
407+
"sidechainnet_casp12_95.pkl": _base_url + "sidechainnet_casp12_95.pkl",
408+
"sidechainnet_casp12_100.pkl": _base_url + "sidechainnet_casp12_100.pkl",
414409

415410
# CASP 11
416-
"sidechainnet_casp11_30.pkl":
417-
"https://pitt.box.com/shared/static/fzil4bgxt4fqpp416xw0e3y0ew4c7yct.pkl",
418-
"sidechainnet_casp11_50.pkl":
419-
"https://pitt.box.com/shared/static/rux3p18k523y8zbo40u1l856826buvui.pkl",
420-
"sidechainnet_casp11_70.pkl":
421-
"https://pitt.box.com/shared/static/tl51ym0hzjdvq4qs5f5shsj0sl9mkvd0.pkl",
422-
"sidechainnet_casp11_90.pkl":
423-
"https://pitt.box.com/shared/static/iheqs3vqszoxsdq46nkzf5kylt8ecjbx.pkl",
424-
"sidechainnet_casp11_95.pkl":
425-
"https://pitt.box.com/shared/static/gbme2a5yifpugtmthwu2989xxyg5b8i6.pkl",
426-
"sidechainnet_casp11_100.pkl":
427-
"https://pitt.box.com/shared/static/3cfx02k2yw4ux2mrbvwrrj91zsftcpbj.pkl",
411+
"sidechainnet_casp11_30.pkl": _base_url + "sidechainnet_casp11_30.pkl",
412+
"sidechainnet_casp11_50.pkl": _base_url + "sidechainnet_casp11_50.pkl",
413+
"sidechainnet_casp11_70.pkl": _base_url + "sidechainnet_casp11_70.pkl",
414+
"sidechainnet_casp11_90.pkl": _base_url + "sidechainnet_casp11_90.pkl",
415+
"sidechainnet_casp11_95.pkl": _base_url + "sidechainnet_casp11_95.pkl",
416+
"sidechainnet_casp11_100.pkl": _base_url + "sidechainnet_casp11_100.pkl",
428417

429418
# CASP 10
430-
"sidechainnet_casp10_30.pkl":
431-
"https://pitt.box.com/shared/static/fe0hpjrldi2y1g374mgdzfpdipajd6s4.pkl",
432-
"sidechainnet_casp10_50.pkl":
433-
"https://pitt.box.com/shared/static/tsnt6s07txas0h37cpzepck580yme9vv.pkl",
434-
"sidechainnet_casp10_70.pkl":
435-
"https://pitt.box.com/shared/static/awmzr4jj68p61ab031smixryt69p8ykm.pkl",
436-
"sidechainnet_casp10_90.pkl":
437-
"https://pitt.box.com/shared/static/it6zcugy997c1550kima3m3fu8kamnh8.pkl",
438-
"sidechainnet_casp10_95.pkl":
439-
"https://pitt.box.com/shared/static/q6ld9h276kobhmmtvdq581qnm61oevup.pkl",
440-
"sidechainnet_casp10_100.pkl":
441-
"https://pitt.box.com/shared/static/fpixgzh9n86xyzpwtlc74lle4fd3p5es.pkl",
419+
"sidechainnet_casp10_30.pkl": _base_url + "sidechainnet_casp10_30.pkl",
420+
"sidechainnet_casp10_50.pkl": _base_url + "sidechainnet_casp10_50.pkl",
421+
"sidechainnet_casp10_70.pkl": _base_url + "sidechainnet_casp10_70.pkl",
422+
"sidechainnet_casp10_90.pkl": _base_url + "sidechainnet_casp10_90.pkl",
423+
"sidechainnet_casp10_95.pkl": _base_url + "sidechainnet_casp10_95.pkl",
424+
"sidechainnet_casp10_100.pkl": _base_url + "sidechainnet_casp10_100.pkl",
442425

443426
# CASP 9
444-
"sidechainnet_casp9_30.pkl":
445-
"https://pitt.box.com/shared/static/j1h3181d2mibqvc7jrqm17dprzj6pxmc.pkl",
446-
"sidechainnet_casp9_50.pkl":
447-
"https://pitt.box.com/shared/static/l363lu9ztpdmcybthtytwnrvvkib2228.pkl",
448-
"sidechainnet_casp9_70.pkl":
449-
"https://pitt.box.com/shared/static/4uh1yggpdhm0aoeisomnyfuac4j20qzc.pkl",
450-
"sidechainnet_casp9_90.pkl":
451-
"https://pitt.box.com/shared/static/scv7l6qfr2j93pn4cu40ouhmxbns6k7x.pkl",
452-
"sidechainnet_casp9_95.pkl":
453-
"https://pitt.box.com/shared/static/tqpugpr7wamvmkyrtd8tqnzft6u53zha.pkl",
454-
"sidechainnet_casp9_100.pkl":
455-
"https://pitt.box.com/shared/static/jjtubu2lxwlv1aw8tfc7u27vcf2yz39v.pkl",
427+
"sidechainnet_casp9_30.pkl": _base_url + "sidechainnet_casp9_30.pkl",
428+
"sidechainnet_casp9_50.pkl": _base_url + "sidechainnet_casp9_50.pkl",
429+
"sidechainnet_casp9_70.pkl": _base_url + "sidechainnet_casp9_70.pkl",
430+
"sidechainnet_casp9_90.pkl": _base_url + "sidechainnet_casp9_90.pkl",
431+
"sidechainnet_casp9_95.pkl": _base_url + "sidechainnet_casp9_95.pkl",
432+
"sidechainnet_casp9_100.pkl": _base_url + "sidechainnet_casp9_100.pkl",
456433

457434
# CASP 8
458-
"sidechainnet_casp8_30.pkl":
459-
"https://pitt.box.com/shared/static/1hx2n3y2gn3flnlsw2wb1e4l4nlru5mz.pkl",
460-
"sidechainnet_casp8_50.pkl":
461-
"https://pitt.box.com/shared/static/4u8tuqkm5pv34hm139uw9dqc4ieebsue.pkl",
462-
"sidechainnet_casp8_70.pkl":
463-
"https://pitt.box.com/shared/static/vj58yaeph55zjb04jezmqams66mn4bil.pkl",
464-
"sidechainnet_casp8_90.pkl":
465-
"https://pitt.box.com/shared/static/1ry2j47lde7zk5fxzvuffv05k1gq29oh.pkl",
466-
"sidechainnet_casp8_95.pkl":
467-
"https://pitt.box.com/shared/static/9uaw2tv61xyfd8gtw9n8e3hfcken4t4x.pkl",
468-
"sidechainnet_casp8_100.pkl":
469-
"https://pitt.box.com/shared/static/crk59vz6dw9cbbvne10owa450zgv1j79.pkl",
435+
"sidechainnet_casp8_30.pkl": _base_url + "sidechainnet_casp8_30.pkl",
436+
"sidechainnet_casp8_50.pkl": _base_url + "sidechainnet_casp8_50.pkl",
437+
"sidechainnet_casp8_70.pkl": _base_url + "sidechainnet_casp8_70.pkl",
438+
"sidechainnet_casp8_90.pkl": _base_url + "sidechainnet_casp8_90.pkl",
439+
"sidechainnet_casp8_95.pkl": _base_url + "sidechainnet_casp8_95.pkl",
440+
"sidechainnet_casp8_100.pkl": _base_url + "sidechainnet_casp8_100.pkl",
470441

471442
# CASP 7
472-
"sidechainnet_casp7_30.pkl":
473-
"https://pitt.box.com/shared/static/hjblmbwei2dkwhfjatttdmamznt1k9ef.pkl",
474-
"sidechainnet_casp7_50.pkl":
475-
"https://pitt.box.com/shared/static/4pw56huei1123a5rd6g460886kg0pex7.pkl",
476-
"sidechainnet_casp7_70.pkl":
477-
"https://pitt.box.com/shared/static/afyow2ki9mwuoago0bzlsp5ame8dq12g.pkl",
478-
"sidechainnet_casp7_90.pkl":
479-
"https://pitt.box.com/shared/static/phsbdw8bj1oiv61d6hps0j62324820f3.pkl",
480-
"sidechainnet_casp7_95.pkl":
481-
"https://pitt.box.com/shared/static/2lgbtdw6c5df0qpe7dtnlaawowy9ic5r.pkl",
482-
"sidechainnet_casp7_100.pkl":
483-
"https://pitt.box.com/shared/static/6qipxz2z2n12a06vln5ucmzu4dcyw5ee.pkl",
443+
"sidechainnet_casp7_30.pkl": _base_url + "sidechainnet_casp7_30.pkl",
444+
"sidechainnet_casp7_50.pkl": _base_url + "sidechainnet_casp7_50.pkl",
445+
"sidechainnet_casp7_70.pkl": _base_url + "sidechainnet_casp7_70.pkl",
446+
"sidechainnet_casp7_90.pkl": _base_url + "sidechainnet_casp7_90.pkl",
447+
"sidechainnet_casp7_95.pkl": _base_url + "sidechainnet_casp7_95.pkl",
448+
"sidechainnet_casp7_100.pkl": _base_url + "sidechainnet_casp7_100.pkl",
484449

485450
# Other
486-
"sidechainnet_debug.pkl":
487-
"https://pitt.box.com/shared/static/tevlb6nuii6kk520vi4x0u7li0eoxuep.pkl"
451+
"sidechainnet_debug.pkl": _base_url + "sidechainnet_debug.pkl",
488452
}

0 commit comments

Comments
 (0)