Pinder index

Download the dataset

NOTE: the default location for the dataset is ~/.local/share/pinder/<release version>

If you want to use a different location, you can do so by setting the PINDER_BASE_DIR environment variable.

The base dir refers to a fully qualified path name up until the <release version> (not inclusive).

For instance, you could:

export PINDER_BASE_DIR=~/my-custom-location-for-pinder/pinder

You can always check the current location of the dataset like so:

from pinder.core import get_pinder_location
get_pinder_location()

from pinder.core import get_pinder_location
get_pinder_location()

PosixPath('/home/runner/.local/share/pinder/2024-02')

To download the complete dataset run the following

from pinder.core import download_dataset
# download_dataset()

Alternatively, use the CLI script pinder_download

pinder_download --help

usage: Download latest pinder dataset to disk [-h] [--pinder_base_dir PINDER_BASE_DIR] [--pinder_release PINDER_RELEASE] [--skip_inflation]

optional arguments:
  -h, --help            show this help message and exit
  --pinder_base_dir PINDER_BASE_DIR
                        specify a non-default pinder base directory
  --pinder_release PINDER_RELEASE
                        specify a pinder dataset version
  --skip_inflation      if passed, will only download the compressed archives without unpacking

The full dataset should look like this

~/.local/share/pinder/<release version>/
    pdbs/
    csvs/
    index.csv.gz

Pinder metadata API

from pinder.core import get_metadata

metadata = get_metadata()
metadata

	id	entry_id	method	date	release_date	resolution	label	probability	chain1_id	chain2_id	...	interface_atom_gaps_4A	missing_interface_residues_4A	interface_atom_gaps_8A	missing_interface_residues_8A	entity_id_R	entity_id_L	pdb_strand_id_R	pdb_strand_id_L	ECOD_names_R	ECOD_names_L
0	7rzb__A1_A0A229LVN5--7rzb__A2_A0A229LVN5	7rzb	X-RAY DIFFRACTION	2021-08-27	2022-04-13	1.599609	BIO	0.576172	R	L	...	0	0	0	0	1	1	A	A	PF06491	PF06491
1	3t2l__A1_Q5LE95--3t2l__A2_Q5LE95	3t2l	X-RAY DIFFRACTION	2011-07-22	2011-08-10	2.330078	BIO	0.983887	R	L	...	0	0	0	0	1	1	A	A	F_UNCLASSIFIED,PF13149	F_UNCLASSIFIED,PF13149
2	6ikj__A1_Q9I4L6--6ikj__B1_Q9I4L6	6ikj	X-RAY DIFFRACTION	2018-10-16	2019-03-13	1.759766	BIO	0.543945	R	L	...	0	0	0	0	1	1	A	B	PF00691	PF00691
3	8iyi__A1_Q6CVU4--8iyi__B1_Q6CVU4	8iyi	X-RAY DIFFRACTION	2023-04-05	2023-06-28	1.900391	BIO	0.992188	R	L	...	0	0	0	0	1	1	A	B	PF17284,PF01564	PF17284,PF01564
4	3uws__B1_A7A9N3--3uws__A1_A7A9N3	3uws	X-RAY DIFFRACTION	2011-12-02	2012-06-13	1.700195	BIO	0.996094	R	L	...	0	0	0	0	2	1	B	A
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2319559	6hbg__C28_Q8V635--6hbg__C35_Q8V635	6hbg	ELECTRON MICROSCOPY	2018-08-10	2019-03-20	3.160156	BIO	0.512207	R	L	...	0	0	0	0	3	3	C	C	PF00073	PF00073
2319560	6hbg__A11_Q8V635--6hbg__A54_Q8V635	6hbg	ELECTRON MICROSCOPY	2018-08-10	2019-03-20	3.160156		0.000000	R	L	...	0	0	0	0	1	1	A	A	PF00073	PF00073
2319561	6hbg__C15_Q8V635--6hbg__D4_Q8V635	6hbg	ELECTRON MICROSCOPY	2018-08-10	2019-03-20	3.160156	XTAL	0.491943	R	L	...	0	0	0	0	3	4	C	D	PF00073	PF02226
2319562	6hbg__C33_Q8V635--6hbg__D52_Q8V635	6hbg	ELECTRON MICROSCOPY	2018-08-10	2019-03-20	3.160156	XTAL	0.491943	R	L	...	0	0	0	0	3	4	C	D	PF00073	PF02226
2319563	6rwh__A1_P31947--6rwh__A2_P31947	6rwh	X-RAY DIFFRACTION	2019-06-05	2020-06-17	1.679688	BIO	0.835938	R	L	...	4	0	64	0	1	1	A	A	PF00244	PF00244

2319564 rows × 51 columns

Pinder index API

from pinder.core import PinderSystem, get_index

index = get_index()
index

	split	id	pdb_id	cluster_id	cluster_id_R	cluster_id_L	pinder_s	pinder_xl	pinder_af2	uniprot_R	...	apo_L	apo_R_quality	apo_L_quality	chain1_neff	chain2_neff	chain_R	chain_L	contains_antibody	contains_antigen	contains_enzyme
0	test	7rzb__A1_A0A229LVN5--7rzb__A2_A0A229LVN5	7rzb	cluster_16129_16129	cluster_16129	cluster_16129	False	True	True	A0A229LVN5	...	False			287.000000	287.000000	A1	A2	False	False	False
1	test	3t2l__A1_Q5LE95--3t2l__A2_Q5LE95	3t2l	cluster_30933_30933	cluster_30933	cluster_30933	False	True	False	Q5LE95	...	False			7.175781	7.175781	A1	A2	False	False	False
2	test	6ikj__A1_Q9I4L6--6ikj__B1_Q9I4L6	6ikj	cluster_1924_1924	cluster_1924	cluster_1924	False	True	False	Q9I4L6	...	True	high	high	845.000000	845.000000	A1	B1	False	False	False
3	test	8iyi__A1_Q6CVU4--8iyi__B1_Q6CVU4	8iyi	cluster_142_142	cluster_142	cluster_142	False	True	False	Q6CVU4	...	False			525.000000	525.000000	A1	B1	False	False	False
4	test	3uws__B1_A7A9N3--3uws__A1_A7A9N3	3uws	cluster_21030_21031	cluster_21030	cluster_21031	False	True	False	A7A9N3	...	False			147.375000	147.375000	B1	A1	False	False	False
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2319559	invalid	6hbg__C28_Q8V635--6hbg__C35_Q8V635	6hbg	cluster_-1_-1	cluster_-1	cluster_-1	False	False	False	Q8V635	...	False			37.656250	37.656250	C28	C35	False	False	True
2319560	invalid	6hbg__A11_Q8V635--6hbg__A54_Q8V635	6hbg	cluster_-1_-1	cluster_-1	cluster_-1	False	False	False	Q8V635	...	False			37.656250	37.656250	A11	A54	False	False	True
2319561	invalid	6hbg__C15_Q8V635--6hbg__D4_Q8V635	6hbg	cluster_-1_p	cluster_p	cluster_-1	False	False	False	Q8V635	...	False			37.656250	37.656250	C15	D4	False	False	True
2319562	invalid	6hbg__C33_Q8V635--6hbg__D52_Q8V635	6hbg	cluster_-1_p	cluster_p	cluster_-1	False	False	False	Q8V635	...	False			37.656250	37.656250	C33	D52	False	False	True
2319563	invalid	6rwh__A1_P31947--6rwh__A2_P31947	6rwh	cluster_2_2	cluster_2	cluster_2	False	False	False	P31947	...	False			457.750000	457.750000	A1	A2	False	False	False

2319564 rows × 34 columns

How to get subsets of data from the index

# Example: I want all of pinder_af2 - apo

af2_apo = index.query(
    'pinder_af2 == True and apo_R and apo_L'
).reset_index(drop=True)
af2_apo

	split	id	pdb_id	cluster_id	cluster_id_R	cluster_id_L	pinder_s	pinder_xl	pinder_af2	uniprot_R	...	apo_L	apo_R_quality	apo_L_quality	chain1_neff	chain2_neff	chain_R	chain_L	contains_antibody	contains_antigen	contains_enzyme
0	test	7ubk__B1_P03047--7ubk__A1_P03047	7ubk	cluster_31523_31523	cluster_31523	cluster_31523	False	True	True	P03047	...	True	high	high	81.750000	81.750000	B1	A1	False	False	False
1	test	7zj1__B1_P55265--7zj1__A1_P55265	7zj1	cluster_1209_1209	cluster_1209	cluster_1209	False	True	True	P55265	...	True	high	high	174.250000	174.250000	B1	A1	False	False	True
2	test	7zjc__A1_P0DV83--7zjc__A2_P0DV83	7zjc	cluster_26441_26441	cluster_26441	cluster_26441	False	True	True	P0DV83	...	True	high	high	6.925781	6.925781	A1	A2	False	False	False
3	test	7ztw__A1_Q66578--7ztw__B1_Q66578	7ztw	cluster_22347_22347	cluster_22347	cluster_22347	False	True	True	Q66578	...	True	high	high	13.382812	13.382812	A1	B1	False	False	False
4	test	8ard__A1_Q64331--8ard__A2_Q64331	8ard	cluster_34280_34280	cluster_34280	cluster_34280	False	True	True	Q64331	...	True	high	high	444.750000	444.750000	A1	A2	False	False	False
5	test	7wbt__A1_Q288C4--7wbt__B1_Q288C4	7wbt	cluster_7371_7371	cluster_7371	cluster_7371	True	True	True	Q288C4	...	True	high	high	169.500000	169.500000	A1	B1	False	False	False
6	test	7z7o__A1_A0A1S4NYF2--7z7o__C1_A0A1S4NYF2	7z7o	cluster_91_91	cluster_91	cluster_91	False	True	True	A0A1S4NYF2	...	True	high	high	10.632812	10.632812	A1	C1	False	False	False
7	test	8pte__A1_P00698--8pte__A2_P00698	8pte	cluster_274_274	cluster_274	cluster_274	False	True	True	P00698	...	True	high	high	254.375000	254.375000	A1	A2	False	False	True
8	test	7yka__B1_Q9Y3D6--7yka__A1_Q9Y3D6	7yka	cluster_13298_13298	cluster_13298	cluster_13298	False	True	True	Q9Y3D6	...	True	high	high	132.875000	132.875000	B1	A1	False	False	False
9	test	7ykv__B1_Q58241--7ykv__A1_Q58241	7ykv	cluster_5358_5358	cluster_5358	cluster_5358	False	True	True	Q58241	...	True	high	high	171.625000	171.625000	B1	A1	False	False	False
10	test	8a60__A1_P06971--8a60__B1_Q38162	8a60	cluster_12107_26846	cluster_12107	cluster_26846	False	True	True	P06971	...	True	high	high	288.000000	2.734375	A1	B1	False	False	False
11	test	7t5y__A1_P0A7E1--7t5y__B1_P0A7E1	7t5y	cluster_7939_7939	cluster_7939	cluster_7939	False	True	True	P0A7E1	...	True	high	high	735.500000	735.500000	A1	B1	False	False	True
12	test	8oru__A1_O93732--8oru__B1_O93732	8oru	cluster_14951_14951	cluster_14951	cluster_14951	False	True	True	O93732	...	True	high	high	103.187500	103.187500	A1	B1	False	False	True
13	test	7z6m__A1_A0A0H3LM39--7z6m__A2_A0A0H3LM39	7z6m	cluster_5362_5362	cluster_5362	cluster_5362	False	True	True	A0A0H3LM39	...	True	high	high	533.000000	533.000000	A1	A2	False	False	False
14	test	8cnx__A1_Q68T42--8cnx__B1_Q68T42	8cnx	cluster_609_609	cluster_609	cluster_609	False	True	True	Q68T42	...	True	high	high	45.000000	45.000000	A1	B1	False	False	True
15	test	7wwo__B1_Q5SH57--7wwo__A1_Q5SH57	7wwo	cluster_5115_5115	cluster_5115	cluster_5115	False	True	True	Q5SH57	...	True	high	high	2.939453	2.939453	B1	A1	False	False	False
16	test	8d0m__A1_P28907--8d0m__A2_P28907	8d0m	cluster_2975_2975	cluster_2975	cluster_2975	True	True	True	P28907	...	True	high	high	48.312500	48.312500	A1	A2	False	False	True
17	test	8avu__A1_Q8GPI4--8avu__A2_Q8GPI4	8avu	cluster_29712_29712	cluster_29712	cluster_29712	False	True	True	Q8GPI4	...	True	high	high	11.882812	11.882812	A1	A2	False	False	False
18	test	8i2e__A1_O34841--8i2e__B1_P54421	8i2e	cluster_11087_12465	cluster_12465	cluster_11087	True	True	True	O34841	...	True	high	high	9.031250	865.000000	A1	B1	False	False	True
19	test	8aeu__A1_Q00987--8aeu__A2_Q00987	8aeu	cluster_1537_1537	cluster_1537	cluster_1537	False	True	True	Q00987	...	True	high	high	350.750000	350.750000	A1	A2	False	False	True
20	test	7vso__A1_P02945--7vso__A2_P02945	7vso	cluster_1035_1035	cluster_1035	cluster_1035	False	True	True	P02945	...	True	high	high	267.250000	267.250000	A1	A2	False	False	False
21	test	7yuj__B1_Q9BYM8--7yuj__A1_Q9BYM8	7yuj	cluster_19439_19439	cluster_19439	cluster_19439	True	True	True	Q9BYM8	...	True	high	high	266.750000	266.750000	B1	A1	False	False	True
22	test	8pvm__A1_P29166--8pvm__B1_P29166	8pvm	cluster_6440_6440	cluster_6440	cluster_6440	False	True	True	P29166	...	True	high	high	392.500000	392.500000	A1	B1	False	False	True
23	test	7yo8__A1_P60520--7yo8__A2_P60520	7yo8	cluster_1022_1022	cluster_1022	cluster_1022	False	True	True	P60520	...	True	high	high	385.500000	385.500000	A1	A2	False	False	False
24	test	7y51__A1_Q8RBF4--7y51__A2_Q8RBF4	7y51	cluster_711_711	cluster_711	cluster_711	False	True	True	Q8RBF4	...	True	high	high	954.500000	954.500000	A1	A2	False	False	False
25	test	7tvh__B1_Q9I2Q1--7tvh__A1_Q9I2Q1	7tvh	cluster_8106_8106	cluster_8106	cluster_8106	False	True	True	Q9I2Q1	...	True	high	high	209.125000	209.125000	B1	A1	False	False	True
26	test	8bwv__D2_A0A482M8M0--8bwv__A1_A0A482M8M0	8bwv	cluster_27613_27613	cluster_27613	cluster_27613	False	True	True	A0A482M8M0	...	True	high	high	395.000000	395.000000	D2	A1	False	False	False
27	test	7t91__A1_P08151--7t91__B1_P08151	7t91	cluster_1801_1801	cluster_1801	cluster_1801	False	True	True	P08151	...	True	high	high	321.250000	321.250000	A1	B1	False	False	False
28	test	7zoo__B1_A0A979GQH9--7zoo__A1_A0A979GQH9	7zoo	cluster_32633_32633	cluster_32633	cluster_32633	False	True	True	A0A979GQH9	...	True	high	high	419.250000	419.250000	B1	A1	False	False	False
29	test	7x4b__A1_A0A2D0TCG3--7x4b__B1_A0A2D0TCG3	7x4b	cluster_7334_7334	cluster_7334	cluster_7334	False	True	True	A0A2D0TCG3	...	True	high	high	9.453125	9.453125	A1	B1	False	False	False

30 rows × 34 columns

Finding the existing local filepaths for systems (without re-writing them per system)

from pinder.core import get_systems


local_paths = {}
for system in get_systems(list(af2_apo.id)):
    local_paths[system.entry.id] = system.filepaths
    

  0%|          | 0/30 [00:00<?, ?it/s]

2024-09-13 20:36:50,162 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=13

2024-09-13 20:36:50,655 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.49s

  3%|▎         | 1/30 [00:01<00:30,  1.06s/it]

2024-09-13 20:36:50,717 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:36:50,925 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.21s

  7%|▋         | 2/30 [00:01<00:16,  1.66it/s]

2024-09-13 20:36:51,000 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=9

2024-09-13 20:36:51,229 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.23s

 10%|█         | 3/30 [00:01<00:12,  2.19it/s]

2024-09-13 20:36:51,283 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=13

2024-09-13 20:36:51,627 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.34s

 13%|█▎        | 4/30 [00:02<00:11,  2.30it/s]

2024-09-13 20:36:51,684 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:36:52,010 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.33s

 17%|█▋        | 5/30 [00:02<00:10,  2.36it/s]

2024-09-13 20:36:52,087 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:36:52,512 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.42s

 20%|██        | 6/30 [00:02<00:11,  2.17it/s]

2024-09-13 20:36:52,622 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=19

2024-09-13 20:36:53,201 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.58s

 23%|██▎       | 7/30 [00:03<00:12,  1.91it/s]

2024-09-13 20:36:53,503 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=4323

2024-09-13 20:38:16,751 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:     83.25s

 27%|██▋       | 8/30 [01:27<09:52, 26.95s/it]

2024-09-13 20:38:16,811 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=15

2024-09-13 20:38:17,205 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.39s

 30%|███       | 9/30 [01:27<06:32, 18.67s/it]

2024-09-13 20:38:17,264 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:17,566 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.30s

 33%|███▎      | 10/30 [01:27<04:20, 13.02s/it]

2024-09-13 20:38:17,643 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=24

2024-09-13 20:38:18,412 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.77s

 37%|███▋      | 11/30 [01:28<02:56,  9.29s/it]

2024-09-13 20:38:18,486 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:18,826 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.34s

 40%|████      | 12/30 [01:29<01:58,  6.59s/it]

2024-09-13 20:38:18,897 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:19,248 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.35s

 43%|████▎     | 13/30 [01:29<01:20,  4.73s/it]

2024-09-13 20:38:19,342 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=19

2024-09-13 20:38:19,823 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.48s

 47%|████▋     | 14/30 [01:30<00:55,  3.47s/it]

2024-09-13 20:38:19,902 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=421

2024-09-13 20:38:27,182 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      7.28s

 50%|█████     | 15/30 [01:37<01:09,  4.64s/it]

2024-09-13 20:38:27,240 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:27,501 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.26s

 53%|█████▎    | 16/30 [01:37<00:46,  3.34s/it]

2024-09-13 20:38:27,566 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=163

2024-09-13 20:38:30,614 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      3.05s

 57%|█████▋    | 17/30 [01:41<00:42,  3.27s/it]

2024-09-13 20:38:30,679 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=19

2024-09-13 20:38:31,113 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.43s

 60%|██████    | 18/30 [01:41<00:29,  2.44s/it]

2024-09-13 20:38:31,166 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:31,401 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.24s

 63%|██████▎   | 19/30 [01:41<00:19,  1.79s/it]

2024-09-13 20:38:31,472 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=287

2024-09-13 20:38:36,189 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      4.72s

 67%|██████▋   | 20/30 [01:46<00:26,  2.69s/it]

2024-09-13 20:38:36,258 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=187

2024-09-13 20:38:40,116 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      3.86s

 70%|███████   | 21/30 [01:50<00:27,  3.06s/it]

2024-09-13 20:38:40,181 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:40,522 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.34s

 73%|███████▎  | 22/30 [01:50<00:18,  2.27s/it]

2024-09-13 20:38:40,592 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=127

2024-09-13 20:38:43,421 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      2.83s

 77%|███████▋  | 23/30 [01:53<00:17,  2.46s/it]

2024-09-13 20:38:43,512 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=15

2024-09-13 20:38:43,881 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.37s

 80%|████████  | 24/30 [01:54<00:11,  1.85s/it]

2024-09-13 20:38:43,938 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:44,260 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.32s

 83%|████████▎ | 25/30 [01:54<00:07,  1.41s/it]

2024-09-13 20:38:44,324 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=43

2024-09-13 20:38:45,115 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.79s

 87%|████████▋ | 26/30 [01:55<00:04,  1.24s/it]

2024-09-13 20:38:45,182 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=15

2024-09-13 20:38:45,564 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.38s

 90%|█████████ | 27/30 [01:55<00:03,  1.00s/it]

2024-09-13 20:38:45,621 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:45,923 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.30s

 93%|█████████▎| 28/30 [01:56<00:01,  1.23it/s]

2024-09-13 20:38:45,992 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=17

2024-09-13 20:38:46,408 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.42s

 97%|█████████▋| 29/30 [01:56<00:00,  1.41it/s]

2024-09-13 20:38:46,462 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=11

2024-09-13 20:38:46,614 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.15s

100%|██████████| 30/30 [01:57<00:00,  1.78it/s]

100%|██████████| 30/30 [01:57<00:00,  3.90s/it]

It should be cached, no need to download if you re-run

local_paths = {}
for system in get_systems(list(af2_apo.id)):
    local_paths[system.entry.id] = system.filepaths
local_paths    

  0%|          | 0/30 [00:00<?, ?it/s]

  7%|▋         | 2/30 [00:00<00:01, 15.74it/s]

 13%|█▎        | 4/30 [00:00<00:01, 17.50it/s]

 20%|██        | 6/30 [00:00<00:01, 13.66it/s]

 27%|██▋       | 8/30 [00:00<00:01, 12.91it/s]

 33%|███▎      | 10/30 [00:00<00:01, 13.38it/s]

 40%|████      | 12/30 [00:00<00:01, 13.76it/s]

 47%|████▋     | 14/30 [00:01<00:01, 13.45it/s]

 53%|█████▎    | 16/30 [00:01<00:00, 14.41it/s]

 60%|██████    | 18/30 [00:01<00:00, 15.10it/s]

 67%|██████▋   | 20/30 [00:01<00:00, 15.54it/s]

 73%|███████▎  | 22/30 [00:01<00:00, 15.59it/s]

 80%|████████  | 24/30 [00:01<00:00, 15.01it/s]

 87%|████████▋ | 26/30 [00:01<00:00, 15.40it/s]

 93%|█████████▎| 28/30 [00:01<00:00, 15.78it/s]

100%|██████████| 30/30 [00:01<00:00, 16.54it/s]

100%|██████████| 30/30 [00:01<00:00, 15.03it/s]

{'7ubk__B1_P03047--7ubk__A1_P03047': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ubk__B1_P03047-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ubk__A1_P03047-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/4mo1__A1_P03047.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/4mo1__A1_P03047.pdb'),
  'pred_receptor': None,
  'pred_ligand': None},
 '7zj1__B1_P55265--7zj1__A1_P55265': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zj1__B1_P55265-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zj1__A1_P55265-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2mdr__A1_P55265.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2mdr__A1_P55265.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P55265.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P55265.pdb')},
 '7zjc__A1_P0DV83--7zjc__A2_P0DV83': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zjc__A1_P0DV83-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zjc__A2_P0DV83-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7qdv__A1_P0DV83.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7qdv__A1_P0DV83.pdb'),
  'pred_receptor': None,
  'pred_ligand': None},
 '7ztw__A1_Q66578--7ztw__B1_Q66578': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ztw__A1_Q66578-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ztw__B1_Q66578-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7zu3__A1_Q66578.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7zu4__A1_Q66578.pdb'),
  'pred_receptor': None,
  'pred_ligand': None},
 '8ard__A1_Q64331--8ard__A2_Q64331': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8ard__A1_Q64331-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8ard__A2_Q64331-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2ld3__A1_Q64331.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2ld3__A1_Q64331.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q64331.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q64331.pdb')},
 '7wbt__A1_Q288C4--7wbt__B1_Q288C4': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7wbt__A1_Q288C4-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7wbt__B1_Q288C4-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7wbu__A1_Q288C4.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7wbu__A1_Q288C4.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q288C4.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q288C4.pdb')},
 '7z7o__A1_A0A1S4NYF2--7z7o__C1_A0A1S4NYF2': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7z7o__A1_A0A1S4NYF2-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7z7o__C1_A0A1S4NYF2-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7z7p__A1_A0A1S4NYF2.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7z7p__A1_A0A1S4NYF2.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A1S4NYF2.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A1S4NYF2.pdb')},
 '8pte__A1_P00698--8pte__A2_P00698': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8pte__A1_P00698-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8pte__A2_P00698-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2q0m__A1_P00698.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2q0m__A1_P00698.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P00698.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P00698.pdb')},
 '7yka__B1_Q9Y3D6--7yka__A1_Q9Y3D6': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yka__B1_Q9Y3D6-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yka__A1_Q9Y3D6-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/1nzn__A1_Q9Y3D6.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/1nzn__A1_Q9Y3D6.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9Y3D6.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9Y3D6.pdb')},
 '7ykv__B1_Q58241--7ykv__A1_Q58241': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ykv__B1_Q58241-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7ykv__A1_Q58241-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/6tvv__A1_Q58241.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/6tvv__A1_Q58241.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q58241.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q58241.pdb')},
 '8a60__A1_P06971--8a60__B1_Q38162': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8a60__A1_P06971-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8a60__B1_Q38162-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2fcp__A1_P06971.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7qjf__A1_Q38162.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P06971.pdb'),
  'pred_ligand': None},
 '7t5y__A1_P0A7E1--7t5y__B1_P0A7E1': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7t5y__A1_P0A7E1-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7t5y__B1_P0A7E1-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/1f76__A1_P0A7E1.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/1f76__A1_P0A7E1.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P0A7E1.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P0A7E1.pdb')},
 '8oru__A1_O93732--8oru__B1_O93732': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8oru__A1_O93732-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8oru__B1_O93732-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8ork__A1_O93732.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8ork__A1_O93732.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__O93732.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__O93732.pdb')},
 '7z6m__A1_A0A0H3LM39--7z6m__A2_A0A0H3LM39': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7z6m__A1_A0A0H3LM39-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7z6m__A2_A0A0H3LM39-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/5tsb__A1_A0A0H3LM39.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/5tsb__A1_A0A0H3LM39.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A0H3LM39.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A0H3LM39.pdb')},
 '8cnx__A1_Q68T42--8cnx__B1_Q68T42': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8cnx__A1_Q68T42-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8cnx__B1_Q68T42-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7goq__A1_Q68T42.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7gqn__A1_Q68T42.pdb'),
  'pred_receptor': None,
  'pred_ligand': None},
 '7wwo__B1_Q5SH57--7wwo__A1_Q5SH57': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7wwo__B1_Q5SH57-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7wwo__A1_Q5SH57-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7wrk__A1_Q5SH57.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7wrk__A1_Q5SH57.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q5SH57.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q5SH57.pdb')},
 '8d0m__A1_P28907--8d0m__A2_P28907': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8d0m__A1_P28907-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8d0m__A2_P28907-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8p8c__A1_P28907.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8p8c__A1_P28907.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P28907.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P28907.pdb')},
 '8avu__A1_Q8GPI4--8avu__A2_Q8GPI4': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8avu__A1_Q8GPI4-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8avu__A2_Q8GPI4-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8avs__A1_Q8GPI4.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8avs__A1_Q8GPI4.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q8GPI4.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q8GPI4.pdb')},
 '8i2e__A1_O34841--8i2e__B1_P54421': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8i2e__A1_O34841-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8i2e__B1_P54421-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2rsx__A1_O34841.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8i2d__A1_P54421.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__O34841.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P54421.pdb')},
 '8aeu__A1_Q00987--8aeu__A2_Q00987': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8aeu__A1_Q00987-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8aeu__A2_Q00987-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/6kzu__A1_Q00987.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/6kzu__A1_Q00987.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q00987.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q00987.pdb')},
 '7vso__A1_P02945--7vso__A2_P02945': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7vso__A1_P02945-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7vso__A2_P02945-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/5b34__A1_P02945.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/5b34__A1_P02945.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P02945.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P02945.pdb')},
 '7yuj__B1_Q9BYM8--7yuj__A1_Q9BYM8': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yuj__B1_Q9BYM8-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yuj__A1_Q9BYM8-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8bvl__A1_Q9BYM8.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8bvl__A1_Q9BYM8.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9BYM8.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9BYM8.pdb')},
 '8pvm__A1_P29166--8pvm__B1_P29166': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8pvm__A1_P29166-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8pvm__B1_P29166-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8aio__A1_P29166.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/5byq__A1_P29166.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P29166.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P29166.pdb')},
 '7yo8__A1_P60520--7yo8__A2_P60520': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yo8__A1_P60520-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7yo8__A2_P60520-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7lk3__A1_P60520.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7lk3__A1_P60520.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P60520.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P60520.pdb')},
 '7y51__A1_Q8RBF4--7y51__A2_Q8RBF4': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7y51__A1_Q8RBF4-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7y51__A2_Q8RBF4-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7fbw__A1_Q8RBF4.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7fbw__A1_Q8RBF4.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q8RBF4.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q8RBF4.pdb')},
 '7tvh__B1_Q9I2Q1--7tvh__A1_Q9I2Q1': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7tvh__B1_Q9I2Q1-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7tvh__A1_Q9I2Q1-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/4fgd__A1_Q9I2Q1.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/4f4m__A1_Q9I2Q1.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9I2Q1.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__Q9I2Q1.pdb')},
 '8bwv__D2_A0A482M8M0--8bwv__A1_A0A482M8M0': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8bwv__D2_A0A482M8M0-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/8bwv__A1_A0A482M8M0-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8bbz__A1_A0A482M8M0.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/8bhu__A1_A0A482M8M0.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A482M8M0.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A482M8M0.pdb')},
 '7t91__A1_P08151--7t91__B1_P08151': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7t91__A1_P08151-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7t91__B1_P08151-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2gli__C1_P08151.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/2gli__C1_P08151.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P08151.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__P08151.pdb')},
 '7zoo__B1_A0A979GQH9--7zoo__A1_A0A979GQH9': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zoo__B1_A0A979GQH9-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7zoo__A1_A0A979GQH9-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7zoh__A1_A0A979GQH9.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7zoh__A1_A0A979GQH9.pdb'),
  'pred_receptor': None,
  'pred_ligand': None},
 '7x4b__A1_A0A2D0TCG3--7x4b__B1_A0A2D0TCG3': {'holo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7x4b__A1_A0A2D0TCG3-R.pdb'),
  'holo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/test_set_pdbs/7x4b__B1_A0A2D0TCG3-L.pdb'),
  'apo_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7x31__A1_A0A2D0TCG3.pdb'),
  'apo_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/7x31__A1_A0A2D0TCG3.pdb'),
  'pred_receptor': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A2D0TCG3.pdb'),
  'pred_ligand': PosixPath('/home/runner/.local/share/pinder/2024-02/pdbs/af__A0A2D0TCG3.pdb')}}

Pinder filters

from pinder.core.loader import filters

pinder_id = "1df0__A1_Q07009--1df0__B1_Q64537"
dimer = PinderSystem(entry=pinder_id)

base_filters = [
    filters.FilterByMissingHolo(),
    filters.FilterSubByContacts(min_contacts=5, radius=10.0, calpha_only=True),
    filters.FilterByHoloElongation(max_var_contribution=0.92),
    filters.FilterDetachedHolo(radius=12, max_components=2),
]
sub_filters = [
    filters.FilterSubByAtomTypes(min_atom_types=4),
    filters.FilterByHoloOverlap(min_overlap=5),
    filters.FilterByHoloSeqIdentity(min_sequence_identity=0.8),
    filters.FilterSubLengths(min_length=0, max_length=1000),
    filters.FilterSubRmsds(rmsd_cutoff=7.5),
    filters.FilterByElongation(max_var_contribution=0.92),
    filters.FilterDetachedSub(radius=12, max_components=2),
]
dimers = [dimer]
for sub_filter in sub_filters:
    dimers = (sub_filter(dimer) for dimer in dimers)

for base_filter in base_filters:
    dimers = (dimer for dimer in dimers if base_filter(dimer))

dimers

2024-09-13 20:38:48,690 | pinder.core.utils.cloud:375 | INFO : Gsutil process_many=download_to_filename, threads=4, items=7

2024-09-13 20:38:48,835 | pinder.core.utils.cloud.process_many:23 | INFO : runtime succeeded:      0.14s

<generator object <genexpr> at 0x7f308c66bb50>

list(dimers)[0]

PinderSystem(
entry = IndexEntry(
    (
        'split',
        'invalid',
    ),
    (
        'id',
        '1df0__A1_Q07009--1df0__B1_Q64537',
    ),
    (
        'pdb_id',
        '1df0',
    ),
    (
        'cluster_id',
        'cluster_1030_1030',
    ),
    (
        'cluster_id_R',
        'cluster_1030',
    ),
    (
        'cluster_id_L',
        'cluster_1030',
    ),
    (
        'pinder_s',
        False,
    ),
    (
        'pinder_xl',
        False,
    ),
    (
        'pinder_af2',
        False,
    ),
    (
        'uniprot_R',
        'Q07009',
    ),
    (
        'uniprot_L',
        'Q64537',
    ),
    (
        'holo_R_pdb',
        '1df0__A1_Q07009-R.pdb',
    ),
    (
        'holo_L_pdb',
        '1df0__B1_Q64537-L.pdb',
    ),
    (
        'predicted_R_pdb',
        'af__Q07009.pdb',
    ),
    (
        'predicted_L_pdb',
        'af__Q64537.pdb',
    ),
    (
        'apo_R_pdb',
        '',
    ),
    (
        'apo_L_pdb',
        '',
    ),
    (
        'apo_R_pdbs',
        '',
    ),
    (
        'apo_L_pdbs',
        '',
    ),
    (
        'holo_R',
        True,
    ),
    (
        'holo_L',
        True,
    ),
    (
        'predicted_R',
        True,
    ),
    (
        'predicted_L',
        True,
    ),
    (
        'apo_R',
        False,
    ),
    (
        'apo_L',
        False,
    ),
    (
        'apo_R_quality',
        '',
    ),
    (
        'apo_L_quality',
        '',
    ),
    (
        'chain1_neff',
        492.25,
    ),
    (
        'chain2_neff',
        528.0,
    ),
    (
        'chain_R',
        'A1',
    ),
    (
        'chain_L',
        'B1',
    ),
    (
        'contains_antibody',
        False,
    ),
    (
        'contains_antigen',
        False,
    ),
    (
        'contains_enzyme',
        True,
    ),
)
native=Structure(
    filepath=/home/runner/.local/share/pinder/2024-02/pdbs/1df0__A1_Q07009--1df0__B1_Q64537.pdb,
    uniprot_map=None,
    pinder_id='1df0__A1_Q07009--1df0__B1_Q64537',
    atom_array=<class 'biotite.structure.AtomArray'> with shape (6391,),
    pdb_engine='fastpdb',
)
holo_receptor=Structure(
    filepath=/home/runner/.local/share/pinder/2024-02/pdbs/1df0__A1_Q07009-R.pdb,
    uniprot_map=/home/runner/.local/share/pinder/2024-02/mappings/1df0__A1_Q07009-R.parquet,
    pinder_id='1df0__A1_Q07009-R',
    atom_array=<class 'biotite.structure.AtomArray'> with shape (4964,),
    pdb_engine='fastpdb',
)
holo_ligand=Structure(
    filepath=/home/runner/.local/share/pinder/2024-02/pdbs/1df0__B1_Q64537-L.pdb,
    uniprot_map=/home/runner/.local/share/pinder/2024-02/mappings/1df0__B1_Q64537-L.parquet,
    pinder_id='1df0__B1_Q64537-L',
    atom_array=<class 'biotite.structure.AtomArray'> with shape (1427,),
    pdb_engine='fastpdb',
)
apo_receptor=None
apo_ligand=None
pred_receptor=Structure(
    filepath=/home/runner/.local/share/pinder/2024-02/pdbs/af__Q07009.pdb,
    uniprot_map=None,
    pinder_id='af__Q07009',
    atom_array=<class 'biotite.structure.AtomArray'> with shape (5631,),
    pdb_engine='fastpdb',
)
pred_ligand=Structure(
    filepath=/home/runner/.local/share/pinder/2024-02/pdbs/af__Q64537.pdb,
    uniprot_map=None,
    pinder_id='af__Q64537',
    atom_array=<class 'biotite.structure.AtomArray'> with shape (2006,),
    pdb_engine='fastpdb',
)
)