Граф коммитов

394 Коммитов

Автор SHA1 Сообщение Дата
Kevin Kaichuang Yang af695772c4 Increment version. 2024-07-31 10:58:35 -04:00
Kevin Kaichuang Yang edaaa04182
Merge pull request #22 from sarahalamdari/main
update alphabet
2024-04-10 13:36:58 -07:00
sarahalamdari eb04f65295 update alphabet 2024-04-10 16:12:49 -04:00
Kevin Kaichuang Yang 354fde009b Specify pad token in LMCollater. 2024-04-10 08:13:15 -04:00
Kevin Kaichuang Yang b50869f6f0 Set use_reentrant explicitly. 2024-03-27 12:47:30 -04:00
Kevin Kaichuang Yang c930f9fe08 Newer versions of numpy don't allow jagged arrays. 2024-03-25 17:24:40 -04:00
Kevin Kaichuang Yang d5e664f526 Clustered sampler. 2024-03-25 17:07:34 -04:00
Kevin Kaichuang Yang 399be5e4ed Fix length bookkeeping. 2024-03-14 10:00:56 -04:00
Kevin Kaichuang Yang 7cf76442b4 Add collater for scl. 2024-03-13 15:14:10 -04:00
Kevin Kaichuang Yang 13df666193 Add enhancer alphabet. 2024-03-13 15:14:00 -04:00
Kevin Kaichuang Yang 28ccf64690 Add collater for scl. 2024-03-13 15:13:39 -04:00
Kevin Kaichuang Yang 142b10a69b Add ability to sample batchsizes in multiples of x. 2024-03-13 15:11:27 -04:00
Kevin Kaichuang Yang 6856e45dac Add ESM2 alphabet. 2023-12-19 11:43:34 -05:00
Kevin Kaichuang Yang c7fc0af894 Add option to add start and stop tokens in seq-fitness collaters. 2023-12-19 11:43:19 -05:00
Kevin Kaichuang Yang 6f77721d0a Add option not to tie weights in ESM models. 2023-12-19 11:42:38 -05:00
Kevin Kaichuang Yang 0eecb6e22d Update the 2d cnn models. 2023-01-18 14:45:14 -05:00
Kevin Kaichuang Yang 3d43b37221 Redefine roberta head. 2022-12-13 14:33:50 -05:00
Kevin Kaichuang Yang eba33ea6e4 Fix type error in MSA datasets. 2022-12-13 14:32:29 -05:00
Kevin Kaichuang Yang f39f194750 Add GVP code. 2022-12-13 14:31:37 -05:00
Kevin Kaichuang Yang 161825191a Update ARDM losses and collaters. 2022-09-30 11:39:52 -04:00
Kevin Kaichuang Yang e69e1e8aeb Change MSA constants to be easier for d3pm. 2022-09-30 11:39:31 -04:00
Kevin Kaichuang Yang 885a24f980 Actually fix constants. 2022-08-29 11:37:57 -04:00
Kevin Kaichuang Yang 29226bfa75 Increment version. 2022-08-26 14:56:12 -04:00
Kevin Kaichuang Yang 6ce7214a2e Merge branch 'msadiff' 2022-08-26 14:48:43 -04:00
Kevin Kaichuang Yang 7830d78b3f Merge branch 'main' of https://github.com/microsoft/protein-sequence-models 2022-08-26 14:48:11 -04:00
Kevin Kaichuang Yang 9e09f90c24 Fix constants. 2022-08-26 14:47:36 -04:00
Kevin Kaichuang Yang a706a6c076 get rid of extra prints. 2022-08-19 14:20:19 -04:00
Kevin Kaichuang Yang cf87977035 Increment version. 2022-08-19 09:27:39 -04:00
Kevin Kaichuang Yang b06bf7a4ce Add option to handle msa-transformer batching. 2022-08-19 09:26:40 -04:00
Kevin Kaichuang Yang 4903ebac4c Only import wget if necessary 2022-08-19 09:26:19 -04:00
Nitya Thakkar 57072e49c3 pulled new changes 2022-08-17 11:51:13 -05:00
Nitya Thakkar a62f886f4d added dataset class for zero shot 2022-08-17 11:46:55 -05:00
Nitya Thakkar ffe5355285 A3M dataset for trrosetta test 2022-08-15 16:51:28 -05:00
Kevin Kaichuang Yang f913b2b266
Merge pull request #11 from LouisRanjard/main
Update argument variable name.
2022-08-11 23:14:14 -04:00
Louis 9febf1a787 Update argument variable name. 2022-08-12 15:07:22 +12:00
Kevin Kaichuang Yang 1930966b18 Merge branch 'main' of https://github.com/microsoft/protein-sequence-models 2022-08-10 14:06:22 -04:00
Kevin Kaichuang Yang 7246166fc3 Add new scripts and fix mif. 2022-08-10 14:05:58 -04:00
Kevin Kaichuang Yang 457527eca7 Update readme. 2022-08-10 14:04:25 -04:00
Nitya Thakkar 51a6c5e54f dataset update 2022-08-07 11:49:54 -05:00
Nitya Thakkar 9e95b5d9ca updated loss function 2022-07-29 13:16:15 -04:00
Kevin Kaichuang Yang fd24ab85c5
Merge pull request #10 from wukevin/patch-1
Test for reading gzip and non-gzipped pdb files
2022-07-28 15:44:04 -04:00
Kevin Wu d418e77c27 Test that reading a pdb file and its gzipped version produce same results 2022-07-28 12:12:10 -07:00
Kevin Kaichuang Yang 4df218f2d3
Merge pull request #9 from wukevin/patch-1
Support for parsing pdb.gz files
2022-07-28 15:00:38 -04:00
Kevin Wu 6b2225d1ab
Support for parsing pdb.gz files 2022-07-28 11:52:43 -07:00
Kevin Kaichuang Yang 8df3de679d Document getting different representations from CARP. 2022-07-27 15:54:41 -04:00
Kevin Kaichuang Yang 673459f22d Merge branch 'main' of https://github.com/microsoft/protein-sequence-models 2022-07-27 15:49:18 -04:00
Kevin Kaichuang Yang 4c63f800e4 Make it easy to extract layer-wise representations from CARP. 2022-07-27 15:48:59 -04:00
Nitya Thakkar a8005e2192 updated openfold dataset alignment 2022-07-26 14:51:31 -04:00
Kevin Kaichuang Yang fda57669ab
Add biorxiv link for BiGCARP. 2022-07-25 11:37:01 -04:00
Nitya Thakkar dd7a1edd76 working dataset and sampler 2022-07-19 15:21:41 -04:00