Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Copy alphafold from colabfold #1

Merged
merged 115 commits into from
Dec 19, 2023
Merged
Changes from 1 commit
Commits
Show all changes
115 commits
Select commit Hold shift + click to select a range
a984544
Update residue_constants.py
konstin Sep 13, 2021
da95c23
Lower log level for unimportant message
konstin Sep 14, 2021
fe570bf
Apply config patch
konstin Oct 12, 2021
d92701d
Apply model patch
konstin Oct 12, 2021
fd8e5b1
Apply patch
konstin Oct 12, 2021
ddf0df3
Apply protein patch
konstin Oct 12, 2021
ab7470d
- Remove seen_sequence from make_msa_features to avoid paired sequenc…
martin-steinegger Nov 7, 2021
a2cda93
Change name for publishing
konstin Nov 8, 2021
e8cd13b
Comment _merge_homomers_dense_msa to improve monomer prediction
martin-steinegger Nov 8, 2021
2ca1db9
Turn on dense MSA again
martin-steinegger Nov 9, 2021
14ca53f
Bump to 2.1.1
konstin Nov 10, 2021
4c4ba8c
Rebase fallout
konstin Nov 10, 2021
2f711c4
Update repo url
konstin Nov 10, 2021
0b49aef
Speed up param loading
konstin Oct 12, 2021
b5ae6dc
Bump to 2.1.2
konstin Nov 25, 2021
cb97fbc
Publish form github actions
konstin Nov 25, 2021
a603b95
Stop at score for recycles
konstin Nov 25, 2021
6a1f885
Make stop_at_score float for #119
konstin Dec 6, 2021
48403a4
Show num_recycles for multimer
konstin Dec 7, 2021
e2147eb
Bump to 2.1.4
konstin Dec 9, 2021
40373b6
Set max_subsequence_ratio to 1.0
martin-steinegger Mar 2, 2022
4d3c8d3
Update version to 2.1.6
martin-steinegger Mar 4, 2022
c5ca042
Merge branch 'main' of https://github.com/deepmind/alphafold into main
martin-steinegger Mar 29, 2022
4c3305e
Update setup.py
martin-steinegger Mar 29, 2022
6675e23
Remove duplicate, template_sequence len and align_ratio check
martin-steinegger Apr 17, 2022
871c0e1
Update setup.py to 2.1.8
martin-steinegger Apr 17, 2022
442769a
Try to improve compiling
martin-steinegger Jun 13, 2022
f8fc267
Update setup.py
martin-steinegger Jun 13, 2022
3ae102a
Update setup.py
martin-steinegger Jun 13, 2022
26fd0e1
Change folding_multimer to compile faster
martin-steinegger Jun 14, 2022
53c5f4f
Merge branch 'main' of https://github.com/steineggerlab/alphafold
martin-steinegger Jun 14, 2022
6aa2c1a
Change return type in multimer
martin-steinegger Jun 14, 2022
e9c90a7
Update modules.py
sokrypton Jun 15, 2022
caed7d9
Update modules.py
sokrypton Jun 15, 2022
85458e1
Update modules.py
sokrypton Jun 15, 2022
3dc7924
adding recycling outside of the jax compiled code
sokrypton Jun 15, 2022
e0f9e74
fixing typo
sokrypton Jun 15, 2022
f0576ed
fixing typos
sokrypton Jun 15, 2022
99faa88
fixing typos
sokrypton Jun 15, 2022
3198c24
typo
sokrypton Jun 15, 2022
220e3ca
Update modules_multimer.py
sokrypton Jun 15, 2022
c677789
Update modules.py
sokrypton Jun 15, 2022
661205b
Update model.py
sokrypton Jun 15, 2022
302e502
adding manual recycling support for multimers
sokrypton Jun 15, 2022
301259c
fixing recycle count
sokrypton Jun 15, 2022
c721f49
Update modules_multimer.py
sokrypton Jun 15, 2022
68a64ac
rm key subsampling
sokrypton Jun 15, 2022
ac9314b
debugging
sokrypton Jun 15, 2022
4f0609d
debugging
sokrypton Jun 15, 2022
a4cd359
Update modules_multimer.py
sokrypton Jun 15, 2022
66a7fd4
Update model.py
sokrypton Jun 15, 2022
8c0e152
cleaning up the code
sokrypton Jun 15, 2022
eee1696
typo
sokrypton Jun 15, 2022
6eb24bd
Merge pull request #1 from steineggerlab/beta
sokrypton Jun 15, 2022
c59135e
Cond fix for older jax version
martin-steinegger Jun 15, 2022
6741fa7
Add recycle early-stopping to the model
martin-steinegger Jun 15, 2022
371776f
Update repository to 2.1.10
martin-steinegger Jun 15, 2022
9efbba8
fixing the missing key in fold_iteration
sokrypton Jun 15, 2022
36239c8
Merge branch 'main' of https://github.com/deepmind/alphafold
martin-steinegger Jun 16, 2022
c10b155
Merge branch 'main' of https://github.com/steineggerlab/alphafold
martin-steinegger Jun 16, 2022
82933e1
Update version to 2.1.11
martin-steinegger Jun 16, 2022
bd696aa
bugfix: removing nans from alphafold-multimer+templates
sokrypton Jun 17, 2022
433dbe0
Update to 2.1.12
martin-steinegger Jun 17, 2022
00ebb93
Update model.py
sokrypton Jun 21, 2022
d6bf859
Update model.py
sokrypton Jun 21, 2022
b78a234
Add 2.1.13 (fix ensemble)
martin-steinegger Jun 21, 2022
829d7f3
Update setup.py
martin-steinegger Jun 21, 2022
9719482
Workaround for breaking change in PDB.PDBIO v1.80 not working correct…
milot-mirdita Nov 20, 2022
68c2feb
Actually fix PDBIO issue
milot-mirdita Nov 20, 2022
f50fd03
Merge branch 'main' of https://github.com/deepmind/alphafold into dee…
sokrypton Dec 24, 2022
7e373e9
Merge branch 'deepmind-main' into main
sokrypton Dec 24, 2022
581ddbc
adding support for fused triangle attention to monomers (#2)
sokrypton Jan 17, 2023
c39f51b
adding option to "unfuse"
sokrypton Jan 18, 2023
dcc29d9
Update utils.py
sokrypton Jan 18, 2023
dfeb777
Update utils.py
sokrypton Jan 18, 2023
aec67d0
Squashed commit of the following:
sokrypton Jan 19, 2023
7875336
set eval_dropout when user specifies is_training
sokrypton Jan 19, 2023
b66109f
Update model.py
sokrypton Jan 19, 2023
db8d806
adjust config to revert back to old settings for multimer v1/v2
sokrypton Jan 20, 2023
f1f406e
enable fuse for all models by default
sokrypton Jan 21, 2023
3e865eb
bugfix: typo in config (v1, v2 multimer settings)
sokrypton Jan 21, 2023
0914bc3
add use_cluster_profile and recycle_early_stop_tolerance support
sokrypton Jan 21, 2023
ea7f5dd
adding recycle_early_stop_tolerance support for monomers
sokrypton Jan 21, 2023
2aa7093
add bfloat16 support for monomers
sokrypton Jan 22, 2023
ffccec9
Update model.py
sokrypton Jan 22, 2023
44a144b
Create stereo_chemical_props.txt
sokrypton Jan 28, 2023
8b78b68
Update setup.py
sokrypton Jan 28, 2023
e322994
fix templates
sokrypton Jan 30, 2023
bf7c767
Create MANIFEST.in
sokrypton Jan 30, 2023
8d57312
fix stereo_chemical_props.txt path
sokrypton Jan 30, 2023
978543a
Merge branch 'pr/4'
sokrypton Jan 30, 2023
83b076e
speedup
sokrypton Feb 1, 2023
4f00a9b
speedup
sokrypton Feb 1, 2023
96a3a2b
adding mask to ptm/iptm calculation
sokrypton Feb 2, 2023
bebd0e2
adding iptm support for ptm models
sokrypton Feb 2, 2023
36c5925
Update modules.py
sokrypton Feb 3, 2023
15eb3e0
Merge pull request #3 from sokrypton/main
martin-steinegger Feb 3, 2023
80092dc
moving key splitting to model.py
sokrypton Feb 7, 2023
5b00c00
keep raw outputs
sokrypton Feb 7, 2023
627a7e9
Update model.py
sokrypton Feb 7, 2023
8730453
Update modules.py
sokrypton Feb 10, 2023
cf096a6
allow for no batch inputs
sokrypton Feb 10, 2023
ba75383
v2.3.2
sokrypton Feb 11, 2023
8f50ccb
v2.3.3 - fixing memory leaks
sokrypton Feb 14, 2023
41807ea
v2.3.4 - fix memory leaks (attempt 2) (#6)
sokrypton Feb 18, 2023
bec81ee
Update modules.py
sokrypton Feb 20, 2023
405dd85
add option to provide custom offset
sokrypton Feb 21, 2023
b39d7dd
Update config.py
sokrypton Feb 21, 2023
3d3fdde
Update config.py
sokrypton Feb 21, 2023
7386194
Update OpenMM imports to work with new OpenMM API
milot-mirdita Apr 29, 2023
ba597e0
Merge pull request #1 from steineggerlab/main
sokrypton May 10, 2023
1f04253
patch for jax > 0.3.25
sokrypton May 24, 2023
024dcb2
fix single representation
sokrypton Jun 2, 2023
7c09316
Update modules_multimer.py
sokrypton Jul 24, 2023
ee6bbad
Update to sokrypton version of alphafold
ajtritt Dec 19, 2023
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
bugfix: removing nans from alphafold-multimer+templates
sokrypton authored Jun 17, 2022
commit bd696aaa91480a2d4af9a50592471276abcb1987
2 changes: 1 addition & 1 deletion alphafold/model/utils.py
Original file line number Diff line number Diff line change
@@ -34,7 +34,7 @@ def final_init(config):

def batched_gather(params, indices, axis=0, batch_dims=0):
"""Implements a JAX equivalent of `tf.gather` with `axis` and `batch_dims`."""
take_fn = lambda p, i: jnp.take(p, i, axis=axis)
take_fn = lambda p, i: jnp.take(p, i, axis=axis, mode="clip")
for _ in range(batch_dims):
take_fn = jax.vmap(take_fn)
return take_fn(params, indices)