rcsb-embedding-model 0.0.26__py3-none-any.whl → 0.0.28__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of rcsb-embedding-model might be problematic. Click here for more details.

@@ -53,6 +53,7 @@ class EsmProtFromChain(Dataset):
53
53
  dtype=str,
54
54
  names=EsmProtFromChain.COLUMNS
55
55
  )
56
+ self.data = self.data.sort_values(by=self.data.columns[0])
56
57
 
57
58
  def __len__(self):
58
59
  return len(self.data)
@@ -52,6 +52,7 @@ class ResidueAssemblyEmbeddingFromTensorFile(Dataset):
52
52
  dtype=str,
53
53
  names=ResidueAssemblyEmbeddingFromTensorFile.COLUMNS
54
54
  )
55
+ self.data = self.data.sort_values(by=self.data.columns[0])
55
56
 
56
57
  def __len__(self):
57
58
  return len(self.data)
@@ -33,6 +33,7 @@ class ResidueEmbeddingFromTensorFile(Dataset):
33
33
  index_col=None,
34
34
  names=ResidueEmbeddingFromTensorFile.COLUMNS
35
35
  )
36
+ self.data = self.data.sort_values(by=self.data.columns[0])
36
37
 
37
38
  def __len__(self):
38
39
  return len(self.data)
@@ -1,7 +1,8 @@
1
1
  import os
2
- from io import StringIO
3
-
4
2
  import requests
3
+ import gzip
4
+ from io import StringIO, BytesIO
5
+
5
6
  import torch
6
7
 
7
8
 
@@ -40,10 +41,24 @@ def stringio_from_url(url):
40
41
  try:
41
42
  response = requests.get(url)
42
43
  response.raise_for_status()
43
- return StringIO(response.text)
44
+ data = response.content
45
+ if url.endswith('.bcif.gz'):
46
+ with gzip.GzipFile(fileobj=BytesIO(data), mode='rb') as gz:
47
+ decompressed_data = gz.read()
48
+ return BytesIO(decompressed_data)
49
+ if url.endswith('.gz'):
50
+ compressed = BytesIO(data)
51
+ with gzip.open(compressed, 'rt') as f:
52
+ return StringIO(f.read())
53
+ else:
54
+ return StringIO(response.text)
44
55
  except requests.exceptions.RequestException as e:
45
56
  print(f"Error fetching URL: {e}")
46
57
  return None
58
+ except (OSError, gzip.BadGzipFile) as e:
59
+ print(f"Error decompressing gzip file: {e}")
60
+ return None
61
+
47
62
 
48
63
 
49
64
  def concatenate_tensors(file_list, max_residues, dim=0):
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: rcsb-embedding-model
3
- Version: 0.0.26
3
+ Version: 0.0.28
4
4
  Summary: Protein Embedding Model for Structure Search
5
5
  Project-URL: Homepage, https://github.com/rcsb/rcsb-embedding-model
6
6
  Project-URL: Issues, https://github.com/rcsb/rcsb-embedding-model/issues
@@ -2,12 +2,12 @@ rcsb_embedding_model/__init__.py,sha256=r3gLdeBIXkQEQA_K6QcRPO-TtYuAQSutk6pXRUE_
2
2
  rcsb_embedding_model/rcsb_structure_embedding.py,sha256=dKp9hXQO0JAnO4SEfjJ_mG_jHu3UxAPguv6jkOjp-BI,4487
3
3
  rcsb_embedding_model/cli/args_utils.py,sha256=7nP2q8pL5dWK_U7opxtWmoFcYVwasky6elHk-dASFaI,165
4
4
  rcsb_embedding_model/cli/inference.py,sha256=tfMvHAhkUIzJ2RbTtQjq7eWmOUrSyVfH5bjTkCCSIS8,19500
5
- rcsb_embedding_model/dataset/esm_prot_from_chain.py,sha256=mYk3Xnm_QK25iyWGPyWRQLpNzpXfZcUbNUSLSXOJe7Q,3889
5
+ rcsb_embedding_model/dataset/esm_prot_from_chain.py,sha256=9YVDONAUaIL0U0J_A_0gokN5sN6FgthJHRg_YXTIFLk,3956
6
6
  rcsb_embedding_model/dataset/esm_prot_from_structure.py,sha256=TeITPdi1uc3qLQ-Pgn807oH6eM0LYv-67RE50ZT4dLI,2551
7
7
  rcsb_embedding_model/dataset/resdiue_assembly_embedding_from_structure.py,sha256=worRiNqOJRjyr693TaillsS65bdTdGOoHfwyT9yE1O4,2866
8
- rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py,sha256=JG4rrhziIUtdTmbuTbMbEYHrvlda4m5VWvdJXe_Sv3c,3449
8
+ rcsb_embedding_model/dataset/residue_assembly_embedding_from_tensor_file.py,sha256=U-XbLVC6d17viKWlSWMs80ztj9VsKjR167B8OvvOfWY,3516
9
9
  rcsb_embedding_model/dataset/residue_embedding_from_structure.py,sha256=dxfUNcVmdl8LrtQf1UJQ4E79e7R9LRsL0fjsq2GJQRk,2796
10
- rcsb_embedding_model/dataset/residue_embedding_from_tensor_file.py,sha256=ehHQuLI2TrE5l4_4n6p3e30i17O1pXW92KOCn7bGtcg,1274
10
+ rcsb_embedding_model/dataset/residue_embedding_from_tensor_file.py,sha256=qxSnbajARYvyl_KUzoDjqtuCI8YH_7ATpWqDSY0D6F0,1341
11
11
  rcsb_embedding_model/inference/assembly_inferece.py,sha256=8fPJjEXy1WsM5XB5U7KfdO5-Du6nEsawsaAjmWoXA9I,2329
12
12
  rcsb_embedding_model/inference/chain_inference.py,sha256=6f5wVzjtRtHU3BPMTe5k3nH_Nl440Am8BL8h1vmK1jI,2925
13
13
  rcsb_embedding_model/inference/esm_inference.py,sha256=rn6H43D8BYzMZbMu7UPsLYg2dgERmmpci5weNItrG5Q,2546
@@ -18,13 +18,13 @@ rcsb_embedding_model/modules/chain_module.py,sha256=KsZw2uagO4rpAKWv6ivqEMxIEzgt
18
18
  rcsb_embedding_model/modules/esm_module.py,sha256=otJRbCb319nCCob_4E1W_UClhkex9eDqcCyzWQO-vIs,740
19
19
  rcsb_embedding_model/modules/structure_module.py,sha256=4js02XzKvhc_G26ELsGhJ9SCi_wlvtVolObxfWt3BhE,1077
20
20
  rcsb_embedding_model/types/api_types.py,sha256=SCwALwvEb0KRKaoWKbuN7JyfOH-1whsI0Z4ki41dht8,1235
21
- rcsb_embedding_model/utils/data.py,sha256=ATgHC6d7xgc2eYtCsEsgMxhAFvYp4R9C0TlNStc1jG0,3254
21
+ rcsb_embedding_model/utils/data.py,sha256=BOjYdIRHrFqk8qFuKGrgCtVyfDupzgOVmH_0C-ecMvg,3813
22
22
  rcsb_embedding_model/utils/model.py,sha256=xr3p02ohOgJ5UInwdIupN68Oq4yvNFhxobZRacS1adg,953
23
23
  rcsb_embedding_model/utils/structure_parser.py,sha256=IWMQ8brlEMe6_ND-DBESOli8vlqHxladTssjbM9RSKw,2751
24
24
  rcsb_embedding_model/utils/structure_provider.py,sha256=eWtxjkPpmRfmil_DKR1J6miaXR3lQ28DF5O0qrqSgGA,786
25
25
  rcsb_embedding_model/writer/batch_writer.py,sha256=rTFNasB0Xp4-XCNTXKeEWZxSrb7lvZytoRldJUWn9Jg,3312
26
- rcsb_embedding_model-0.0.26.dist-info/METADATA,sha256=eQ2PQmXlSEWkXQHW9dXQaPN-_YzcQq_tYGmGygT_WM4,5310
27
- rcsb_embedding_model-0.0.26.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
28
- rcsb_embedding_model-0.0.26.dist-info/entry_points.txt,sha256=MK11jTIEmaV-x4CkPX5IymDaVs7Ky_f2xxU8BJVZ_9Q,69
29
- rcsb_embedding_model-0.0.26.dist-info/licenses/LICENSE.md,sha256=oUaHiKgfBkChth_Sm67WemEvatO1U0Go8LHjaskXY0w,1522
30
- rcsb_embedding_model-0.0.26.dist-info/RECORD,,
26
+ rcsb_embedding_model-0.0.28.dist-info/METADATA,sha256=JRvgA3ENLMvuixsucnu2MYvKybrXpCki1h01pfLD0ho,5310
27
+ rcsb_embedding_model-0.0.28.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
28
+ rcsb_embedding_model-0.0.28.dist-info/entry_points.txt,sha256=MK11jTIEmaV-x4CkPX5IymDaVs7Ky_f2xxU8BJVZ_9Q,69
29
+ rcsb_embedding_model-0.0.28.dist-info/licenses/LICENSE.md,sha256=oUaHiKgfBkChth_Sm67WemEvatO1U0Go8LHjaskXY0w,1522
30
+ rcsb_embedding_model-0.0.28.dist-info/RECORD,,