kprot 0.0.1__tar.gz

kprot-0.0.1/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

kprot-0.0.1/MANIFEST.in

@@ -0,0 +1,5 @@
+include pyproject.toml
+include LICENSE
+include CONTRIBUTING.md
+include README.md
+recursive-exclude * __pycache__

kprot-0.0.1/PKG-INFO

@@ -0,0 +1,92 @@
+Metadata-Version: 2.4
+Name: kprot
+Version: 0.0.1
+Summary: nbdev project for kprot
+Author-email: sky1ove <lcai888666@gmail.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/sky1ove/kprot
+Project-URL: Documentation, https://sky1ove.github.io/kprot/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython>=1.87
+Requires-Dist: matplotlib>=3.10.8
+Requires-Dist: pandas>=2.3.3
+Requires-Dist: requests>=2.33.1
+Requires-Dist: scikit-learn>=1.7.2
+Requires-Dist: sentencepiece>=0.2.1
+Requires-Dist: torch>=2.11.0
+Requires-Dist: tqdm>=4.67.3
+Requires-Dist: transformers>=5.5.3
+Dynamic: license-file
+
+# kprot
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+This file will become your README and also the index of your
+documentation.
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install kprot in Development mode
+
+``` sh
+# make sure kprot package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to kprot
+$ nbdev_prepare
+```
+
+## Usage
+
+### Installation
+
+Install latest from the GitHub
+[repository](https://github.com/sky1ove/kprot):
+
+``` sh
+$ pip install git+https://github.com/sky1ove/kprot.git
+```
+
+or from [conda](https://anaconda.org/sky1ove/kprot)
+
+``` sh
+$ conda install -c sky1ove kprot
+```
+
+or from [pypi](https://pypi.org/project/kprot/)
+
+``` sh
+$ pip install kprot
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/sky1ove/kprot)’s
+[pages](https://sky1ove.github.io/kprot/). Additionally you can find
+package manager specific guidelines on
+[conda](https://anaconda.org/sky1ove/kprot) and
+[pypi](https://pypi.org/project/kprot/) respectively.
+
+## How to use
+
+Fill me in please! Don’t forget code examples:
+
+``` python
+1+1
+```
+
+    2

kprot-0.0.1/README.md

@@ -0,0 +1,67 @@
+# kprot
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+This file will become your README and also the index of your
+documentation.
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install kprot in Development mode
+
+``` sh
+# make sure kprot package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to kprot
+$ nbdev_prepare
+```
+
+## Usage
+
+### Installation
+
+Install latest from the GitHub
+[repository](https://github.com/sky1ove/kprot):
+
+``` sh
+$ pip install git+https://github.com/sky1ove/kprot.git
+```
+
+or from [conda](https://anaconda.org/sky1ove/kprot)
+
+``` sh
+$ conda install -c sky1ove kprot
+```
+
+or from [pypi](https://pypi.org/project/kprot/)
+
+``` sh
+$ pip install kprot
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/sky1ove/kprot)’s
+[pages](https://sky1ove.github.io/kprot/). Additionally you can find
+package manager specific guidelines on
+[conda](https://anaconda.org/sky1ove/kprot) and
+[pypi](https://pypi.org/project/kprot/) respectively.
+
+## How to use
+
+Fill me in please! Don’t forget code examples:
+
+``` python
+1+1
+```
+
+    2

kprot-0.0.1/kprot/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.1"

kprot-0.0.1/kprot/_modidx.py

@@ -0,0 +1,22 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/kprot',
+                'doc_host': 'https://sky1ove.github.io',
+                'git_url': 'https://github.com/sky1ove/kprot',
+                'lib_path': 'kprot'},
+  'syms': { 'kprot.embeddings': { 'kprot.embeddings.get_esm': ('embeddings.html#get_esm', 'kprot/embeddings.py'),
+                                  'kprot.embeddings.get_t5': ('embeddings.html#get_t5', 'kprot/embeddings.py'),
+                                  'kprot.embeddings.get_t5_bfd': ('embeddings.html#get_t5_bfd', 'kprot/embeddings.py')},
+            'kprot.onehot': { 'kprot.onehot.filter_range_columns': ('onehot_kmeans.html#filter_range_columns', 'kprot/onehot.py'),
+                              'kprot.onehot.get_clusters_elbow': ('onehot_kmeans.html#get_clusters_elbow', 'kprot/onehot.py'),
+                              'kprot.onehot.onehot_encode': ('onehot_kmeans.html#onehot_encode', 'kprot/onehot.py'),
+                              'kprot.onehot.onehot_encode_df': ('onehot_kmeans.html#onehot_encode_df', 'kprot/onehot.py'),
+                              'kprot.onehot.run_kmeans': ('onehot_kmeans.html#run_kmeans', 'kprot/onehot.py')},
+            'kprot.uniprot': { 'kprot.uniprot.apply_mut_complex': ('utils.html#apply_mut_complex', 'kprot/uniprot.py'),
+                               'kprot.uniprot.apply_mut_single': ('utils.html#apply_mut_single', 'kprot/uniprot.py'),
+                               'kprot.uniprot.compare_seq': ('utils.html#compare_seq', 'kprot/uniprot.py'),
+                               'kprot.uniprot.get_uniprot_features': ('utils.html#get_uniprot_features', 'kprot/uniprot.py'),
+                               'kprot.uniprot.get_uniprot_kd': ('utils.html#get_uniprot_kd', 'kprot/uniprot.py'),
+                               'kprot.uniprot.get_uniprot_seq': ('utils.html#get_uniprot_seq', 'kprot/uniprot.py'),
+                               'kprot.uniprot.get_uniprot_type': ('utils.html#get_uniprot_type', 'kprot/uniprot.py')}}}

kprot-0.0.1/kprot/embeddings.py

@@ -0,0 +1,165 @@
+""".."""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/03_embeddings.ipynb.
+
+# %% auto #0
+__all__ = ['def_device', 'get_esm', 'get_t5', 'get_t5_bfd']
+
+# %% ../nbs/03_embeddings.ipynb #5ff79e13
+import gc
+import re
+
+import pandas as pd
+import torch
+from tqdm.notebook import tqdm; tqdm.pandas()
+
+# %% ../nbs/03_embeddings.ipynb #cc83e8ac
+def_device = 'mps' if torch.backends.mps.is_available() else 'cuda' if torch.cuda.is_available() else 'cpu'
+
+# %% ../nbs/03_embeddings.ipynb #8400a96d
+def get_esm(
+    df: pd.DataFrame, # DataFrame containing protein sequences
+    col: str, # column with amino acid sequences
+    model_name: str = "esm2_t33_650M_UR50D",
+    batch_size: int = 1, # Number of sequences per batch
+):
+    "Extract ESM2 embeddings (mean pooled per sequence)."
+
+    # model, alphabet = esm.pretrained.load_model_and_alphabet(model_name)
+    model, alphabet = torch.hub.load("facebookresearch/esm:main", model_name)
+    model = model.to(def_device)
+    model.eval()
+
+    batch_converter = alphabet.get_batch_converter()
+
+    # Infer repr layer
+    match = re.search(r"_t(\d+)_", model_name)
+    if not match:
+        raise ValueError(f"Cannot infer repr layer from {model_name}")
+    layer = int(match.group(1))
+
+    print(f"Using ESM layer {layer}")
+    print("Available models:\n"
+          "esm2_t48_15B_UR50D\n"
+          "esm2_t36_3B_UR50D\n"
+          "esm2_t33_650M_UR50D\n"
+          "esm2_t30_150M_UR50D\n"
+          "esm2_t12_35M_UR50D\n"
+          "esm2_t6_8M_UR50D\n")
+
+    sequences = df[col].tolist()
+    all_embeddings = []
+
+    for i in tqdm(range(0, len(sequences), batch_size)):
+        batch_seqs = sequences[i : i + batch_size]
+        data = [(f"seq_{j}", s) for j, s in enumerate(batch_seqs)]
+
+        batch_labels, batch_strs, batch_tokens = batch_converter(data)
+        batch_tokens = batch_tokens.to(def_device)
+
+        with torch.no_grad():
+            results = model(batch_tokens, repr_layers=[layer], return_contacts=False)
+
+        token_reps = results["representations"][layer]
+        batch_lens = (batch_tokens != alphabet.padding_idx).sum(1)
+
+        for j, seq_len in enumerate(batch_lens):
+            # skip BOS (0), stop before EOS
+            emb = token_reps[j, 1 : seq_len - 1].mean(0)
+            all_embeddings.append(emb.cpu().numpy())
+
+        del results, token_reps, batch_tokens
+        torch.cuda.empty_cache()
+        gc.collect()
+
+    df_emb = pd.DataFrame(
+        all_embeddings,
+        index=df.index,
+        columns=[f"esm_{i}" for i in range(len(all_embeddings[0]))],
+    )
+
+    return df_emb
+
+# %% ../nbs/03_embeddings.ipynb #8f95abe4
+def get_t5(df: pd.DataFrame, 
+           col: str = 'sequence'
+           ):
+    "Extract ProtT5-XL-uniref50 embeddings from protein sequence in a dataframe"
+    from transformers import T5Tokenizer, T5EncoderModel
+    
+    # Reference: https://github.com/agemagician/ProtTrans/tree/master/Embedding/PyTorch/Advanced
+    # Load the tokenizer
+    tokenizer = T5Tokenizer.from_pretrained('Rostlab/prot_t5_xl_half_uniref50-enc', do_lower_case=False)
+
+    # Load the model
+    model = T5EncoderModel.from_pretrained("Rostlab/prot_t5_xl_half_uniref50-enc").to(def_device)
+
+    # Set the model precision based on the device
+    model.half()
+    
+    def T5_embeddings(sequence):
+        seq_len = len(sequence)
+        # Prepare the protein sequences as a list
+        sequence = [" ".join(list(re.sub(r"[UZOB]", "X", sequence)))]
+
+        # Tokenize sequences and pad up to the longest sequence in the batch
+        ids = tokenizer.batch_encode_plus(sequence, add_special_tokens=True, padding="longest")
+        input_ids = torch.tensor(ids['input_ids']).to(def_device)
+        attention_mask = torch.tensor(ids['attention_mask']).to(def_device)
+        # Generate embeddings
+        with torch.no_grad():
+            embedding_rpr = model(input_ids=input_ids, attention_mask=attention_mask)
+
+        emb_mean = embedding_rpr.last_hidden_state[0][:seq_len].detach().to(torch.float32).cpu().numpy().mean(axis=0)
+
+        return emb_mean
+
+    series = df[col].progress_apply(T5_embeddings)
+        
+
+    T5_feature = pd.DataFrame(series.tolist(),index=df.index)
+    T5_feature.columns = 'T5_' + T5_feature.columns.astype(str)
+    
+    return T5_feature
+
+# %% ../nbs/03_embeddings.ipynb #90fd2058
+def get_t5_bfd(df:pd.DataFrame, 
+               col: str = 'sequence'
+               ):
+    
+    "Extract ProtT5-XL-BFD embeddings from protein sequence in a dataframe"
+    # Reference: https://github.com/agemagician/ProtTrans/tree/master/Embedding/PyTorch/Advanced
+    from transformers import T5Tokenizer, T5Model
+    # Load the tokenizer
+    tokenizer = T5Tokenizer.from_pretrained('Rostlab/prot_t5_xl_bfd', do_lower_case=False)
+
+    model = T5Model.from_pretrained("Rostlab/prot_t5_xl_bfd").to(def_device)
+
+    model.eval()
+    
+    def T5_embeddings_bfd(sequence, device = def_device):
+        seq_len = len(sequence)
+
+        # Prepare the protein sequences as a list
+        sequence = [" ".join(list(re.sub(r"[UZOB]", "X", sequence)))]
+
+        # Tokenize sequences and pad up to the longest sequence in the batch
+        ids = tokenizer.batch_encode_plus(sequence, add_special_tokens=True, padding="longest")
+        input_ids = torch.tensor(ids['input_ids']).to(def_device)
+        attention_mask = torch.tensor(ids['attention_mask']).to(def_device)
+
+        # Generate embeddings
+        with torch.no_grad():
+            embedding_rpr = model(input_ids=input_ids, attention_mask=attention_mask, decoder_input_ids = input_ids)
+
+        emb_mean = embedding_rpr.last_hidden_state[0][:seq_len].detach().to(torch.float32).cpu().numpy().mean(axis=0)
+
+        return emb_mean
+
+    series = df[col].progress_apply(T5_embeddings_bfd)
+        
+
+    T5_feature = pd.DataFrame(series.tolist(),index=df.index)
+    T5_feature.columns = 'T5bfd_' + T5_feature.columns.astype(str)
+    
+    return T5_feature

kprot-0.0.1/kprot/onehot.py

@@ -0,0 +1,56 @@
+"""onehot & kmeans"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/02_onehot_kmeans.ipynb.
+
+# %% auto #0
+__all__ = ['onehot_encode', 'onehot_encode_df', 'run_kmeans', 'filter_range_columns', 'get_clusters_elbow']
+
+# %% ../nbs/02_onehot_kmeans.ipynb #5ff79e13
+import pandas as pd
+from sklearn.cluster import KMeans
+from sklearn.preprocessing import OneHotEncoder
+from matplotlib import pyplot as plt
+
+# %% ../nbs/02_onehot_kmeans.ipynb #0589ced9
+def onehot_encode(sequences, transform_colname=True, n=20):
+    encoder = OneHotEncoder(handle_unknown='ignore', sparse_output=False)
+    encoded_array = encoder.fit_transform([list(seq) for seq in sequences])
+    colnames = [x[1:] for x in encoder.get_feature_names_out()]
+    if transform_colname:
+        colnames = [f"{int(item.split('_', 1)[0]) - n}{item.split('_', 1)[1]}" for item in colnames]
+    encoded_df = pd.DataFrame(encoded_array)
+    encoded_df.columns=colnames
+    return encoded_df
+
+# %% ../nbs/02_onehot_kmeans.ipynb #56e3bace
+def onehot_encode_df(df,seq_col='site_seq', **kwargs):
+    return onehot_encode(df[seq_col],**kwargs)
+
+# %% ../nbs/02_onehot_kmeans.ipynb #ca2244e2
+def run_kmeans(onehot,n=2,seed=42):
+    "Take onehot encoded and regurn the cluster number."
+    kmeans = KMeans(n_clusters=n, random_state=seed,n_init='auto')
+    return kmeans.fit_predict(onehot)
+
+# %% ../nbs/02_onehot_kmeans.ipynb #9dc8cea5
+def filter_range_columns(df, # df need to have column names of position + aa
+                         low=-10,high=10):
+    positions = df.columns.str[:-1].astype(int)
+    mask = (positions >= low) & (positions <= high)
+    return df.loc[:,mask]
+
+# %% ../nbs/02_onehot_kmeans.ipynb #5f3cf9f9
+def get_clusters_elbow(encoded_data,max_cluster=400, interval=50):
+
+    wcss = []
+    for i in range(1, max_cluster,interval):
+        kmeans = KMeans(n_clusters=i, random_state=42)
+        kmeans.fit(encoded_data)
+        wcss.append(kmeans.inertia_)
+
+    # Plot the Elbow graph
+    plt.figure(figsize=(5, 3))
+    plt.plot(range(1, max_cluster,interval), wcss)
+    plt.title(f'Elbow Method (n={len(encoded_data)})')
+    plt.xlabel('# Clusters')
+    plt.ylabel('WCSS')

kprot-0.0.1/kprot/uniprot.py

@@ -0,0 +1,281 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/01_utils.ipynb.
+
+# %% auto #0
+__all__ = ['get_uniprot_seq', 'get_uniprot_features', 'get_uniprot_kd', 'get_uniprot_type', 'apply_mut_single',
+           'apply_mut_complex', 'compare_seq']
+
+# %% ../nbs/01_utils.ipynb #d1ba401f-ec26-4182-986a-e40837f9a915
+import requests, re
+from functools import lru_cache
+
+from Bio.Align import PairwiseAligner
+
+# %% ../nbs/01_utils.ipynb #81c804f5-a4d8-4b99-a47e-3355779a1bbd
+@lru_cache()
+def get_uniprot_seq(uniprot_id):
+    "Queries the UniProt database to retrieve the protein sequence for a given UniProt ID."
+    
+    url = f"https://www.uniprot.org/uniprot/{uniprot_id}.fasta"
+    response = requests.get(url)
+
+    # Check if the request was successful (status code 200)
+    if response.status_code == 200:
+        data = response.text
+        # The sequence starts after the first line, which is a description
+        sequence = ''.join(data.split('\n')[1:]).strip()
+        return sequence
+    else:
+        return f"Error: Unable to retrieve sequence for UniProt ID {uniprot_id}. Status code: {response.status_code}"
+
+# %% ../nbs/01_utils.ipynb #68c733a5-bbc9-4373-b9d2-23c545e74316
+@lru_cache()
+def get_uniprot_features(uniprot_id):
+    "Given uniprot_id, get specific region for uniprot features."
+    # uniprot REST API
+    url = f"https://rest.uniprot.org/uniprotkb/{uniprot_id}.json"
+    response = requests.get(url)
+
+    if response.status_code == 200:
+        data = response.json()
+        # Extract the "features" section which contains information
+        features = data.get('features', [])
+        
+        protein_name = (
+            data.get("proteinDescription", {})
+                .get("recommendedName", {})
+                .get("fullName", {})
+                .get("value")
+        )
+
+        gene_name = (
+            data.get("genes", [{}])[0]
+                .get("geneName", {})
+                .get("value")
+        )
+        return {
+            "uniprot_id": uniprot_id,
+            "protein_name": protein_name,
+            "gene_name": gene_name,
+            "features": features
+        }
+    else:
+        raise ValueError(f"Failed to retrieve UniProt features for {uniprot_id}")
+
+# %% ../nbs/01_utils.ipynb #26d793bb-3f87-4e84-bcf6-6ca62a794b32
+def get_uniprot_kd(uniprot_id):
+    "Query 'Domain: Protein kinase' based on UniProt ID and get its sequence info."
+    data = get_uniprot_features(uniprot_id)
+    seq = get_uniprot_seq(uniprot_id)
+    out = []
+
+    for feature in data['features']:
+        if feature.get("type") == "Domain" and "Protein kinase" in feature.get("description", ""):
+            start = feature['location']['start']['value']
+            end = feature['location']['end']['value']
+            out.append({
+                "uniprot_id": uniprot_id,
+                "protein_name": data["protein_name"],
+                "gene_name": data["gene_name"],
+                "start": start,
+                "end": end,
+                "description": feature.get("description", ""),
+                "sequence": seq[start-1:end]
+            })
+
+    return out
+
+# %% ../nbs/01_utils.ipynb #4005a8aa-f8a1-4b99-819e-d7c08d487bf2
+def get_uniprot_type(uniprot_id,type_='Signal'):
+    "Get region sequences based on UniProt ID features."
+    data = get_uniprot_features(uniprot_id)
+    seq = get_uniprot_seq(uniprot_id)
+
+    out = []
+
+    for feature in data['features']:
+        if feature.get("type") == type_:
+            start = feature['location']['start']['value']
+            end = feature['location']['end']['value']
+            region = {
+                'uniprot_id': uniprot_id,
+                'type': feature['type'],
+                "protein_name": data["protein_name"],
+                "gene_name": data["gene_name"],
+                'start': start,
+                'end': end,
+                'description': feature['description'],
+                'sequence': seq[start-1:end]
+            }
+            out.append(region)
+
+    if not out:
+        available = sorted({f.get("type") for f in data['features'] if f.get("type")})
+        print(f"No feature of type '{type_}' found for {uniprot_id}.")
+        print(f"Available feature types: {', '.join(available)}")
+        return available
+
+    return out
+
+# %% ../nbs/01_utils.ipynb #f06c0c1d-829d-4f9e-bcc2-9457050faaf4
+def apply_mut_single(seq, # protein sequence
+           *mutations, # e.g., E709A
+           start_pos=1, # if the protein sequence does not start from index 1, indicate the start index to match the mutations
+           ):
+    "Apply mutations to a protein sequence."
+    seq_list = list(seq)  # convert to list for mutability
+    
+    for mut in mutations:
+        # check mutation format
+        if len(mut) < 3: raise ValueError(f"Invalid mutation format: {mut}")
+        
+        from_aa,pos,to_aa = mut[0],int(mut[1:-1])-start_pos,mut[-1]
+
+        # make sure position is within the sequence length
+        if pos < 0 or pos >= len(seq_list): raise IndexError(f"Position {pos + 1} out of range for sequence length {len(seq_list)}")
+        # make sure aa from mutations matches the residue on the sequence
+        if seq_list[pos] != from_aa: raise ValueError(f"Expected {from_aa} at position {pos + 1}, found {seq_list[pos]}")
+        
+        seq_list[pos] = to_aa
+        print('Converted:', mut)
+        
+    return ''.join(seq_list)
+
+# %% ../nbs/01_utils.ipynb #5c66ef12-8348-4dc6-affc-04858c1411f5
+def apply_mut_complex(seq, # protein sequence
+                      mut, # mutation (e.g., G776delinsVC/S783C, G778dupGSP)
+                      start_pos=1, # if truncated protein sequence, indicate where it starts to match the position of mutation
+                      ):
+    """
+    Apply a composite mutation like 'G776delinsVC/S783C' to `seq`,
+    assuming `seq[0]` corresponds to residue number `start_pos`.
+
+    * At most one delins **or** dup is allowed.
+    * Point substitutions are executed first; the indel/dup is done last.
+    """
+    _sub_pat    = re.compile(r'^([A-Z])(\d+)([A-Z])$')          # e.g. S783C
+    _delins_pat = re.compile(r'^([A-Z])(\d+)delins([A-Z]+)$')   # e.g. G776delinsVC
+    _dup_pat    = re.compile(r'^([A-Z])(\d+)dup([A-Z]+)$')      # e.g. G778dupGSP
+
+    seq = list(seq)
+    tokens = mut.split('/')
+
+    # ---------- 1) substitutions (length-neutral) ----------
+    for m in tokens:
+        if _sub_pat.match(m):
+            orig, pos, new = _sub_pat.match(m).groups()
+            idx = int(pos) - start_pos
+            if seq[idx] != orig:
+                raise ValueError(
+                    f"Mismatch at position {pos}: expected {orig}, got {seq[idx]}"
+                )
+            seq[idx] = new
+
+    # ---------- 2) the single length-changing event ----------
+    for m in tokens:
+        if _delins_pat.match(m):
+            orig, pos, ins = _delins_pat.match(m).groups()
+            idx = int(pos) - start_pos
+            if seq[idx] != orig:
+                raise ValueError(
+                    f"Mismatch at position {pos}: expected {orig}, got {seq[idx]}"
+                )
+            seq[idx : idx + 1] = list(ins)         # replace 1 residue with many
+            break
+
+        if _dup_pat.match(m):
+            orig, pos, dup = _dup_pat.match(m).groups()
+            idx = int(pos) - start_pos
+            if seq[idx] != orig:
+                raise ValueError(
+                    f"Mismatch at position {pos}: expected {orig}, got {seq[idx]}"
+                )
+            seq[idx + 1 : idx + 1] = list(dup)     # insert right after the residue
+            break
+
+    return ''.join(seq)
+
+# %% ../nbs/01_utils.ipynb #5ac69a8c-fe83-48fc-926f-b99a15624ce3
+def compare_seq(
+    seq1: str,
+    seq2: str,
+    *,
+    start_pos: int = 1,
+    label1: str = "Original",
+    label2: str = "Mutant",
+    visualize: bool = True,
+    return_text: bool = False,
+):
+    """
+    Align two protein sequences and summarise differences.
+    Returns a formatted text block (and can optionally print it).
+    """
+
+    # ----- global alignment using PairwiseAligner -----
+    aligner = PairwiseAligner()
+    aligner.mode = "global"
+    aligner.match_score = 2
+    aligner.mismatch_score = -1
+    aligner.open_gap_score = -5
+    aligner.extend_gap_score = -0.5
+
+    alignment = aligner.align(seq1, seq2)[0]
+    aln1 = alignment.aligned[0]
+    aln2 = alignment.aligned[1]
+
+    # Reconstruct aligned strings from aligned segments
+    aligned_seq1, aligned_seq2 = [], []
+    i1, i2 = 0, 0
+
+    for (start1, end1), (start2, end2) in zip(aln1, aln2):
+        while i1 < start1:
+            aligned_seq1.append(seq1[i1]); aligned_seq2.append('-'); i1 += 1
+        while i2 < start2:
+            aligned_seq1.append('-'); aligned_seq2.append(seq2[i2]); i2 += 1
+        for _ in range(end1 - start1):
+            aligned_seq1.append(seq1[i1]); aligned_seq2.append(seq2[i2]); i1 += 1; i2 += 1
+
+    while i1 < len(seq1):
+        aligned_seq1.append(seq1[i1]); aligned_seq2.append('-'); i1 += 1
+    while i2 < len(seq2):
+        aligned_seq1.append('-'); aligned_seq2.append(seq2[i2]); i2 += 1
+
+    aln1_str = ''.join(aligned_seq1)
+    aln2_str = ''.join(aligned_seq2)
+
+    # ----- find differences -----
+    diffs, raw_i1, raw_i2 = [], 0, 0
+    for a1, a2 in zip(aln1_str, aln2_str):
+        if a1 != '-' and a2 != '-':
+            if a1 != a2:
+                diffs.append((start_pos + raw_i1, a1, a2, 'substitution'))
+            raw_i1 += 1
+            raw_i2 += 1
+        elif a1 == '-' and a2 != '-':
+            diffs.append((start_pos + raw_i1, '-', a2, 'insertion'))
+            raw_i2 += 1
+        elif a1 != '-' and a2 == '-':
+            diffs.append((start_pos + raw_i1, a1, '-', 'deletion'))
+            raw_i1 += 1
+
+    # ----- build output text -----
+    lines = []
+    if visualize:
+        for block in range(0, len(aln1_str), 80):
+            s1_block = aln1_str[block:block + 80]
+            s2_block = aln2_str[block:block + 80]
+            marker = ''.join(' ' if x == y else '^' for x, y in zip(s1_block, s2_block))
+            left_idx = start_pos + len(aln1_str[:block].replace('-', ''))
+            right_idx = left_idx + len(s1_block.replace('-', '')) - 1
+            lines.append(f"{label1:<10} {left_idx:>5}-{right_idx:<5}: {s1_block}")
+            lines.append(f"{label2:<10} {'':>11}: {s2_block}")
+            lines.append(f"{'':>22}  {marker}\n")
+
+    lines.append("Differences:")
+    for pos, ref, new, kind in diffs:
+        lines.append(f"  {kind:<12} at {pos:>4}: {ref} → {new}")
+
+    text = "\n".join(lines)
+
+    if not return_text: print(text)
+
+    return text if return_text else None

kprot-0.0.1/kprot.egg-info/PKG-INFO

@@ -0,0 +1,92 @@
+Metadata-Version: 2.4
+Name: kprot
+Version: 0.0.1
+Summary: nbdev project for kprot
+Author-email: sky1ove <lcai888666@gmail.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/sky1ove/kprot
+Project-URL: Documentation, https://sky1ove.github.io/kprot/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython>=1.87
+Requires-Dist: matplotlib>=3.10.8
+Requires-Dist: pandas>=2.3.3
+Requires-Dist: requests>=2.33.1
+Requires-Dist: scikit-learn>=1.7.2
+Requires-Dist: sentencepiece>=0.2.1
+Requires-Dist: torch>=2.11.0
+Requires-Dist: tqdm>=4.67.3
+Requires-Dist: transformers>=5.5.3
+Dynamic: license-file
+
+# kprot
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+This file will become your README and also the index of your
+documentation.
+
+## Developer Guide
+
+If you are new to using `nbdev` here are some useful pointers to get you
+started.
+
+### Install kprot in Development mode
+
+``` sh
+# make sure kprot package is installed in development mode
+$ pip install -e .
+
+# make changes under nbs/ directory
+# ...
+
+# compile to have changes apply to kprot
+$ nbdev_prepare
+```
+
+## Usage
+
+### Installation
+
+Install latest from the GitHub
+[repository](https://github.com/sky1ove/kprot):
+
+``` sh
+$ pip install git+https://github.com/sky1ove/kprot.git
+```
+
+or from [conda](https://anaconda.org/sky1ove/kprot)
+
+``` sh
+$ conda install -c sky1ove kprot
+```
+
+or from [pypi](https://pypi.org/project/kprot/)
+
+``` sh
+$ pip install kprot
+```
+
+### Documentation
+
+Documentation can be found hosted on this GitHub
+[repository](https://github.com/sky1ove/kprot)’s
+[pages](https://sky1ove.github.io/kprot/). Additionally you can find
+package manager specific guidelines on
+[conda](https://anaconda.org/sky1ove/kprot) and
+[pypi](https://pypi.org/project/kprot/) respectively.
+
+## How to use
+
+Fill me in please! Don’t forget code examples:
+
+``` python
+1+1
+```
+
+    2

kprot-0.0.1/kprot.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+kprot/__init__.py
+kprot/_modidx.py
+kprot/embeddings.py
+kprot/onehot.py
+kprot/uniprot.py
+kprot.egg-info/PKG-INFO
+kprot.egg-info/SOURCES.txt
+kprot.egg-info/dependency_links.txt
+kprot.egg-info/entry_points.txt
+kprot.egg-info/requires.txt
+kprot.egg-info/top_level.txt

kprot-0.0.1/kprot.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

kprot-0.0.1/kprot.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[nbdev]
+kprot = kprot._modidx:d

kprot-0.0.1/kprot.egg-info/requires.txt

@@ -0,0 +1,9 @@
+biopython>=1.87
+matplotlib>=3.10.8
+pandas>=2.3.3
+requests>=2.33.1
+scikit-learn>=1.7.2
+sentencepiece>=0.2.1
+torch>=2.11.0
+tqdm>=4.67.3
+transformers>=5.5.3

kprot-0.0.1/kprot.egg-info/top_level.txt

@@ -0,0 +1 @@
+kprot

kprot-0.0.1/pyproject.toml

@@ -0,0 +1,45 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "kprot"
+dynamic = ["version"]
+description = "nbdev project for kprot"
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "Apache-2.0"}
+authors = [{name = "sky1ove", email = "lcai888666@gmail.com"}]
+keywords = ['nbdev']
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+]
+dependencies = [
+    "biopython>=1.87",
+    "matplotlib>=3.10.8",
+    "pandas>=2.3.3",
+    "requests>=2.33.1",
+    "scikit-learn>=1.7.2",
+    "sentencepiece>=0.2.1",
+    "torch>=2.11.0",
+    "tqdm>=4.67.3",
+    "transformers>=5.5.3",
+]
+
+[project.urls]
+Repository = "https://github.com/sky1ove/kprot"
+Documentation = "https://sky1ove.github.io/kprot/"
+
+[project.entry-points.nbdev]
+kprot = "kprot._modidx:d"
+
+[tool.setuptools.dynamic]
+version = {attr = "kprot.__version__"}
+
+[tool.setuptools.packages.find]
+include = ["kprot"]
+
+[tool.nbdev]
+title = "kprot"
+lib_path = "kprot"

kprot-0.0.1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+