DeepMutSim 1.0.0__tar.gz

deepmutsim-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Liu Sun
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

deepmutsim-1.0.0/PKG-INFO

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: DeepMutSim
+Version: 1.0.0
+Summary: Generates all possible SNVs for MANE transcripts using HGVS nomenclature.
+Author-email: Liu Sun <sunliu@yxnu.edu.cn>, Jian Yang <yangjian@yxnu.edu.cn>
+Project-URL: Homepage, https://github.com/liu-sun/DeepMutSim
+Project-URL: Issues, https://github.com/liu-sun/DeepMutSim/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: License :: OSI Approved :: MIT License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython
+Dynamic: license-file
+
+# DeepMutSim
+
+DeepMutSim generates simulations for all possible single nucleotide variants (SNVs) for the Matched Annotation from NCBI and EMBL-EBI (MANE) transcript, along with the corresponding protein using HGVS notation.
+
+**INSTALLATION**
+
+```powershell
+pip install deepmutsim
+```
+CONFIGURATION (Mandatory)
+
+Before you can use DeepMutSim, you must set two environment variables to query the NCBI Entrez database.
+
+    EMAIL: (Required by NCBI) A valid email address so NCBI can contact you if there's an issue with your queries.
+
+    API_KEY: (Recommended) An NCBI API key, which allows for a much higher query rate. You can obtain one from your NCBI account settings.
+
+Linux/macOS:
+```Bash
+
+export EMAIL="your.email@example.com"
+export API_KEY="your_api_key_here"
+```
+Windows (PowerShell):
+
+```powershell
+set EMAIL="your.email@example.com"
+set API_KEY="your_api_key_here"
+```
+USAGE
+
+Variant Simulator
+```Python
+
+import deepmutsim
+# Assumes EMAIL and API_KEY are set
+deepmutsim.cds("INS")
+```
+
+```python
+[('NM_000207.3:c.1A>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ... ('NM_000207.3:c.328A>T', 'NP_000198.1:p.(N110Y)', 'NP_000198.1:p.(Asn110Tyr)'), ('NM_000207.3:c.328A>C', 'NP_000198.1:p.(N110H)', 'NP_000198.1:p.(Asn110His)'), ('NM_000207.3:c.329A>T', 'NP_000198.1:p.(N110I)', 'NP_000198.1:p.(Asn110Ile)'), ('NM_000207.3:c.329A>C', 'NP_000198.1:p.(N110T)', 'NP_000198.1:p.(Asn110Thr)'), ('NM_000207.3:c.330C>T', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>A', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>G', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)')]
+```
+```Python
+
+deepmutsim.utr5("INS")
+```
+```python
+['NM_000207.3:c.-59A>G', 'NM_000207.3:c.-59A>T', 'NM_000207.3:c.-59A>C', 'NM_000207.3:c.-58G>A', 'NM_000207.3:c.-58G>T', ... 'NM_000207.3:c.-2C>A', 'NM_000207.3:c.-2C>T', 'NM_000207.3:c.-1C>G', 'NM_000207.3:c.-1C>A', 'NM_000207.3:c.-1C>T']
+```
+```Python
+
+deepmutsim.utr3("INS")
+```
+```python
+['NM_000207.3:c.*1A>G', 'NM_000207.3:c.*1A>T', 'NM_000207.3:c.*1A>C', 'NM_000207.3:c.*2C>G', 'NM_000207.3:c.*2C>A', ... 'NM_000207.3:c.*72G>T', 'NM_000207.3:c.*72G>C', 'NM_000207.3:c.*73C>G', 'NM_000207.3:c.*73C>A', 'NM_000207.3:c.*73C>T']
+```
+```Python
+
+deepmutsim.splice_site("INS")
+```
+```python
+['NC_000011.10(NM_000207.3):c.187+1G>A', 'NC_000011.10(NM_000207.3):c.187+1G>T', 'NC_000011.10(NM_000207.3):c.187+1G>C', 'NC_000011.10(NM_000207.3):c.187+2T>A', 'NC_000011.10(NM_000207.3):c.187+2T>G', 'NC_000011.10(NM_000207.3):c.187+2T>C', 'NC_000011.10(NM_000207.3):c.188-2A>G', 'NC_000011.10(NM_000207.3):c.188-2A>T', 'NC_000011.10(NM_000207.3):c.188-2A>C', 'NC_000011.10(NM_000207.3):c.188-1G>A', 'NC_000011.10(NM_000207.3):c.188-1G>T', 'NC_000011.10(NM_000207.3):c.188-1G>C']
+```

deepmutsim-1.0.0/README.md

@@ -0,0 +1,63 @@
+# DeepMutSim
+
+DeepMutSim generates simulations for all possible single nucleotide variants (SNVs) for the Matched Annotation from NCBI and EMBL-EBI (MANE) transcript, along with the corresponding protein using HGVS notation.
+
+**INSTALLATION**
+
+```powershell
+pip install deepmutsim
+```
+CONFIGURATION (Mandatory)
+
+Before you can use DeepMutSim, you must set two environment variables to query the NCBI Entrez database.
+
+    EMAIL: (Required by NCBI) A valid email address so NCBI can contact you if there's an issue with your queries.
+
+    API_KEY: (Recommended) An NCBI API key, which allows for a much higher query rate. You can obtain one from your NCBI account settings.
+
+Linux/macOS:
+```Bash
+
+export EMAIL="your.email@example.com"
+export API_KEY="your_api_key_here"
+```
+Windows (PowerShell):
+
+```powershell
+set EMAIL="your.email@example.com"
+set API_KEY="your_api_key_here"
+```
+USAGE
+
+Variant Simulator
+```Python
+
+import deepmutsim
+# Assumes EMAIL and API_KEY are set
+deepmutsim.cds("INS")
+```
+
+```python
+[('NM_000207.3:c.1A>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ... ('NM_000207.3:c.328A>T', 'NP_000198.1:p.(N110Y)', 'NP_000198.1:p.(Asn110Tyr)'), ('NM_000207.3:c.328A>C', 'NP_000198.1:p.(N110H)', 'NP_000198.1:p.(Asn110His)'), ('NM_000207.3:c.329A>T', 'NP_000198.1:p.(N110I)', 'NP_000198.1:p.(Asn110Ile)'), ('NM_000207.3:c.329A>C', 'NP_000198.1:p.(N110T)', 'NP_000198.1:p.(Asn110Thr)'), ('NM_000207.3:c.330C>T', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>A', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>G', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)')]
+```
+```Python
+
+deepmutsim.utr5("INS")
+```
+```python
+['NM_000207.3:c.-59A>G', 'NM_000207.3:c.-59A>T', 'NM_000207.3:c.-59A>C', 'NM_000207.3:c.-58G>A', 'NM_000207.3:c.-58G>T', ... 'NM_000207.3:c.-2C>A', 'NM_000207.3:c.-2C>T', 'NM_000207.3:c.-1C>G', 'NM_000207.3:c.-1C>A', 'NM_000207.3:c.-1C>T']
+```
+```Python
+
+deepmutsim.utr3("INS")
+```
+```python
+['NM_000207.3:c.*1A>G', 'NM_000207.3:c.*1A>T', 'NM_000207.3:c.*1A>C', 'NM_000207.3:c.*2C>G', 'NM_000207.3:c.*2C>A', ... 'NM_000207.3:c.*72G>T', 'NM_000207.3:c.*72G>C', 'NM_000207.3:c.*73C>G', 'NM_000207.3:c.*73C>A', 'NM_000207.3:c.*73C>T']
+```
+```Python
+
+deepmutsim.splice_site("INS")
+```
+```python
+['NC_000011.10(NM_000207.3):c.187+1G>A', 'NC_000011.10(NM_000207.3):c.187+1G>T', 'NC_000011.10(NM_000207.3):c.187+1G>C', 'NC_000011.10(NM_000207.3):c.187+2T>A', 'NC_000011.10(NM_000207.3):c.187+2T>G', 'NC_000011.10(NM_000207.3):c.187+2T>C', 'NC_000011.10(NM_000207.3):c.188-2A>G', 'NC_000011.10(NM_000207.3):c.188-2A>T', 'NC_000011.10(NM_000207.3):c.188-2A>C', 'NC_000011.10(NM_000207.3):c.188-1G>A', 'NC_000011.10(NM_000207.3):c.188-1G>T', 'NC_000011.10(NM_000207.3):c.188-1G>C']
+```

deepmutsim-1.0.0/pyproject.toml

@@ -0,0 +1,26 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "DeepMutSim"
+version = "1.0.0"
+authors = [
+  { name="Liu Sun", email="sunliu@yxnu.edu.cn" },
+  { name="Jian Yang", email="yangjian@yxnu.edu.cn" },
+]
+description = "Generates all possible SNVs for MANE transcripts using HGVS nomenclature."
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = [
+  "biopython",
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "License :: OSI Approved :: MIT License",
+]
+
+[project.urls]
+Homepage = "https://github.com/liu-sun/DeepMutSim"
+Issues = "https://github.com/liu-sun/DeepMutSim/issues"

deepmutsim-1.0.0/setup.cfg

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

deepmutsim-1.0.0/src/DeepMutSim.egg-info/PKG-INFO

@@ -0,0 +1,79 @@
+Metadata-Version: 2.4
+Name: DeepMutSim
+Version: 1.0.0
+Summary: Generates all possible SNVs for MANE transcripts using HGVS nomenclature.
+Author-email: Liu Sun <sunliu@yxnu.edu.cn>, Jian Yang <yangjian@yxnu.edu.cn>
+Project-URL: Homepage, https://github.com/liu-sun/DeepMutSim
+Project-URL: Issues, https://github.com/liu-sun/DeepMutSim/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: License :: OSI Approved :: MIT License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython
+Dynamic: license-file
+
+# DeepMutSim
+
+DeepMutSim generates simulations for all possible single nucleotide variants (SNVs) for the Matched Annotation from NCBI and EMBL-EBI (MANE) transcript, along with the corresponding protein using HGVS notation.
+
+**INSTALLATION**
+
+```powershell
+pip install deepmutsim
+```
+CONFIGURATION (Mandatory)
+
+Before you can use DeepMutSim, you must set two environment variables to query the NCBI Entrez database.
+
+    EMAIL: (Required by NCBI) A valid email address so NCBI can contact you if there's an issue with your queries.
+
+    API_KEY: (Recommended) An NCBI API key, which allows for a much higher query rate. You can obtain one from your NCBI account settings.
+
+Linux/macOS:
+```Bash
+
+export EMAIL="your.email@example.com"
+export API_KEY="your_api_key_here"
+```
+Windows (PowerShell):
+
+```powershell
+set EMAIL="your.email@example.com"
+set API_KEY="your_api_key_here"
+```
+USAGE
+
+Variant Simulator
+```Python
+
+import deepmutsim
+# Assumes EMAIL and API_KEY are set
+deepmutsim.cds("INS")
+```
+
+```python
+[('NM_000207.3:c.1A>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.1A>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>G', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.2T>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>A', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>T', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ('NM_000207.3:c.3G>C', 'NP_000198.1:p.(M1?)', 'NP_000198.1:p.(Met1?)'), ... ('NM_000207.3:c.328A>T', 'NP_000198.1:p.(N110Y)', 'NP_000198.1:p.(Asn110Tyr)'), ('NM_000207.3:c.328A>C', 'NP_000198.1:p.(N110H)', 'NP_000198.1:p.(Asn110His)'), ('NM_000207.3:c.329A>T', 'NP_000198.1:p.(N110I)', 'NP_000198.1:p.(Asn110Ile)'), ('NM_000207.3:c.329A>C', 'NP_000198.1:p.(N110T)', 'NP_000198.1:p.(Asn110Thr)'), ('NM_000207.3:c.330C>T', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>A', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)'), ('NM_000207.3:c.330C>G', 'NP_000198.1:p.(N110=)', 'NP_000198.1:p.(Asn110=)')]
+```
+```Python
+
+deepmutsim.utr5("INS")
+```
+```python
+['NM_000207.3:c.-59A>G', 'NM_000207.3:c.-59A>T', 'NM_000207.3:c.-59A>C', 'NM_000207.3:c.-58G>A', 'NM_000207.3:c.-58G>T', ... 'NM_000207.3:c.-2C>A', 'NM_000207.3:c.-2C>T', 'NM_000207.3:c.-1C>G', 'NM_000207.3:c.-1C>A', 'NM_000207.3:c.-1C>T']
+```
+```Python
+
+deepmutsim.utr3("INS")
+```
+```python
+['NM_000207.3:c.*1A>G', 'NM_000207.3:c.*1A>T', 'NM_000207.3:c.*1A>C', 'NM_000207.3:c.*2C>G', 'NM_000207.3:c.*2C>A', ... 'NM_000207.3:c.*72G>T', 'NM_000207.3:c.*72G>C', 'NM_000207.3:c.*73C>G', 'NM_000207.3:c.*73C>A', 'NM_000207.3:c.*73C>T']
+```
+```Python
+
+deepmutsim.splice_site("INS")
+```
+```python
+['NC_000011.10(NM_000207.3):c.187+1G>A', 'NC_000011.10(NM_000207.3):c.187+1G>T', 'NC_000011.10(NM_000207.3):c.187+1G>C', 'NC_000011.10(NM_000207.3):c.187+2T>A', 'NC_000011.10(NM_000207.3):c.187+2T>G', 'NC_000011.10(NM_000207.3):c.187+2T>C', 'NC_000011.10(NM_000207.3):c.188-2A>G', 'NC_000011.10(NM_000207.3):c.188-2A>T', 'NC_000011.10(NM_000207.3):c.188-2A>C', 'NC_000011.10(NM_000207.3):c.188-1G>A', 'NC_000011.10(NM_000207.3):c.188-1G>T', 'NC_000011.10(NM_000207.3):c.188-1G>C']
+```

deepmutsim-1.0.0/src/DeepMutSim.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+src/DeepMutSim.egg-info/PKG-INFO
+src/DeepMutSim.egg-info/SOURCES.txt
+src/DeepMutSim.egg-info/dependency_links.txt
+src/DeepMutSim.egg-info/requires.txt
+src/DeepMutSim.egg-info/top_level.txt
+src/deepmutsim/__init__.py

deepmutsim-1.0.0/src/DeepMutSim.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

deepmutsim-1.0.0/src/DeepMutSim.egg-info/requires.txt

@@ -0,0 +1 @@
+biopython

deepmutsim-1.0.0/src/DeepMutSim.egg-info/top_level.txt

@@ -0,0 +1 @@
+deepmutsim

deepmutsim-1.0.0/src/deepmutsim/__init__.py

@@ -0,0 +1,611 @@
+import os
+
+from Bio import Entrez, SeqIO
+from Bio.Data.CodonTable import standard_dna_table
+from Bio.Data.IUPACData import unambiguous_dna_letters, protein_letters
+from Bio.Seq import Seq
+from Bio.SeqFeature import SimpleLocation
+from Bio.SeqUtils import seq3, seq1
+
+Entrez.email = os.environ["EMAIL"]
+Entrez.api_key = os.environ["API_KEY"]
+genetic_code = list(standard_dna_table.forward_table.keys())+standard_dna_table.stop_codons
+
+
+def nm(gene: str) -> str:
+    stream = Entrez.esearch(
+        db="nucleotide",
+        term=f'{gene}[Gene Name] AND ("MANE Select"[Keyword] OR "MANE Plus Clinical"[keyword])',
+    )
+    record = Entrez.read(stream)
+    stream = Entrez.efetch(
+        db="nucleotide", id=record["IdList"], rettype="gb", retmode="text"
+    )
+    seqrecord = SeqIO.read(stream, "genbank")
+    return seqrecord
+
+
+def np(gene: str) -> str:
+    stream = Entrez.esearch(
+        db="protein",
+        term=f'{gene}[Gene Name] AND ("MANE Select"[Keyword] OR "MANE Plus Clinical"[keyword])',
+    )
+    record = Entrez.read(stream)
+    stream = Entrez.efetch(
+        db="protein", id=record["IdList"], rettype="fasta", retmode="text"
+    )
+    seqrecord = SeqIO.read(stream, "fasta")
+    return seqrecord
+
+
+def nc(gene: str) -> str:
+    stream = Entrez.esearch(
+        db="nucleotide",
+        term=f'{gene}[Gene Name] AND "Primary Assembly"[Title] AND human[Organism]',
+    )
+    record = Entrez.read(stream)
+    stream = Entrez.efetch(
+        db="nucleotide", id=record["IdList"], rettype="acc", retmode="text"
+    )
+    acc = stream.read().strip()
+    return acc
+
+
+def cds(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    protein_seqrecord = np(gene)
+    protein = str(protein_seqrecord.seq)
+    protein_id = protein_seqrecord.id
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            cds = feature.extract(seqrecord).seq
+    for index, codon in enumerate(range(0, len(cds) - 3, 3)):
+        for base in unambiguous_dna_letters:
+            if index == 0:
+                if base != "A":
+                    variants.append(
+                        (
+                            f"{seqrecord.id}:c.1A>{base}",
+                            f"{protein_id}:p.(M1?)",
+                            f"{protein_id}:p.(Met1?)",
+                        )
+                    )
+            else:
+                if base != cds[codon]:
+                    seq = Seq(base) + cds[codon + 1 : codon + 3]
+                    if protein[index] != seq.translate():
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                            )
+                        )
+                    else:
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                            )
+                        )
+            if index == 0:
+                if base != "T":
+                    variants.append(
+                        (
+                            f"{seqrecord.id}:c.2T>{base}",
+                            f"{protein_id}:p.(M1?)",
+                            f"{protein_id}:p.(Met1?)",
+                        )
+                    )
+            else:
+                if base != cds[codon + 1]:
+                    seq = cds[codon] + Seq(base) + cds[codon + 2]
+                    if protein[index] != seq.translate():
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                            )
+                        )
+                    else:
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                            )
+                        )
+            if index == 0:
+                if base != "G":
+                    variants.append(
+                        (
+                            f"{seqrecord.id}:c.3G>{base}",
+                            f"{protein_id}:p.(M1?)",
+                            f"{protein_id}:p.(Met1?)",
+                        )
+                    )
+            else:
+                if base != cds[codon + 2]:
+                    seq = cds[codon : codon + 2] + Seq(base)
+                    if protein[index] != seq.translate():
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                            )
+                        )
+                    else:
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base}",
+                                f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                            )
+                        )
+    return variants
+
+
+def utr5(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            utr5 = SimpleLocation(0, feature.location.start).extract(seqrecord).seq
+    for index in range(len(utr5)):
+        for base in unambiguous_dna_letters:
+            if base != utr5[index]:
+                variants.append(
+                    f"{seqrecord.id}:c.{index - len(utr5)}{utr5[index]}>{base}"
+                )
+    return variants
+
+
+def utr3(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            utr3 = (
+                SimpleLocation(feature.location.end, len(seqrecord))
+                .extract(seqrecord)
+                .seq
+            )
+    for index in range(len(utr3)):
+        for base in unambiguous_dna_letters:
+            if base != utr3[index]:
+                variants.append(f"{seqrecord.id}:c.*{index + 1}{utr3[index]}>{base}")
+    return variants
+
+
+def splice_site(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    acc = nc(gene)
+    splicing = []
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            start = feature.location.start
+            end = feature.location.end
+    for feature in seqrecord.features:
+        if feature.type == "exon":
+            if feature.location.end < start or feature.location.start > end:
+                continue
+            else:
+                splicing.extend(
+                    (feature.location.start - start, feature.location.end - start)
+                )
+
+    for coordinate in range(1, len(splicing) - 1, 2):
+        site = splicing[coordinate], splicing[coordinate] + 1
+        for base in unambiguous_dna_letters:
+            if base != "G":
+                variants.append(f"{acc}({seqrecord.id}):c.{site[0]}+1G>{base}")
+            if base != "T":
+                variants.append(f"{acc}({seqrecord.id}):c.{site[0]}+2T>{base}")
+            if base != "A":
+                variants.append(f"{acc}({seqrecord.id}):c.{site[1]}-2A>{base}")
+            if base != "G":
+                variants.append(f"{acc}({seqrecord.id}):c.{site[1]}-1G>{base}")
+    return variants
+
+
+def aa_sub(gene: str) -> list:
+    variants = []
+    seqrecord = np(gene)
+    for index, residue in enumerate(seqrecord.seq, 1):
+        for aa in protein_letters:
+            if aa != residue:
+                if index != 1:
+                    variants.append(
+                        (
+                            f"{seqrecord.id}:p.({residue}{index}{aa})",
+                            f"{seqrecord.id}:p.({seq3(residue)}{index}{seq3(aa)})",
+                        )
+                    )
+                else:
+                    variants.append(
+                        (
+                            f"{seqrecord.id}:p.({residue}{index}?)",
+                            f"{seqrecord.id}:p.({seq3(residue)}{index}?)",
+                        )
+                    )
+    return variants
+
+
+def codon_sub(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            cds = feature.location.extract(seqrecord).seq
+    for index, codon in enumerate(range(0, len(cds) - 3, 3)):
+        for base in genetic_code:
+            if base != cds[codon : codon + 3]:
+                seq = Seq(base)
+                if all(
+                    (
+                        base[0] != cds[codon],
+                        base[1] != cds[codon + 1],
+                        base[2] != cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}"
+                    )
+                elif all(
+                    (
+                        base[0] == cds[codon],
+                        base[1] != cds[codon + 1],
+                        base[2] != cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}"
+                    )
+                elif all(
+                    (
+                        base[0] != cds[codon],
+                        base[1] == cds[codon + 1],
+                        base[2] != cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}"
+                    )
+                elif all(
+                    (
+                        base[0] != cds[codon],
+                        base[1] != cds[codon + 1],
+                        base[2] == cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}"
+                    )
+                elif all(
+                    (
+                        base[0] == cds[codon],
+                        base[1] == cds[codon + 1],
+                        base[2] != cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}"
+                    )
+                elif all(
+                    (
+                        base[0] == cds[codon],
+                        base[1] != cds[codon + 1],
+                        base[2] == cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}"
+                    )
+                elif all(
+                    (
+                        base[0] != cds[codon],
+                        base[1] == cds[codon + 1],
+                        base[2] == cds[codon + 2],
+                    )
+                ):
+                    variants.append(
+                        f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}"
+                    )
+    return variants
+
+
+def missense(gene: str) -> list:
+    variants = []
+    seqrecord = nm(gene)
+    protein_seqrecord = np(gene)
+    protein = str(protein_seqrecord.seq)
+    protein_id = protein_seqrecord.id
+    for feature in seqrecord.features:
+        if feature.type == "CDS":
+            cds = feature.location.extract(seqrecord).seq
+    for index, codon in enumerate(range(0, len(cds) - 3, 3)):
+        for base in genetic_code:
+            if base != cds[codon : codon + 3]:
+                seq = Seq(base)
+                if index == 0:
+                    if all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        variants.append(
+                            (
+                                f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
+                                f"{protein_id}:p.(M1?)",
+                                f"{protein_id}:p.(Met1?)",
+                            )
+                        )
+                else:
+                    if all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 2}_{codon + 3}delins{base[1:3]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 3}delins{base}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}_{codon + 2}delins{base[0:2]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] != cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 3}{cds[codon + 2]}>{base[2]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] == cds[codon],
+                            base[1] != cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 2}{cds[codon + 1]}>{base[1]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+                    elif all(
+                        (
+                            base[0] != cds[codon],
+                            base[1] == cds[codon + 1],
+                            base[2] == cds[codon + 2],
+                        )
+                    ):
+                        if protein[index] != seq.translate():
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}{seq.translate()})",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}{seq3(seq.translate())})",
+                                )
+                            )
+                        else:
+                            variants.append(
+                                (
+                                    f"{seqrecord.id}:c.{codon + 1}{cds[codon]}>{base[0]}",
+                                    f"{protein_id}:p.({protein[index]}{index + 1}=)",
+                                    f"{protein_id}:p.({seq3(protein[index])}{index + 1}=)",
+                                )
+                            )
+    return variants
+
+
+if __name__ == "__main__":
+    import pprint
+
+    # pprint.pprint(cds("INS"))
+    # pprint.pprint(missense("INS"))
+    # pprint.pprint(aa_sub("INS"))
+    # pprint.pprint(utr5("INS"))
+    # pprint.pprint(utr3("INS"))
+    pprint.pprint(splice_site("INS"))
+    # pprint.pprint(codon_sub("INS"))
+    # pprint.pprint(nc("INS"))
+    # pprint.pprint(np("INS"))
+    # pprint.pprint(nm("INS"))