Skip to content

Fixes mutations docs #151

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.

Sign up for GitHub

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

Merged
haeussma merged 11 commits into from
Jun 6, 2025
Merged

Fixes mutations docs #151

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
e1cf658
fixed old functions for embeddings
NiklasAbraham May 28, 2025
c96b543
major refactor of all embeddings related thing new strucutre in many …
NiklasAbraham May 29, 2025
d3b7639
fixed special token errors
NiklasAbraham May 30, 2025
cdd88c9
major linter refactor
NiklasAbraham May 30, 2025
e0e033c
update with ruff
NiklasAbraham May 30, 2025
921cd6c
ruff format check
NiklasAbraham May 30, 2025
657ac15
update the utils
NiklasAbraham May 30, 2025
460e8e3
ruff
NiklasAbraham May 30, 2025
d636c04
update embeddings for esm no more error
NiklasAbraham Jun 3, 2025
b238319
fixes in esm2
NiklasAbraham Jun 4, 2025
cfd284d
update ruff and mypy
NiklasAbraham Jun 4, 2025
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
329 changes: 329 additions & 0 deletions docs/usage/embedding_different_models.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

209 changes: 85 additions & 124 deletions docs/usage/embeddings_analysis.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

78 changes: 38 additions & 40 deletions docs/usage/mutation_analysis.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,18 +11,9 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/nab/anaconda3/envs/pyeed_niklas_env/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"outputs": [],
"source": [
"import sys\n",
"\n",
Expand All @@ -47,15 +38,15 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"📡 Connected to database.\n",
"The provided date does not match the current date. Date is you gave is 2025-03-19 actual date is 2025-04-09\n"
"All data has been wiped from the database.\n"
]
}
],
Expand All @@ -66,7 +57,7 @@
"\n",
"eedb = Pyeed(uri, user=user, password=password)\n",
"\n",
"eedb.db.wipe_database(date=\"2025-03-19\")"
"eedb.db.wipe_database(date=\"2025-05-16\")"
]
},
{
Expand All @@ -85,7 +76,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -111,21 +102,18 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">/home/nab/anaconda3/envs/pyeed_niklas_env/lib/python3.10/site-packages/rich/live.py:231: UserWarning: install \n",
"\"ipywidgets\" for Jupyter support\n",
" warnings.warn('install \"ipywidgets\" for Jupyter support')\n",
"</pre>\n"
],
"application/vnd.jupyter.widget-view+json": {
"model_id": "2dec96f51ab84ce3af3750b48065738d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"/home/nab/anaconda3/envs/pyeed_niklas_env/lib/python3.10/site-packages/rich/live.py:231: UserWarning: install \n",
"\"ipywidgets\" for Jupyter support\n",
" warnings.warn('install \"ipywidgets\" for Jupyter support')\n"
"Output()"
]
},
"metadata": {},
Expand All @@ -135,8 +123,11 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Region ids: [5206, 5205, 5203, 5201, 5207]\n",
"len of ids: 5\n"
"Region ids: [849, 843, 848, 842, 847, 841, 846, 839, 850, 844]\n",
"len of ids: 5\n",
"Number of existing pairs: 0\n",
"Number of total pairs: 4\n",
"Number of pairs to align: 4\n"
]
},
{
Expand Down Expand Up @@ -200,7 +191,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -217,7 +208,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -253,14 +244,14 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'from_positions': [272, 241, 125], 'to_positions': [272, 241, 125], 'from_monomers': ['D', 'R', 'V'], 'to_monomers': ['N', 'S', 'I']}\n"
"{'from_positions': [241, 272, 125], 'to_positions': [241, 272, 125], 'from_monomers': ['R', 'D', 'V'], 'to_monomers': ['S', 'N', 'I']}\n"
]
}
],
Expand Down Expand Up @@ -298,21 +289,21 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 15,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Mutation on position 17 -> 17 with a nucleotide change of T -> C\n",
"Mutation on position 395 -> 395 with a nucleotide change of T -> G\n",
"Mutation on position 198 -> 198 with a nucleotide change of C -> A\n",
"Mutation on position 716 -> 716 with a nucleotide change of G -> A\n",
"Mutation on position 705 -> 705 with a nucleotide change of G -> A\n",
"Mutation on position 473 -> 473 with a nucleotide change of T -> C\n",
"Mutation on position 720 -> 720 with a nucleotide change of A -> C\n",
"Mutation on position 137 -> 137 with a nucleotide change of A -> G\n"
"Mutation on position 474 -> 474 with a nucleotide change of T -> C\n",
"Mutation on position 199 -> 199 with a nucleotide change of C -> A\n",
"Mutation on position 138 -> 138 with a nucleotide change of A -> G\n",
"Mutation on position 18 -> 18 with a nucleotide change of T -> C\n",
"Mutation on position 396 -> 396 with a nucleotide change of T -> G\n",
"Mutation on position 721 -> 721 with a nucleotide change of A -> C\n",
"Mutation on position 706 -> 706 with a nucleotide change of G -> A\n",
"Mutation on position 717 -> 717 with a nucleotide change of G -> A\n"
]
}
],
Expand All @@ -323,6 +314,13 @@
" )"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
Expand Down
3 changes: 3 additions & 0 deletions pyproject.toml
View file
Open in desktop
Copy link
Member

@haeussma haeussma Jun 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

umap cannot be dependency, since no cross-platform support

Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,9 @@ crc64iso = "0.0.2"
SPARQLWrapper = "2.0.0"
pysam = "0.23.0"
types-requests = "2.32.0.20250328"
ipywidgets = "^8.1.7"
sentencepiece = "^0.2.0"
umap = "^0.1.1"

[tool.poetry.group.dev.dependencies]
mkdocstrings = {extras = ["python"], version = "^0.26.2"}
Expand Down
Loading