Upload 7 files

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.11-slim
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Jan Piotrzkowski
+
+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.

README.md

@@ -1,12 +1,64 @@
+# protein-similarity-api
+
+A lightweight, production-ready FastAPI service for comparing protein sequences using state-of-the-art transformer embeddings (ESM-2).
+
+It provides a simple REST API to measure semantic similarity between protein sequences, returning a similarity score based on cosine distance in embedding space.
+
 ---
-title: Protein Similarity Api
-emoji: 🏆
-colorFrom: red
-colorTo: gray
-sdk: docker
-pinned: false
-license: mit
-short_description: About A lightweight FastAPI service for comparing protein se
+
+## Why this matters?
+
+Protein similarity is at the heart of functional annotation, homology detection, and structure prediction. This API lets anyone (researcher, student, dev) compare protein sequences using powerful models.
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## Features
+
+- Compare two protein sequences using [ESM-2](https://huggingface.co/facebook/esm2_t33_650M_UR50D)
+- Returns cosine similarity + classification (homologous vs. non-homologous)
+- Lightweight, deployable on free-tier platforms like Render or Railway
+- Clean FastAPI structure, easy to extend (e.g. embeddings endpoint, caching)
+
+---
+
+## API Endpoints
+
+### `POST /compare`
+
+Compare two sequences and get similarity:
+
+#### Request:
+
+```json
+{
+  "sequence_1": "MSSKVIFF...",
+  "sequence_2": "MTTRLIFF...",
+  "model": "esm_2_650m"
+}
+```
+
+#### Response:
+
+```json
+{
+  "cosine_similarity": 0.57,
+  "classification": "moderate similarity (possible remote homolog)",
+  "model": "ESM-2 650M"
+}
+```
+
+## How to run it?
+
+```shell
+python3 -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+
+uvicorn main:app --reload
+```
+
+## How to deploy it?
+
+```
+
+```

main.py

@@ -0,0 +1,44 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from utils import compare_embeddings
+
+from models.esm_2_650m import get_embedding as get_embedding_esm_2_650m
+
+app = FastAPI()
+
+
+class CompareRequest(BaseModel):
+    sequence_1: str
+    sequence_2: str
+    model: str = "esm_2_650m"
+
+
+model_mapping = {"esm_2_650m": get_embedding_esm_2_650m}
+
+
+# ----------------------------------------------------------------------
+@app.get("/")
+def root():
+    return {
+        "message": "API is running. Use POST /compare to compare protein sequences."
+    }
+
+
+# ----------------------------------------------------------------------
+@app.post("/compare")
+def compare(request: CompareRequest):
+    model = request.model
+
+    if model not in model_mapping:
+        return {"error": "Model not supported"}
+
+    emb1 = model_mapping[model](request.sequence_1)
+    emb2 = model_mapping[model](request.sequence_2)
+
+    similarity, classification = compare_embeddings(emb1, emb2)
+
+    return {
+        "cosine_similarity": float(similarity),
+        "classification": classification,
+        "model": model,
+    }

pyproject.toml

@@ -0,0 +1,10 @@
+[tool.black]
+line-length = 88
+target-version = ["py311"]
+
+[tool.isort]
+profile = "black"
+
+[tool.flake8]
+max-line-length = 88
+extend-ignore = ["E203", "W503"]

requirements.txt

@@ -0,0 +1,77 @@
+annotated-types==0.7.0
+anyio==4.9.0
+black==25.1.0
+certifi==2025.7.14
+charset-normalizer==3.4.2
+click==8.2.1
+coverage==7.10.1
+dnspython==2.7.0
+email_validator==2.2.0
+fastapi==0.116.1
+fastapi-cli==0.0.8
+fastapi-cloud-cli==0.1.5
+filelock==3.18.0
+flake8==7.3.0
+fsspec==2025.7.0
+h11==0.16.0
+hf-xet==1.1.5
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.34.3
+idna==3.10
+iniconfig==2.1.0
+isort==6.0.1
+itsdangerous==2.2.0
+Jinja2==3.1.6
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+mccabe==0.7.0
+mdurl==0.1.2
+mpmath==1.3.0
+mypy_extensions==1.1.0
+networkx==3.5
+numpy==2.3.2
+orjson==3.11.1
+packaging==25.0
+pathspec==0.12.1
+platformdirs==4.3.8
+pluggy==1.6.0
+pycodestyle==2.14.0
+pydantic==2.11.7
+pydantic-extra-types==2.10.5
+pydantic-settings==2.10.1
+pydantic_core==2.33.2
+pyflakes==3.4.0
+Pygments==2.19.2
+pytest==8.4.1
+pytest-cov==6.2.1
+python-dotenv==1.1.1
+python-multipart==0.0.20
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.4
+rich==14.1.0
+rich-toolkit==0.14.9
+rignore==0.6.4
+safetensors==0.5.3
+scipy==1.16.1
+sentry-sdk==2.33.2
+setuptools==80.9.0
+shellingham==1.5.4
+sniffio==1.3.1
+starlette==0.47.2
+sympy==1.14.0
+tokenizers==0.21.4
+torch==2.7.1
+tqdm==4.67.1
+transformers==4.54.0
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.1
+ujson==5.10.0
+urllib3==2.5.0
+uvicorn==0.35.0
+uvloop==0.21.0
+watchfiles==1.1.0
+websockets==15.0.1

utils.py

@@ -0,0 +1,18 @@
+from scipy.spatial.distance import cosine
+
+
+def compare_embeddings(emb1, emb2):
+    similarity = 1 - cosine(emb1, emb2)
+
+    if similarity >= 0.85:
+        classification = "very high similarity (clear homology)"
+    elif similarity >= 0.70:
+        classification = "high similarity (likely homologous)"
+    elif similarity >= 0.50:
+        classification = "moderate similarity (possible remote homolog)"
+    elif similarity >= 0.30:
+        classification = "low similarity (likely not homologous)"
+    else:
+        classification = "very low similarity (unrelated / random match)"
+
+    return similarity, classification