Upload folder using huggingface_hub

README.md

@@ -0,0 +1,222 @@
+---
+library_name: pytorch
+license: mit
+tags:
+  - protein
+  - enzyme
+  - protein-language-model
+  - bioinformatics
+  - protein-function-prediction
+---
+
+# UNKAI
+
+UNKAI is a protein-pair classification model for predicting whether two proteins are associated with the same enzymatic reaction.
+
+The model takes per-residue protein embeddings as input, independently pools the two proteins using attention pooling, computes the absolute difference between the resulting protein-level representations, and performs binary classification with a multilayer perceptron.
+
+Code and inference utilities are available at:
+
+https://github.com/ukai3313/UNKAI
+
+## Model variants
+
+This repository contains two pretrained UNKAI variants.
+
+### Original
+
+Architecture:
+
+```text
+Per-residue embeddings
+        |
+Attention Pooling
+        |
+Protein vectors v1, v2
+        |
+    |v1 - v2|
+        |
+2560 -> 1599 -> 781 -> 117 -> 1
+        |
+     Sigmoid
+```
+
+The original model uses:
+
+* Input embedding dimension: 2560
+* Attention pooling
+* Pair representation: absolute difference `|v1 - v2|`
+* MLP dimensions: `2560 -> 1599 -> 781 -> 117 -> 1`
+* Dropout: `0.302766`
+
+Checkpoint:
+
+```text
+original/model.pth
+```
+
+### Seen-unseen
+
+The seen-unseen model is designed for evaluation where one side of a validation or test pair belongs to a protein cluster observed during training, while the other side belongs to a cluster not observed during training.
+
+Architecture:
+
+```text
+Per-residue embeddings
+        |
+Attention Pooling
+with attention dropout
+        |
+Protein vectors v1, v2
+        |
+    |v1 - v2|
+        |
+2560 -> 1408 -> 640 -> 512 -> 1
+```
+
+The model uses:
+
+* Input embedding dimension: 2560
+* Attention pooling
+* Attention dropout: `0.1627294925`
+* Pair representation: absolute difference `|v1 - v2|`
+* MLP dimensions: `2560 -> 1408 -> 640 -> 512 -> 1`
+* Classifier dropout: `0.5282298379`
+
+Checkpoint:
+
+```text
+seen_unseen/model.pth
+```
+
+The checkpoint produces logits. A sigmoid transformation is applied during inference to obtain a probability.
+
+## Input format
+
+UNKAI expects one per-residue embedding file for each protein.
+
+Expected filename:
+
+```text
+<UNIPROT_ACCESSION>_embedding.npy
+```
+
+Supported array shapes are:
+
+```text
+(L, 2560)
+```
+
+or:
+
+```text
+(1, L, 2560)
+```
+
+where `L` is the protein sequence length.
+
+The released checkpoints were trained using 2560-dimensional per-residue protein embeddings.
+
+## Installation
+
+Clone the UNKAI GitHub repository:
+
+```bash
+git clone https://github.com/ukai3313/UNKAI.git
+cd UNKAI
+pip install -r requirements.txt
+```
+
+Add the source directory to `PYTHONPATH`:
+
+```bash
+export PYTHONPATH="$PWD/src"
+```
+
+## Inference
+
+### Original model
+
+```bash
+python -m unkai.predict \
+  --model original \
+  --protein1 Q6GZV6 \
+  --protein2 Q6GZN7 \
+  --embeddings-dir /path/to/embeddings \
+  --checkpoint /path/to/original/model.pth
+```
+
+### Seen-unseen model
+
+```bash
+python -m unkai.predict \
+  --model seen_unseen \
+  --protein1 Q6GZV6 \
+  --protein2 Q6GZN7 \
+  --embeddings-dir /path/to/embeddings \
+  --checkpoint /path/to/seen_unseen/model.pth
+```
+
+Example output:
+
+```text
+Protein 1   : Q6GZV6
+Protein 2   : Q6GZN7
+Model       : original
+Probability : 0.002518
+Prediction  : 0
+```
+
+The current inference utility uses a probability threshold of `0.5`.
+
+* `Prediction = 1`: predicted to be associated with the same enzymatic reaction.
+* `Prediction = 0`: predicted not to be associated with the same enzymatic reaction.
+
+## Files
+
+```text
+original/
+└── model.pth
+
+seen_unseen/
+└── model.pth
+```
+
+## Datasets
+
+Datasets used with UNKAI are released separately:
+
+```text
+ukaikotaro/UNKAI-dataset
+```
+
+Three dataset variants are provided:
+
+* original
+* seen_unseen
+* strict
+
+See the dataset repository for details about the splitting strategies.
+
+## Embeddings
+
+The pretrained UNKAI checkpoints require precomputed per-residue protein embeddings.
+
+The embedding collection used in this project is planned to be distributed separately.
+
+## Limitations
+
+UNKAI predicts association between a pair of proteins with respect to enzymatic reactions and should not be interpreted as direct experimental evidence of identical biochemical function.
+
+Performance may depend on the distribution of proteins, sequence similarity, clustering strategy, and embedding model used to construct the input representations.
+
+The original and seen-unseen checkpoints were trained using different dataset splitting strategies and should therefore not be directly compared without considering the evaluation setting.
+
+## Citation
+
+Citation information for the associated publication will be added here.
+
+## License
+
+MIT License.
+

original/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13b34eb3fe53995a2065150a881904ab5d112145f95f89c495f8a9d4304bd6a4
+size 21800658

seen_unseen/model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced59dacf9ae72768090bc4cedd5b38ef30e6b5c89cb5de0c2b3fcb898837869
+size 19395893