tetss2 0.1.0__py3-none-any.whl

tetss2/__init__.py

@@ -0,0 +1,3 @@
+from .predictor import TETSS2Predictor
+
+__all__ = ["TETSS2Predictor"]

tetss2/cli.py

@@ -0,0 +1,108 @@
+import os
+
+os.environ["MKL_THREADING_LAYER"] = "GNU"
+
+import argparse
+import json
+
+from .predictor import TETSS2Predictor
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="TETSS2.0: predict TE-TSS activity from 201 bp DNA sequence."
+    )
+
+    subparsers = parser.add_subparsers(dest="command")
+
+    predict_parser = subparsers.add_parser(
+        "predict",
+        help="Predict one DNA sequence."
+    )
+    predict_parser.add_argument(
+        "--sequence",
+        required=True,
+        help="Input DNA sequence. TETSS2.0 expects exactly 201 bp."
+    )
+    predict_parser.add_argument(
+        "--threshold",
+        type=float,
+        default=0.5,
+        help="Classification threshold. Default: 0.5"
+    )
+    predict_parser.add_argument(
+        "--no-length-check",
+        action="store_true",
+        help="Disable 201 bp length check. Mainly for debugging."
+    )
+
+    file_parser = subparsers.add_parser(
+        "predict-file",
+        help="Predict sequences from a TSV or CSV file."
+    )
+    file_parser.add_argument(
+        "--input",
+        required=True,
+        help="Input file path. The file should contain a sequence column."
+    )
+    file_parser.add_argument(
+        "--output",
+        required=True,
+        help="Output file path."
+    )
+    file_parser.add_argument(
+        "--sequence-column",
+        default="sequence",
+        help="Column name containing DNA sequences. Default: sequence"
+    )
+    file_parser.add_argument(
+        "--threshold",
+        type=float,
+        default=0.5,
+        help="Classification threshold. Default: 0.5"
+    )
+    file_parser.add_argument(
+        "--sep",
+        default="\t",
+        help="File separator. Default: tab. Use ',' for CSV."
+    )
+    file_parser.add_argument(
+        "--no-length-check",
+        action="store_true",
+        help="Disable 201 bp length check. Mainly for debugging."
+    )
+
+    args = parser.parse_args()
+
+    if args.command == "predict":
+        predictor = TETSS2Predictor()
+        result = predictor.predict(
+            args.sequence,
+            threshold=args.threshold,
+            check_length=not args.no_length_check,
+        )
+        print(json.dumps(result, indent=2))
+
+    elif args.command == "predict-file":
+        sep = args.sep
+        if sep == "\\t":
+            sep = "\t"
+
+        predictor = TETSS2Predictor()
+        predictor.predict_file(
+            input_path=args.input,
+            output_path=args.output,
+            sequence_column=args.sequence_column,
+            threshold=args.threshold,
+            sep=sep,
+            check_length=not args.no_length_check,
+        )
+
+        print(f"Prediction finished. Results saved to: {args.output}")
+
+    else:
+        parser.print_help()
+
+
+if __name__ == "__main__":
+    main()

tetss2/model.py

@@ -0,0 +1,27 @@
+import torch
+import torch.nn as nn
+
+
+class TETSSClassifier(nn.Module):
+    def __init__(self):
+        super().__init__()
+        self.features = nn.Sequential(
+            nn.Conv1d(4, 64, kernel_size=15, padding=7),
+            nn.BatchNorm1d(64), nn.ReLU(), nn.MaxPool1d(2),
+            nn.Conv1d(64, 128, kernel_size=15, padding=7),
+            nn.BatchNorm1d(128), nn.ReLU(), nn.MaxPool1d(2),
+            nn.Conv1d(128, 128, kernel_size=15, padding=7),
+            nn.BatchNorm1d(128), nn.ReLU(), nn.MaxPool1d(2),
+            nn.Conv1d(128, 256, kernel_size=7, padding=3),
+            nn.BatchNorm1d(256), nn.ReLU(), nn.AdaptiveMaxPool1d(1)
+        )
+        self.classifier = nn.Sequential(
+            nn.Flatten(),
+            nn.Linear(256, 128),
+            nn.ReLU(),
+            nn.Dropout(0.3),
+            nn.Linear(128, 1)
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.classifier(self.features(x)).squeeze(1)

tetss2/predictor.py

@@ -0,0 +1,139 @@
+import os
+
+os.environ["MKL_THREADING_LAYER"] = "GNU"
+
+import torch
+import numpy as np
+import pandas as pd
+from importlib.resources import files
+
+from .model import TETSSClassifier
+
+
+EXPECTED_SEQUENCE_LENGTH = 201
+
+
+def clean_sequence(seq: str) -> str:
+    seq = str(seq).strip().upper()
+    return seq
+
+
+def validate_sequence(seq: str, expected_length: int = EXPECTED_SEQUENCE_LENGTH) -> None:
+    allowed_bases = set("ACGTN")
+
+    invalid_bases = sorted(set(seq) - allowed_bases)
+    if invalid_bases:
+        raise ValueError(
+            f"Invalid bases found: {invalid_bases}. "
+            "Only A, C, G, T, and N are allowed."
+        )
+
+    if len(seq) != expected_length:
+        raise ValueError(
+            f"Invalid sequence length: {len(seq)} bp. "
+            f"TETSS2.0 expects exactly {expected_length} bp."
+        )
+
+
+def seq_to_onehot(seq: str) -> np.ndarray:
+    mapping = {"A": 0, "C": 1, "G": 2, "T": 3}
+    arr = np.zeros((4, len(seq)), dtype=np.float32)
+
+    for i, base in enumerate(seq.upper()):
+        idx = mapping.get(base)
+        if idx is not None:
+            arr[idx, i] = 1.0
+
+    return arr
+
+
+class TETSS2Predictor:
+    def __init__(self, model_path=None, device=None):
+        self.device = device or ("cuda" if torch.cuda.is_available() else "cpu")
+
+        if model_path is None:
+            model_path = files("tetss2").joinpath("assets/best_model.pth")
+
+        self.model = TETSSClassifier().to(self.device)
+        state_dict = torch.load(model_path, map_location=self.device)
+        self.model.load_state_dict(state_dict)
+        self.model.eval()
+
+    def predict_proba(self, sequence: str, check_length: bool = True) -> float:
+        sequence = clean_sequence(sequence)
+
+        if check_length:
+            validate_sequence(sequence)
+
+        x = seq_to_onehot(sequence)
+        x = torch.from_numpy(x).unsqueeze(0).to(self.device)
+
+        with torch.no_grad():
+            logits = self.model(x)
+            prob = torch.sigmoid(logits).item()
+
+        return float(prob)
+
+    def predict(
+        self,
+        sequence: str,
+        threshold: float = 0.5,
+        check_length: bool = True,
+    ) -> dict:
+        sequence = clean_sequence(sequence)
+
+        prob = self.predict_proba(sequence, check_length=check_length)
+        label = int(prob > threshold)
+
+        return {
+            "model": "TETSS2.0",
+            "sequence": sequence,
+            "sequence_length": len(sequence),
+            "probability": prob,
+            "prediction": label,
+            "threshold": threshold,
+        }
+
+    def predict_file(
+        self,
+        input_path: str,
+        output_path: str,
+        sequence_column: str = "sequence",
+        threshold: float = 0.5,
+        sep: str = "\t",
+        check_length: bool = True,
+    ) -> None:
+        df = pd.read_csv(input_path, sep=sep)
+
+        if sequence_column not in df.columns:
+            raise ValueError(
+                f"Cannot find sequence column '{sequence_column}' in input file. "
+                f"Available columns are: {list(df.columns)}"
+            )
+
+        probabilities = []
+        predictions = []
+        sequence_lengths = []
+
+        for idx, seq in enumerate(df[sequence_column], start=1):
+            seq = clean_sequence(seq)
+
+            try:
+                prob = self.predict_proba(seq, check_length=check_length)
+            except ValueError as e:
+                raise ValueError(
+                    f"Error in row {idx}: {e}"
+                )
+
+            pred = int(prob > threshold)
+
+            probabilities.append(prob)
+            predictions.append(pred)
+            sequence_lengths.append(len(seq))
+
+        df["tetss2_sequence_length"] = sequence_lengths
+        df["tetss2_probability"] = probabilities
+        df["tetss2_prediction"] = predictions
+        df["tetss2_threshold"] = threshold
+
+        df.to_csv(output_path, sep=sep, index=False)

tetss2-0.1.0.dist-info/METADATA

@@ -0,0 +1,375 @@
+Metadata-Version: 2.4
+Name: tetss2
+Version: 0.1.0
+Summary: TETSS2.0: a PyTorch model for predicting TE-TSS activity from DNA sequences.
+Author-email: Moriyaa Cui <2311459@tongji.edu.cn>
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: numpy>=1.21
+Requires-Dist: pandas>=1.3
+Requires-Dist: torch>=1.10
+
+# TETSS2.0
+
+**TETSS2.0** is a deep learning model for predicting TE-derived transcription start site (TE-TSS) activity from DNA sequences.
+
+The Python package name and command-line tool name are **`tetss2`**. The model name shown in documents, figures, and the website is **TETSS2.0**.
+
+---
+
+## Overview
+
+TETSS2.0 is a PyTorch-based convolutional neural network classifier designed to predict whether an input DNA sequence is associated with TE-TSS activity.
+
+The model takes a DNA sequence as input and returns:
+
+* a prediction probability
+* a binary prediction label
+* the classification threshold used for prediction
+
+By default, TETSS2.0 uses a threshold of `0.5`.
+
+---
+
+## Input requirement
+
+TETSS2.0 expects DNA sequences of exactly **201 bp**.
+
+Allowed bases:
+
+```text
+A, C, G, T, N
+```
+
+Notes:
+
+* Input sequences are automatically converted to uppercase.
+* `N` is allowed but is encoded as an all-zero position in the one-hot representation.
+* Sequences shorter or longer than 201 bp are rejected by default.
+* The option `--no-length-check` is available only for debugging and is not recommended for normal prediction.
+
+---
+
+## Output
+
+For each input sequence, TETSS2.0 outputs:
+
+| Column                   | Description                              |
+| ------------------------ | ---------------------------------------- |
+| `tetss2_sequence_length` | Length of the input sequence             |
+| `tetss2_probability`     | Predicted probability score              |
+| `tetss2_prediction`      | Binary prediction result, `0` or `1`     |
+| `tetss2_threshold`       | Threshold used for binary classification |
+
+---
+
+## Installation
+
+### Option 1: Install from a local source directory
+
+If you have downloaded or cloned this package locally, enter the package directory and install it with:
+
+```bash
+cd tetss_rampage_package
+pip install -e .
+```
+
+After installation, check whether the command-line tool is available:
+
+```bash
+tetss2 --help
+```
+
+### Option 2: Recommended conda environment
+
+We recommend creating a clean conda environment before installation:
+
+```bash
+
+conda create -n tetss2 python=3.9
+conda activate tetss2
+conda install numpy pandas scikit-learn
+pip install torch==1.10.2
+
+pip install -e .
+
+```
+
+A future public release may support:
+
+```bash
+pip install tetss2
+```
+
+---
+
+## Command-line usage
+
+### 1. Predict a single sequence
+
+```bash
+tetss2 predict --sequence ACGTACGTACGTACGT
+```
+
+For normal use, the input sequence should be exactly 201 bp:
+
+```bash
+tetss2 predict --sequence YOUR_201BP_DNA_SEQUENCE
+```
+
+Example output:
+
+```json
+{
+  "model": "TETSS2.0",
+  "sequence": "ACGTACGTACGTACGT",
+  "sequence_length": 16,
+  "probability": 0.35490313172340393,
+  "prediction": 0,
+  "threshold": 0.5
+}
+```
+
+Note: the example above uses a short sequence only to demonstrate the command format. For biological prediction, please use a 201 bp sequence.
+
+---
+
+### 2. Batch prediction from a TSV file
+
+Prepare an input file containing a `sequence` column.
+
+Example input file: `input.tsv`
+
+```tsv
+sample_id	sequence
+sample1	ACGT...
+sample2	TTTT...
+sample3	GCGC...
+```
+
+Run batch prediction:
+
+```bash
+tetss2 predict-file \
+  --input input.tsv \
+  --output tetss2_predictions.tsv
+```
+
+The output file will contain the original columns plus TETSS2.0 prediction results.
+
+Example output:
+
+```tsv
+sample_id	sequence	tetss2_sequence_length	tetss2_probability	tetss2_prediction	tetss2_threshold
+sample1	ACGT...	201	0.3549	0	0.5
+sample2	TTTT...	201	0.8123	1	0.5
+sample3	GCGC...	201	0.4471	0	0.5
+```
+
+---
+
+### 3. Batch prediction from a CSV file
+
+If your input file is comma-separated, use `--sep ","`:
+
+```bash
+tetss2 predict-file \
+  --input input.csv \
+  --output tetss2_predictions.csv \
+  --sep ","
+```
+
+---
+
+### 4. Use a custom sequence column name
+
+If the sequence column is not named `sequence`, specify it with `--sequence-column`.
+
+For example, if the input file contains a column named `dna`:
+
+```bash
+tetss2 predict-file \
+  --input input.tsv \
+  --output tetss2_predictions.tsv \
+  --sequence-column dna
+```
+
+---
+
+## Python API usage
+
+TETSS2.0 can also be used directly in Python.
+
+```python
+from tetss2 import TETSS2Predictor
+
+predictor = TETSS2Predictor()
+
+result = predictor.predict("YOUR_201BP_DNA_SEQUENCE")
+print(result)
+```
+
+Example output:
+
+```python
+{
+    "model": "TETSS2.0",
+    "sequence": "YOUR_201BP_DNA_SEQUENCE",
+    "sequence_length": 201,
+    "probability": 0.73,
+    "prediction": 1,
+    "threshold": 0.5,
+}
+```
+
+---
+
+## Model architecture
+
+TETSS2.0 uses a one-dimensional convolutional neural network for DNA sequence classification.
+
+The model contains:
+
+* one-hot encoding of DNA sequences
+* multiple 1D convolutional layers
+* batch normalization
+* ReLU activation
+* max pooling
+* adaptive max pooling
+* fully connected classification layers
+
+The model outputs a single logit, which is converted to a probability using the sigmoid function.
+
+---
+
+## Model files
+
+The package includes the trained model weight file:
+
+```text
+best_model.pth
+```
+
+The original training output directory also contains:
+
+```text
+best_model.pth
+run_config.json
+train_history.tsv
+final_val_metrics.json
+split_summary.json
+train_split.tsv
+val_split.tsv
+```
+
+These files can be used to document model configuration, validation performance, and data splitting information.
+
+---
+
+## Validation performance
+
+Please fill in the following values using `final_val_metrics.json`:
+
+| Metric          | Value |
+| --------------- | ----: |
+| AUROC           |  TODO |
+| AUPRC           |  TODO |
+| Accuracy        |  TODO |
+| Precision       |  TODO |
+| Recall          |  TODO |
+| True negatives  |  TODO |
+| False positives |  TODO |
+| False negatives |  TODO |
+| True positives  |  TODO |
+
+To view the metrics file:
+
+```bash
+cat final_val_metrics.json
+```
+
+---
+
+## Troubleshooting
+
+### MKL threading error
+
+If you see an error similar to:
+
+```text
+mkl-service + Intel(R) MKL: MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1
+```
+
+try running:
+
+```bash
+export MKL_THREADING_LAYER=GNU
+```
+
+Then run the prediction command again.
+
+---
+
+### Cannot find sequence column
+
+If you see an error like:
+
+```text
+Cannot find sequence column 'sequence'
+```
+
+check whether your input file contains a real tab or comma separator.
+
+For a TSV file, you can check tabs with:
+
+```bash
+cat -A input.tsv
+```
+
+A real tab will appear as:
+
+```text
+^I
+```
+
+A correct TSV file should look like:
+
+```text
+sample_id^Isequence$
+sample1^IACGT...$
+```
+
+---
+
+## Citation
+
+If you use TETSS2 in your research, please cite:
+
+@software{tetss2,
+  title={TETSS2: Deep Learning Model for TE-TSS Prediction},
+  year={2026}
+}
+
+---
+
+## Contact
+
+For questions or issues, please contact the developer or open an issue in the project repository.
+
+---
+
+## License
+
+License information will be added later.
+
+## Repository
+
+https://github.com/MoriyaaCui/TETSS2.git
+
+
+## Live Demo
+
+A Gradio demo is available:
+
+```bash
+python demo/app.py

tetss2-0.1.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+tetss2/__init__.py,sha256=wUcpvTkelXY7ojAkjJEPFtsrXsMCj62yF3p1No1AbS4,69
+tetss2/cli.py,sha256=V-DwHpLYpMwze_J1nvRTqZlAzfdpxzTaOEHjepBL7e0,2797
+tetss2/model.py,sha256=2xk9li3HeqyYISGtM48vQ6iqdNWZr-89GvTR0La_ItY,964
+tetss2/predictor.py,sha256=HepcNNtg0ByVAuv9hsdN4JwB6zFBULPd2BAxZ1jvXlY,3905
+tetss2/assets/best_model.pth,sha256=8hgt7gTBuEW4OJbZrsW80ImSSjcmKwFOwf5rDB0ppRc,2560965
+tetss2-0.1.0.dist-info/METADATA,sha256=GKBdNlmMabgpKyqkO_ljmsrgfrcx35JnQB3Gpc7_grA,7242
+tetss2-0.1.0.dist-info/WHEEL,sha256=aeYiig01lYGDzBgS8HxWXOg3uV61G9ijOsup-k9o1sk,91
+tetss2-0.1.0.dist-info/entry_points.txt,sha256=AihRYcxX3CsK_d5rM870SAfq-EnA1ysRbpNXjqW2KMc,43
+tetss2-0.1.0.dist-info/top_level.txt,sha256=XbiPCKEihTZkQbisfvwjJb7-SHteuzSyyVH3MHjCFAI,7
+tetss2-0.1.0.dist-info/RECORD,,

tetss2-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (82.0.1)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

tetss2-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+tetss2 = tetss2.cli:main

tetss2-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+tetss2