Upload Model

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,13 +1,13 @@
----
-title: Predict Tfbs
-emoji: 🐨
-colorFrom: green
-colorTo: purple
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-short_description: Predict Transcription Factor Binding Site – TFBS
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Predict Tfbs
+emoji: 🐨
+colorFrom: green
+colorTo: purple
+sdk: gradio
+sdk_version: 5.49.1
+app_file: app.py
+pinned: false
+short_description: Predict Transcription Factor Binding Site – TFBS
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

best_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ceb5e3ce3c81064cf2bf7e736f302bf11cbddeb0b7aaebb41d29c4a2f401892
+size 192032

gradio_app.py

@@ -0,0 +1,77 @@
+# gradio_app.py
+# Gradio rewrite of the original Streamlit app for TFBS prediction
+
+import os
+import gradio as gr
+import numpy as np
+from utils import dnaseq_features
+from keras.models import load_model
+
+# Load model once at startup (make sure best_model.h5 is present in the repo)
+model = load_model('best_model.h5')
+
+
+def predict(dna_seq: str):
+    """Take a DNA sequence string, compute features, run the model and return a Markdown summary."""
+    dna_seq = (dna_seq or "").strip()
+    if not dna_seq:
+        return "**Please provide an input DNA sequence.**"
+
+    # compute features using user's util function
+    try:
+        dna_ohe_feat, ds_index, ds_val = dnaseq_features(seq=dna_seq)
+    except Exception as e:
+        return f"Error while computing features: {e}"
+
+    # predict
+    try:
+        predicted = model.predict(dna_ohe_feat)
+    except Exception as e:
+        return f"Error during model prediction: {e}"
+
+    # build output as Markdown list with probabilities/scores
+    lines = []
+    for i, j in zip(ds_val, predicted):
+        try:
+            # if prediction is a vector like [p0, p1]
+            if hasattr(j, "__len__") and len(j) >= 2:
+                prob = float(j[1])
+                label = "**TFBS found ✅**" if np.argmax(j) == 1 else "**TFBS not found ❌**"
+                lines.append(f"- `{i}` — {label} (probability: {prob:.4f})")
+            else:
+                # single scalar output
+                score = float(j)
+                label = "**TFBS found ✅**" if score > 0.5 else "**TFBS not found ❌**"
+                lines.append(f"- `{i}` — {label} (score: {score:.4f})")
+        except Exception:
+            # fallback
+            lines.append(f"- `{i}` — prediction: {j}")
+
+    if not lines:
+        return "No predictions were produced. Check the input or the model."
+
+    return "\n".join(lines)
+
+
+# Gradio UI
+title = "Simple Model Serving Web App for TFBS prediction"
+description = "Get TFBS predictions from the latest model. Paste a DNA sequence and click **Make Prediction**."
+
+with gr.Blocks(theme=None) as demo:
+    gr.Markdown(f"# {title}")
+    gr.Markdown(description)
+
+    with gr.Row():
+        seq_input = gr.Textbox(lines=6, placeholder="ATAGAGAC...", label="Input DNA sequence")
+
+    with gr.Row():
+        predict_btn = gr.Button("Make Prediction")
+
+    output = gr.Markdown()
+
+    predict_btn.click(fn=predict, inputs=seq_input, outputs=output)
+
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 7860))
+    demo.launch(server_name="0.0.0.0", server_port=port)

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=3.0
+tensorflow>=2.10
+keras
+numpy

utils.py

@@ -0,0 +1,42 @@
+# Function for when you want to prepare DNA sequence feature for ML applications
+import numpy as np
+
+# Function for when you want to prepare DNA sequence feature for ML applications
+def dnaseq_features(seq):
+    start=0
+    n_segs=101
+    seq_name = 'seq'
+    remaind = len(seq)%n_segs
+    if(remaind != 0):
+        last_id = len(seq) - remaind
+    upd_seq = seq[start:last_id]
+    dic_seq = {}
+    for i in range(0,3):
+        a = int(i*n_segs) ; b = int(i*n_segs)+n_segs 
+        identifier = f"{seq_name}_{a}:{b}"
+        dic_seq[identifier] = upd_seq[a:b]
+    lst_seq = dic_seq.values()
+    index = list(dic_seq.keys())
+    values = list(dic_seq.values())
+
+    # One hot encode    
+    ii=-1
+    for data in lst_seq:
+        ii+=1
+        abc = 'ACGT'
+        char_to_int = dict((c, i) for i, c in enumerate(abc))
+        int_enc = [char_to_int[char] for char in data]
+        ohe = []
+        for value in int_enc:
+            base = [0 for _ in range(len(abc))]
+            base[value] = 1
+            ohe.append(base)
+        np_mat = np.array(ohe)
+        np_mat = np.expand_dims(np_mat,axis=0)
+
+        if(ii != 0):
+            matrix = np.concatenate([np_mat,matrix],axis=0)
+        else:
+            matrix = np_mat
+        
+    return matrix,index,values