initial commit

app.py

@@ -0,0 +1,29 @@
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from scipy.special import softmax
+import gradio as gr
+
+tokenizer = AutoTokenizer.from_pretrained("armheb/DNA_bert_6")
+model2 = AutoModelForSequenceClassification.from_pretrained("simecek/promoters_demo")
+
+def kmers(s, k=6):
+  return [s[i:i + k] for i in range(0, len(s)-k+1)]
+
+def tokenization(x): 
+  return tokenizer(" ".join(kmers(x["seq"])), return_tensors="pt")
+
+categories = ["not-promoter", "promoter"]
+
+def is_promoter(DNAseq):
+  input = tokenization({"seq": DNAseq})
+  logits = model2(**input)['logits'].detach().numpy()
+  probs = softmax(logits, axis=1)[0]
+  probs = map(float, probs)
+
+  return dict(zip(categories, probs))
+
+text = gr.inputs.Textbox(placeholder="Input DNA sequence", lines=5)
+label = gr.outputs.Label(label = "Is it a promoter?")
+
+intf = gr.Interface(fn=is_promoter, inputs=text, outputs=label)
+
+intf.launch()