first push

app.py

@@ -0,0 +1,62 @@
+import streamlit as st
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer
+import pandas as pd
+
+# title
+st.title('Raven AI')
+
+# text input with label
+sequence = st.text_input('Enter Amino Acid Sequence')
+
+model_type = st.radio(
+    "Choose Linear Epitope Classifier",
+    ('Linear T-Cells (MHC Class I Restriction)', 'Linear T-Cells (MHC Class II Restriction)', 'Linear B-Cell'))
+
+# windows length slider
+length = st.slider('Window Length', 1, 20, 10)
+threshold = st.slider('Probability Threshold', 0.0, 1.0, 0.5)
+
+model_checkpoint = "facebook/esm2_t6_8M_UR50D"
+
+tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
+
+if model_type == 'Linear T-Cells (MHC Class I Restriction)':
+    model = TFAutoModelForSequenceClassification.from_pretrained('classifier')
+elif model_type == 'Linear T-Cells (MHC Class II Restriction)':
+    model = TFAutoModelForSequenceClassification.from_pretrained('classifier2')
+elif model_type == 'Linear B-Cell':
+    model = TFAutoModelForSequenceClassification.from_pretrained('bcell')
+# submit button
+if st.button('Submit'):
+    # run model
+    locations = []
+    for i in range(len(sequence) - length):
+        peptide_name = sequence[i:i+length]
+        peptide = tokenizer(peptide_name, return_tensors="tf")
+        output = model(peptide)
+        locations.append([peptide_name, output.logits.numpy()[0][0]])
+    
+    locations = pd.DataFrame(locations, columns = ['Peptide', 'Probability'])
+
+    # display table with sequence and probability as the headers
+    def color_survived(x: float): # x between 0 and 1
+        # red to green scale based on x
+        # 0 -> red
+        # 0.5 -> clear
+        # 1 -> green
+
+        # red
+        if x < threshold:
+            r = 179
+            g = 40
+            b = 2
+        # green
+        else:
+            r = 18
+            g = 150
+            b = 6
+
+        return f'background-color: rgb({r}, {g}, {b})'
+
+    st.table(locations.style.applymap(color_survived, subset=['Probability']))

bcell/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/esm2_t6_8M_UR50D",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 320,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "is_folding_model": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

bcell/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc764936c96b97e3e5678e26e08f8e96eb7a1effaabc4b8cc1173471f0c3eb5d
+size 30211508

classifier/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/esm2_t6_8M_UR50D",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 320,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "is_folding_model": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

classifier/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7283cc436b2737289b6174da635b372aaac170458a5772f3d31a851aa076b25c
+size 30211508

classifier2/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/esm2_t6_8M_UR50D",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 320,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "is_folding_model": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

classifier2/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c373b0000c019df443691ee21b3429901181d425c74b89f866bf135cacbcb39d
+size 30211508

requirements.txt

@@ -0,0 +1,2 @@
+pandas
+transformers