init

README.md

@@ -0,0 +1,23 @@
+# ProtBert-BFD finetuned on Rosetta 20,40,60AA dataset
+
+This model is finetuned to predict Rosetta fold energy using a dataset of 300k protein sequences:
+100k of 20AA, 100k of 40AA, and 100k of 60AA
+
+Current model in this repo: `prot_bert_bfd-finetuned-032822_1323`
+
+## Performance
+
+On a held-out eval set the performance is:
+- 20AA sequences (1k eval set): 
+Metrics: 'mae': 0.100418, 'r2': 0.989028, 'mse': 0.016266, 'rmse': 0.127537
+- 40AA sequences (10k eval set):
+Metrics: 'mae': 0.173888, 'r2': 0.963361, 'mse': 0.048218, 'rmse': 0.219587
+- 60AA sequences (10k eval set):
+Metrics: 'mae': 0.235238, 'r2': 0.930164, 'mse': 0.088131, 'rmse': 0.2968
+
+## `prot_bert_bfd` from ProtTrans
+The starting pretrained model is from ProtTrans, trained on 2.1 billion proteins from BFD.
+It was trained on protein sequences using a masked language modeling (MLM) objective. It was introduced in
+[this paper](https://doi.org/10.1101/2020.07.12.199554) and first released in
+[this repository](https://github.com/agemagician/ProtTrans).
+

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Rostlab/prot_bert_bfd",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 40000,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 30,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "regression",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d7ef6b70b6d2aec36a03d432f4f29a324823538b2d3761e0893273b87ae96d
+size 1680247213

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer.json

@@ -0,0 +1,180 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "[CLS]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 3,
+      "content": "[SEP]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 4,
+      "content": "[MASK]",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "BertNormalizer",
+    "clean_text": true,
+    "handle_chinese_chars": true,
+    "strip_accents": null,
+    "lowercase": false
+  },
+  "pre_tokenizer": {
+    "type": "BertPreTokenizer"
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "SpecialToken": {
+          "id": "[CLS]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      },
+      {
+        "SpecialToken": {
+          "id": "[SEP]",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {
+      "[CLS]": {
+        "id": "[CLS]",
+        "ids": [
+          2
+        ],
+        "tokens": [
+          "[CLS]"
+        ]
+      },
+      "[SEP]": {
+        "id": "[SEP]",
+        "ids": [
+          3
+        ],
+        "tokens": [
+          "[SEP]"
+        ]
+      }
+    }
+  },
+  "decoder": {
+    "type": "WordPiece",
+    "prefix": "##",
+    "cleanup": true
+  },
+  "model": {
+    "type": "WordPiece",
+    "unk_token": "[UNK]",
+    "continuing_subword_prefix": "##",
+    "max_input_chars_per_word": 100,
+    "vocab": {
+      "[PAD]": 0,
+      "[UNK]": 1,
+      "[CLS]": 2,
+      "[SEP]": 3,
+      "[MASK]": 4,
+      "L": 5,
+      "A": 6,
+      "G": 7,
+      "V": 8,
+      "E": 9,
+      "S": 10,
+      "I": 11,
+      "K": 12,
+      "R": 13,
+      "D": 14,
+      "T": 15,
+      "P": 16,
+      "N": 17,
+      "Q": 18,
+      "F": 19,
+      "Y": 20,
+      "M": 21,
+      "H": 22,
+      "C": 23,
+      "W": 24,
+      "X": 25,
+      "U": 26,
+      "B": 27,
+      "Z": 28,
+      "O": 29
+    }
+  }
+}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "full_tokenizer_file": null, "name_or_path": "Rostlab/prot_bert_bfd", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e28fb0e1bc54eb95ba166aaa5181e97f33801131164088bd55fea45251f95eb
+size 2991

vocab.txt

@@ -0,0 +1,30 @@
+[PAD]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+L
+A
+G
+V
+E
+S
+I
+K
+R
+D
+T
+P
+N
+Q
+F
+Y
+M
+H
+C
+W
+X
+U
+B
+Z
+O