Upload 8 files

README.md

@@ -0,0 +1,110 @@
+---
+language:
+- en
+tags:
+- ner
+- gene
+- protein
+- rna
+- bioinfomatics
+license: apache-2.0
+datasets:
+- jnlpba
+- tner/bc5cdr
+- jnlpba
+- bc2gm_corpus
+- drAbreu/bc4chemd_ner
+- linnaeus
+- ncbi_disease
+widget:
+- text: "It consists of 25 exons encoding a 1,278-amino acid glycoprotein that is composed of 13 transmembrane domains"
+---
+
+# NER to find Gene & Gene products
+> The model was trained on jnlpba dataset, pretrained on this [pubmed-pretrained roberta model](/raynardj/roberta-pubmed)
+
+All the labels, the possible token classes.
+```json
+{"label2id": {
+    "DNA": 2,
+    "O": 0,
+    "RNA": 5,
+    "cell_line": 4,
+    "cell_type": 3,
+    "protein": 1
+  }
+ }
+```
+ 
+Notice, we removed the 'B-','I-' etc from data label.🗡
+ 
+## This is the template we suggest for using the model
+```python
+from transformers import pipeline
+
+PRETRAINED = "raynardj/ner-gene-dna-rna-jnlpba-pubmed"
+ner = pipeline(task="ner",model=PRETRAINED, tokenizer=PRETRAINED)
+ner("Your text", aggregation_strategy="first")
+```
+And here is to make your output more consecutive ⭐️
+
+```python
+import pandas as pd
+from transformers import AutoTokenizer
+tokenizer = AutoTokenizer.from_pretrained(PRETRAINED)
+
+def clean_output(outputs):
+    results = []
+    current = []
+    last_idx = 0
+    # make to sub group by position
+    for output in outputs:
+        if output["index"]-1==last_idx:
+            current.append(output)
+        else:
+            results.append(current)
+            current = [output, ]
+        last_idx = output["index"]
+    if len(current)>0:
+        results.append(current)
+    
+    # from tokens to string
+    strings = []
+    for c in results:
+        tokens = []
+        starts = []
+        ends = []
+        for o in c:
+            tokens.append(o['word'])
+            starts.append(o['start'])
+            ends.append(o['end'])
+
+        new_str = tokenizer.convert_tokens_to_string(tokens)
+        if new_str!='':
+            strings.append(dict(
+                word=new_str,
+                start = min(starts),
+                end = max(ends),
+                entity = c[0]['entity']
+            ))
+    return strings
+
+def entity_table(pipeline, **pipeline_kw):
+    if "aggregation_strategy" not in pipeline_kw:
+        pipeline_kw["aggregation_strategy"] = "first"
+    def create_table(text):
+        return pd.DataFrame(
+            clean_output(
+                pipeline(text, **pipeline_kw)
+            )
+        )
+    return create_table
+
+# will return a dataframe
+entity_table(ner)(YOUR_VERY_CONTENTFUL_TEXT)
+```
+
+> check our NER model on
+* [gene and gene products](/raynardj/ner-gene-dna-rna-jnlpba-pubmed)
+* [chemical substance](/raynardj/ner-chemical-bionlp-bc5cdr-pubmed).
+* [disease](/raynardj/ner-disease-ncbi-bionlp-bc5cdr-pubmed)

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "raynardj/roberta-pubmed",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "protein",
+    "2": "DNA",
+    "3": "cell_type",
+    "4": "cell_line",
+    "5": "RNA"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "DNA": 2,
+    "O": 0,
+    "RNA": 5,
+    "cell_line": 4,
+    "cell_type": 3,
+    "protein": 1
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255a480aa20741d98de5708721f9431b0b1394ed1f6e90d4094226ee45197733
+size 496325623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "raynardj/roberta-pubmed", "tokenizer_class": "RobertaTokenizer"}