Transformers Bio NLP

pip install transformers torch datasets accelerate sentencepiece
# For GPU (CUDA 11.8)
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu118

from transformers import pipeline

# Named entity recognition with BioBERT
ner = pipeline("ner", model="allenai/scibert_scivocab_cased",
               aggregation_strategy="simple")

text = "BRCA1 mutations are associated with increased risk of breast cancer and ovarian cancer."
entities = ner(text)
for ent in entities:
    print(f"  {ent['word']:20s} {ent['entity_group']:10s} score={ent['score']:.3f}")

from transformers import pipeline, AutoTokenizer, AutoModelForTokenClassification

# BioBERT fine-tuned for NER (genes, diseases, chemicals)
# Common choices:
#   "allenai/scibert_scivocab_cased"  — scientific NER
#   "d4data/biomedical-ner-all"       — multi-entity biomedical NER
#   "pruas/BENT-PubMedBERT-NER-Gene"  — gene-specific NER
ner_pipe = pipeline(
    "ner",
    model="d4data/biomedical-ner-all",
    aggregation_strategy="simple",  # merge subword tokens into words
    device=-1  # -1=CPU, 0=GPU
)

abstracts = [
    "Imatinib inhibits the BCR-ABL1 tyrosine kinase and is first-line treatment for CML.",
    "EGFR mutations in non-small cell lung cancer predict response to erlotinib.",
]

for text in abstracts:
    entities = ner_pipe(text)
    print(f"\nText: {text[:60]}...")
    for e in entities:
        print(f"  [{e['entity_group']}] '{e['word']}' (score={e['score']:.2f})")

# Manual tokenization + inference for batch processing
from transformers import AutoTokenizer, AutoModelForTokenClassification
import torch

model_name = "allenai/scibert_scivocab_cased"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)
model.eval()

text = "Metformin activates AMPK and reduces hepatic glucose production in type 2 diabetes."
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=512)

with torch.no_grad():
    outputs = model(**inputs)

logits = outputs.logits  # shape: (1, seq_len, n_labels)
predictions = logits.argmax(dim=-1)[0]
tokens = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])
labels = [model.config.id2label[p.item()] for p in predictions]

for token, label in zip(tokens[1:-1], labels[1:-1]):  # skip [CLS] and [SEP]
    if label != "O":
        print(f"  {token:20s} {label}")

from transformers import pipeline

# Zero-shot classification — no fine-tuning needed
zs_clf = pipeline("zero-shot-classification",
                  model="facebook/bart-large-mnli",
                  device=-1)

abstract = """
This randomized controlled trial evaluated the efficacy of pembrolizumab versus
chemotherapy in patients with advanced non-small-cell lung cancer. Overall survival
was significantly improved in the pembrolizumab arm (HR=0.60, 95% CI 0.41-0.89).
"""

candidate_labels = ["clinical trial", "basic research", "meta-analysis", "review"]
result = zs_clf(abstract, candidate_labels)
print("Zero-shot classification:")
for label, score in zip(result["labels"], result["scores"]):
    print(f"  {label:20s}: {score:.3f}")

# Fine-tuned sentiment/outcome classification
from transformers import pipeline

# Example: classify clinical outcome sentiment
clf = pipeline("text-classification",
               model="pruas/BENT-PubMedBERT-NER-Gene",  # use appropriate task-specific model
               device=-1)

sentences = [
    "Treatment significantly improved overall survival (p<0.001).",
    "No statistically significant difference was observed between groups.",
]
results = clf(sentences)
for sent, result in zip(sentences, results):
    print(f"  [{result['label']} | {result['score']:.2f}] {sent[:50]}...")

from transformers import pipeline

# Extractive QA: find answer span within context
qa_pipe = pipeline(
    "question-answering",
    model="sultan/BioM-ELECTRA-Large-SQuAD2",  # biomedical QA model
    device=-1
)

context = """
BRCA1 is a tumor suppressor gene located on chromosome 17q21. Pathogenic variants
in BRCA1 confer a lifetime breast cancer risk of 50-72% and ovarian cancer risk
of 44-46%. BRCA1 protein functions in DNA double-strand break repair via
homologous recombination.
"""

questions = [
    "What chromosome is BRCA1 located on?",
    "What is the lifetime breast cancer risk from BRCA1 variants?",
    "What DNA repair pathway does BRCA1 participate in?",
]

for q in questions:
    result = qa_pipe(question=q, context=context)
    print(f"Q: {q}")
    print(f"A: {result['answer']} (score={result['score']:.3f})\n")

from transformers import AutoTokenizer, BioGptForCausalLM
import torch

model_name = "microsoft/biogpt"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = BioGptForCausalLM.from_pretrained(model_name)
model.eval()

prompt = "The role of VEGF in tumor angiogenesis"
inputs = tokenizer(prompt, return_tensors="pt")

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        num_beams=5,
        early_stopping=True,
        no_repeat_ngram_size=3,
        pad_token_id=tokenizer.eos_token_id,
    )

generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(f"Generated:\n{generated}")

from transformers import AutoTokenizer, AutoModel
import torch
import numpy as np

def mean_pooling(model_output, attention_mask):
    """Mean pooling across token embeddings."""
    token_embeddings = model_output.last_hidden_state
    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
    return (token_embeddings * input_mask_expanded).sum(1) / input_mask_expanded.sum(1)

# PubMedBERT for biomedical sentence embeddings
model_name = "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)
model.eval()

sentences = [
    "BRCA1 is involved in DNA double-strand break repair.",
    "Homologous recombination requires BRCA1 and BRCA2.",
    "Metformin inhibits hepatic gluconeogenesis via AMPK.",
]

inputs = tokenizer(sentences, padding=True, truncation=True,
                   max_length=512, return_tensors="pt")
with torch.no_grad():
    outputs = model(**inputs)

embeddings = mean_pooling(outputs, inputs["attention_mask"])
embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1).numpy()

# Compute cosine similarity
from numpy.linalg import norm
sim_01 = np.dot(embeddings[0], embeddings[1])
sim_02 = np.dot(embeddings[0], embeddings[2])
print(f"Similarity (BRCA1 repair vs. HR): {sim_01:.3f}")
print(f"Similarity (BRCA1 repair vs. Metformin): {sim_02:.3f}")

from transformers import (AutoTokenizer, AutoModelForTokenClassification,
                           TrainingArguments, Trainer, DataCollatorForTokenClassification)
from datasets import Dataset
import numpy as np

# Example: minimal NER fine-tuning setup
model_name = "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract"
label_list = ["O", "B-GENE", "I-GENE", "B-DISEASE", "I-DISEASE"]
id2label = {i: l for i, l in enumerate(label_list)}
label2id = {l: i for i, l in enumerate(label_list)}

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(
    model_name, num_labels=len(label_list), id2label=id2label, label2id=label2id
)

# Training arguments
training_args = TrainingArguments(
    output_dir="./biomed_ner_finetuned",
    num_train_epochs=3,
    per_device_train_batch_size=16,
    per_device_eval_batch_size=32,
    warmup_steps=100,
    weight_decay=0.01,
    logging_dir="./logs",
    evaluation_strategy="epoch",
    save_strategy="epoch",
    load_best_model_at_end=True,
)

print(f"Model ready for fine-tuning: {model_name}")
print(f"Labels: {label_list}")
# trainer = Trainer(model=model, args=training_args, ...)
# trainer.train()

from transformers import pipeline
import pandas as pd

ner_pipe = pipeline("ner", model="d4data/biomedical-ner-all",
                    aggregation_strategy="simple", device=-1)

abstracts = [
    "Pembrolizumab combined with chemotherapy significantly improved progression-free survival in HER2-positive breast cancer.",
    "Inhibition of EGFR by gefitinib is effective in patients with activating EGFR mutations in exons 19 and 21.",
    "CRISPR-Cas9 editing of the PCSK9 gene in hepatocytes reduces LDL cholesterol in murine models.",
]

records = []
for i, text in enumerate(abstracts):
    entities = ner_pipe(text)
    for e in entities:
        records.append({
            "abstract_id": i,
            "entity": e["word"],
            "type": e["entity_group"],
            "score": round(e["score"], 3),
        })

df = pd.DataFrame(records)
print(df.groupby("type")["entity"].apply(list).to_string())
df.to_csv("extracted_entities.csv", index=False)
print(f"\nExtracted {len(df)} entity mentions across {len(abstracts)} abstracts")

from transformers import AutoTokenizer, AutoModel
import torch
import numpy as np

model_name = "microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract-fulltext"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name)
model.eval()

def embed(texts):
    enc = tokenizer(texts, padding=True, truncation=True,
                    max_length=512, return_tensors="pt")
    with torch.no_grad():
        out = model(**enc)
    vecs = out.last_hidden_state[:, 0, :]  # [CLS] token
    return torch.nn.functional.normalize(vecs, dim=1).numpy()

query = "CRISPR base editing for correction of point mutations in genetic disease"
corpus = [
    "Base editing enables precise single-base changes in genomic DNA without double-strand breaks.",
    "CAR-T cell therapy targets CD19 in B-cell acute lymphoblastic leukemia.",
    "Prime editing uses reverse transcriptase to install targeted edits at specific loci.",
    "RNA interference silences gene expression via RISC-mediated mRNA cleavage.",
]

q_emb = embed([query])
c_emb = embed(corpus)
scores = (q_emb @ c_emb.T).flatten()
ranked = sorted(zip(scores, corpus), reverse=True)

print("Top results:")
for score, text in ranked:
    print(f"  [{score:.3f}] {text[:70]}...")