This repository contains the implementation of BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining, by Renqian Luo, Liai Sun, Yingce Xia, Tao Qin, Sheng Zhang, Hoifung Poon and Tie-Yan Liu.

• BioGPT-Large model with 1.5B parameters is coming, currently available on PubMedQA task with SOTA performance of 81% accuracy. See Question Answering on PubMedQA for evaluation.

• PyTorch version == 1.12.0
• Python version == 3.10
• fairseq version == 0.12.0:

git clone https://github.com/pytorch/fairseq
cd fairseq
git checkout v0.12.0
pip install .
python setup.py build_ext --inplace
cd ..

• Moses

git clone https://github.com/moses-smt/mosesdecoder.git
export MOSES=${PWD}/mosesdecoder

• fastBPE

git clone https://github.com/glample/fastBPE.git
export FASTBPE=${PWD}/fastBPE
cd fastBPE
g++ -std=c++11 -pthread -O3 fastBPE/main.cc -IfastBPE -o fast

• sacremoses

pip install sacremoses

• sklearn

pip install scikit-learn

Remember to set the environment variables MOSES and FASTBPE to the path of Moses and fastBPE respetively, as they will be required later.

We provide our pre-trained BioGPT model checkpoints along with fine-tuned checkpoints for downstream tasks, available both through URL download as well as through the Hugging Face 🤗 Hub.

Download them and extract them to the checkpoints folder of this project.

For example:

mkdir checkpoints
cd checkpoints
wget https://msramllasc.blob.core.windows.net/modelrelease/BioGPT/checkpoints/Pre-trained-BioGPT.tgz
tar -zxvf Pre-trained-BioGPT.tgz

Use pre-trained BioGPT model in your code:

import torch
from fairseq.models.transformer_lm import TransformerLanguageModel
m = TransformerLanguageModel.from_pretrained(
        "checkpoints/Pre-trained-BioGPT", 
        "checkpoint.pt", 
        "data",
        tokenizer='moses', 
        bpe='fastbpe', 
        bpe_codes="data/bpecodes",
        min_len=100,
        max_len_b=1024)
m.cuda()
src_tokens = m.encode("COVID-19 is")
generate = m.generate([src_tokens], beam=5)[0]
output = m.decode(generate[0]["tokens"])
print(output)

Use fine-tuned BioGPT model on KD-DTI for drug-target-interaction in your code:

import torch
from src.transformer_lm_prompt import TransformerLanguageModelPrompt
m = TransformerLanguageModelPrompt.from_pretrained(
        "checkpoints/RE-DTI-BioGPT", 
        "checkpoint_avg.pt", 
        "data/KD-DTI/relis-bin",
        tokenizer='moses', 
        bpe='fastbpe', 
        bpe_codes="data/bpecodes",
        max_len_b=1024,
        beam=1)
m.cuda()
src_text="" # input text, e.g., a PubMed abstract
src_tokens = m.encode(src_text)
generate = m.generate([src_tokens], beam=args.beam)[0]
output = m.decode(generate[0]["tokens"])
print(output)

For more downstream tasks, please see below.

See corresponding folder in examples:

BioGPT has also been integrated into the Hugging Face transformers library, and model checkpoints are available on the Hugging Face Hub.

You can use this model directly with a pipeline for text generation. Since the generation relies on some randomness, we set a seed for reproducibility:

from transformers import pipeline, set_seed
from transformers import BioGptTokenizer, BioGptForCausalLM
model = BioGptForCausalLM.from_pretrained("microsoft/biogpt")
tokenizer = BioGptTokenizer.from_pretrained("microsoft/biogpt")
generator = pipeline('text-generation', model=model, tokenizer=tokenizer)
set_seed(42)
generator("COVID-19 is", max_length=20, num_return_sequences=5, do_sample=True)

Here is how to use this model to get the features of a given text in PyTorch:

from transformers import BioGptTokenizer, BioGptForCausalLM
tokenizer = BioGptTokenizer.from_pretrained("microsoft/biogpt")
model = BioGptForCausalLM.from_pretrained("microsoft/biogpt")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)

Beam-search decoding:

import torch
from transformers import BioGptTokenizer, BioGptForCausalLM, set_seed

tokenizer = BioGptTokenizer.from_pretrained("microsoft/biogpt")
model = BioGptForCausalLM.from_pretrained("microsoft/biogpt")

sentence = "COVID-19 is"
inputs = tokenizer(sentence, return_tensors="pt")

set_seed(42)

with torch.no_grad():
    beam_output = model.generate(**inputs,
                                 min_length=100,
                                 max_length=1024,
                                 num_beams=5,
                                 early_stopping=True
                                )
tokenizer.decode(beam_output[0], skip_special_tokens=True)

For more information, please see the documentation on the Hugging Face website.

Check out these demos on Hugging Face Spaces:

• Text Generation with BioGPT-Large
• Question Answering with BioGPT-Large-PubMedQA

BioGPT is MIT-licensed. The license applies to the pre-trained models as well.

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.