BioGPT Agent

Generates biomedical text using a GPT-style transformer architecture pre-trained exclusively on biomedical literature, enabling domain-aware language modeling without generic LLM hallucinations. The model uses Moses tokenization and FastBPE byte-pair encoding specifically tuned for biomedical terminology, allowing it to understand and generate text containing chemical names, drug interactions, and genomic sequences with higher accuracy than general-purpose models.

Answers biomedical questions by leveraging a fine-tuned model trained on the PubMedQA dataset, which contains yes/no/maybe questions paired with PubMed abstracts. The model encodes the question and document context through transformer attention layers, then predicts the answer class. This approach enables direct question-answering over biomedical literature without requiring external retrieval or knowledge base lookups.

Provides pre-trained and fine-tuned model checkpoints accessible via direct download or Hugging Face Hub, with clear versioning for base models (BioGPT, BioGPT-Large) and task-specific variants (QA, RE, DC). Checkpoints include model weights, vocabulary files (dict.txt), and BPE codes (bpecodes), enabling reproducible model loading and inference across environments without retraining.

Extracts structured relationships from biomedical text by identifying entity pairs and their interaction types using fine-tuned models trained on specialized datasets (BC5CDR for chemical-disease relations, DDI for drug-drug interactions, KD-DTI for drug-target interactions). The model uses sequence labeling or span-based extraction with transformer encoders to identify entity boundaries and classify relationship types, outputting structured triples suitable for knowledge graph construction.

Classifies biomedical documents into a hierarchical taxonomy of concepts using a fine-tuned model trained on the HoC (Hierarchy of Concepts) dataset. The model encodes document text through transformer layers and predicts multi-label concept assignments organized in a hierarchy, enabling automatic categorization of research papers, clinical documents, or biomedical literature into standardized concept frameworks without manual annotation.

Provides native inference interface through Fairseq's TransformerLanguageModel class, the original implementation used in the BioGPT paper. This integration exposes low-level control over beam search, sampling parameters, and token-level probabilities, enabling advanced inference patterns like constrained decoding, probability scoring, and custom stopping criteria. Fairseq integration is the reference implementation with full access to model internals.

Provides high-level inference interface through Hugging Face Transformers library using BioGptTokenizer and BioGptForCausalLM classes, enabling straightforward integration with standard transformer workflows and pipelines. This integration abstracts away Fairseq complexity, offering simplified model loading, batching, and generation with automatic device management, making BioGPT accessible to developers unfamiliar with Fairseq.

Tokenizes biomedical text using a two-stage pipeline: Moses tokenizer for linguistic segmentation (handling punctuation, contractions, and sentence boundaries specific to biomedical writing), followed by FastBPE byte-pair encoding with vocabulary learned from biomedical corpora. This approach preserves biomedical terminology (chemical names, protein identifiers, drug abbreviations) as atomic tokens rather than subword fragments, improving downstream model performance on domain-specific tasks.

Provides two model size variants (BioGPT and BioGPT-Large) with different parameter counts and computational requirements, enabling developers to choose between inference speed and generation quality based on deployment constraints. Both variants share the same architecture and tokenization but differ in layer depth and hidden dimensions, allowing trade-offs between latency, memory usage, and accuracy without changing application code.

Orchestrates multi-stage biomedical information extraction by chaining relation extraction, question answering, and document classification models in sequence. A developer can build pipelines that extract entities and relationships from documents, then answer questions about extracted relationships, or classify documents based on extracted concepts. This capability enables complex biomedical knowledge mining workflows without manual orchestration code.

Enables fine-tuning of BioGPT base models on custom biomedical datasets using Fairseq or Hugging Face training frameworks. Developers can adapt the pre-trained biomedical vocabulary and tokenization to new downstream tasks (e.g., adverse event extraction, clinical trial outcome prediction) by continuing training on task-specific labeled data. Fine-tuning preserves biomedical domain knowledge while specializing to new tasks.