Research map / Large language models / Instruction and fine-tuning
AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design
Ling Luo, Wenbin Jiang, Hongyuan Chang, Xinkang Wang, Xushi Zhang, Yueting Xiong, Mengsha Tong, Rongshan Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| instruction-tune on AFD-Instruction | Qwen2-7B · Antibody disease association classification | accuracy: 32.96 -> 87.83 | Improved |
| instruction-tune on AFD-Instruction | LLaMA-8B · Antibody disease association classification | accuracy: 6.19 -> 85.11 | Improved |
| instruction-tune on AFD-Instruction | Qwen2-7B · Antibody binding classification | accuracy: 53.42 -> 87.81 | Improved |
| instruction-tune on AFD-Instruction | LLaMA-8B · Antibody mechanism classification | accuracy: 59.72 -> 92.91 | Improved |
| instruction-tune on AFD-Instruction | Qwen2-7B · Antibody class classification | accuracy: 90.47 -> 98.86 | Improved |
| instruction-tune on AFD-Instruction | Qwen2-7B · Antibody function classification | accuracy: 64.59 -> 85.01 | Improved |
| scale tuned model from 8B to 70B | LLaMAB · Antibody understanding (accuracy) | accuracy: 87.01 -> 88.35 | No clear effect |
| instruction-tune on AFD-Instruction | Qwen2-7B · Disease caption | ROUGE-L: 33.37 -> 61.81 | Improved |
| instruction-tune on AFD-Instruction | LLaMA-8B · Binding caption | ROUGE-L: 22.47 -> 37.33 | Improved |
| instruction-tune on AFD-Instruction vs strongest antibody-specific model | LLaMA-8B · CDR-H3 design | SRR: 0.852 -> 0.884 | Improved |
| instruction-tune on AFD-Instruction vs general LLM | Qwen · CDR-H3 design | SRR: 0.163 -> 0.875 | Improved |
| instruction-tune on AFD-Instruction vs antibody-specific model | LLaMA-70B · CDR-H3 design | ipTM: 0.423 -> 0.491 | Improved |
Closest papers by meaning
- Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints (ICML 2024 · similarity 0.87)
- How to make the most of your masked language model for protein engineering (NeurIPS 2026 · similarity 0.87)
- Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models (ICLR 2024 · similarity 0.86)
- Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies (NeurIPS 2025 · similarity 0.86)
- Synergy of GFlowNet and Protein Language Model Makes a Diverse Antibody Designer (AAAI 2025 · similarity 0.86)
- Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization (ICLR 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
