nfsrulesFR/mega-moledit-large
收藏资源简介:
--- license: gpl-3.0 task_categories: - text-generation language: - en tags: - chemistry - molecular-editing - drug-discovery - smiles - molecule-generation pretty_name: MEGA Molecular Editing Dataset (Large - 62M) size_categories: - 10M<n<100M dataset_info: features: - name: task_id dtype: int64 - name: prompt dtype: string - name: input_smiles dtype: string - name: output_smiles dtype: string - name: action_type dtype: string - name: edit dtype: string - name: target_delta dtype: float64 - name: SA_delta dtype: float64 - name: MW_delta dtype: float64 - name: QED_delta dtype: float64 - name: murcko_scaffold_retained dtype: bool splits: - name: train num_bytes: 10576225637 num_examples: 28219060 - name: validation num_bytes: 1175208625 num_examples: 3135462 - name: train_neg num_bytes: 8843010060 num_examples: 23684301 - name: validation_neg num_bytes: 982619844 num_examples: 2631604 download_size: 6506509462 dataset_size: 21577064166 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: train_neg path: data/train_neg-* - split: validation_neg path: data/validation_neg-* --- # MEGA: A Large-Scale Molecular Editing Dataset for Guided-Action Optimization Large-scale annotated molecular editing dataset with 57M examplesfor training models to modify molecular structures based on natural language instructions. **Paper**: [MEGA: A Large-Scale Molecular Editing Dataset for Guided-Action Optimization](https://openreview.net/pdf?id=MaS7e2EVFm) **Official Repository**: [https://github.com/nfsrules/MEGA-moledit](https://github.com/nfsrules/MEGA-moledit) ## Dataset Structure Each example will contain: - `task_id`: Task identifier - `prompt`: Natural language instruction - `input_smiles`: Input molecule - `output_smiles`: Target molecule - `action_type`: Edit operation type - `edit`: Specific edit applied - `target_delta`: Change in target property - `SA_delta`: Change in Synthetic Accessibility - `MW_delta`: Change in Molecular Weight - `QED_delta`: Change in Drug-likeness - `murcko_scaffold_retained`: Scaffold preservation flag ## Supported Tasks | Task ID | Description | |---------|-------------| | 101 | Increase water solubility | | 102 | Decrease water solubility | | 103 | Increase drug-likeness | | 104 | Decrease drug-likeness | | 105 | Increase permeability | | 106 | Decrease permeability | | 107 | Increase hydrogen bond acceptors | | 108 | Increase hydrogen bond donors | | 201 | Increase solubility + HBA | | 202 | Decrease solubility + increase HBA | | 203 | Increase solubility + HBD | | 204 | Decrease solubility + increase HBD | | 205 | Increase solubility + permeability | | 206 | Increase solubility + decrease permeability | **Splits**: `train` (31M positive + 26M negative), `validation` ## Smaller Variant Check out the smaller version: [nfsrulesFR/mega-moledit-522K](https://huggingface.co/datasets/nfsrulesFR/mega-moledit-522K) ## Trained Models Llama 3 8B-based models for molecular optimization: - **MEGA-SFT**: [nfsrulesFR/mega-sft](https://huggingface.co/nfsrulesFR/mega-sft) - Supervised fine-tuning model - **MEGA-GRPO**: [nfsrulesFR/mega-grpo](https://huggingface.co/nfsrulesFR/mega-grpo) - Tanimoto-GRPO optimized model ## Citation ```bibtex @article{ fernandezillouz2025mega, title={MEGA: A Large-Scale Molecular Editing Dataset for Guided-Action Optimization}, author={Nelson Fernandez and Maxime Illouz and Luis Pinto and Entao Yang and Habiboulaye Amadou Boubacar}, journal={Under review at International Conference on Learning Representations}, year={2025}, url={https://openreview.net/pdf?id=MaS7e2EVFm} } ```
许可证:GPL-3.0 任务类别: - 文本生成 语言: - 英语 标签: - 化学 - 分子编辑 - 药物发现 - SMILES(Simplified Molecular Input Line Entry System) - 分子生成 数据集展示名称:MEGA 分子编辑数据集(大型版——6200万样本) 样本规模类别:1000万 < n < 1亿 数据集信息: 特征: - 名称:task_id 数据类型:int64 - 名称:prompt 数据类型:字符串 - 名称:input_smiles 数据类型:字符串 - 名称:output_smiles 数据类型:字符串 - 名称:action_type 数据类型:字符串 - 名称:edit 数据类型:字符串 - 名称:target_delta 数据类型:float64 - 名称:SA_delta 数据类型:float64 - 名称:MW_delta 数据类型:float64 - 名称:QED_delta 数据类型:float64 - 名称:murcko_scaffold_retained 数据类型:布尔值 数据集划分: - 名称:train 字节数:10576225637 样本数:28219060 - 名称:validation 字节数:1175208625 样本数:3135462 - 名称:train_neg 字节数:8843010060 样本数:23684301 - 名称:validation_neg 字节数:982619844 样本数:2631604 下载大小:6506509462 数据集总大小:21577064166 配置项: - 配置名称:default 数据文件: - 划分:train 路径:data/train-* - 划分:validation 路径:data/validation-* - 划分:train_neg 路径:data/train_neg-* - 划分:validation_neg 路径:data/validation_neg-* --- # MEGA:面向引导动作优化的大规模分子编辑数据集 本数据集为大规模标注分子编辑数据集,包含5700万条样本,用于训练可基于自然语言指令修改分子结构的模型。 **论文**:[MEGA:面向引导动作优化的大规模分子编辑数据集](https://openreview.net/pdf?id=MaS7e2EVFm) **官方仓库**:[https://github.com/nfsrules/MEGA-moledit](https://github.com/nfsrules/MEGA-moledit) ## 数据集结构 每条样本包含以下字段: - `task_id`:任务标识符 - `prompt`:自然语言指令 - `input_smiles`:输入分子的SMILES字符串 - `output_smiles`:目标分子的SMILES字符串 - `action_type`:编辑操作类型 - `edit`:所应用的具体编辑操作 - `target_delta`:目标属性变化量 - `SA_delta`:合成可及性(Synthetic Accessibility)变化量 - `MW_delta`:分子量(Molecular Weight)变化量 - `QED_delta`:药物相似性(Drug-likeness)变化量 - `murcko_scaffold_retained`:默克骨架保留标志 ## 支持任务 | 任务ID | 任务描述 | |---------|-------------| | 101 | 提升水溶性 | | 102 | 降低水溶性 | | 103 | 提升药物相似性 | | 104 | 降低药物相似性 | | 105 | 提升膜通透性 | | 106 | 降低膜通透性 | | 107 | 增加氢键受体数目 | | 108 | 增加氢键供体数目 | | 201 | 提升水溶性并增加氢键受体数目 | | 202 | 降低水溶性并增加氢键受体数目 | | 203 | 提升水溶性并增加氢键供体数目 | | 204 | 降低水溶性并增加氢键供体数目 | | 205 | 提升水溶性并提升膜通透性 | | 206 | 提升水溶性并降低膜通透性 | **数据集划分**:`train`(3100万正样本 + 2600万负样本),`validation` ## 小型变体 可查看精简版本:[nfsrulesFR/mega-moledit-522K](https://huggingface.co/datasets/nfsrulesFR/mega-moledit-522K) ## 预训练模型 基于Llama 3 8B的分子优化模型: - **MEGA-SFT**:[nfsrulesFR/mega-sft](https://huggingface.co/nfsrulesFR/mega-sft) —— 监督微调模型 - **MEGA-GRPO**:[nfsrulesFR/mega-grpo](https://huggingface.co/nfsrulesFR/mega-grpo) —— 基于Tanimoto-GRPO优化的模型 ## 引用格式 bibtex @article{ fernandezillouz2025mega, title={MEGA: A Large-Scale Molecular Editing Dataset for Guided-Action Optimization}, author={Nelson Fernandez and Maxime Illouz and Luis Pinto and Entao Yang and Habiboulaye Amadou Boubacar}, journal={Under review at International Conference on Learning Representations}, year={2025}, url={https://openreview.net/pdf?id=MaS7e2EVFm} }



