用代数数据类型重构分子表示，让模型更懂化学结构逻辑
Representing Molecules with Algebraic Data Types: Beyond SMILES and SELFIES
- 用代数数据类型拆分分子的组成、立体几何和电子信息
- 支持确定性校验与局部变换，避免传统字符串编辑错误
- 适合需要精确化学规则的生成模型与量子化学学习任务
分子机器学习基准常将分子表示视为中立输入格式，但表示方式决定了有效性语法、可编辑操作和模型隐式学习的不变性。我们提出 MolADT，一种基于代数数据类型的分子中间表示，分离了（i）通过 Dietz 风格键合系统定义的组成，（ii）三维几何与立体化学，以及（iii）可选的电子标注。通过从字符串编辑转向结构化值操作，MolADT 显式表达表示假设，支持确定性验证与局部变换，并为对称性感知与贝叶斯工作流提供接口。我们提供了 Haskell 的开源实现（已归档，含 DOI），并展示了离域/多中心键合、验证不变性、反应扩展及几何学习相关的群作用等应用实例。
原文摘要 · Abstract (English)
Benchmarks of molecular machine learning models often treat the molecular representation as a neutral input format, yet the representation defines the syntax of validity, edit operations, and invariances that models implicitly learn. We propose MolADT, a typed intermediate representation (IR) for molecules expressed as a family of algebraic data types that separates (i) constitution via Dietz-style bonding systems, (ii) 3D geometry and stereochemistry, and (iii) optional electronic annotations. By shifting from string edits to operations over structured values, MolADT makes representational assumptions explicit, supports deterministic validation and localized transformations, and provides hooks for symmetry-aware and Bayesian workflows. We provide a reference implementation in Haskell (open-source, archived with DOI) and worked examples demonstrating delocalised/multicentre bonding, validation invariants, reaction extensions, and group actions relevant to geometric learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。