chem-bond-dissociation
Calculate homolytic and heterolytic bond dissociation energies (BDEs) for all single bonds in a molecule using MLIPs with RDKit fragmentation.
learningmatter-mit · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add learningmatter-mit/AtomisticSkills --skill chem-bond-dissociation技能说明
name: chem-bond-dissociation description: Calculate homolytic and heterolytic bond dissociation energies (BDEs) for all single bonds in a molecule using MLIPs with RDKit fragmentation. category: [chemistry]
Bond Dissociation Energy Skill
Goal
Calculate the homolytic and/or heterolytic bond dissociation energy (BDE) for each single bond in a molecule using Machine Learning Interatomic Potentials (MLIPs).
Homolytic BDE (radical fragments): $$\text{BDE}_\text{homo}(A{-}B) = E(A\bullet) + E(B\bullet) - E(A{-}B)$$
Heterolytic BDE (ionic fragments, minimum over both polarity variants): $$\text{BDE}_\text{hetero}(A{-}B) = \min!\bigl(E(A^+)+E(B^-),; E(A^-)+E(B^+)\bigr) - E(A{-}B)$$
[!IMPORTANT] This skill computes BDEs by relaxing both the intact molecule and fragments with an MLIP. For purpose-trained GNN models that predict BDE directly from SMILES (MAE ~0.6 kcal/mol), consider ALFABET or BonDNet instead.
Background
BDE is a fundamental thermodynamic quantity that determines:
- Drug metabolism: CYP450 enzymes abstract H from the weakest C–H bond
- Electrolyte stability: Which bonds break first under electrochemical voltage
- Combustion chemistry: Rate-determining bond-breaking steps in fuel oxidation
- Polymer degradation: Weakest links in polymer backbone chains
A 2024 study (Zubatyuk et al., JCTC) demonstrated that MACE potentials achieve BDE RMSE of 1.37 kcal/mol for aliphatic C–H bonds in drug-like molecules, outperforming semi-empirical methods and ALFABET for BDE ranking.
1. Prerequisites
- Conda Environment:
mace-agent(includes RDKit, ASE, and MACE) - Input: SMILES string or structure file (
.sdf,.mol2) - RDKit: Required for bond identification and molecular fragmentation
2. Choosing a Foundation Potential
Refer to the foundation-potentials skill for model selection.
[!IMPORTANT] Model requirements by cleavage mode:
Mode Recommended model supports_charge_spinValidated? homolyticMACE-OFF23-small/medium/largeNot required ✅ heterolyticorbothMACE-OMOL-extra-large(env:mace-agent)✅ Required ✅ heterolyticorbothMACE-MH-1with omol head (env:mace-agent)✅ Required ✅ heterolyticorbothFairChem uma-s-1p1with--task_name omol(env:fairchem-agent)✅ Required ✅ Setting charge/spin on MACE models: use
atoms.info["charge"]andatoms.info["spin"](the calculator's defaultinfo_keysmaps"charge"→total_charge/"spin"→total_spin). Both MACE-OMOL and MACE-MH usejoint_embeddingto condition the network on these scalars.If you request
--cleavage bothwith a model that does not support charge/spin, the skill will log a warning and silently fall back to homolytic-only. Using--cleavage heterolyticwith an unsupported model raises an error.Note on single-atom fragments: When a bond produces a bare H (or other single atom), heterolytic BDE is automatically skipped — neither MACE nor FairChem UMA has signed single-atom energies (only neutral H, C, N, O… are in the reference tables).
3. Calculation Workflow
Step 1: Provide a molecule
# SMILES input (most common)
--smiles "CCO"
# Or from a structure file
--structure molecule.sdf
Step 2: Run BDE calculation
Homolytic only (default, no charge/spin needed):
# Env: mace-agent
python .agents/skills/chem-bond-dissociation/scripts/calculate_bde.py \
--smiles CCO \
--all_bonds \
--cleavage homolytic \
--model_type mace \
--model_name MACE-OFF23-small \
--output_dir research/my_folder/bde_results
Both homolytic and heterolytic (MACE-OMOL):
# Env: mace-agent
python .agents/skills/chem-bond-dissociation/scripts/calculate_bde.py \
--smiles CCO \
--all_bonds \
--cleavage both \
--model_type mace \
--model_name MACE-OMOL-extra-large \
--output_dir research/my_folder/bde_results_both
Both homolytic and heterolytic (FairChem UMA omol):
# Env: fairchem-agent
python .agents/skills/chem-bond-dissociation/scripts/calculate_bde.py \
--smiles CCO \
--all_bonds \
--cleavage both \
--model_type fairchem \
--model_name uma-s-1p1 \
--task_name omol \
--output_dir research/my_folder/bde_results_both
Heterolytic only with FairChem UMA:
# Env: fairchem-agent
python .agents/skills/chem-bond-dissociation/scripts/calculate_bde.py \
--smiles CCO \
--all_bonds \
--cleavage heterolytic \
--model_type fairchem \
--model_name uma-s-1p1 \
--task_name omol \
--output_dir research/my_folder/bde_hetero
Key Parameters
| Argument | Default | Description |
|---|---|---|
--smiles | — | SMILES string of the molecule |
--structure | — | Path to structure file (.sdf, .mol2) |
--bond | — | Specific bond as atom indices "i-j" (0-indexed) |
--all_bonds | True | Compute BDE for all single bonds |
--include_h_bonds | False | Include X–H bonds |
--cleavage | homolytic | homolytic, heterolytic, or both |
--model_type | mace | MLIP backend (mace, fairchem) |
--model_name | auto | Model checkpoint (default: MACE-OFF23-small for homolytic; uma-s-1p1 for hetero/both) |
--task_name | — | Task head for multi-task models (e.g. omol for FairChem UMA) |
--fmax | 0.01 | Force convergence for relaxation (eV/Å) |
--output_dir | required | Output directory |
4. Output Files
bde_results.json— Full results including:metadata: model name, cleavage mode,supports_charge_spin, SMILES, etc.intact_energy_eV: Energy of the relaxed intact moleculebonds: List of per-bond results:bde_eV,bde_kJ_mol,bde_kcal_mol: Homolytic BDE (if computed)