boron-nmr-predict
Installation
SKILL.md
Boron NMR Predict
Use the bundled scripts for deterministic local inference.
Workflow
- Create and activate a fresh conda environment for this skill.
- Install Python dependencies from
requirements-core.txtandrequirements-pyg.txt. - Ensure model files exist locally by running
scripts/ensure_model.py. - Run
scripts/predict_boron_nmr.pywith a SMILES string and solvent. - Return the predicted chemical shift for each boron atom in text form.
- Generate the labeled PNG image into the user's tmp directory so each ppm value can be matched to
B(index)in the structure image.
Input contract
Prefer SMILES input.
Required:
- Molecule SMILES containing at least one boron atom
Related skills
More from internscience/chemclaw
molecular_properties_predictor
预测小分子多种物化性质（沸点、折射率、密度、黏度、表面张力等），当前已真实接入 bamboo_mixer 单分子物性模型后端。
14literature-parsing
将 PDF 文献转换为 Markdown 文件，并提取所有图表图片。使用 MinerU (opendatalab) 进行工业级高质量解析。
14reaction-data-extraction
从 PDF 文献中提取化学反应数据，特别是反应条件优化信息。支持提取反应物、产物、催化剂、溶剂、温度、时间、产率等，并输出结构化 CSV 文件。使用 MinerU + NLP + 规则匹配进行精确提取。
14mineru-pdf-converter
|
13adme-prediction
ADME 性质预测工具。预测分子的吸收、分布、代谢、排泄性质，包括 Caco-2 通透性、PAMPA、HIA、Pgp 抑制、生物利用度、亲脂性等。使用 Morgan 指纹 + Random Forest/XGBoost。当用户提到 ADME 预测、药物性质、通透性、吸收、代谢等时触发。
13nmr-prediction
Predict liquid-phase ¹H and ¹³C NMR chemical shifts from a SMILES string using NMRNet (deep learning, SE(3)-Transformer). Outputs per-atom shift values (ppm) and Lorentzian-broadened spectrum PNG files.
13