【PPMat Dataset No.4】tmQM_MEGNet #198
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for your contribution! |
31 tasks
leeleolay
requested changes
Nov 10, 2025
Collaborator
leeleolay
left a comment
leeleolay
left a comment
There was a problem hiding this comment.
在megnet readme文件中添加这个数据集的训练结果
property_prediction/configs/megnet/megnet_tmqm_train_108k_electronic_e.yaml
Outdated
Show resolved
Hide resolved
| path_bond: "./data/tmqm/tmQM_X.BO" | ||
| electronic_e_key: "electronic_e" | ||
| property_names: ${Global.label_names} | ||
| use_atomic_charge: True |
| electronic_e_key: "electronic_e" | ||
| property_names: ${Global.label_names} | ||
| use_atomic_charge: True | ||
| use_chemical_bonding: True |
leeleolay
reviewed
Nov 10, 2025
| sample_structure = structures[0] | ||
| logger.info(f"Structure object type: {type(sample_structure)}") | ||
| logger.info(f"Structure object attributes: {dir(sample_structure)}") | ||
| # If you use supplementary data, incorporate it into the structure |
Collaborator
There was a problem hiding this comment.
if len(structures) > 0:
sample_structure = structures[0]
logger.info(f"Structure object type: {type(sample_structure)}")
logger.info(f"Structure object attributes: {dir(sample_structure)}")
这块代码的作用是什么
Author
There was a problem hiding this comment.
在生成结构数据后,获取第一个结构对象作为样本,并通过日志记录其类型和所有可用属性,用于调试和验证 BuildStructure 返回的对象是否符合预期。
Author
并没有完整的训练（所需时间太长，在学校没有始终运行和监督的条件）。数据适配器可以正常运行，我会补充表格中有关数据集信息和配置文件的部分😊 |
leeleolay
reviewed
Nov 12, 2025
| <td nowrap="nowrap">megnet_tmqm_train_108k_dispersion_e</td> | ||
| <td nowrap="nowrap">tmQM_108k</td> | ||
| <td nowrap="nowrap">Dispersion Energy (Hartree)</td> | ||
| <td nowrap="nowrap"> 0.000 / 0.000</td> |
Collaborator
There was a problem hiding this comment.
‘0.000 / 0.000’这里修改为‘-’，
| <td nowrap="nowrap">Electronic Energy (Hartree)</td> | ||
| <td nowrap="nowrap"> 0.000 / 0.000</td> | ||
| <td nowrap="nowrap">1</td> | ||
| <td nowrap="nowrap">~0 hours</td> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
PR Category
Dataset adaptation
PR Types
Add adapters
Description
tmQM数据集是一个全面的过渡金属配合物量子化学数据库，包含多个互补的数据文件：.xyz文件提供了在GFN2-xTB级别优化的分子几何结构；.csv文件包含了SMILES分子表示以及在TPSSh/def2SVP级别计算的量子化学属性，包括电子能、色散能、偶极矩、金属电荷、HOMO/LUMO能隙和能量以及极化率；.q文件提供了在TPSSh/def2SVP水平计算的自然原子电荷分布；.BO文件则包含了在GFN2-xTB水平计算的Wiberg键级和原子价指数（其中极化率除外，是在GFN2-xTB水平单独计算的）。
网址： https://www.uiocompcat.info/tmqmdataset
现将.xyz文件的几何结构信息和.csv文件特征属性融合为一个数据集用于训练，同时出于模型适用性提供选择：”是否使用.q文件和.BO文件进行训练“，已在MEGNet模型上测试
示例bash: python property_prediction/train.py -c property_prediction/configs/megnet/megnet_tmqm_train_108k_electronic_e.yaml