From 65b07f376149795ccbda0e3c55d7acd106010022 Mon Sep 17 00:00:00 2001 From: Siyu Yang Date: Tue, 18 Mar 2025 02:50:18 +0000 Subject: [PATCH 01/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang --- .../docs/source_zh_cn/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index 28a0e275c8..a9c0ab14e9 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -1,4 +1,4 @@ -# 分子生成 +# 结构生成 [![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) -- Gitee From 72f8c263076fd6f28c5447e0e1d70de6c7ab6b19 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 03:49:20 +0000 Subject: [PATCH 02/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_zh_cn/user/molecular_generation.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index a9c0ab14e9..506a1db28e 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -2,10 +2,10 @@ [![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) -分子生成，通过深度学习的生成模型去预测并生成粒子体系中的组成. 我们集成了基于主动学习进行高熵合金设计的方法，设计热膨胀系数极低的高熵合金组分。在主动学习流程中，首先基于AI模型生成候选的高熵合金组分，并基于预测模型和热动力学计算预测热膨胀系数对候选组分进行筛选，最终需要研究者基于实验验证确定最终的高熵合金组分。 +结构生成，深度学习的生成模型用于预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，并且在晶体结构预测任务中表现出色。 ## 已支持网络 | 功能 | 模型 | 训练 | 推理 | 后端 | | :------------- | :-------------------- | :--- | :--- | :-------- | -| 分子生成| [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/high_entropy_alloy_design) | √ | √ | Ascend | +| 结构生成| [DiffCSP](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/diffcsp) | √ | √ | Ascend | -- Gitee From 3395bb226837410559481b987d3ae2c7fa73e61f Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 03:50:55 +0000 Subject: [PATCH 03/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_zh_cn/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index 506a1db28e..e731a4ef70 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -2,7 +2,7 @@ [![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) -结构生成，深度学习的生成模型用于预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，并且在晶体结构预测任务中表现出色。 +结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，并且在晶体结构预测任务中表现出色。 ## 已支持网络 -- Gitee From 87fd462dc05f9294e189102331280af1cef5f90e Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 03:51:18 +0000 Subject: [PATCH 04/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_zh_cn/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index e731a4ef70..5d6d75d44a 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -2,7 +2,7 @@ [![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) -结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，并且在晶体结构预测任务中表现出色。 +结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，且在晶体结构预测任务中表现出色。 ## 已支持网络 -- Gitee From 93d3b485184efbe4adaa2968466c087d33d99bb8 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 05:58:42 +0000 Subject: [PATCH 05/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_zh_cn/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index 5d6d75d44a..b8c9918776 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -1,6 +1,6 @@ # 结构生成 -[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) +[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md) 结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，且在晶体结构预测任务中表现出色。 -- Gitee From 8e97d08ed63f5eb183079f9c476b04358cde9cf2 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 05:59:07 +0000 Subject: [PATCH 06/11] update docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_zh_cn/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md index b8c9918776..5d6d75d44a 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md @@ -1,6 +1,6 @@ # 结构生成 -[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md) +[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) 结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，且在晶体结构预测任务中表现出色。 -- Gitee From 131724e489b7d33b270a52997cbe851d42147555 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 06:08:26 +0000 Subject: [PATCH 07/11] update docs/mindchemistry/docs/source_en/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../docs/source_en/user/molecular_generation.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/docs/mindchemistry/docs/source_en/user/molecular_generation.md b/docs/mindchemistry/docs/source_en/user/molecular_generation.md index 69d8a7b22e..c377c8d58c 100644 --- a/docs/mindchemistry/docs/source_en/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_en/user/molecular_generation.md @@ -1,11 +1,11 @@ -# Molecular Generation +# Structure Generation [![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) -Molecular generation, using deep learning generation models to predict and generate components in the particle system. We have integrated a method based on active learning for high entropy alloy design, designing high entropy alloy components with extremely low thermal expansion coefficients. In the active learning process, first, candidate high entropy alloy components are generated based on AI models, and the candidate components are screened based on predictive models and thermodynamic calculations to predict the thermal expansion coefficient. Finally, researchers need to determine the final high entropy alloy components based on experimental verification. +Structure generation, which is a structure generation model based on deep learning to predict the structures of crystalline materials. DiffCSP integrates graph neural networks and equivalent diffusion models to jointly generate crystal lattices and atomic coordinates. It also leverages a periodic E(3)-equivalent denouncing model to better simulate the geometric properties of crystals. Compared with traditional methods based on density functional theory, DiffCSP significantly reduces computational costs and demonstrates excellent performance in crystal structure prediction tasks. ## Supported Networks | Function | Model | Training | Inferring | Back-end | |:---------------------| :-------------------- | :--- | :--- |:-----------| -| molecular generation | [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/high_entropy_alloy_design) | √ | √ | Ascend | +| structure generation | [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/high_entropy_alloy_design) | √ | √ | Ascend | -- Gitee From 4ce70ae11bfc8f28c34f9f3e0adf6d2b5c06991b Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 06:15:10 +0000 Subject: [PATCH 08/11] update docs/mindchemistry/docs/source_en/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- docs/mindchemistry/docs/source_en/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_en/user/molecular_generation.md b/docs/mindchemistry/docs/source_en/user/molecular_generation.md index c377c8d58c..3097364ba7 100644 --- a/docs/mindchemistry/docs/source_en/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_en/user/molecular_generation.md @@ -8,4 +8,4 @@ Structure generation, which is a structure generation model based on deep learni | Function | Model | Training | Inferring | Back-end | |:---------------------| :-------------------- | :--- | :--- |:-----------| -| structure generation | [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/high_entropy_alloy_design) | √ | √ | Ascend | +| structure generation | [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/diffcsp) | √ | √ | Ascend | -- Gitee From 0363f6407ab9c0b1ef39a1472b98bd53d91cb249 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 06:16:19 +0000 Subject: [PATCH 09/11] update docs/mindchemistry/docs/source_en/user/molecular_generation.md. Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- docs/mindchemistry/docs/source_en/user/molecular_generation.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/mindchemistry/docs/source_en/user/molecular_generation.md b/docs/mindchemistry/docs/source_en/user/molecular_generation.md index 3097364ba7..3c8ae0fd62 100644 --- a/docs/mindchemistry/docs/source_en/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_en/user/molecular_generation.md @@ -8,4 +8,4 @@ Structure generation, which is a structure generation model based on deep learni | Function | Model | Training | Inferring | Back-end | |:---------------------| :-------------------- | :--- | :--- |:-----------| -| structure generation | [high_entropy_alloy_design](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/diffcsp) | √ | √ | Ascend | +| structure generation | [DiffCSP](https://gitee.com/mindspore/mindscience/tree/master/MindChemistry/applications/diffcsp) | √ | √ | Ascend | -- Gitee From 73623ea1a765f38326d4c210b31621727be095c1 Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 06:42:14 +0000 Subject: [PATCH 10/11] rename docs/mindchemistry/docs/source_en/user/molecular_generation.md Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../user/{molecular_generation.md => structure_generation.md} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename docs/mindchemistry/docs/source_en/user/{molecular_generation.md => structure_generation.md} (94%) diff --git a/docs/mindchemistry/docs/source_en/user/molecular_generation.md b/docs/mindchemistry/docs/source_en/user/structure_generation.md similarity index 94% rename from docs/mindchemistry/docs/source_en/user/molecular_generation.md rename to docs/mindchemistry/docs/source_en/user/structure_generation.md index 3c8ae0fd62..268d294c06 100644 --- a/docs/mindchemistry/docs/source_en/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_en/user/structure_generation.md @@ -1,6 +1,6 @@ # Structure Generation -[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) +[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md) Structure generation, which is a structure generation model based on deep learning to predict the structures of crystalline materials. DiffCSP integrates graph neural networks and equivalent diffusion models to jointly generate crystal lattices and atomic coordinates. It also leverages a periodic E(3)-equivalent denouncing model to better simulate the geometric properties of crystals. Compared with traditional methods based on density functional theory, DiffCSP significantly reduces computational costs and demonstrates excellent performance in crystal structure prediction tasks. -- Gitee From 6512b1c4e9af41e75dc238f3c9808cff7eadf75f Mon Sep 17 00:00:00 2001 From: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> Date: Tue, 18 Mar 2025 06:52:12 +0000 Subject: [PATCH 11/11] rename docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md Signed-off-by: Siyu Yang <14763552+yang-siyu9777@user.noreply.gitee.com> --- .../user/{molecular_generation.md => structure_generation.md} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename docs/mindchemistry/docs/source_zh_cn/user/{molecular_generation.md => structure_generation.md} (94%) diff --git a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md b/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md similarity index 94% rename from docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md rename to docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md index 5d6d75d44a..b8c9918776 100644 --- a/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md +++ b/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md @@ -1,6 +1,6 @@ # 结构生成 -[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/molecular_generation.md) +[![查看源文件](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg)](https://gitee.com/mindspore/docs/blob/master/docs/mindchemistry/docs/source_zh_cn/user/structure_generation.md) 结构生成，通过深度学习的生成模型预测晶体材料的结构。我们集成了基于图神经网络和等变扩散模型的晶体生成模型 DiffCSP，它通过联合生成晶格和原子坐标来预测晶体结构，并利用周期性 E(3) 等变去噪模型来更好地模拟晶体的几何特性。它在计算成本上远低于传统的基于密度泛函理论的方法，且在晶体结构预测任务中表现出色。 -- Gitee