Skip to content

Commit b05ae80

Browse files
Kinicia7Kinicia7
authored
Update README.md
1 parent 7ae4703 commit b05ae80

File tree

1 file changed

+15
-13
lines changed

1 file changed

+15
-13
lines changed

‎README.md‎

Lines changed: 15 additions & 13 deletions
Original file line numberDiff line numberDiff line change
@@ -16,14 +16,14 @@ Authors: Jingqi Wang, Jiapeng Liu, Hongshuai Wang, Guolin Ke, Linfeng Zhang, Jia
1616

1717
Uni-MOF is an innovative framework for large-scale, three-dimensional MOF representation learning, designed for universal multi-gas prediction. Specifically, Uni-MOF serves as a versatile "gas adsorption detector" for MOF materials, employing pure three-dimensional representations learned from over 631,000 collected MOF and COF structures. Our experimental results show that Uni-MOF can automatically extract structural representations and predict adsorption capacities under various operating conditions using a single model. For simulated data, Uni-MOF exhibits remarkably high predictive accuracy across all datasets. Impressively, the values predicted by Uni-MOF correspond with the outcomes of adsorption experiments. Furthermore, Uni-MOF demonstrates considerable potential for broad applicability in predicting a wide array of other properties.
1818

19-
Uni-MOF's data
19+
<!--Uni-MOF's data
2020
------------------------------
2121
Code and model weights will be released continuously.
22-
22+
-->
2323

2424
Dependencies
2525
------------
26-
- [Uni-Core](https://github.com/dptech-corp/Uni-Core), check its [Installation Documentation](https://github.com/dptech-corp/Uni-Core#installation).
26+
- [Uni-Core](https://github.com/dptech-corp/Uni-Core), check its [Installation Documentation](https://github.com/dptech-corp/Uni-Core#installation), this will take several minutes.
2727

2828
To use GPUs within docker you need to [install nvidia-docker-2](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html#docker) first. Use the following command to pull the docker image:
2929

@@ -32,19 +32,20 @@ docker pull dptechnology/unimol:latest-pytorch1.11.0-cuda11.3
3232
```
3333

3434

35-
<!-- Uni-MOF's data
35+
Uni-MOF's data
3636
------------------------------
3737

3838
For the details of datasets, please refer to Table 1 in our [paper](https://chemrxiv.org/engage/chemrxiv/article-details/6447d756e4bbbe4bbf3afeaa).
3939

40-
There are total 6 datasets:
40+
<!-- There are total 6 datasets:
4141
4242
4343
| Data | File Size | Update Date | Download Link |
4444
|--------------------------|------------| ----------- |---------------------------------------------------------------------------------------------------------------------------|
4545
| nanoporous material pretrain | GB | May 10 2023 | |
4646
| gas adsorption property | GB | May 10 2023 | |
4747
| material structural property | GB | May 10 2023 | |
48+
-->
4849

4950
We use [LMDB](https://lmdb.readthedocs.io) to store data, you can use the following code snippets to read from the LMDB file.
5051

@@ -77,20 +78,17 @@ Uni-Mol's pretrained model weights
7778

7879
| Model | File Size |Update Date | Download Link |
7980
|--------------------------|------------| ------------|--------------------------------------------------------------|
80-
| nanoporous material pretrain | MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/ |
81+
| nanoporous material pretrain |303 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/unimof_pretrain_best.pt|
8182

8283

8384
Uni-Mol's finetuned model weights
8485
----------------------------------
8586

8687
| Model | File Size| Update Date| Download Link |
8788
|-------------------------------------------------|---------| -----------|--------------------------------------------------------------------|
88-
| hMOF_MOFX_DB | MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download |
89-
| CoRE_MOFX_DB | MB | May 10 2023 |https://github.com/dptech-corp/Uni-Mol/releases/download |
90-
| CoRE_MAP_DB | MB | May 10 2023 |https://github.com/dptech-corp/Uni-Mol/releases/download |
91-
| hMOF_MOFX_DB w/o pretraining | MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download |
92-
| CoRE_MOFX_DB w/o pretraining | MB | May 10 2023 |https://github.com/dptech-corp/Uni-Mol/releases/download |
93-
| CoRE_MAP_DB w/o pretraining | MB | May 10 2023 |https://github.com/dptech-corp/Uni-Mol/releases/download |
89+
| hMOF_MOFX_DB |304 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/unimof_hMOF_MOFX_DB_finetune_best.pt|
90+
| CoRE_MOFX_DB |304 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/unimof_CoRE_MOFX_DB_finetune_best.pt|
91+
| CoRE_MAP_DB |168 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/unimof_CoRE_MAP_DB_fintune_best.pt|
9492

9593
Dependencies
9694
------------
@@ -231,6 +229,11 @@ nohup python -m torch.distributed.launch --nproc_per_node=$n_gpu --master_port=$
231229

232230
Single-system Gas Adsorption Property Prediction
233231
---------------------
232+
The prediction of MOF structural feature could be taken as demo. It may take 4 hours to obtain the best model performance [coefficient of determination (R2)] for the test set.
233+
| File | File Size| Update Date| Download Link |
234+
|-------------------------------------------------|---------| -----------|--------------------------------------------------------------------|
235+
| Data |304 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/MOF_structure_data.zip|
236+
| Weight |304 MB | May 10 2023 |https://github.com/dptech-corp/Uni-MOF/releases/download/v0.1/CoRE_PLD_bset.pt|
234237
```
235238
data_path="./single-system_gas_adsorption_property_prediction" # replace to your data path
236239
save_dir="./save_finetune" # replace to your save path
@@ -266,7 +269,6 @@ nohup python $(which unicore-train) $data_path --user-dir ./unimat --task-name $
266269
--best-checkpoint-metric valid_r2 --maximize-best-checkpoint-metric \
267270
> ./logs_finetune/$save_dir.log &
268271
```
269-
-->
270272

271273

272274
Citation

0 commit comments

Comments
 (0)