Commit 9c213d7a authored by zhuwenwen's avatar zhuwenwen
Browse files

update readme std

parent 898a3706
...@@ -42,33 +42,44 @@ docker run -it --name alphafold --shm-size=32G --device=/dev/kfd --device=/dev/ ...@@ -42,33 +42,44 @@ docker run -it --name alphafold --shm-size=32G --device=/dev/kfd --device=/dev/
## 数据集 ## 数据集
推荐使用AlphaFold2中的开源数据集,包括BFD、MGnify、PDB70、Uniclust、Uniref90等,数据集大小约2.2TB。数据集格式如下: 推荐使用AlphaFold2中的开源数据集,包括BFD、MGnify、PDB70、Uniclust、Uniref90等,数据集大小约2.2TB。数据集格式如下:
``` ```
$DOWNLOAD_DIR/ # Total: ~ 2.2 TB (download: 438 GB) $DOWNLOAD_DIR/
bfd/ # ~ 1.7 TB (download: 271.6 GB) bfd/
# 6 files. bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt_hhm.ffindex
mgnify/ # ~ 64 GB (download: 32.9 GB) bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt_hhm.ffdata
bfd_metaclust_clu_complete_id30_c90_final_seq.sorted_opt_cs219.ffindex
...
mgnify/
mgy_clusters_2018_12.fa mgy_clusters_2018_12.fa
params/ # ~ 3.5 GB (download: 3.5 GB) params/
# 5 CASP14 models, params_model_1.npz
# 5 pTM models, params_model_2.npz
# 5 AlphaFold-Multimer models, params_model_3.npz
# LICENSE, ...
# = 16 files. pdb70/
pdb70/ # ~ 56 GB (download: 19.5 GB) pdb_filter.dat
# 9 files. pdb70_hhm.ffindex
pdb_mmcif/ # ~ 206 GB (download: 46 GB) pdb70_hhm.ffdata
...
pdb_mmcif/
mmcif_files/ mmcif_files/
# About 180,000 .cif files. 100d.cif
101d.cif
101m.cif
...
obsolete.dat obsolete.dat
pdb_seqres/ # ~ 0.2 GB (download: 0.2 GB) pdb_seqres/
pdb_seqres.txt pdb_seqres.txt
small_bfd/ # ~ 17 GB (download: 9.6 GB) small_bfd/
bfd-first_non_consensus_sequences.fasta bfd-first_non_consensus_sequences.fasta
uniclust30/ # ~ 86 GB (download: 24.9 GB) uniclust30/
uniclust30_2018_08/ uniclust30_2018_08/
# 13 files. uniclust30_2018_08_md5sum
uniprot/ # ~ 98.3 GB (download: 49 GB) uniclust30_2018_08_hhm_db.index
uniclust30_2018_08_hhm_db
...
uniprot/
uniprot.fasta uniprot.fasta
uniref90/ # ~ 58 GB (download: 29.7 GB) uniref90/
uniref90.fasta uniref90.fasta
``` ```
...@@ -137,6 +148,7 @@ multimer.fasta为推理的多体序列,data为数据集下载路径,其他 ...@@ -137,6 +148,7 @@ multimer.fasta为推理的多体序列,data为数据集下载路径,其他
... ...
``` ```
查看蛋白质3D结构:[https://www.pdbus.org/3d-view](https://www.pdbus.org/3d-view)
![img](./docs/result_pdb.png) ![img](./docs/result_pdb.png)
## 精度 ## 精度
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment