Online Services

●D-I-TASSER ●DMFold ●LOMETS3 ●DeepMSA2 ●HPmod ●BioLiP2 ●US-align ●InterLabelGO ●StarFunc ●ShapeME

[an error occurred while processing this directive]

DeepMSA2 standalone package is a program for deep multiple sequence alignment generation for both monomer and multimer proteins. Please report bugs and questions at Zhang Lab Service System Discussion Board. The DeepMSA2 package is free for academic and non-profit researchers.

---

DeepMSA2 download:

• For academic users, please click here to download the DeepMSA2 package.
• If you need DeepMSA2 for a commercial use, please contact us through jlspzw@nankai.edu.cn.

---

Release Note:

v2.2 (2024/03/22)
1. Fix a MSA combination scoring function issue in MSA_combination.py

v2.1 (2024/02/09)
1. Fix a JGI search bug when dMSA does have enough sequences but qMSA does not
2. Update Install_af2_env.sh with the numpy and tensorflow

v2.0 (2024/01/01)
original version of DeepMSA2

---

We recommand you use "Download_lib.py" in DeepMSA2 package to download all required databases. However you can also manually download all sequence library below:

The third-party genomics and metagenomics sequence databases.

• uniclust30_2017_04: Uniclust30 HHblits style HMM sequence library (for MSA construction).
• uniref90: UniRef90 library (for MSA construction).
• metaclust: Metaclust library (for MSA construction).
• UniRef30_2022_02: UniRef30 HHblits style HMM sequence library (for MSA construction).
• BFD: BFD HHblits style HMM sequence library (for MSA construction).
• MGnify: MGnify library (for MSA construction).

DeepMSA2 sequence library, JGIclust, TaraDB and MetaSourceDB metagenome databases with 30% redundancy removed, producted by Zhang Lab (for MSA construction). We recommand you download the DeepMSA2 first, then use Download_lib.py download this library.

• JGI list
• DB.fasta.aa
• DB.fasta.aa.ssi
• DB.fasta.ab
• DB.fasta.ab.ssi
• DB.fasta.ac
• DB.fasta.ac.ssi
• DB.fasta.ad
• DB.fasta.ad.ssi

AlphaFold2 library used in DeepMSA2 for MSA ranking:

• AlphaFold2 parameters.
• PDB70 library.
• MMCIF format coordinates.
• PDB sequences.
• Small BFD sequence database.
• Uniprot sequence database.

How to cite DeepMSA2?

• Wei Zheng, Qiqige Wuyun, Yang Li, Chengxin Zhang, P Lydia Freddolino, Yang Zhang. Improving deep learning protein monomer and complex structure prediction using DeepMSA2 with huge metagenomics data. Nature Methods, (2024). https://doi.org/10.1038/s41592-023-02130-4.