Skip to main content

Simple MSA

Project description

MSA by ML researchers for ML researchers --️ in pytorch/cuda ❤️
# install
pip install sseqs
wget https://foldify.org/uniref_bfd_mgy_cf.xbit 

# python 
from sseqs import msa
msa("HPETLVKVKDAEDQLGARVG"*10, "msa.a3m")
db_len=998 q_len=200: 100%|█████████| 121/121 [00:11<00:00, 10.40GB/s]

# boltz2 msa-server 🔥
DBPATH=uniref_bfd_mgy_cf.xbit python server.py --port 8000
boltz predict demo.fasta --msa_server_url http://0.0.0.0:8000 --use_msa_server

No need for $5h/h server with 1000GB RAM. Developed for $0.3/h rtx4090+128GB RAM.

limitations

  • no protein pairing
  • sequence length < 1000 (working on 2048)
  • 128gb RAM (working on 64GB w/ compression)
  • no <16GB approximate version (yet)
  • no evals (working on runs'n'poses + antibody)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sseqs-0.0.9.tar.gz (36.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sseqs-0.0.9-py3-none-any.whl (39.1 kB view details)

Uploaded Python 3

File details

Details for the file sseqs-0.0.9.tar.gz.

File metadata

  • Download URL: sseqs-0.0.9.tar.gz
  • Upload date:
  • Size: 36.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0

File hashes

Hashes for sseqs-0.0.9.tar.gz
Algorithm Hash digest
SHA256 5471e4c31b46a48d08586def5a8dbe26596e8aedbc8f9d265e208f15332287aa
MD5 14cbf131cc98a929b4aacfa7c84a8f9a
BLAKE2b-256 aa565464e1252c8ce2d5c73001c2aa9075e67fdc7c8c56ff7616f8ec08737650

See more details on using hashes here.

File details

Details for the file sseqs-0.0.9-py3-none-any.whl.

File metadata

  • Download URL: sseqs-0.0.9-py3-none-any.whl
  • Upload date:
  • Size: 39.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0

File hashes

Hashes for sseqs-0.0.9-py3-none-any.whl
Algorithm Hash digest
SHA256 10bc3311bd9d72e6d3f22fe55e2ed6848b154fcf2241e35695dc9d0060ae5a7d
MD5 75b8963b00a2402ac4077ee67adf1f9b
BLAKE2b-256 0ab99cf0c2c2c125bbc72dafe0d6d47372dd5314084828eed139c8166078c755

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page