Generate protein sequences and structures with ESM3 and embeddings with ESM C.
npx skills add https://github.com/hxk622/TokenDance --skill esm-hxk622
Please help me install this Agent Skill. Skill: esm Source: https://github.com/hxk622/TokenDance/tree/main/backend/app/skills/builtin/scientific/bioinformatics/esm Command: npx skills add https://github.com/hxk622/TokenDance --skill esm-hxk622
This Skill empowers researchers and developers to design novel proteins, predict their structures, and generate embeddings for downstream analysis, streamlining complex bioinformatics workflows.
Use the esm skill to generate a protein sequence of 100 residues with the label "fluorescent_protein".
High-intent search queries and answers about installing and using this skill.
Protein language models enable generative protein design by creating new sequences and structures. Using ESM3, you can generate novel protein sequences, such as a 100-residue sequence with a specific functional label, to solve bioinformatics and drug discovery problems.
Yes, structure prediction and inverse folding are supported. You can predict 3D protein structures from amino acid sequences or design new sequences that fold into given target structures, facilitating complex bioinformatics workflows.
Protein embeddings for classification and clustering are generated using ESM C. This creates powerful numerical representations of protein sequences, enabling representation learning for downstream bioinformatics analysis.
Yes, the toolkit supports local model execution and cloud-based Forge API. This allows you to scale protein inference workloads efficiently, from local sequence generation to cloud-based structure prediction.
Streamlining enzyme design workflows involves using a comprehensive protein language modeling toolkit. It combines generative design with ESM3 and efficient embeddings with ESM C to solve sequence generation, function annotation, and structure prediction problems.
No specialized dependencies are required to start. The toolkit provides scripts and references for protein language modeling, allowing you to execute generative design and structure prediction directly or via the cloud-based Forge API.
MDheweiCompute physicochemical properties, motifs, and domains from protein sequences.
InternScienceRebuild missing atoms in protein PDB structures for docking and simulation preparation.
K-Dense-AIRetrieve AlphaFold-predicted protein structures and confidence metrics by UniProt IDs.
IDEA-XLRun BLAST analyses against chosen databases to identify homologous sequences.
