Generate protein sequences and extract embeddings using ESM3 and ESM C.
npx skills add https://github.com/jimmc414/Kosmos --skill esm-jimmc414
Please help me install this Agent Skill. Skill: esm Source: https://github.com/jimmc414/Kosmos/tree/main/kosmos-claude-scientific-skills/scientific-skills/esm Command: npx skills add https://github.com/jimmc414/Kosmos --skill esm-jimmc414
This Skill provides a comprehensive toolkit for working with advanced protein language models, enabling complex tasks in protein design, analysis, and engineering.
Use the esm skill to generate a novel protein sequence for a given prompt.
High-intent search queries and answers about installing and using this skill.
To generate a novel protein sequence for a specific catalytic function, you guide ESM3 using functional annotations and structural constraints. This allows you to design targeted enzymes by specifying the desired biological activity.
You can extract embeddings for protein representation learning by using ESM C. This provides high-quality vectors for downstream machine learning tasks like sequence classification and similarity analysis.
Yes, you can predict protein structure and perform inverse folding. The ESM3 model integrates multimodal protein generation to design sequences from target structures and predict 3D conformations.
The best way to design proteins from target structures is by applying inverse folding with ESM3. This multimodal protein generation technique maps structural constraints directly to novel amino acid sequences.
Yes, providing specific functional annotations and structural constraints is required to effectively guide ESM3. This input ensures the generated protein sequences match your targeted catalytic activities and design requirements.
Estrella-231Generate protein sequences, predict structures, and extract embeddings with ESM3 and ESM C.
biomaps-infraGenerate protein sequences and embeddings using ESM3 and ESM C.
Lord1EgyptPredict 3D protein conformations from amino acid sequences using AlphaFold2 and ESMFold.
RigohlCompute TF-IDF cosine similarity and fuzzy matching via Julia-Rust FFI.
