Automate protein design and analysis workflows using the esm Python SDK.
npx skills add https://github.com/dralkh/seerai --skill esm-dralkh
Please help me install this Agent Skill. Skill: esm Source: https://github.com/dralkh/seerai/tree/main/skills/esm Command: npx skills add https://github.com/dralkh/seerai --skill esm-dralkh
This Skill helps you work directly with ESM protein models without piecing together model IDs, authentication rules, and workflow details from multiple sources. It turns protein sequence design, embedding generation, and structure prediction into a guided workflow for research and engineering tasks.
Use the esm skill to complete a masked protein sequence with ESM3 and return the designed amino acid sequence.
High-intent search queries and answers about installing and using this skill.
Protein sequence generation with ESM3 automates masked completion, variant design, and inverse folding by guiding workflow configuration for function-conditioned generation tasks. You provide partial sequences and the workflow returns designed amino acid sequences.
Extracting protein embeddings with ESM C supports clustering, classification, retrieval, and downstream machine learning feature generation. The workflow guides batch inference requests to produce numerical representations of protein sequences for analysis.
Running structure prediction and batch inference on Forge or Biohub requires ESM_API_KEY authentication. The workflow provides hosted inference guidance including authentication setup, batch request formatting, rate limits, and retry patterns for API access.
Predicting protein structure and exporting all-atom folding models is handled through ESMFold2 references within the workflow. The process generates structure predictions and exports results in PDB or mmCIF format for validation and downstream analysis.
Designing protein variants and scoring them with embeddings in one workflow is supported. A researcher can generate variants with ESM3, score candidates using ESM C embeddings, and validate the best ones with structure prediction sequentially.
ESM C embeddings provide specialized numerical representations of protein sequences optimized for biological similarity. These embeddings outperform generic methods for clustering, classification, and retrieval tasks in protein engineering research by capturing sequence-level biological features.
jasrajtulsiGenerate and analyze protein sequences, structures, and functions with ESM models.
jimmc414Retrieve AlphaFold protein structures by UniProt ID and analyze pLDDT and PAE metrics.
ovachieverGenerate protein sequences, structures, and embeddings using ESM3 and ESM C models.
jimmc414Generate protein sequences and extract embeddings using ESM3 and ESM C.
