What problem does it solve? Comparing multiple protein sequences to assess similarity, domain conservation, or key residue conservation requires a reliable multiple sequence alignment, and manually orchestrating the EBI Clustal Omega web service (submission, polling, rate limits, result retrieval) is error-prone and tedious. ## Core Features & Use Cases - Automated Clustal Omega Alignment: Submits FASTA files (2 to 4000 sequences, up to 4 MB) to the EBI Clustal Omega REST API, polls for completion, and saves the alignment locally. - Rate-Limited API Client: Uses a polite HTTP client enforcing EBI's terms of use, with a 15-minute polling timeout and clear error handling for failed jobs. - Guided Result Interpretation: Provides identity metric options (sequence coverage, global identity, overlap identity, conservation index) and feature-mapping guidance to tie alignment columns to known functional residues. - Use Case: A researcher has five homologous kinase sequences and wants to verify whether a catalytic residue is conserved; the skill aligns them and maps the residue to its alignment column for targeted conservation analysis. ## Quick Start Align the protein sequences in my FASTA file using EBI Clustal Omega and tell me which residues are fully conserved.
