Parse biological sequence, alignment, structure, BLAST, and Entrez data into Python workflows.
npx skills add https://github.com/dralkh/seerai --skill biopython-dralkh
Please help me install this Agent Skill. Skill: biopython Source: https://github.com/dralkh/seerai/tree/main/skills/biopython Command: npx skills add https://github.com/dralkh/seerai --skill biopython-dralkh
Biopython helps researchers stop juggling ad hoc scripts and scattered tools when they need to read biological files, query NCBI, compare sequences, or turn raw results into reproducible analyses.
Use the biopython skill to analyze the attached sequence or GenBank file and return a concise summary of the records, annotations, and recommended next analysis steps.
High-intent search queries and answers about installing and using this skill.
You can parse biological sequence files by reading, writing, and converting formats like FASTA, GenBank, FASTQ, and EMBL into structured Python objects. This allows you to filter records, clean sequence sets, and prepare data for alignment or phylogenetic workflows.
You can query NCBI databases using the Entrez API to search PubMed or GenBank, fetch records in batches, and run or parse BLAST results. This requires providing an explicit email address and optional API key for network-dependent NCBI retrieval.
Yes, you can perform pairwise and multiple sequence alignments, build phylogenetic trees with Bio.Phylo, and compare tree topologies. This enables end-to-end workflows from raw sequence cleaning through alignment to tree construction for biological interpretation.
Yes, you can inspect protein structures using the Bio.PDB module and scan for sequence motifs. These capabilities integrate directly into Python workflows, allowing structural analysis alongside standard sequence and alignment processing tasks.
Querying Entrez databases requires an explicit email address for NCBI usage tracking and rate limiting, along with an optional API key to increase request limits. Proper Entrez parameter handling ensures reliable batch retrieval of GenBank and PubMed records.
Batch sequence processing supports reading, writing, and converting across biological file formats including FASTA, GenBank, FASTQ, and EMBL. This enables reliable file conversion to standardize heterogeneous sequence data for downstream alignment and phylogenetic analysis.
Estrella-231Parse FASTA, GenBank, and PDB files using Biopython submodules.
galeepConstruct phylogenetic trees from biological sequences using MAFFT, IQ-TREE 2, and FastTree.
Imad-OuteAnalyze DNA, RNA, and protein sequences with alignment and phylogenetic tree construction.
DrugClawGuide reproducible bioinformatics workflows for sequence analysis and quality control.
