Skip to main content
Glama
coreymhudson

MCP Sequence Simulation Server

by coreymhudson

generate_protein_sequence

Generate random protein sequences with specified length, model, and composition for bioinformatics simulation and testing.

Instructions

Generate random protein sequences with specified parameters

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lengthYesLength of the protein sequence to generate
countNoNumber of sequences to generate, default is 1
seedNoRandom seed for reproducible results (optional)
modelNoGeneration model: 'random', 'hydrophobic-bias', or 'disorder-prone'
compositionNoCustom amino acid composition (frequencies should sum to 1)
outputFormatNoOutput format: 'fasta' or 'plain'

Implementation Reference

  • The main handler function that generates protein sequences. It supports multiple generation models (random, hydrophobic-bias, disorder-prone), custom amino acid composition, and output formats (fasta, plain). Returns sequence data with statistics including hydrophobic, charged, and aromatic ratios.
    async handler({ length, count = 1, seed, model = "random", composition, outputFormat = "fasta" }: { length: number; count?: number; seed?: number; model?: string; composition?: Record<string, number>; outputFormat?: string; }) { const generator = new SequenceGenerator(seed); const sequences = []; for (let i = 0; i < count; i++) { let sequence: string; switch (model) { case "random": if (composition) { sequence = generateCustomComposition(length, composition, generator); } else { sequence = generator.generateRandomProtein(length); } break; case "hydrophobic-bias": sequence = generateHydrophobicBiased(length, generator); break; case "disorder-prone": sequence = generateDisorderProne(length, generator); break; default: sequence = generator.generateRandomProtein(length); } const analysis = analyzeProtein(sequence); sequences.push({ id: `sim_protein_${i + 1}`, sequence, length: sequence.length, model, ...analysis }); } let output = ''; if (outputFormat === 'fasta') { output = sequences.map(seq => `>${seq.id} length=${seq.length} hydrophobic=${seq.hydrophobicRatio}% model=${seq.model}\n${seq.sequence}` ).join('\n\n'); } else { output = sequences.map(seq => seq.sequence).join('\n'); } const stats = { totalSequences: sequences.length, averageLength: Math.round(sequences.reduce((sum, seq) => sum + seq.length, 0) / sequences.length), averageHydrophobic: Math.round(sequences.reduce((sum, seq) => sum + seq.hydrophobicRatio, 0) / sequences.length * 100) / 100, model, seed: seed || "random" }; return { content: [{ type: "text", text: JSON.stringify({ statistics: stats, sequences: outputFormat === 'fasta' ? output : sequences, rawOutput: outputFormat === 'plain' ? output : undefined }, null, 2) }] }; }
  • Tool definition with input schema specifying parameters: length (required), count, seed, model (random/hydrophobic-bias/disorder-prone), composition (custom amino acid frequencies), and outputFormat (fasta/plain).
    export const generateProtein = { definition: { name: "generate_protein_sequence", description: "Generate random protein sequences with specified parameters", inputSchema: { type: "object", properties: { length: { type: "number", description: "Length of the protein sequence to generate" }, count: { type: "number", description: "Number of sequences to generate, default is 1", minimum: 1 }, seed: { type: "number", description: "Random seed for reproducible results (optional)" }, model: { type: "string", description: "Generation model: 'random', 'hydrophobic-bias', or 'disorder-prone'", enum: ["random", "hydrophobic-bias", "disorder-prone"] }, composition: { type: "object", description: "Custom amino acid composition (frequencies should sum to 1)", additionalProperties: { type: "number", minimum: 0, maximum: 1 } }, outputFormat: { type: "string", description: "Output format: 'fasta' or 'plain'", enum: ["fasta", "plain"] } }, required: ["length"] }, },
  • src/server.ts:57-65 (registration)
    Registration of the generate_protein_sequence tool in the server's request handler. Routes tool calls to the generateProtein.handler function with type-safe argument casting.
    case "generate_protein_sequence": return await generateProtein.handler(args as { length: number; count?: number; seed?: number; model?: string; composition?: Record<string, number>; outputFormat?: string; });
  • Helper functions generateHydrophobicBiased and generateDisorderProne that implement specialized protein generation models with biased amino acid selection.
    function generateHydrophobicBiased(length: number, generator: SequenceGenerator): string { const hydrophobic = ['A', 'V', 'I', 'L', 'M', 'F', 'Y', 'W']; const hydrophilic = ['R', 'N', 'D', 'C', 'Q', 'E', 'G', 'H', 'K', 'P', 'S', 'T']; let sequence = ''; for (let i = 0; i < length; i++) { if (Math.random() < 0.6) { sequence += hydrophobic[Math.floor(Math.random() * hydrophobic.length)]; } else { sequence += hydrophilic[Math.floor(Math.random() * hydrophilic.length)]; } } return sequence; } function generateDisorderProne(length: number, generator: SequenceGenerator): string { const disorderProne = ['A', 'R', 'G', 'Q', 'S', 'P', 'E', 'K']; const orderProne = ['V', 'I', 'Y', 'F', 'W', 'L']; const neutral = ['N', 'D', 'C', 'H', 'M', 'T']; let sequence = ''; for (let i = 0; i < length; i++) { const rand = Math.random(); if (rand < 0.5) { sequence += disorderProne[Math.floor(Math.random() * disorderProne.length)]; } else if (rand < 0.75) { sequence += neutral[Math.floor(Math.random() * neutral.length)]; } else { sequence += orderProne[Math.floor(Math.random() * orderProne.length)]; } } return sequence; }
  • Helper function analyzeProtein that computes sequence statistics including hydrophobic ratio, charged ratio, aromatic ratio, and amino acid composition percentages.
    function analyzeProtein(sequence: string): { hydrophobicRatio: number; chargedRatio: number; aromaticRatio: number; composition: Record<string, number>; } { const hydrophobic = new Set(['A', 'V', 'I', 'L', 'M', 'F', 'Y', 'W']); const charged = new Set(['R', 'K', 'D', 'E']); const aromatic = new Set(['F', 'Y', 'W']); const composition: Record<string, number> = {}; let hydrophobicCount = 0; let chargedCount = 0; let aromaticCount = 0; for (const aa of sequence) { composition[aa] = (composition[aa] || 0) + 1; if (hydrophobic.has(aa)) hydrophobicCount++; if (charged.has(aa)) chargedCount++; if (aromatic.has(aa)) aromaticCount++; } return { hydrophobicRatio: Math.round((hydrophobicCount / sequence.length) * 10000) / 100, chargedRatio: Math.round((chargedCount / sequence.length) * 10000) / 100, aromaticRatio: Math.round((aromaticCount / sequence.length) * 10000) / 100, composition: Object.fromEntries( Object.entries(composition).map(([aa, count]) => [ aa, Math.round((count / sequence.length) * 10000) / 100 ]) ) }; }

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/coreymhudson/mcp-sequence-simulation'

If you have feedback or need assistance with the MCP directory API, please join our Discord server