Jean — Molecular Biology & Genomics

bayesian_protein_inference

Read-only

Bayesian protein inference, Epifany (validated against OpenMS BayesianProteinInferenceAlgorithm on PXD000001): the posterior probability that each protein, each indistinguishable group and each peptide-spectrum match is present, from the matches' posterior error probabilities under a network in which present proteins emit their peptides.

Input Schema

Name	Required	Description	Default
`beta`	No	spurious emission probability β: the chance a peptide is reported with none of its proteins present.
`psms`	Yes	the matches as a table with a header row naming spectrum, peptide, charge and a posterior error probability column (tab- or comma-separated); peptides are ProForma.
`alpha`	No	peptide emission probability α: the chance a present protein yields a given one of its peptides.
`gamma`	No	protein prior γ: the chance a protein is present before any evidence.
`_files`	No	The project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
`_subject`	No	The record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
`database`	Yes	the protein database searched, as FASTA; the accession is the header up to the first space.
`psmCutoff`	No	drop matches whose probability (1 − PEP) is below this.
`gridSearch`	No	choose α, β and γ instead: run OpenMS's grid (α 0.1–0.8 × β 0.01–0.4 × γ 0.2–0.7) and keep the combination whose protein posteriors best agree with target-decoy FDR and separate targets from decoys; needs decoy proteins.
`decoyPrefix`	No	accession prefix marking a decoy protein, for the grid search.	DECOY_
`scoreColumn`	No	the column holding each match's posterior error probability (PEP, 0 to 1).	pep
`ilEquivalent`	No	treat isoleucine and leucine (and a database J) as the same residue when mapping peptides.
`peptidePrior`	No	peptide prior π, dividing each match's probability back out of its evidence.
`appendReversedDecoys`	No	add the reversed sequence of every database protein as a decoy (accession decoyPrefix + accession), for a database searched with reversed decoys that holds only targets.
`maxAmbiguousResidues`	No	how many ambiguous database residues (B, J, Z, X) one peptide match may resolve.

Output Schema

Name	Required	Description
`grid`	Yes	with the grid search: every α, β, γ tried, with its FDR-curve difference, ROC-100 and objective (skipped when improbable)
`count`	Yes	proteins reported
`groups`	Yes	indistinguishable protein groups, most probable first: probability that at least one member is present, and accessions
`proteins`	Yes	one row per protein: accession, posterior probability, matches counted, sequence coverage (%)
`psmPosteriors`	Yes	the matches inference used (the best per peptide): spectrum, peptide, prior (1 − PEP) and posterior

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 20, 2026

TDQS

A3.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that: it names the reference implementation (OpenMS BayesianProteinInferenceAlgorithm), cites a validation dataset (PXD000001), and explains the underlying emission network, which tells the agent what the computation actually assumes. It does not discuss cost or determinism, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence, front-loaded with the tool's function and elaborated through a colon into the model and output semantics. No filler; every clause carries technical information about inputs, outputs or assumptions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and all 15 parameters are documented in the schema. The description supplies algorithm provenance and model semantics, which is the right division of labour for a complex statistical tool. The main omission is routing versus related inference and FDR tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every one of the 15 parameters (alpha, beta, gamma, psmCutoff, gridSearch, decoyPrefix, ilEquivalent, etc.) is already documented in detail in the schema. The description mentions posterior error probabilities as the input driver but adds no parameter-level meaning beyond it. Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific technique (Bayesian protein inference via Epifany) and states precisely what is computed: posterior probabilities for proteins, indistinguishable groups and PSMs, derived from PSM posterior error probabilities. That is far more than a restatement of the name. It stops short of a 5 because it never distinguishes itself from the sibling infer_proteins, which an agent would plausibly consider for the same task.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use or when-not guidance and no reference to alternatives such as infer_proteins or target_decoy_qvalues. The requirement for PEP-bearing matches is implied by the algorithm description, but nothing tells the agent when this Bayesian approach is preferred over simpler inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Jean — Molecular Biology & Genomics tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?