Skip to main content
Glama

Prime-editing efficiency (PRIDICT2.0)

prime_editing_efficiency
Read-onlyIdempotent

Predict per-pegRNA prime-editing efficiency for one edit with PRIDICT2.0, and return the top-scoring pegRNA designs ranked by it. Takes the target as context, the edit in brackets, then context — ACGT...(A/G)...ACGT, with roughly 100+ bp each side — and enumerates PBS/RTT length combinations, scoring every one in HEK293 and K562. Each candidate comes back with both scores, its percentile against the training library, its rank, the spacer, PBS and RTT lengths, the full pegRNA, and Golden Gate cloning oligos. Use it to CHOOSE between designs; the number is not a promised editing percentage. PREDICTED, NOT MEASURED (Spearman ρ = 0.85 on held-out data from the libraries it was trained on). Spearman rho of about 0.85 for intended edits on held-out library data — the best-validated figure of any model in this registry, and roughly double OSTIR's 0.39 on independent data. That figure is still within the library and cell lines it was trained on. Valid for: human sequence, and efficiency ranking within one locus. It is parameterised on HEK293 and K562; your cell type, delivery method, and chromatin context will all move the absolute efficiency, chromatin alone by severalfold. Nothing here is predicted for a non-human host or for editors outside the PE2/PE3 architecture the training libraries used.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topNNoHow many top-ranked pegRNAs to return, out of the hundreds enumerated. Max 50.
cellTypeNoWhich trained context to RANK by. Both scores are always returned; this decides the ordering. There is no generic-mammalian option because the model has no such training data.HEK
sequenceYesTarget with the edit in brackets: context, then (original/edited), then context. Roughly 100+ bp each side — the model reads that context. Keep unchanged flanking bases OUTSIDE the brackets: T(a/g)C, not (TAC/TGC). Insertions and deletions leave one side empty, e.g. (/AGG) or (AGG/).
use5FoldsNoAverage all five trained folds instead of the first. Modestly steadier scores for five times the compute, and it is charged five times as much.

TDQS

A4.6/5.0
Behavior5/5

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

The annotations already mark the tool as readOnlyHint=true and idempotentHint=true, but the description adds extensive behavioral context: it enumerates PBS/RTT combinations, returns multiple scores and design details, explains the Spearman correlation and its limitations, validates against human PE2/PE3 libraries, and clarifies that the number is a ranking not an absolute percentage. This goes well beyond what annotations provide.

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?

The description is front-loaded with the core purpose in the first sentence, then progressively adds input format, output details, usage guidance, validation statistics, and limitations. Every sentence earns its place—there is no redundancy or filler. Despite its length, it is efficiently organized and essential for correct tool usage.

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

Completeness5/5

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

For a complex tool with 4 parameters and no output schema, the description comprehensively covers input format (bracketed edit with flanking context), output fields (scores, percentiles, ranks, spacer, PBS/RTT, pegRNA, oligos), ranking behavior, model limitations (cell types, host, editor architecture), and a validation metric. An AI agent has all necessary context to invoke and interpret results.

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

Parameters5/5

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

All four parameters have schema descriptions (100% coverage), and the narrative description adds substantial extra meaning. For 'sequence', it details the bracket format with examples for insertions and deletions. For 'cellType', it explains the absence of a generic option. For 'topN', it mentions enumeration size. For 'use5Folds', it describes the trade-off in compute and stability. This goes well beyond the schema's descriptions.

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 clearly states the tool predicts per-pegRNA prime-editing efficiency and returns top-scoring designs. It uses a specific verb ('Predict'), identifies the resource ('PRIDICT2.0'), and describes the input format. While it implicitly differentiates from sibling tools like prime_editing_design by focusing on efficiency scoring rather than design, it does not explicitly name or contrast them, preventing a top score.

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

Usage Guidelines4/5

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

The description provides clear context for when to use the tool ('to CHOOSE between designs') and when not to (non-human hosts, editors outside PE2/PE3 architecture, other cell types). It warns that the output is a ranking, not a promised percentage, and notes limitations on absolute efficiency. However, it does not directly compare to sibling tools like prime_editing_design or prime_editing_twin_design, which would make the guidance more explicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools have highly specific purposes (e.g., crispr_grna_design vs base_editing_design vs prime_editing_design). However, there is some overlap in sequence analysis tools (characterize_sequence, sequence_report) and plasmid annotation tools (plasmid_annotate vs plasmid_deep_annotate) which could cause confusion.

Naming Consistency3/5

The naming pattern is largely consistent with snake_case verb_noun or noun_descriptor (e.g., primer_design, plasmid_annotate, fastq_trim). However, there are exceptions like 'batch', 'workflow', 'gc_content', and 'cloning_diagnose' which don't follow the verb_noun pattern consistently. Also, some names are phrases like 'golden_gate_from_parts'.

Tool Count2/5

With 101 tools, this server is extremely large and likely overwhelming for agents. Even for a comprehensive bioinformatics toolkit, this exceeds a manageable scope, risking agent confusion and inefficient tool selection. A more modular approach would be advisable.

Completeness4/5

The tool surface covers a wide range of bioinformatics workflows including sequence analysis, primer design, cloning, CRISPR, NGS, expression analysis, and data export. There are minor gaps such as lack of a dedicated protein structure prediction tool and limited off-target genome coverage, but overall the set is impressively complete for its domain.

Resources