Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for biochemists

Metabolomics Peak Annotation Review Agent

Produce an annotation table where each name has stated evidence and confidence

Quality controlScience and research
See how it worksGet access
Metabolomics Peak Annotation Review Agent: what goes in, what the agent does and what you get

What it does

A metabolomics run yields thousands of peaks, and the software labels many with compound names based on a mass match alone. Weak labels end up in the paper. This agent reviews the annotation evidence. It matches peaks to library entries, checks mass error, isotope pattern and retention time, assigns a confidence level by the community scale, and flags weak matches. For uncertain peaks, it requests standards or fragmentation data and rechecks after they arrive. It builds an annotation table with the evidence for each. The scientist approves the table. Edge case: two isomers share the same mass. The agent labels the peak as ambiguous and lists both.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Peak table produced 2 USES A TOOL Match each peak to library entries by mass 3 DOES Check mass error and isotope pattern for eachcandidate 4 DOES Compare retention time with standards or predictedvalues 5 DOES Assign a confidence level to each annotation 6 CHECKS THE RESULT Is the evidence at least two independent lines forhigh confidence? If not: Lower the level and mark the peak as uncertain.Back to step 3. 7 USES A TOOL Request standards or fragmentation scans foruncertain peaks of interest 8 DOES Re-evaluate the peaks with the new data 9 CHECKS THE RESULT Does the new evidence raise confidence or resolvethe isomer ambiguity? If not: Keep the peak as unresolved and list thecandidates. Back to step 7. 10 YOU APPROVE Scientist approves the annotation table 11 RESULT Annotation table with confidence and evidence
Read the steps as a list
  1. Peak table produced
  2. Match each peak to library entries by mass
  3. Check mass error and isotope pattern for each candidate
  4. Compare retention time with standards or predicted values
  5. Assign a confidence level to each annotation
  6. Is the evidence at least two independent lines for high confidence?If not: Lower the level and mark the peak as uncertain. Back to step 3.
  7. Request standards or fragmentation scans for uncertain peaks of interest
  8. Re-evaluate the peaks with the new data
  9. Does the new evidence raise confidence or resolve the isomer ambiguity?If not: Keep the peak as unresolved and list the candidates. Back to step 7.
  10. Scientist approves the annotation tableThe agent waits here for your OK.
  11. Annotation table with confidence and evidence

How it decides

It scores matches on mass error, isotope pattern, retention time against standards and fragmentation similarity. Only matches with at least two independent lines of evidence get high confidence.

  • Mass error must be under 5 ppm
  • Retention time must be within 0.2 minutes of the standard for high confidence
  • Isomers with the same mass are labeled ambiguous
  • Only peaks of interest get follow-up requests

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Mass error limit (default 5 ppm)
  • Confidence scale
  • Libraries to use
  • Peaks of interest criteria
  • Table format

What keeps you in control

It always asks you first

  • Scientist approves the annotation table before it is used in reports

Hard limits

  • Never raises confidence without evidence
  • Lists alternative candidates for ambiguous peaks

It stops when

  • Done: table approved with confidence levels
  • Stop: library or data missing for most peaks, report the limits

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensThe agent reviews 3,400 peaks. It gives 210 high confidence with mass error under 3 ppm and retention time within 0.1 minutes of standards. A peak labeled citrate has only a mass match and could be isocitrate. It requests fragmentation data and the result separates them. The scientist approves the table with 210 high and 620 medium.

More agents for biochemists

Research · Document handling

Research Literature Update Agent

An up-to-date evidence map with every new study screened.

7 steps1 check11 jobs
Data cleanup · Risk management

Seed Lot and Sample Inventory Reconciliation Agent

Inventory records that match physical stock and cover every planned experiment before it starts.

11 steps2 checks5 jobs
Creating · Science and research

Plate Layout Design and Check Agent

A plate layout that passes every assay rule check and can be loaded onto the plate without manual rework.

10 steps2 checks3 jobs
Quality control · Analysis

Blot and Gel Quantification Check Agent

Consistent normalized band values in which every lane passes quality checks or is flagged with a reason.

11 steps2 checks5 jobs