agentsclimarketplace

Custom database searching

Skill HolobiomicsLab/asb-skill-collections/packs/metabolomics/lc-ms/skills/custom-database-searching

Curated, evidence-grounded skill and software-tool collections for scientific AI agents, generated by the AgenticScienceBuilder

Install
npx -y skills add HolobiomicsLab/asb-skill-collections --skill custom-database-searching

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 14 stars14 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when when you have LC-MS/MS data in Mascot Generic Format (mgf) files and need to identify compounds against a curated custom database (e.g., prepared using CFM-id for a specific metabolite class or organism) rather than relying on in-built commercial spectral libraries alone.

The file declares its own license as CC-BY-4.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

5.8 KB, 908 tokens by cl100k_base, as published. Nobody here has run it

custom-database-searching

Summary

Search LC-MS/MS metabolomics spectra against custom compound databases prepared with CFM-id fragment predictions to identify compounds by spectral matching. This skill enables targeted compound identification when standard databases are insufficient or when organism-specific or metabolite-class-specific databases are needed.

When to use

When you have LC-MS/MS data in Mascot Generic Format (mgf) files and need to identify compounds against a curated custom database (e.g., prepared using CFM-id for a specific metabolite class or organism) rather than relying on in-built commercial spectral libraries alone.

When NOT to use

  • Input query file is not in Mascot Generic Format (mgf)
  • Custom database was not prepared using CFM-id or is in an incompatible format
  • Only generic/in-built spectral databases are available and custom databases cannot be constructed

Inputs

  • Custom compound database (prepared using CFM-id)
  • Mascot Generic Format (mgf) query file containing LC-MS/MS spectra

Outputs

  • Identified compounds with match scores and metadata
  • Results file with ranked compound identifications

How to apply

Load a custom compound database prepared using CFM-id (a fragment prediction tool) into MS2Compound v1.0.2, import the mgf query file containing LC-MS/MS spectra, execute the matching algorithm to compare query spectra against database entries, and compute similarity scores for each match. The tool generates a results file with identified compounds ranked by match score and annotated with metadata. Success requires that the custom database was properly constructed using CFM-id in a compatible format and that the mgf file contains valid MS/MS spectra with appropriate precursor and fragment m/z values.

Related tools

  • MS2Compound (Graphical user interface for spectral matching and compound identification against custom databases) — https://sourceforge.net/projects/ms2compound/
  • CFM-id (Fragment prediction tool used to prepare and generate custom compound databases compatible with MS2Compound)

Evaluation signals

  • Match scores are computed and returned for each spectrum-to-database comparison
  • All query spectra from the mgf file are processed and assigned at least one match result
  • Identified compounds are ranked by match score (highest confidence first)
  • Results file contains structured metadata (e.g., compound name, database ID, similarity metric) for each match
  • No errors or warnings related to database format compatibility or mgf parsing are reported during execution

Limitations

  • MS2Compound v1.0.2 is Windows-only (Windows 7, 8, and 10) with no cross-platform support
  • Requires minimum 2 GB RAM and Intel i3 64-bit CPU; performance with very large custom databases or mgf files on minimal hardware is not characterized
  • Dependency on CFM-id-generated databases means accuracy is limited by the quality and completeness of fragment predictions from CFM-id
  • No changelog or version history available; updates and bug fixes are not documented
  • Installation directory path must not contain spaces, which may complicate deployment in certain environments

Evidence

  • [readme] MS2Compound (v1.0.2) is a user friendly Graphical User Interface (GUI) for the identification of the compounds from LC-MS and MS/MS metabolomics data.: "MS2Compound (v1.0.2) is a user friendly Graphical User Interface (GUI) for the identification of the compounds from LC-MS and MS/MS metabolomics data."
  • [readme] The current version of MS2Compound is compatible with the customized database prepared using CFM-id, the fragment prediction tool. Mascot Generic Format (mgf) files can be used as query input file: "The current version of MS2Compound is compatible with the customized database prepared using CFM-id, the fragment prediction tool. Mascot Generic Format (mgf) files can be used as query input file"
  • [other] Execute the matching algorithm to compare query spectra against database entries and compute similarity scores.: "Execute the matching algorithm to compare query spectra against database entries and compute similarity scores."
  • [readme] The tool is independent from all the pre-requisite dependencies.: "The tool is independent from all the pre-requisite dependencies."
  • [readme] Windows 7, 8, and 10: "Windows 7, 8, and 10"

Gives 0 of the 12 instructions most databases sql skills give in 908 tokens

Counted across 589 of the 662 authors here whose files we hold, read 2026-08-06

  • use parameterized queriesin 36 of 589, across 32 files
  • use timestamptz for timestampsin 30 of 589, across 12 files
  • create indexes concurrentlyin 29 of 589, across 23 files
  • index foreign keysin 28 of 589, across 17 files
  • use numeric type for moneyin 25 of 589, across 8 files
  • select only required columnsin 24 of 589, across 19 files
  • use cursor pagination instead of OFFSETin 23 of 589, across 15 files
  • add indexes manually on foreign key columnsin 22 of 589, across 11 files
  • read individual rule files for detailed explanationsin 18 of 589, across 4 files
  • configure connection poolingin 18 of 589, across 16 files
  • put equality columns before range columns in indexesin 17 of 589, across 9 files
  • normalize to third normal formin 17 of 589, across 8 files

Said here and by no other author read

  • load a custom compound database into MS2Compound
  • import the mgf query file containing spectra
  • execute the matching algorithm to compare spectra
  • compute similarity scores for each match
  • rank identified compounds by match score

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.