agentleFS
PharMolixPharMolix/OpenBioMed/skills/molecule-biochemical-significance-query-biot5/SKILL.md

molecule-biochemical-significance-query-biot5

Skill1.1k starsChanged 8 months agoMITView on GitHub

Query a molecule's biochemical significance and roles in biology and chemistry using BioT5 multi-modal model. Use this skill when: (1) Understanding a molecule's biological roles and functions, (2) Describing a molecule's chemical significance and applications, (3) Getting natural language explanations of molecular properties, (4) Summarizing what a molecule is used for or its metabolic relevance.

Trending

Quiet this year.thin dataabout the whole repository

Dec 2025: 0 mentionsJan 2026: 0 mentionsFeb 2026: 0 mentionsMar 2026: 0 mentionsApr 2026: 0 mentionsMay 2026: 0 mentionsJun 2026: 0 mentionsJul 2026: 0 mentionsAug 2026: 0 mentionsSep 2026: 0 mentionsOct 2026: 0 mentionsNov 2026: 0 mentions
Dec 2025Jun 2026Nov 2026
Mentions a month of the PharMolix/OpenBioMed repository that our weekly crawl found: only 1 in all, so this is a hint, not a trend. There is no adoption data for this file yet.

Who's talking about PharMolix/OpenBioMed

The biggest 1 of 1 mention linking to the repository that our crawl found. Each line is their own headline.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create molecule from SMILES string.

    line 31
  2. Distinctive:

    Use the molecule_question_answering tool with the default question.

    line 40
  3. Distinctive:

    If you have a molecule name instead of SMILES:

    line 57

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Molecule Biochemical Significance Query

Query a molecule's biochemical significance using BioT5 multi-modal model.

When to Use

  • User asks about a molecule's biological roles or functions
  • User wants to understand what a molecule is used for
  • User requests natural language description of molecular properties
  • User asks about a molecule's metabolic or chemical significance

Workflow

Step 1: Create Molecule

Create molecule from SMILES string.

from open_biomed.data import Molecule
molecule = Molecule.from_smiles("CCCCCCCc1ccco1")  # Heptylfuran

Step 2: Ask About Biochemical Significance

Use the molecule_question_answering tool with the default question.

from open_biomed.data import Text
from open_biomed.tools.tool_registry import TOOLS

qa_tool = TOOLS["molecule_question_answering"]
question = Text.from_str(
    "I am interested in understanding the molecule biochemical significance; "
    "can you describe its roles in biology and chemistry?"
)
outputs, _ = qa_tool.run(molecule=molecule, text=question)
print(outputs[0])  # Natural language answer

Alternative: Get Molecule by Name

If you have a molecule name instead of SMILES:

from open_biomed.tools.tool_registry import TOOLS

# Get molecule from name
name_tool = TOOLS["molecule_name_request"]
molecules, _ = name_tool.run("aspirin")
molecule = molecules[0]

# Then proceed with QA
qa_tool = TOOLS["molecule_question_answering"]
question = Text.from_str(
    "I am interested in understanding the molecule biochemical significance; "
    "can you describe its roles in biology and chemistry?"
)
outputs, _ = qa_tool.run(molecule=molecule, text=question)

Expected Outputs

OutputDescription
Natural language textDescription of biochemical roles, applications, and significance

Example Outputs

MoleculeOutput
CCCCCCCc1ccco1 (heptylfuran)"flavouring agent; fragrance; metabolite"
CC(=O)OC1=CC=CC=C1C(=O)O (aspirin)"analgesic; anti-inflammatory; antipyretic"

Model Details

  • Model: BioT5
  • Checkpoint: ./checkpoints/server/molecule_question_answering_biot5.ckpt
  • Device: CUDA (default: cuda:0)

Error Handling

ErrorSolution
Checkpoint not foundEnsure ./checkpoints/server/molecule_question_answering_biot5.ckpt exists
Invalid SMILESValidate SMILES format or use molecule name lookup
CUDA out of memorySet device to "cpu" in the tool configuration

See Also

  • examples/basic_example.py - Complete runnable example
  • references/custom_questions.md - Other question templates

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.