Smiles De Salter

Source: https://github.com/aipoch/medical-research-skills

SMILES De-salter

ID: 176

Batch process chemical structure strings, removing salt ion portions and retaining only the active core.

When to Use

• Use this skill when the task needs Batch process chemical SMILES strings to remove salt ions and retain.
• Use this skill for data analysis tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Key Features

• Scope-focused workflow aligned to: Analyze data with smiles-de-salter using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation.
• Packaged executable path(s): scripts/main.py.
• Reference material available in references/ for task-specific guidance.
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

• Python >= 3.8
• rdkit >= 2022.03.1

Example Usage

See ## Usage above for related details.

cd "20260318/scientific-skills/Data Analytics/smiles-de-salter"
python -m py_compile scripts/main.py
python scripts/main.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/main.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

See ## Workflow above for related details.

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/main.py.
• Reference guidance: references/ contains supporting rules, prompts, or checklists.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py --input "Audit validation sample with explicit symptoms, history, assessment, and next-step plan."

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Function Description

This Skill is used to process chemical SMILES strings, automatically identifying and removing counterions, retaining only the active pharmaceutical ingredient (API).

Salt Ion Identification Rules

• Identify multiple components through . separator
• Salt ions are usually smaller ions (such as Na⁺, Cl⁻, K⁺, Br⁻, etc.)
• Retain the component with the most atoms as the core
• Support common inorganic salts and organic acid salts

Supported Salt Types

Usage

Command Line

python -m py_compile scripts/main.py

# Example invocation: python scripts/main.py -i input.csv -o output.csv -c smiles_column

Parameter Description

Single Processing Example

python scripts/main.py -s "CC(C)CN1C(=O)N(C)C(=O)C2=C1N=CN2C.[Na+]"

# Output: CC(C)CN1C(=O)N(C)C(=O)C2=C1N=CN2C

Input Format

CSV/TSV Files

id,smiles,name
1,CCO.[Na+],ethanol_sodium
2,c1ccccc1.[Cl-],benzene_hcl

Pure SMILES Files

One SMILES string per line:

CCO.[Na+]
c1ccccc1.[Cl-]

Output Format

Output file contains original data and new processing result columns:

id,smiles,name,desalted_smiles,status
1,CCO.[Na+],ethanol_sodium,CCO,success
2,c1ccccc1.[Cl-],benzene_hcl,c1ccccc1,success

Install Dependencies

pip install rdkit pandas

Processing Logic

1. Parse SMILES: Use RDKit to parse input string
2. Component Splitting: Identify multiple molecular components separated by .
3. Core Identification:
   • Default selects component with the most atoms
   • Optional: based on molecular weight, ring count, etc.
4. Output Result: Return clean core SMILES

Error Handling

• If required inputs are missing, state exactly which fields are missing and request only the minimum additional information.
• If the task goes outside the documented scope, stop instead of guessing or silently widening the assignment.
• If scripts/main.py fails, report the failure point, summarize what still can be completed safely, and provide a manual fallback.
• Do not fabricate files, citations, data, search results, or execution outcomes.

Examples

Example 1: Simple Inorganic Salt

Input: CCO.[Na+] Output: CCO

Example 2: HCl Salt

Input: CN1C=NC2=C1C(=O)N(C)C(=O)N2C.Cl Output: CN1C=NC2=C1C(=O)N(C)C(=O)N2C

Example 3: Complex Organic Salt

Input: CC(C)CN1C(=O)N(C)C(=O)C2=C1N=CN2C.C(C(=O)O)C(CC(=O)O)(C(=O)O)O Output: CC(C)CN1C(=O)N(C)C(=O)C2=C1N=CN2C (retains larger caffeine molecule)

Notes

1. This tool assumes the core is the component with the most atoms
2. For co-crystals or multi-component drugs, manual review may be needed
3. Some hydrochloride salts may exist as [Cl-] or Cl
4. It is recommended to sample and verify results