skills.rest
InternScience
InternScienceOFFICIAL
Explore all skills by this author →
GitHub

molclaw-mol-opt-physchem

Optimize drug molecule LogP, QED, and solubility through iterative SMILES edits.

28|2|Updated Mar 31, 2026
Search Tags:#optimization#molecule#smiles#physicochemical#solubility#logp#qed
One-click install
npx skills add https://github.com/InternScience/MolClaw --skill molclaw-mol-opt-physchem
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: molclaw-mol-opt-physchem
Source: https://github.com/InternScience/MolClaw/tree/main/skills/L1_tools/molclaw-mol-opt-physchem
Command: npx skills add https://github.com/InternScience/MolClaw --skill molclaw-mol-opt-physchem

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines iterative optimization of small-molecule physicochemical properties (LogP, QED, solubility) by combining computed property analysis, optional RL-driven candidate generation, and LLM-guided structural edits while preserving stereochemistry and synthetic feasibility.

Core Features & Use Cases

  • Computed Property Analysis: Integrates with molclaw-admet to generate precise ADMET and physicochemical metrics used as the basis for edits.
  • RL-Assisted Candidate Generation: Supports numeric-target optimization via reinvent_similarity_optimization to explore nearby chemotypes when precise property ranges are specified.
  • LLM-Guided Design + Validation: Provides stepwise medicinal-chemistry rationale, preserves stereochemical markers, and routes generated SMILES through molclaw-smiles-valid-check before re-evaluation.
  • Use Case: Improve aqueous solubility of a lead compound while maintaining core pharmacophore and synthetic accessibility.

Quick Start

Optimize the provided SMILES to decrease LogP into the 1–3 range and increase QED above 0.7 while preserving all stereochemical markers.

Frequently Asked Questions about molclaw-mol-opt-physchem

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize molecule physicochemical properties like LogP and solubility from a SMILES string?▼

You can optimize molecule physicochemical properties by iteratively editing a SMILES string to meet explicit target ranges for LogP, QED, and solubility. The process applies computed property analysis and LLM-guided structural modifications to generate valid candidates.

What is the best way to improve drug aqueous solubility while preserving the core pharmacophore?▼

Improving drug aqueous solubility while preserving the core pharmacophore involves stepwise medicinal-chemistry rationale and optional RL-driven candidate generation. This explores nearby chemotypes to refine lead compounds without losing structural features.

Can I set specific numeric targets for LogP and QED when optimizing drug molecules?▼

Yes, you can set specific numeric targets for LogP and QED during drug molecule optimization. The process supports numeric-target optimization via reinvent_similarity_optimization to explore nearby chemotypes when precise property ranges are specified.

Does the structural optimization process preserve stereochemical markers in the SMILES output?▼

Yes, structural optimization preserves stereochemical markers in the SMILES output. Generated SMILES are routed through validation checks to ensure syntactic validity and maintain stereochemistry and synthetic feasibility.

When should I use LLM-guided structural modifications for lead optimization?▼

Use LLM-guided structural modifications for lead optimization during post-screening candidate refinement or property-driven virtual screening. It provides stepwise medicinal-chemistry rationale to iteratively edit molecules into target physicochemical ranges.

Are generated SMILES strings validated for syntactic correctness after structural edits?▼

Yes, generated SMILES strings are validated for syntactic correctness after structural edits. The workflow routes all generated candidates through SMILES validation before re-evaluating their computed physicochemical properties.

Related Skills

Explore More Education & Research Skills→
InternScienceInternScience
28

molclaw-similarity-optimization

Generate target-similar molecules while optimizing physicochemical properties via reinforcement learning.

Official
Intermediate
PlaidmustachePlaidmustache

drug-discovery

Integrates ChEMBL, PubChem, and OpenFDA to rank drug-like candidates and flag liabilities.

Community
Advanced
InternScienceInternScience
28

molclaw-mol-charge-metrics

Calculate Gasteiger and formal charges for SMILES strings with aggregate statistics.

Official
Intermediate
qcmuuqcmuu

creative-thinking-for-research

Generate novel AI research directions using cognitive science creativity frameworks.

Community
Intermediate