🧬 Molecule of the Week · April 1, 2026
PCL-AD-002 2D Structure

PCL-AD-002

Novel Pyrimidine-Morpholine BACE1 Inhibitor Variant

c1cc(c(cc1F)NC(=O)c2cnc(nc2)N3CCOCC3)F

🧠

Alzheimer's Disease

BACE1 inhibitor with CNS-penetrant scaffold

Pyrimidine-morpholine core targeting BACE1. Difluoroaniline for BBB penetration. Morpholine ring for solubility and metabolic stability. Low IP risk (max Tanimoto 0.26).

7.0

GOOD — Viable with Modifications

PharmaClaw Consensus Score (0-10)

MW

320.3

LogP

1.84

QED

0.935

Tox Risk

LOW

IP Risk

LOW

Lipinski

✅ PASS

8 Agents Consulted

Chemistry Cheminformatics Pharmacology Toxicology Synthesis Catalyst Literature IP Expansion

Suggested Modifications

  • → Phenyl → pyridyl for improved solubility
  • → Phenyl → pyrimidyl for novel IP + solubility
  • → Cyclopropyl substitution to reduce LogP
  • → CF₃ group for novel IP space

Generated by PharmaClaw AI Pipeline v2.0.0 · Updated every Wednesday

View Archive →

⚠️ For research purposes only. Not a therapeutic recommendation. All novel molecules require experimental validation.

PharmaClaw

AI-Powered Drug Discovery Pipeline

Generate molecular insights · Analyze ADME & toxicology · Synthesize retrosynthesis routes · Monitor safety signals — 9 chained AI agents with CLI + LangGraph orchestration on OpenClaw.

🔬 Live Demo 🔬 Live PharmaLab Dashboard pip Install

Install in 3 Commands

1️⃣

pip install

pip install pharmaclaw[agents]
2️⃣

Setup

pharmaclaw setup

Enter your OpenAI/Anthropic API key

3️⃣

Ask

pharmaclaw ask "Analyze aspirin"
Full Walkthrough → ⭐ GitHub

Why PharmaClaw?

End-to-end drug discovery in one pipeline. From SMILES input to polished report — Chemistry, Cheminformatics, ADME, Synthesis Planning, Toxicology, IP Analysis, Market Intelligence, and PDF Export. No black box: OpenClaw transparency, real-time data from PubChem, openFDA, and RDKit.

🧪

Chemistry + Synthesis

PubChem queries, RDKit properties, retrosynthesis routes with feasibility scoring. SMILES in, actionable chemistry out.

💊

ADME + Toxicology

80+ ADME properties, Lipinski/Veber rules, hERG risk, hepatotoxicity flags, FAERS adverse event monitoring.

💼

IP + Market Intel

FTO analysis, bioisostere suggestions, patent landscape, market trends, and competitive intelligence reports.

Discovery Pipeline

⌨️

Input SMILES

↓
🧪

Chemistry

↓
🧬

Cheminformatics

↓
💊

Pharmacology

↓
☠️

Toxicology

↓
🔬

Synthesis

↓
💼

IP Check

↓
📊

Market Intel

↓
📄

Report

Each stage is a specialized AI agent. Chain them all in one command — or run individually.

Pro Report Demo

Pick a drug to generate a Pro chain report...

🔒 Pro users get: Compound Comparison · PDF Export · Batch Mode · Synthesis Planning

Compare candidates, export team-ready PDFs, analyze up to 500 compounds, and plan retrosynthesis routes.

See Pro Plans →

Pro Features

Unlock powerful workflows built for discovery teams.

NEW · PRO
🧬

Cheminformatics Agent

3D conformer ensembles (ETKDG + MMFF), pharmacophore mapping & fingerprints, RECAP fragmentation for library design, stereoisomer enumeration (R/S, E/Z), and format conversion (SDF, MOL, PDB, XYZ, InChI).

PRO
⚖️

Compound Comparison

Compare 2–5 SMILES side-by-side with ranked analysis across molecular properties, ADME, safety, and IP. Pick winners faster.

PRO
📄

PDF Report Export

Color-coded reports with 2D structure images, ADME tables, safety flags, and synthesis routes. One click to team-ready PDF.

PRO
📦

Batch Mode

Upload a CSV of 1–500 compounds for parallel analysis. Get aggregated results with per-compound scoring and CSV/PDF output.

PRO
🔬

Synthesis Planning

AI-powered retrosynthesis with multi-step route proposals, feasibility scoring, reagent availability, and estimated yields.

PRO
💊

Enhanced ADME Profiling

80+ computed properties including CYP inhibition, BBB permeability, plasma protein binding, Pgp substrate prediction, and bioavailability scoring.

PRO
👁️

Watch Lists & Alerts

Monitor drugs via FAERS safety signals with automated alerts. Coming soon: patent expiry watches and PubChem new-compound tracking.

Example: Compound Comparison Output

Property Compound A Compound B Compound C
MW315.7206.3560.6
LogP4.03.974.0
TPSA38.337.3102.0
HBD / HBA1 / 51 / 31 / 7
Lipinski✅ Pass✅ Pass⚠️ 1 violation
FAERS SignalsPsychiatric 22%GI bleed 28%Hepatotox 20%

Command-Line Interface

9 agents. One terminal. JSON in, JSON out. Built for researchers and AI agents alike.

pip install pharmaclaw-cli

pharmaclaw — bash

# Full 9-agent pipeline with consensus scoring

$ pharmaclaw langgraph \

--smiles "CC1=NN(C(=O)C1=CC2=C(N=C(C=C2)NC3=CC(=NN3C)C(F)(F)F)Cl)C4CC4" \

--workflow full --verbose

🔗 LangGraph full pipeline starting...

[1/9] Chemistry — molecular properties...

[2/9] Cheminformatics — 3D conformers, pharmacophores...

[3/9] Pharmacology — ADME/PK profiling...

[4/9] Toxicology — safety profiling...

[5/9] Synthesis — route planning...

[6/9] Catalyst — recommendation...

[7/9] Literature — PubMed search...

[8/9] IP — freedom-to-operate...

[9/9] Market Intel — FAERS query...

✅ Score: 7.0/10 — GOOD — viable with modifications

Warnings: HIGH IP risk (Tanimoto 1.0)

Recommendations: bioisosteres, prodrug/salt form, DDI check

# Pipe agents together

$ pharmaclaw chemistry -s "CCO" | pharmaclaw toxicology | jq '.risk'

"Low"

Every Agent, One Command

🧪

Chemistry

pharmaclaw chemistry -s "CCO" --mode props

MW, LogP, TPSA, retrosynthesis, PubChem, fingerprints, reactions

🧬

Cheminformatics

pharmaclaw cheminformatics -s "CCO"

3D conformers, pharmacophores, SDF/MOL/PDB, RECAP fragments, stereoisomers

💊

Pharmacology

pharmaclaw pharmacology -s "CCO"

Lipinski, Veber, QED, BBB, CYP3A4, P-gp, PAINS, SA Score

☠️

Toxicology

pharmaclaw toxicology -s "CCO"

Safety profiling, structural alerts, PAINS, risk scoring

🔬

Synthesis

pharmaclaw synthesis -s "CCO" --steps 3

Multi-step BRICS retrosynthesis, feasibility scoring

🔧

Catalyst Design

pharmaclaw catalyst --reaction suzuki

28 reaction types, Pd/Ru/Ni/Cu catalysts, novel ligand design

📚

Literature

pharmaclaw literature -q "KRAS 2026"

PubMed + Semantic Scholar, TLDRs, citations, open-access PDFs

💼

IP Check

pharmaclaw ip -s "CCO" --bioisosteres

FTO analysis, Tanimoto similarity, bioisostere suggestions

📊

Market Intel

pharmaclaw market --drug sotorasib

FDA FAERS adverse events, trends, prediction markets

LangGraph Multi-Agent Orchestration

Stateful pipelines with dynamic routing, self-correction, and consensus scoring — powered by LangChain + LangGraph.

4 Workflows

full — All 9 agents + conditional routing
~10s
quick — Chemistry + Toxicology
~2s
safety — Chem + Pharm + Tox
~4s
synthesis — Chem + Synth + Catalyst
~5s

Smart Features

⚡
Dynamic Routing

High tox risk? Auto-reroutes to Pharmacology for derivative suggestions

🔄
Self-Correction

SMILES validation, error recovery, retry tracking

🎯
Consensus Scoring

0–10 score with verdict, warnings, and actionable recommendations

🤖
Agent-Native

JSON in/out — any AI framework can plug in

Consensus Scoring

8–10
EXCELLENT
Strong candidate
6–7
GOOD
Viable with mods
4–5
FAIR
Needs improvement
0–3
POOR
Major concerns

Utility Commands

⚖️

Compare

pharmaclaw compare -s "A,B,C"

Side-by-side multi-compound analysis

📦

Batch

pharmaclaw batch -f compounds.csv

Process up to 500 compounds from CSV

📄

Report

pharmaclaw report -s "CCO" -o out.json

Full pipeline → JSON report file

From Question to Novel Drug Candidates in 3 Minutes

See what happens when you ask PharmaClaw: "Create a novel lung cancer drug"

①

The Prompt

U
You

"Create a novel lung cancer drug"

One sentence. That's all it takes.

②

The Pipeline Activates

🧪Chemistry✅
🧬Cheminformatics✅
💊Pharmacology✅
☠️Toxicology✅
🔬Synthesis✅
📊Market Intel✅
💼IP Analysis✅
📄Report✅
③

Real-World Safety Data

🔍 FDA FAERS Analysis — Osimertinib & EGFR Class

📋

29,206 adverse event reports analyzed for osimertinib

🥇

6,134 diarrhoea reports across EGFR class — identified as #1 safety concern

🥈

Rash (3,667 reports) identified as #2 unmet need

Live FDA FAERS data — not simulated, not cached.

④

3 Novel Compounds Designed

PharmaClaw-1

Skin Toxicity ↓

Strategy: Chloroacetamide warhead (less reactive)

Lipinski: Pass SA: 2.86

Why: Targets the #2 adverse event (rash)

⭐ TOP PICK

PharmaClaw-2

GI Toxicity ↓

Strategy: N-methylpiperazine side chain

Lipinski: Pass Composite: 0.369 (best) Feasibility: Easy

Why: Targets the #1 adverse event (diarrhoea)

PharmaClaw-3

Metabolic Stability ↑

Strategy: Difluoromethoxy group

Lipinski: Borderline

Note: Higher MW pushes Lipinski borderline

Why: Extended half-life for once-daily dosing

⑤

Head-to-Head Comparison

Compound MW LogP QED Lipinski Score
Gefitinib446.94.280.518Pass0.518
Erlotinib395.54.450.508Pass0.508
Afatinib486.04.390.457Pass0.457
PharmaClaw-2 ⭐497.64.260.369Pass0.369
Osimertinib499.64.510.311Pass0.311
⑥

The Recommendation

✅

PharmaClaw-2 recommended for advancement

Best balance of drug-likeness, synthetic feasibility, and rationale for reduced GI toxicity.

Next: molecular docking against EGFR (PDB: 6JX0)

This entire analysis took 3 minutes and cost less than $0.04 in compute.

🧪 Try It Free See Pricing →

Pricing

Freemium to Enterprise.

Free

$0

  • ✅ Chemistry Query agent
  • ✅ Pharmacology profiling
  • ✅ Self-host on OpenClaw
  • ✅ Demo compound reports
Install Free
Most Popular

Pro

$29/mo founding member

$49/mo

  • ✅ All 9 agents + chaining
  • ✅ Compound comparison
  • ✅ PDF exports
  • ✅ Batch mode (500 runs/mo)
  • ✅ Synthesis planning
  • ✅ Enhanced ADME (80+ props)
  • ✅ Watch lists (10 watches)
  • ✅ API access
Start Pro Trial

Enterprise

Custom

  • ✅ Unlimited watches
  • ✅ Custom agents
  • ✅ On-prem deployment
  • ✅ Priority support
  • ✅ Unlimited runs
Contact Sales

FAQ

What is PharmaClaw? +

PharmaClaw is a suite of 9 AI agents built on OpenClaw, designed for drug discovery teams. They chain together PubChem data, RDKit cheminformatics (2D and 3D), FAERS adverse event intel, ADME/PK profiling, toxicology screening, synthesis planning, catalyst design, literature search, and IP/patent analysis into unified workflows.

What input formats do the agents accept? +

Agents accept SMILES strings, drug names, PubChem CIDs, and natural language queries. The Chemistry Query agent resolves names to structures automatically via PubChem. You can chain outputs between agents seamlessly.

Is PharmaClaw free? +

Yes! The Free tier includes Chemistry Query and Pharmacology agents with demo reports. Pro ($49/mo, $29/mo for founding members) unlocks all 9 agents including Cheminformatics (3D conformers, pharmacophores, stereoisomers), multi-agent chaining, compound comparison, batch mode, synthesis planning, PDF exports, watch lists, and API access. Enterprise plans are available for teams needing on-prem deployment.

Can I self-host PharmaClaw? +

Absolutely. PharmaClaw agents are open-source OpenClaw skills. Install them from ClawHub (clawhub install chemistry-query) and run on your own infrastructure. You bring your own LLM API key.

What's "agent chaining"? +

Agent chaining lets you pipe the output of one agent into the next. For example: enter a SMILES string → Chemistry Query identifies the compound → Pharmacology profiles ADME → Toxicology flags alerts → Synthesis plans routes → IP checks patents → Market Intel finds trends — all in one workflow. This is a Pro feature.

How accurate is the data? +

PharmaClaw agents query authoritative sources in real-time: PubChem, openFDA FAERS, and patent databases. RDKit computations are deterministic. AI-generated insights (synthesis planning, IP suggestions) should be validated by domain experts before use in regulatory contexts.

What is synthesis planning? +

Synthesis planning uses AI-powered retrosynthesis to break down a target molecule into commercially available precursors. PharmaClaw proposes multi-step synthetic routes, scores each for feasibility (yield estimates, reagent availability, reaction complexity), and suggests alternative pathways. This helps medicinal chemists evaluate synthetic accessibility before committing lab resources.

How do watch lists work? +

Watch lists let you monitor drugs for new safety signals. PharmaClaw scans the FDA FAERS database for new adverse event reports on your watched compounds and sends alerts when significant changes are detected — new signal spikes, serious outcomes, or emerging reaction patterns. Coming soon: patent expiry monitoring and PubChem new-compound watches.

Need Help?

We're here to help you get the most out of PharmaClaw.

📧

Email Us

Questions, feedback, or partnership inquiries.

cheminem602@gmail.com
🐛

Report Issues

Bug reports, feature requests, and agent feedback.

GitHub Issues →
💬

Community

Chat with other users and the OpenClaw community.

Join Discord →