AIMI Lab · 2026

AI + TCM
Panoramic Database Report

Proprietary TCM knowledge base × Yunnan collaborative natural product library
From data to decision — redefining bioactive discovery in Chinese medicine

AIMI Lab Internal Report 2026

Two Core Database Assets

An end-to-end knowledge system covering formulas, compounds, targets, and activity data — the high-quality structured data foundation for AI-driven discovery.

AIMI TCM Private · 220K CP · 7K Formulas Yunnan NP DB 200K NPs · 49K Herbs Public Bioactivity 1.1M Activity Pairs AI Multi-Agent Integration Layer

Proprietary · AIMI TCM

Structured private knowledge base, continuously updated

220K+
TCM Compounds
7K+
Formulas
8.7K
Targets
1.1M
Activity Data Pairs
ProprietaryFully StructuredContinuously Updated

Yunnan · Herbal Bioactive Library

Collaborative construction · Yunnan ethnic medicine focus

200K
Natural Products
49K
Medicinal Materials
5,800+ Yunnan Local Herbs3,000+ Ethnic Formulas
Multi-ethnic heritage · Unreplicable regional advantage
Yunnan Ethnic MedicineMulti-Ethnic Formulas5,800 Local Herbs

Multi-Agent Algorithm Architecture

Unlike a stack of single-point tools, we built an AI Multi-Agent System (MAS): each agent plays an independent specialist role, automatically handing off tasks with zero manual intervention.

🧬 KG Agent Knowledge Graph · Target Discovery + Candidate Association 155K association pairs 65,000 → Top 500 auto 🔬 VS Agent Virtual Screening · Molecular Docking + Binding Prediction AI Docking Engine Top 500 → Top 50 auto ⚛️ MD Agent Molecular Dynamics · Stability Validation + Conformation MD Simulation Top 50 → Top 20 auto 📋 Report Agent Comprehensive Report · Traditional Use Context Final Deliverable End-to-End Report 65K 500 50 20 Stage 1 Stage 2 Stage 3 Stage 4 Fully Autonomous Pipeline · Zero Manual Intervention
🧬

Knowledge Graph Agent

TCM Knowledge Graph

Queries the 5-layer TCM knowledge network (Formula → Herb → Compound → Target → Disease), infers candidate compounds from 65,108 compounds, and auto-prioritizes. Handoff to next agent — no manual filtering.

155,351 CP-target pairsms-level graph traversal65K → Top 500
🔬

Virtual Screening Agent

AI Docking Engine

Receives candidate list, autonomously dispatches the molecular docking engine for batch scoring, ranks by binding free energy (ΔG), applies autonomous threshold judgment for next-stage advancement.

AI molecular dockingBatch scoringTop 500 → Top 50
⚛️

Molecular Dynamics Agent

Stability Validation

Autonomously runs molecular dynamics simulation, eliminates false positives "unstable in real physiological conditions" via binding stability trajectory analysis over time.

Stability validationDynamic conformationTop 50 → Top 20
📋

Report Synthesis Agent

Final Deliverable

Synthesizes all three agents' outputs, traces each candidate to its original formula with centuries of use history, adds modern target mechanism interpretation — generates the complete deliverable report.

Traditional use tracingMechanism annotationEnd-to-end report

MAS Automated Pipeline: ① KG Agent (65K candidates) → ② VS Agent (Top 500) → ③ MD Agent (Top 20) → ④ Report Agent. Fully autonomous — zero manual handoffs.

TopAI Core Advantages

From data to algorithm to delivery — an end-to-end, irreplaceable AI engine for bioactive compound discovery.

TopAI Full-Spectrum Scoring MAS Automation Multi-Target Synergy Rapid Turnaround Data-Anchored End-to-End Pipeline
📊

Full-Spectrum Scoring Matrix

220K+ TCM compounds × 8,700 targets — comprehensive cross-scoring without blind spots.

🤖

MAS Automation Pipeline

4 AI specialist agents with zero manual intervention. From target discovery to report delivery — 100× efficiency gain.

Lightning Turnaround

1–2 weeks for single-target, 4–6 weeks for full multi-target analysis. Traditional methods: months to years.

🎯

Measured Data Anchoring

Models anchored by measured activity data — not purely theoretical. Predictions ready for R&D decisions.

🔗

Multi-Target Synergy

MAS evaluates multi-compound, multi-target cooperative effects that traditional methods cannot handle.

📋

End-to-End Deliverable

Quantitative candidate lists with efficacy scores, mechanism annotations, and traditional use traceability.

The Core Moat

The real barrier is the combination of our proprietary TCM knowledge graph and integrated multi-layer analytical capability — not any single tool in isolation.

Sustainable Competitive Advantage
01

Private TCM Knowledge Graph

7,443 formulas · 65,108 compounds · 155,351 association pairs. A 5-layer network (Formula→Herb→Compound→Target→Disease) that partners cannot replicate internally.

02

Black-Box IP Protection

Clients receive analysis results without accessing the underlying knowledge base. Our models remain independent IP — data sovereignty clear, IP boundaries locked.

03

Dual Validation: Ancient + Modern

Every candidate traces to a specific formula with centuries of human use. Simultaneously validated by modern target mechanism science. Double-backed, undeniable.

04

China Market Differentiation

TCM constitution–skin phenotype mapping provides an unreplicable product narrative: Damp-Heat → elevated TEWL → soothing targets; Blood-Stasis → microcirculation → activating compounds.

05

Multi-Target Synergy Capability

TCM active compounds frequently interact with multiple targets (off-target, moonlighting, synergy). Traditional methods ignore this complexity — MAS makes it tractable.

06

Integrated MAS, Not Tool Stack

Not a patchwork of tools — a deeply integrated system. KG + AI docking + MD + reporting, seamless 4-stage pipeline. Industry-exclusive automation.

From Knowledge Retrieval to Scientific Prediction

Traditional network pharmacology navigates on a known map. Our AI engine draws a new chemical-activity space map anchored by measured data.

Traditional Network Pharmacology Navigates on known maps (existing literature) Knowledge boundaries limit novel discoveries Manual filtering — slow and subjective Knowledge Retrieval LEAP AI-Driven · Our Approach ✦ AI draws new chemical-activity space map ✦ 220K+ compounds fully scored — no blind spots ✦ Quantitative candidate lists for R&D decisions Scientific Prediction "Knowledge Retrieval" → "Scientific Prediction" — An Essential Leap

Traditional Network Pharmacology

  • Navigates on known maps only
  • Bound by existing literature & databases
  • Cannot discover novel connections
  • Manual screening — slow, subjective
  • Scales poorly to large CP-target matrices

AI-Driven · Our Solution

  • AI draws new chemical-activity space maps
  • Anchored by measured data — 220K+ compounds scored
  • Multi-agent automated harness drives screening
  • Quantitative candidate lists for cosmetic R&D
  • Breaks knowledge boundaries — discovers new associations

The Essential Leap: Traditional methods navigate on known maps. Our AI engine draws an entirely new chemical-activity space map, anchors it with measured data, scores 220K+ TCM compounds comprehensively through a multi-agent automated pipeline, and outputs quantitative candidate lists ready for R&D decisions. This is the leap from knowledge retrieval to scientific prediction.

Multi-Compound – Multi-Target Network Regulation

The core advantage of natural products: multi-target network regulation — not a single pathway, but systemic biological network modulation.

Traditional: Lock-and-Key Lock & Key 1 drug → 1 target → 1 disease Limited efficacy, side effects ✕ Cannot handle network complexity vs TCM Multi-Compound · Multi-Target Network C1 C2 C3 C4 Compounds (Multi-Component) T1 T2 T3 T4 T5 Targets (Multi-Target) Synergistic Cocktail Effect: 1+1 > 2

Traditional Drug Paradigm

1 Drug1 Target1 Disease

"Lock-and-key" model — single compound, single target. Limited efficacy, significant side effects, prone to resistance.

TCM Multi-Target Paradigm

Multi-CompoundMulti-TargetNetwork Control

Natural product cocktail effect — multiple compounds acting synergistically on multiple targets, producing 1+1 > 2 systemic therapeutic outcomes.

🌿

Synergy

Multiple compounds produce additive or synergistic effects across targets — overall efficacy exceeds any single component.

🔗

Network Regulation

Modulating entire biological networks rather than single pathways — achieving more balanced, durable intervention.

⚖️

Reduced Side Effects

Weak multi-target inhibition achieves efficacy while significantly reducing toxicity compared to single-target strong inhibition.

AI-Powered Multi-Target Discovery

Combining full-spectrum AI scoring with multi-target network pharmacology for end-to-end intelligent candidate discovery.

AI Full-Spectrum Scoring Matrix

  • 220K+ compounds × 8.7K targets
  • Multi-agent automated pipeline
  • Network pharmacology + GNN modeling
  • Multi-target synergy index computation

Cosmetic R&D Applications

  • Whitening: tyrosinase + MITF + melanin transport
  • Anti-inflammatory–antioxidant–repair cascade
  • Anti-aging: collagen + ECM + autophagy
  • From single pathway to holistic skin ecosystem
Multi-Target Decision Pipeline
Compound Lib AI Scoring MT Rank Candidates R&D Decision

Core Value: Traditional methods evaluate 1 compound × 1 target at a time. Our AI multi-target engine simultaneously scores the full 220K+ compound × 8,700+ target matrix, automatically identifies optimal synergistic combinations, and compresses the discovery cycle from months to days.

Thank You

AI + TCM · From Data to Decision

220K+ Compounds8,700 TargetsAI Full ScoringMulti-Target Synergy