molAIcure - AI-Powered Drug Discovery

Our Services

Comprehensive computational solutions for modern drug discovery

🧬

Omics Data Analysis

Advanced deep learning models surpassing standard analysis software for biomarker identification. Multi-stage disease analysis capabilities provide holistic insights into disease progression.

🔬

Virtual Screening

AI-powered models combined with physics-based docking for rapid hit identification. Targets include proteins, RNA, and DNA with unprecedented accuracy.

⚡

Molecular Dynamics

Rigorous computational simulations ensuring scientific explainability of identified hits, significantly reducing false positives in our pipeline.

🧪

Wet-Lab Validation

In vitro testing services including cell viability assays, binding kinetics, and flow cytometry to validate computational predictions.

Our Expert Team

Leading researchers in computational drug discovery

Prof. Mu Yuguang

NTU Associate Professor

30 years of CADD experience leading the Biomolecular Simulations and Data Analysis Lab

Tan Lai Heng

4th Year PhD Student

4 years in CADD & ML, 1st author of RmsdXNA

Sun Ao

1st Year PhD Student

4 years CADD & ML, 5 years wet-lab experience, 1st author of GATomics

Guan Jia Sheng

1st Year PhD Student

4 years in CADD & ML, 2nd author of BIND and GATomics

Hit Identifications

Proven success across diverse therapeutic targets

Acute Myeloid Leukemia

Identified Gene X as therapeutic target using GATomics. Virtual screening of 2M compounds yielded 2 hits with μM IC50.

Hit Rate: 67% (4/6)

Cancer Protein Target

Screened 1.2M molecules identifying 4 compounds with mM range Kd values through collaboration with Tsinghua University.

Hit Rate: 21% (4/19)

Z-alpha ADAR1

FDA library screening (2,115 molecules) identified 6 inhibitors of Z-DNA recognition with confirmed activity.

Hit Rate: 60% (6/10)

Chikungunya Virus

Discovered 2 inhibitors with μM range EC50 values from 10 candidates tested.

Hit Rate: 20% (2/10)

Parkinson's Disease

4 compounds showed superior inhibition compared to known inhibitors, particularly compounds 11 and 12.

Hit Rate: 33% (4/12)

MALAT1 lncRNA

RNA-targeting screen identified stabilizing and destabilizing compounds with 1.2μM Kd binding affinity.

Hit Rate: 20% (2/10)

Miniprotein Design Excellence

Transcription Factor Targeting

Using advanced AI tools for sequence generation and filtering, we designed miniproteins to target transcription factor proteins with exceptional success.

Hit Rate: 88% (7/8)

Publications

Cutting-edge research in computational drug discovery

Protein-Small Molecule Docking: OnionNet, OnionNet2, OnionNet-SFCT, DeepRMSD

Sequence-Based Virtual Screening: BIND

Ligand Language Model: NYAN

Nucleic Acid-Small Molecule Docking: RmsdXNA

Protein-Protein Binding Affinity: ProAffinity-GNN

Accelerating Drug Discovery with AI