Computer Aided Drug Design

AI Based Computer Aided Drug Design & Discovery 

                                                                                                                                    Joon Hwang Ph.D.

New drugs with better efficacy and reduced toxicity are always in high demand, however the process of drug discovery and development is costly and time consuming and presents a number of challenges.

The process of drug discovery starts with target identification, followed by target validation, hit discovery, lead optimisation, and preclinical/clinical development. If successful, a drug candidate progresses to the development stage, where it passes through different phases of clinical trials and eventually submission for approval to launch on the market.  After hit compounds are identified, properties, such as absorption, distribution, metabolism, excretion (ADME), and toxicity should be considered and optimised early in the drug discovery process. Unfavourable pharmacokinetic and toxicity profile of a drug candidate is one of the hurdles that often leads to failure in the clinical trials.  

Computer-aided drug design (CADD) utilises this information and knowledge to screen for novel drug candidates. With the advancement in technology and computer power in recent years, CADD has proven to be a tool that reduces the time and resources required in the drug discovery pipeline. 

1. Support for Screening Anticancer Drug and Gene Delivery Candidates Using Lipid Nanoparticle

(1) Molecular Docking and Simulation

• Drug Conjugation: Molecular docking simulations are used to study the interactions between anticancer drugs and lipid nanoparticle components, optimizing drug encapsulation efficiency and release profiles.

• Gene Delivery Optimization: Using in silico models, screen for nanoparticles that efficiently interact with nucleic acids (DNA, RNA). Modeling lipid-nucleic acid interactions allows for prediction of gene delivery efficiency.

(2) Lipid Nanoparticle Drug Candidate Design

• Select functional lipids, such as other lipid derivatives (e.g., cancer-specific targeting ligands), that can enhance lipid nanoparticle gene delivery, maintain nanoparticle stability, and enhance cellular uptake and targeting ability.

• Provide nanoparticle design information considering lipid layer structure, surface charge, size, encapsulation, and stability.

(3) Prediction of Toxicity and Stability Assessment

• Pharmacokinetic and Toxicity Prediction (PK/ADMET): Establish an in silico toxicity prediction model, verify the in vivo safety of candidate substances and potential side effects.

• PK correlation analysis and database of prediction simulation data and experimental data linked to in vitro and in vivo experimental data.

2. Support for New Drug Candidate Design through Peptide Structure Prediction

(1) Target Identification and Peptide Library Creation

• Target Identification: Deriving identification information for key protein targets (immune checkpoint proteins, cytokine receptors, metabolic regulators, etc.).

• Target Polypeptide Library Creation: Designing peptides that can interact with identified targets based on known receptor binding sites and epitopes, and building a peptide sequence library.

(2) Pharmacological Evaluation through Molecular Docking and Molecular Dynamics Simulation

• • Molecular Docking: Predicting the binding affinity between peptides and target proteins through molecular docking analysis. Analysis of binding energy and interaction patterns to select the most promising candidates.

  • Molecular Dynamics (MD) Simulation: Evaluate the stability of peptide-protein complexes over time and pharmacologically optimize peptide structures for enhanced binding affinity and stability. Peptide Sequence Analysis and Structure Prediction: 3D structure prediction for selected peptides using peptide sequence analysis based on established databases/libraries and machine learning/deep learning.

(3) Toxicity/Stability Evaluation and Optimization

• In silico ADMET modeling is used to evaluate the metabolism/safety of candidates, to evaluate PK characteristics, and to optimize hit-to-lead compounds. This process is then combined with QSAR model validation to increase the commercialization potential of drug candidates.