AI in Clinical Medicine, ISSN 2819-7437 online, Open Access
Article copyright, the authors; Journal compilation copyright, AI Clin Med and Elmer Press Inc
Journal website https://aicm.elmerpub.com

Review

Volume 1, 2025, e8

The Role of Artificial Intelligence in Accelerating Drug Discovery and Development

Figures

↓  Figure 1. Comparison of the functional capabilities of four AI platforms. Venn diagram illustrating the overlap of identified items among four AI tools: C-ChatGPT (red, eight items), D-DeepSeek (green, six items), G-Grok (blue, 10 items), and P-Perplexity (yellow, 10 items). The central intersection (six items) represents elements common to all four tools. Two additional overlaps are observed between G-Grok and P-Perplexity (two items) and between C-ChatGPT and G-Grok (two items). All other pairwise or triple intersections contain no shared items (0). This visualization highlights the degree of consensus and uniqueness among the AI outputs, emphasizing the core set of commonly identified elements across platforms.
Figure 1.
↓  Figure 2. Schematic representation of the AI core engine’s role across the drug development pipeline. In the discovery phase, AI enables target discovery by uncovering novel disease mechanisms and identifying druggable targets through advanced computational analysis. Biomarker discovery integrates multi-omics datasets to design molecular candidates and facilitate precision medicine approaches. In the preclinical stage, AI enhances preclinical safety via predictive toxicology, bioavailability modeling, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) profiling, reducing reliance on extensive in vivo testing. During clinical trials, AI improves clinical trial design by optimizing patient selection, predicting outcomes, and refining trial protocols. In the market phase, AI drives RWE generation for post-market surveillance, drug repurposing, and proactive safety monitoring. Across all stages, AI delivers cost and time efficiency through accelerated development timelines, improved decision-making, and reduced operational expenses. Color coding indicates phase categories: discovery (blue), preclinical (orange), clinical trial (green), and market (red/brown). AI: artificial intelligence; RWE: real-world evidence.
Figure 2.

Tables

↓  Table 1. AI Impacts on Drug R&D Identified by ChatGPT
 
Stage AI applications
AI: artificial intelligence; R&D: research and development; ADMET: absorption, distribution, metabolism, excretion, and toxicity; EHRs: electronic health records.
Target identification Analyzes omics data and literature to find and validate disease-relevant targets
Speeds up discovery of novel and druggable targets
Hit discovery Screens virtual compound libraries, predicts binding affinities, de novo design
Rapid identification of candidate molecules
Lead optimization Models structure-activity relationships (SAR), predicts ADMET properties, suggests synthetic pathways
Improves efficacy, reduces toxicity, enhances developability
Preclinical modeling Predicts in vivo outcomes, toxicity, and off-target effects
Enhances animal model selection and safety profiling
Biomarker discovery Extracts predictive and prognostic biomarkers from multi-modal data
Enables precision medicine and better patient stratification
Clinical trial design Selects optimal patient cohorts, predicts outcomes, designs adaptive trials
Increases trial efficiency and success rates
Real-world evidence Analyzes EHRs, registries, and wearable data
Improves post-market surveillance and supports drug repurposing
Cost and time reduction Automates processes, reduces lab and trial failures
Shortens development timelines and lowers overall R&D costs

 

↓  Table 2. AI Impacts on Drug R&D Identified by DeepSeek
 
Stage of drug R&D AI applications
AI: artificial intelligence; R&D: research and development; ADMET: absorption, distribution, metabolism, excretion, and toxicity; EHRs: electronic health records; COVID-19: coronavirus disease 2019.
Target identification Analyzes genomics/proteomics data
Predicts protein structures (e.g., AlphaFold)
Prioritizes high-value targets
Drug discovery Generative AI designs novel molecules
Virtual screening (e.g., Schrodinger)
De novo drug design (e.g., Insilico Medicine)
Preclinical testing Predicts ADMET (toxicity/safety)
AI-driven lab automation (robotics)
Reduces animal testing
Clinical trials AI matches patients using EHRs
Predicts trial success/failure
Monitors adverse effects in real time
Drug repurposing Identifies new uses for existing drugs (e.g., baricitinib for COVID-19)
Saves time/resources vs. developing new drugs
Manufacturing Optimizes production with predictive AI
AI forecasts supply chain demands
Reduces waste and ensures consistent drug supply

 

↓  Table 3. AI Impacts on Drug R&D Identified by Grok
 
Stage AI applications
AI: artificial intelligence; R&D: research and development.
Target identification Analyzes genomics/proteomics data to identify novel drug targets with high precision
Drug design Predicts molecular interactions to design compounds with optimal binding properties
Virtual screening Screens millions of compounds in silico to identify candidates, reducing experimental costs
Predictive toxicology Assesses toxicity and side effects early, minimizing late-stage clinical trial failures
Clinical trial optimization Improves patient recruitment and predicts outcomes, streamlining trial design
Repurposing drugs Identifies new uses for existing drugs, accelerating development for new indications
Personalized medicine Tailors treatments using patient data, speeding up precision therapy development
Automation of data analysis Processes complex datasets (imaging, chemical, clinical), reducing errors and manual effort
Synthesis prediction Predicts optimal chemical synthesis routes, minimizing iterations and costs
Regulatory support Streamlines documentation and predicts regulatory outcomes, speeding up submissions

 

↓  Table 4. AI Impacts on Drug R&D Identified by Perplexity
 
Stage AI application
AI: artificial intelligence; R&D: research and development.
Identification of drug candidates Speeds up discovery of potential compounds
Prediction of drug properties and safety Improves accuracy in forecasting efficacy, toxicity, and interactions
Optimization of preclinical and clinical trials Streamlines trial design, patient recruitment, monitoring, and outcome prediction
Integration of experimental feedback (“lab in the loop”) Enables iterative refinement of drug candidates using AI and lab data
Cost and time reduction Significantly lowers R&D expenses and shortens development timelines
Advanced structural biology AI tools like AlphaFold predict protein structures, aiding targeted drug design
Drug repurposing Identifies new therapeutic uses for existing drugs
Personalized medicine Analyzes genomics, proteomics, and clinical data to tailor treatments
Generative AI for molecule design Designs new molecular structures with desired properties
Higher success rates in clinical development Increases probability of drug candidates progressing through clinical phases

 

↓  Table 5. Summary of Four AI Platforms
 
Category ChatGPT (C) DeepSeek (D) Grok (G) Perplexity (P)
The table summarizes the outputs from four AI platforms, intended as an illustrative comparison of emphasis areas rather than a systematic analysis. AI: artificial intelligence.
Target identification Target identification Target identification Target identification Identification of drug candidates
Hit discovery Hit discovery Drug discovery Drug design Prediction of drug properties and safety
Lead optimization Lead optimization Preclinical testing Virtual screening Optimization of preclinical and clinical trials
Preclinical modeling Preclinical modeling Clinical trials Predictive toxicology Integration of experimental feedback (“lab in the loop”)
Biomarker discovery Biomarker discovery Drug repurposing Clinical trial optimization Cost and time reduction
Clinical trial design Clinical trial design Manufacturing Repurposing drugs Advanced structural biology
Real-world evidence Real-world evidence - Personalized medicine Drug repurposing
Cost and time reduction Cost and time reduction - Automation of data analysis Personalized medicine
Molecular synthesis - - Synthesis prediction Generative AI for molecule design
Regulatory and success - - Regulatory support Higher success rates in clinical development