The Role of Artificial Intelligence in Accelerating Drug Discovery and Development
Bibliographic record
Abstract
Artificial intelligence (AI) is rapidly reshaping the pharmaceutical industry through its impact in the way drugs are discovered, developed, and delivered. Traditionally, drug development has been a lengthy, expensive, and failure-prone process, often requiring over a decade and billions of dollars to bring a single therapy to market. AI has the potential to address some of these inefficiencies by supporting faster, more data-driven decision-making in certain areas across the research and development (R&D) pipeline. This review summarizes ten key domains where AI applications are emerging, with varying degrees of demonstrated impact: 1) target identification; 2) hit discovery; 3) lead optimization; 4) preclinical modeling; 5) clinical trial design and stratification; 6) post-marketing surveillance and real-world evidence generation; 7) biomarker discovery; 8) molecular synthesis automation; 9) cost and time reduction; and 10) regulatory decision support. AI techniques - including machine learning, natural language processing, deep learning, and generative models - have shown capability in accelerating in silico screening, predicting pharmacokinetic and toxicity profiles, simulating clinical trials, and optimizing molecular design. Additionally, AI is enabling dynamic clinical trial designs, synthetic control arms, and automated patient matching, improving trial success rates. Through automated synthesis planning and robotic chemistry, AI reduces the cycle time from hypothesis to compound validation. Post-market, AI enhances pharmacovigilance by mining electronic health records and social media to detect adverse drug events earlier than traditional systems. As regulatory agencies increasingly accept AI-derived evidence, the pharmaceutical landscape is transitioning toward more efficient, scalable, and personalized drug development pathways. Despite its momentum, challenges remain, such as data bias, model transparency, and regulatory harmonization. This review underscores AI’s potential role in shaping the future of therapeutic innovation and highlights the areas that must be addressed to fully realize its potential.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.017 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.006 | 0.009 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".