Scholarlink

<p>Artificial intelligence (AI), three-dimensional (3D) printing, and pharmacogenomics are coming together to change the pharmaceutical development, but most of the published reviews treat these technologies in isolation. This narrative review explains how these three domains interact all through the drug discovery-to-delivery process and tries to identify the scientific, regulatory and ethical requirements for their integration. AI-driven approaches will help in accelerating drug discovery by identifying targets, generating molecular candidates, and predicting drug-target interactions. However, less than 20% of identified lead molecules tend to cross Phase I trials, which show that there are many gaps in generalization across different domains. Additive manufacturing helps us develop personalized dosage forms for paediatric doses and orphan disease therapies but the thermal degradation of active pharmaceutical ingredients takes place and limited scalability lead to non-selection. In Pharmacogenomics, the genetic variations is backbone for selection of dosing, but it is affected by bias in genomic datasets, and a phenomenon called clinician alert fatigue. To tackle such problems, the critical points of investigation include head-to-head clinical trials linking 3D-printed outputs to therapeutic outcomes, validation of AI algorithms based on independent datasets, and multi-disciplinary pharmacogenomic datasets. In this review, a new conceptual integration framework is proposed so that we can learn to illustrate how AI, additive manufacturing, and pharmacogenomics can operate by complementing across the pharmaceutical lifecycle. The successful translation of this idea will require collaboration at various levels among discovery scientists, manufacturing engineers, clinicians, and informaticians to deliver personalized therapies within less development timelines for improved patient outcomes, and equal access to all people.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AI-driven drug development: integrating computational design, 3D printing, and genomic medicine

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月10日

查看全文
  • Mihir Medhansh Doneparthi,
  • Devadharuna Mohan,
  • Roshan Barwa,
  • Tanvi Painginkar,
  • Veera Venkata Satyanarayana Reddy Karri,
  • Riyaz Ali M. Osmani,
  • B. S. Muddukrishna,
  • Gundawar Ravi

摘要

Artificial intelligence (AI), three-dimensional (3D) printing, and pharmacogenomics are coming together to change the pharmaceutical development, but most of the published reviews treat these technologies in isolation. This narrative review explains how these three domains interact all through the drug discovery-to-delivery process and tries to identify the scientific, regulatory and ethical requirements for their integration. AI-driven approaches will help in accelerating drug discovery by identifying targets, generating molecular candidates, and predicting drug-target interactions. However, less than 20% of identified lead molecules tend to cross Phase I trials, which show that there are many gaps in generalization across different domains. Additive manufacturing helps us develop personalized dosage forms for paediatric doses and orphan disease therapies but the thermal degradation of active pharmaceutical ingredients takes place and limited scalability lead to non-selection. In Pharmacogenomics, the genetic variations is backbone for selection of dosing, but it is affected by bias in genomic datasets, and a phenomenon called clinician alert fatigue. To tackle such problems, the critical points of investigation include head-to-head clinical trials linking 3D-printed outputs to therapeutic outcomes, validation of AI algorithms based on independent datasets, and multi-disciplinary pharmacogenomic datasets. In this review, a new conceptual integration framework is proposed so that we can learn to illustrate how AI, additive manufacturing, and pharmacogenomics can operate by complementing across the pharmaceutical lifecycle. The successful translation of this idea will require collaboration at various levels among discovery scientists, manufacturing engineers, clinicians, and informaticians to deliver personalized therapies within less development timelines for improved patient outcomes, and equal access to all people.