Advances of Artificial Intelligence in Anti-Cancer Drug Design: A Review of the Past Decade

Pharmaceuticals, Год журнала: 2023, Номер 16(2), С. 253 - 253

Опубликована: Фев. 7, 2023

Anti-cancer drug design has been acknowledged as a complicated, expensive, time-consuming, and challenging task. How to reduce the research costs speed up development process of anti-cancer designs become urgent question for pharmaceutical industry. Computer-aided methods have played major role in cancer treatments over three decades. Recently, artificial intelligence emerged powerful promising technology faster, cheaper, more effective designs. This study is narrative review that reviews wide range applications intelligence-based design. We further clarify fundamental principles these methods, along with their advantages disadvantages. Furthermore, we collate large number databases, including omics database, epigenomics chemical compound databases. Other researchers can consider them adapt own requirements.

Язык: Английский

---

A comprehensive evaluation of large Language models on benchmark biomedical text processing tasks

Computers in Biology and Medicine, Год журнала: 2024, Номер 171, С. 108189 - 108189

Опубликована: Фев. 20, 2024

Recently, Large Language Models (LLMs) have demonstrated impressive capability to solve a wide range of tasks. However, despite their success across various tasks, no prior work has investigated in the biomedical domain yet. To this end, paper aims evaluate performance LLMs on benchmark For purpose, comprehensive evaluation 4 popular 6 diverse tasks 26 datasets been conducted. best our knowledge, is first that conducts an extensive and comparison domain. Interestingly, we find based smaller training sets, zero-shot even outperform current state-of-the-art models when they were fine-tuned only set these datasets. This suggests pre-training large text corpora makes quite specialized We also not single LLM can other all with different may vary depending task. While still poor findings demonstrate potential be valuable tool for lack annotated data.

Язык: Английский

---

Explainable Artificial Intelligence for Drug Discovery and Development: A Comprehensive Survey

IEEE Access, Год журнала: 2024, Номер 12, С. 35796 - 35812

Опубликована: Янв. 1, 2024

The field of drug discovery has experienced a remarkable transformation with the advent artificial intelligence (AI) and machine learning (ML) technologies. However, as these AI ML models are becoming more complex, there is growing need for transparency interpretability models. Explainable Artificial Intelligence (XAI) novel approach that addresses this issue provides interpretable understanding predictions made by In recent years, been an increasing interest in application XAI techniques to discovery. This review article comprehensive overview current state-of-the-art discovery, including various methods, their challenges limitations also covers target identification, compound design, toxicity prediction. Furthermore, suggests potential future research directions aims provide state its transform field.

Язык: Английский

---

Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods

Computers in Biology and Medicine, Год журнала: 2022, Номер 152, С. 106443 - 106443

Опубликована: Дек. 19, 2022

Язык: Английский

---

Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning

Balkan Medical Journal, Год журнала: 2022, Номер 40(1), С. 3 - 12

Опубликована: Дек. 29, 2022

In the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques allow machines to learn and get better at such recognition prediction, which form basis clinical practice, referred machine learning, is a subfield intelligence. number intelligence-and learnings-related publications in journals has grown exponentially, driven recent developments computation accessibility simple tools. However, clinicians often not included data science teams, may limit relevance, explanability, workflow compatibility, quality improvement intelligence solutions. Thus, this results language barrier between developers. Healthcare practitioners sometimes lack basic understanding research because approach difficult for non-specialists understand. Furthermore, many editors reviewers medical might be familiar with fundamental ideas behind these technologies, prevent from publishing high-quality studies or, worse still, could publication low-quality works. review, we aim improve readers’ literacy critical thinking. As result, concentrated on what consider 10 most important qualities research: valid scientific purpose, set, robust reference standard, input, no information leakage, optimal bias-variance tradeoff, proper model evaluation, proven utility, transparent reporting, open science. Before designing study, one should have defined sound purpose. Then, it backed solid standard. development pipeline leakage. For models, tradeoff achieved, generalizability assessment must adequately performed. value final models also established. After thought given transparency process well sharing data, code, models. We hope work mindset readers.

Язык: Английский

---

Exploring the role of artificial intelligence in chemotherapy development, cancer diagnosis, and treatment: present achievements and future outlook

Frontiers in Oncology, Год журнала: 2025, Номер 15

Опубликована: Фев. 4, 2025

Background Artificial intelligence (AI) has emerged as a transformative tool in oncology, offering promising applications chemotherapy development, cancer diagnosis, and predicting response. Despite its potential, debates persist regarding the predictive accuracy of AI technologies, particularly machine learning (ML) deep (DL). Objective This review aims to explore role forecasting outcomes related treatment response, synthesizing current advancements identifying critical gaps field. Methods A comprehensive literature search was conducted across PubMed, Embase, Web Science, Cochrane databases up 2023. Keywords included “Artificial Intelligence (AI),” “Machine Learning (ML),” “Deep (DL)” combined with “chemotherapy development,” “cancer diagnosis,” treatment.” Articles published within last four years written English were included. The Prediction Model Risk Bias Assessment utilized assess risk bias selected studies. Conclusion underscores substantial impact AI, including ML DL, on innovation, response for both solid hematological tumors. Evidence from recent studies highlights AI’s potential reduce cancer-related mortality by optimizing diagnostic accuracy, personalizing plans, improving therapeutic outcomes. Future research should focus addressing challenges clinical implementation, ethical considerations, scalability enhance integration into oncology care.

Язык: Английский

---

New Drug Discovery

Advances in medical diagnosis, treatment, and care (AMDTC) book series, Год журнала: 2023, Номер unknown, С. 134 - 184

Опубликована: Июнь 16, 2023

The field of drug discovery is continually advancing with the emergence new technologies and scientific developments. Moreover, there a recent growing interest in exploiting natural products as potential source novel leads. This chapter provides an overview current state discovery, specific focus on integrative medicine. process discussed, including target identification, lead generation, optimization, preclinical clinical development, along challenges associated each step solutions. use leads explored, examples that have been transformed into drugs efforts to discover product-based drugs. Furthermore, proposes valuable insights opportunities this field, well solutions for discovering developing

Язык: Английский

---

Discovery of novel SOS1 inhibitors using machine learning

RSC Medicinal Chemistry, Год журнала: 2024, Номер 15(4), С. 1392 - 1403

Опубликована: Янв. 1, 2024

Overactivation of the rat sarcoma virus (RAS) signaling is responsible for 30% all human malignancies. Son sevenless 1 (SOS1), a crucial node in RAS pathway, could modulate activation, offering promising therapeutic strategy RAS-driven cancers. Applying machine learning (ML)-based virtual screening (VS) on small-molecule databases, we selected random forest (RF) regressor its robustness and performance. Screening was performed with L-series EGFR-related datasets, extended to Chinese National Compound Library (CNCL) more than 1.4 million compounds. In addition series documented SOS1-related molecules, uncovered nine compounds that have an unexplored chemical framework displayed inhibitory activity, most potent achieving 50% inhibition rate KRAS G12C/SOS1 PPI assay IC

Язык: Английский

---

Artificial intelligence for small molecule anticancer drug discovery

Expert Opinion on Drug Discovery, Год журнала: 2024, Номер 19(8), С. 933 - 948

Опубликована: Июнь 18, 2024

Introduction The transition from conventional cytotoxic chemotherapy to targeted cancer therapy with small-molecule anticancer drugs has enhanced treatment outcomes. This approach, which now dominates treatment, its advantages. Despite the regulatory approval of several molecules for clinical use, challenges such as low response rates and drug resistance still persist. Conventional discovery methods are costly time-consuming, necessitating more efficient approaches. rise artificial intelligence (AI) access large-scale datasets have revolutionized field discovery. Machine learning (ML), particularly deep (DL) techniques, enables rapid identification development novel agents by analyzing vast amounts genomic, proteomic, imaging data uncover hidden patterns relationships.

Язык: Английский

---

The role of artificial intelligence in drug screening, drug design, and clinical trials

Frontiers in Pharmacology, Год журнала: 2024, Номер 15

Опубликована: Ноя. 29, 2024

The role of computational tools in drug discovery and development is becoming increasingly important due to the rapid computing power advancements chemistry biology, improving research efficiency reducing costs potential risks preclinical clinical trials. Machine learning, especially deep a subfield artificial intelligence (AI), has demonstrated significant advantages development, including high-throughput virtual screening,

Язык: Английский

---