Robust Theoretical Models in Medicinal Chemistry : QSAR, Artificial Intelligence, Machine Learning, and Deep Learning

Scotti, Luciana (EDT)/ Scotti, Marcus Tullius (EDT)

Elsevier - Health Sciences Division（2025/11発売）

• 製本 Paperback:紙装版/ペーパーバック版／ページ数 350 p.
• 言語 ENG
• 商品コード 9780443274206

Full Description

Robust Theoretical Models in Medicinal Chemistry: QSAR, Artificial Intelligence, Machine Learning, and Deep Learning serves as a valuable resource chock full of applications extending into multiple knowledge domains. The meticulous construction of a robust model holds significance, not only in drug discovery but also in engineering, chemistry, pharmaceutical, and food-related research, illustrating the broad spectrum of fields where QSAR methodologies can be instrumental. The activities considered in QSAR span chemical measurements and biological assays, making this approach a versatile tool applicable across various scientific domains. Currently, QSAR finds extensive use in diverse disciplines, prominently in drug design and environmental risk assessment.

Quantitative Structure-Activity Relationships (QSAR) represent a concerted effort to establish correlations between structural or property descriptors of compounds and their respective activities. These physicochemical descriptors encompass a wide array of parameters, accounting for hydrophobicity, topology, electronic properties, and steric effects, and can be determined empirically or, more recently, through advanced computational methods.

Contents

1. Building QSAR models
2. Model, validation and prediction
3. Outliers and Negative Data
4. QSAR3- and 4D
5. QSAR and QSRP modelling
6. QSAR In Food Science
7. Interpretation of recent computational methods
8. Recent theoretical methods in the industry
9. Understanding the difference between machine learning and deep learning
10. Can artificial intelligence replace QSAR?