About the Book
This brief introduces the readers of predictive cheminformatics to the concept of cliffs in the structure-activity landscape, which may greatly affect the data set modelability and the quality of predictions, hence generating disappointment from the performance of Quantitative Structure-Activity Relationship (QSAR) models. Although QSAR models are based on the assumption of a smooth activity landscape, where similar molecules are expected to have similar activities, some similar molecules can occasionally exhibit large differences in activity (for example, 100-fold). The definition of similarity for identifying activity cliffs may be based on chemical fingerprints or descriptors (classical activity cliffs), substructures (chirality cliffs, matched molecular pair cliffs), three-dimensional structure-based cliffs (3D cliffs), or the target-set-dependent potency difference. Some prediction outliers, even within the applicability domain of QSAR models, may arise due to the activity cliff (AC) behavior. In addition to compound pairs, activity cliffs may also be visualized in coordinated networks forming AC clusters. Despite using high-quality data, the data set's modelability may be significantly compromised in the presence of ACs, among other factors. The modelability of the dataset has been studied using different approaches like modelability index (MODI), weighted modelability index (WMODI), rivality index, etc. At the same time, the applicability domain of QSAR models is evaluated using a variety of methods, including leverage, principal components, standardization methods, and distance to the model in X-space, among others. Different methods for identifying activity cliffs have been proposed, such as the structure-activity landscape index (SALI), the structure-activity relationship (SAR) index, and the structure-activity similarity (SAS) maps. Recently, the Arithmetic Residuals in K-Groups Analysis (ARKA) has been shown to be successful in identifying activity cliffs. This approach has also been applied in small data set classification modeling. A multiclass ARKA approach has also been developed for its possible application in regression-based problems by integrating it with the quantitative read-across structure-activity relationship (q-RASAR) framework. This book showcases the evolution and the current status of the concept of activity cliffs as relevant to QSAR predictions and indicates the future directions in the research on activity cliffs. Researchers in the fields of medicinal chemistry, predictive toxicology, nanosciences, food science, agricultural sciences, and materials informatics should benefit from the concept of activity cliffs, impacting model-derived predictions.
Table of Contents:
QSAR – A tool of Predictive Cheminformatics.- Outliers and the Applicability Domain of QSAR models.- Cliffs in Biological Activity Landscape.- The Arithmetic Residuals in K-Group Analysis (ARKA) for the Detection of Activity Cliffs.- Activity Cliffs and Dataset Modelability – Future Roadmaps.
About the Author :
Dr. Kunal Roy Professor & Ex-Head in the Department of Pharmaceutical Technology, Jadavpur University, Kolkata, India. He has been a recipient of Commonwealth Academic Staff Fellowship (University of Manchester, 2007) and Marie Curie International Incoming Fellowship (University of Manchester, 2013) and a former visiting scientist of Istituto di Ricerche Farmacologiche "Mario Negri" IRCCS, Milano. Italy. The field of his research interest is Quantitative Structure-Activity Relationship (QSAR) and Molecular Modeling with application in Drug Design, Property Modeling and Predictive Ecotoxicology. Dr. Roy has published more than 450 research articles in refereed journals (current SCOPUS h index 56; total citations to date more than 17000). He has also coauthored three QSAR-related books (Academic Press and Springer), edited thirteen QSAR books (Springer, Academic Press, and IGI Global), and published twenty five book chapters. Dr. Roy is the Co-Editor-in-Chief of Molecular Diversity (Springer Nature) and an Associate Editor of Computational and Structural Biotechnology Journal (Elsevier). Dr. Roy serves on the Editorial Boards of several International Journals including (1) European Journal of Medicinal Chemistry (Elsevier); (2) Journal of Molecular Graphics and Modelling (Elsevier); (3) Chemical Biology and Drug Design (Wiley); (4) Expert Opinion on Drug Discovery (Informa). Apart from this, Prof. Roy is a regular reviewer for QSAR papers in the journals like Chemosphere (Elsevier), Journal of Hazardous Materials (Elsevier), Ecotoxicology and Environmental Safety (Elsevier), Journal of Chemical Information and Modeling (ACS), ACS Omega (ACS), RSC Advances (RSC), Molecular Informatics (Wiley), SAR and QSAR in Environmental Research (T&F), etc. Prof. Roy has been recipient of several awards including AICTE Career Award (2003-04), DST Fast Track Scheme for Young Scientists (2005), Bioorganic and Medicinal Chemistry Most Cited Paper 2003-2006, 2004-2007 and 2006-2009 Awards from Elsevier, The Netherlands, Bioorganic and Medicinal Chemistry Letters Most Cited Paper 2006-2009 Award from Elsevier, The Netherlands, Professor R. D. Desai 80th Birthday Commemoration Medal & Prize (2017) from Indian Chemical Society, etc. Prof. Roy has been a participant in the EU funded projects nanoBRIDGES and IONTOX apart from several national Government funded projects (UGC, AICTE, CSIR, ICMR, DBT, DAE). Prof. Roy has recently been placed in the list of the World's Top 2% science-wide author database (whole career data) (World rank 52 in the subfield of Medicinal & Biomolecular Chemistry) (Ioannidis, John P.A. (2025), "August 2025 data-update for "Updated science-wide author databases of standardized citation indicators", Elsevier Data Repository).
Arkaprava Banerjee is a Researcher (funded by the Life Sciences Research Board, DRDO, Govt. of India) working at the Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata. Mr. Banerjee has twenty-nine research articles published in reputed journals and four book chapters with overall citations of 751 and an h-index of 17 (Scopus). His expertise lies in the similarity-based cheminformatic approaches like Read-Across and Read-Across Structure-Activity Relationship (RASAR) - a novel method that combines the concept of QSAR and Read-Across. Mr. Banerjee is also a Java programmer who has developed various cheminformatic tools based on QSAR, Read-Across, and RASAR, and the tools are freely available from the DTC Laboratory Supplementary Website. He received the Prof. Anupam Sengupta Bronze medal from Jadavpur University for securing the highest marks in Pharmaceutical Chemistry in the MPharm examination. He has also received a special diploma awarded by the Institute of Biomedical Chemistry, Moscow, Russia (2022), and the ASCCT Travel Award from the American Society for Cellular and Computational Toxicology (2023). Together with Prof. Kunal Roy, he has been one of the first researchers to develop quantitative models using similarity and error-based descriptors (quantitative/classification Read-Across Structure-Activity Relationship: q-RASAR/c-RASAR models) with applications in drug design, materials science, and property modeling. Recently, he coauthored a book on "q-RASAR," which was published by Springer. He has also co-edited three volumes of "Materials Informatics" published by Springer. He has recently been placed in the list of the World's Top 2% science-wide author database (Single-year data 2024) (World rank 769 in the subfield of Toxicology) (Ioannidis, John P.A. (2025), "August 2025 data-update for 'Updated science-wide author databases of standardized citation indicators', Elsevier Data Repository).
