Article
Chemistry, Multidisciplinary
Zi-Yi Yang, Li Fu, Ai-Ping Lu, Shao Liu, Ting-Jun Hou, Dong-Sheng Cao
Summary: Matched molecular pair analysis (MMPA) is a promising tool for local structural optimization tasks, and its integration with QSAR modeling can further strengthen its utility in molecular optimization navigation.
JOURNAL OF CHEMINFORMATICS
(2021)
Article
Computer Science, Information Systems
Radek Barvir, Alena Vondrakova, Jan Brus
Summary: Despite growing efficiency in map design, tactile mapping remains on the periphery of mainstream cartography. Tactile maps are crucial for visually impaired individuals, but their complex production and limited user base have hindered widespread adoption. Advancements in technologies like 3D printing offer new possibilities to make tactile map production more efficient and contemporary.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Biotechnology & Applied Microbiology
Tesia Bobrowski, Lu Chen, Richard T. Eastman, Zina Itkin, Paul Shinn, Catherine Z. Chen, Hui Guo, Wei Zheng, Sam Michael, Anton Simeonov, Matthew D. Hall, Alexey Zakharov, Eugene N. Muratov
Summary: This study identified 16 synergistic drug combinations against SARS-CoV-2, with nitazoxanide combined with remdesivir, amodiaquine, or umifenovir showing significant synergy. However, the combination of remdesivir with lysosomotropic drugs like hydroxychloroquine exhibited strong antagonism. The results highlight the potential of drug repurposing and preclinical testing of drug combinations for treating COVID-19.
Article
Biochemical Research Methods
Emanuele Di Lieto, Angela Serra, Simo Iisakki Inkala, Laura Aliisa Saarimaki, Giusy del Giudice, Michele Fratello, Veera Hautanen, Maria Annala, Antonio Federico, Dario Greco
Summary: Biological data repositories provide valuable research evidence, but the lack of a common metadata annotation strategy results in low FAIRness of the data. ESPERANTO is an innovative framework that enables the standardized harmonization and integration of toxicogenomics metadata, increasing their FAIRness in a Good Laboratory Practice-compliant fashion. The tool facilitates user-friendly metadata harmonization, regardless of the user's background and expertise. ESPERANTO and its user manual are freely available for academic use.
Article
Engineering, Biomedical
A. van Kootwijk, V Moosabeiki, M. Cruz Saldivar, H. Pahlavani, M. A. Leeflang, S. Kazemivand Niar, P. Pellikaan, B. P. Jonker, S. M. Ahmadi, E. B. Wolvius, N. Tumer, M. J. Mirzaali, J. Zhou, A. A. Zadpoor
Summary: This study aims to design patient-specific mandibular reconstruction implants and evaluate the effects of topology optimization on their biomechanical performance. The results show that the designed implants have good mechanical performance, and the proposed workflow is capable of developing high-precision implants with superior mechanical performance, which can greatly improve cost- and time-effective pre-surgical planning and enhance surgical outcome.
JOURNAL OF THE MECHANICAL BEHAVIOR OF BIOMEDICAL MATERIALS
(2022)
Article
Computer Science, Information Systems
Xiaoyuan Guo, Judy Wawira Gichoya, Hari Trivedi, Saptarshi Purkayastha, Imon Banerjee
Summary: Automated curation of noisy external medical data is necessary for validating AI technologies using clean, annotated data from various sources. Detecting the variance between internal and external data sources is crucial, as different distributions can impact AI model performance.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Tomas Petricek, Gerrit J. J. van den Burg, Alfredo Nazabal, Taha Ceritli, Ernesto Jimenez-Ruiz, Christopher K. I. Williams
Summary: Data wrangling tasks can account for up to 80% of data engineering work and remain manual despite advancements in AI. To streamline data wrangling, we introduce AI assistants, which guide analysts through specific tasks by recommending suitable data transformations based on interaction. We implement AI assistants for common data wrangling tasks and make them accessible in an open-source notebook environment. Quantitative and qualitative evaluations demonstrate the effectiveness of our AI assistants in simplifying complex tasks.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Biochemistry & Molecular Biology
Barbara Zdrazil, Eloy Felix, Fiona Hunter, Emma J. Manners, James Blackshaw, Sybilla Corbett, Marleen de Veij, Harris Ioannidis, David Mendez Lopez, Juan F. Mosquera, Maria Paula Magarinos, Nicolas Bosc, Ricardo Arcila, Tevfik Kiziloren, Anna Gaulton, A. Patricia Bento, Melissa F. Adasme, Peter Monecke, Gregory A. Landrum, Andrew R. Leach
Summary: ChEMBL is a curated resource of bioactive molecules with drug-like properties. It has evolved significantly in size and diversity of data types over time. The inclusion of new datasets has expanded the bioactivity data available and added new features to ChEMBL.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Environmental Sciences
Nikolai G. Nikolov, Ana C. V. E. Nissen, Eva B. Wedebye
Summary: Large screening programs like US Tox21 are sharing in vitro experimental results for various endpoints related to human health. To ensure accurate (Q)SAR modelling, it is crucial to clearly define the endpoint and extract the most reliable data points. This study presents a comprehensive data curation procedure for interpreting in vitro experimental data sets, including selecting actives based on curve fitting quality, activity magnitude, and potency cut-offs, as well as considering factors like non-cytotoxicity and assay signal interference.
ENVIRONMENTAL TOXICOLOGY AND PHARMACOLOGY
(2023)
Article
Engineering, Environmental
Elisa Giaccone, Fabio Oriani, Marj Tonini, Christophe Lambiel, Gregoire Mariethoz
Summary: This study compares the performance of two data-driven algorithms, Direct Sampling (DS) and Random Forest (RF), in geomorphological classification. Both DS and RF show similar levels of accuracy and Kappa values, making them suitable for semi-automated geomorphological mapping in alpine environments.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Physics, Multidisciplinary
G. Angloher, S. Banik, D. Bartolot, G. Benato, A. Bento, A. Bertolini, R. Breier, C. Bucci, J. Burkhart, L. Canonica, A. D'Addabbo, S. Di Lorenzo, L. Einfalt, A. Erb, F. V. Feilitzsch, N. Ferreiro Iachellini, S. Fichtinger, D. Fuchs, A. Fuss, A. Garai, V. M. Ghete, S. Gerster, P. Gorla, P. V. Guillaumon, S. Gupta, D. Hauff, M. Jeskovsky, J. Jochum, M. Kaznacheeva, A. Kinast, H. Kluck, H. Kraus, M. Lackner, A. Langenkaemper, M. Mancuso, L. Marini, L. Meyer, V. Mokina, A. Nilima, M. Olmi, T. Ortmann, C. Pagliarone, L. Pattavina, F. Petricca, W. Potzel, P. Povinec, F. Proebst, F. Pucci, F. Reindl, D. Rizvanovic, J. Rothe, K. Schaeffner, J. Schieck, D. Schmiedmayer, S. Schoenert, C. Schwertner, M. Stahlberg, L. Stodolsky, C. Strandhagen, R. Strauss, I. Usherov, F. Wagner, M. Willers, V. Zema, W. Waltenberger
Summary: The CRESST experiment uses cryogenic calorimeters to measure nuclear recoils induced by dark matter particles, and proposes to automate the signal cleaning process with neural networks. With a data set of over one million labeled records, four neural network architectures are tested for their capability to learn the cleaning task. The best model achieves a balanced accuracy of 0.932 on the test set, confirming its suitability for the data cleaning task.
EUROPEAN PHYSICAL JOURNAL PLUS
(2023)
Article
Chemistry, Physical
Tucker Burgin, Samuel Ellis, Heather B. Mayes
Summary: Transition path sampling methods are powerful but often limited to experts. ATESA is an open-source software that automates the transition path sampling workflow, making it accessible to researchers new to this approach.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2023)
Article
Computer Science, Artificial Intelligence
Xueying Shi, Yueming Jin, Qi Dou, Pheng-Ann Heng
Summary: In this paper, a novel two-stage Semi-Supervised Learning method SurgSSL is proposed for label-efficient Surgical workflow recognition, leveraging the inherent knowledge in unlabeled data for improved performance. The method first implicitly excavates motion knowledge from unlabeled data and then performs explicit excavation using pre-knowledge pseudo labeling, achieving superior results compared to existing methods.
MEDICAL IMAGE ANALYSIS
(2021)
Article
Geosciences, Multidisciplinary
R. Guardo, L. De Siena
Summary: Active seismic experiments are vital for improving the interpretation of volcanic processes by reconstructing the subsurface structure of volcanoes with unprecedented resolution. This study presents a semi-automated workflow for data selection and inversion of amplitude-dependent information, which can produce high-quality seismic images and provide detailed information about volcanic structures.
FRONTIERS IN EARTH SCIENCE
(2022)
Article
Chemistry, Multidisciplinary
Bouhedjar Khalid, Hamida Ghorab, Abdelhamid Benkhemissa
Summary: In the past two decades, there has been a constant increase in the volumes of chemical and biological data. Converting these data sets into knowledge is a costly and time-consuming process. To address this issue, a workflow technology with platforms like KNIME has been developed to facilitate searching and extracting hidden information from heterogeneous data sources. In this study, KNIME was proposed as an automated solution for data curation, development, and validation of predictive QSAR models from a large dataset. A case study was conducted using 250250 structures from the NCI database to improve existing log P calculation algorithms.
JOURNAL OF THE INDIAN CHEMICAL SOCIETY
(2022)
Article
Chemistry, Medicinal
Domenico Gadaleta, Marco Marzo, Andrey Toropov, Alla Toropova, Giovanna J. Lavado, Sylvia E. Escher, Jean Lou C. M. Dorne, Emilio Benfenati
Summary: This study attempted to model NO(A)EL and LO(A)EL simultaneously, integrating the models to improve performance. The strategy presented here proved effective in assessing RDT of chemicals using in silico models.
CHEMICAL RESEARCH IN TOXICOLOGY
(2021)
Article
Biochemistry & Molecular Biology
Cosimo Toma, Alberto Manganaro, Giuseppa Raitano, Marco Marzo, Domenico Gadaleta, Diego Baderna, Alessandra Roncaglioni, Nynke Kramer, Emilio Benfenati
Summary: This study developed classification and regression models for inhalation and oral slope factors, which showed good accuracy and R^2 values. These models may assist regulatory authorities in decision-making and weighing evidence in chemical safety assessments.
Correction
Environmental Sciences
Kamel Mansouri, Agnes Karmaus, Jeremy Fitzpatrick, Grace Patlewicz, Prachi Pradeep, Domenico Alberga, Nathalie Alepee, Timothy E. H. Allen, Dave Allen, Vinicius M. Alves, Carolina H. Andrade, Tyler R. Auernhammer, Davide Ballabio, Shannon Bell, Emilio Benfenati, Sudin Bhattacharya, Joyce V. Bastos, Stephen Boyd, J. B. Brown, Stephen J. Capuzzi, Yaroslav Chushak, Heather Ciallella, Alex M. Clark, Viviana Consonni, Pankaj R. Daga, Sean Ekins, Sherif Farag, Maxim Fedorov, Denis Fourches, Domenico Gadaleta, Feng Gao, Jeffery M. Gearhart, Garett Goh, Jonathan M. Goodman, Francesca Grisoni, Christopher M. Grulke, Thomas Hartung, Matthew Hirn, Pavel Karpov, Alexandru Korotcov, Giovanna J. Lavado, Michael Lawless, Xinhao Li, Thomas Luechtefeld, Filippo Lunghini, Giuseppe F. Mangiatordi, Gilles Marcou, Dan Marsh, Todd Martin, Andrea Mauri, Eugene N. Muratov, Glenn J. Myatt, Dac-Trung Nguyen, Orazio Nicolotti, Reine Note, Paritosh Pande, Amanda K. Parks, Tyler Peryea, Ahsan Polash, Robert Rallo, Alessandra Roncaglioni, Craig Rowlands, Patricia Ruiz, Daniel Russo, Ahmed Sayed, Risa Sayre, Timothy Sheils, Charles Siegel, Arthur C. Silva, Anton Simeonov, Sergey Sosnin, Noel Southall, Judy Strickland, Yun Tang, Brian Teppen, Igor V. Tetko, Dennis Thomas, Valery Tkachenko, Roberto Todeschini, Cosimo Toma, Ignacio Tripodi, Daniela Trisciuzzi, Alexander Tropsha, Alexandre Varnek, Kristijan Vukovic, Zhongyu Wang, Liguo Wang, Katrina M. Waters, Andrew J. Wedlake, Sanjeeva J. Wijeyesakere, Dan Wilson, Zijun Xiao, Hongbin Yang, Gergely Zahoranszky-Kohalmi, Alexey V. Zakharov, Fagen F. Zhang, Zhen Zhang, Tongan Zhao, Hao Zhu, Kimberley M. Zorn, Warren Casey, Nicole C. Kleinstreuer
ENVIRONMENTAL HEALTH PERSPECTIVES
(2021)
Article
Pharmacology & Pharmacy
Domenico Gadaleta, Luca D'Alessandro, Marco Marzo, Emilio Benfenati, Alessandra Roncaglioni
Summary: The thyroid system plays a crucial role in physiological processes but can be disrupted by xenobiotics and contaminants, leading to various diseases. This study introduces QSAR models to predict the TPO inhibitory potential, developed using machine learning methods and validated rigorously internally and externally.
FRONTIERS IN PHARMACOLOGY
(2021)
Article
Environmental Sciences
Giovanna J. Lavado, Diego Baderna, Domenico Gadaleta, Marta Ultre, Kunal Roy, Emilio Benfenati
Summary: Research interest in environmental toxicity assessment using T. platyurus has increased, but there are currently no computational models to predict acute toxicity in this organism. This study developed QSAR models for predicting acute toxicity in T. platyurus, following OECD principles and using advanced machine learning techniques to achieve promising statistical quality in the dataset.
Correction
Environmental Sciences
Kamel Mansouri, Agnes L. Karmaus, Jeremy Fitzpatrick, Grace Patlewicz, Prachi Pradeep, Domenico Alberga, Nathalie Alepee, Timothy E. H. Allen, Dave Allen, Vinicius M. Alves, Carolina H. Andrade, Tyler R. Auernhammer, Davide Ballabio, Shannon Bell, Emilio Benfenati, Sudin Bhattacharya, Joyce V. Bastos, Stephen Boyd, J. B. Brown, Stephen J. Capuzzi, Yaroslav Chushak, Heather Ciallella, Alex M. Clark, Viviana Consonni, Pankaj R. Daga, Sean Ekins, Sherif Farag, Maxim Fedorov, Denis Fourches, Domenico Gadaleta, Feng Gao, Jeffery M. Gearhart, Garett Goh, Jonathan M. Goodman, Francesca Grisoni, Christopher M. Grulke, Thomas Hartung, Matthew Hirn, Pavel Karpov, Alexandru Korotcov, Giovanna J. Lavado, Michael Lawless, Xinhao Li, Thomas Luechtefeld, Filippo Lunghini, Giuseppe F. Mangiatordi, Gilles Marcou, Dan Marsh, Todd Martin, Andrea Mauri, Eugene N. Muratov, Glenn J. Myatt, Dac-Trung Nguyen, Orazio Nicolotti, Reine Note, Paritosh Pande, Amanda K. Parks, Tyler Peryea, Ahsan H. Polash, Robert Rallo, Alessandra Roncaglioni, Craig Rowlands, Patricia Ruiz, Daniel P. Russo, Ahmed Sayed, Risa Sayre, Timothy Sheils, Charles Siegel, Arthur C. Silva, Anton Simeonov, Sergey Sosnin, Noel Southall, Judy Strickland, Yun Tang, Brian Teppen, Igor V. Tetko, Dennis Thomas, Valery Tkachenko, Roberto Todeschini, Cosimo Toma, Ignacio Tripodi, Daniela Trisciuzzi, Alexander Tropsha, Alexandre Varnek, Kristijan Vukovic, Zhongyu Wang, Liguo Wang, Katrina M. Waters, Andrew J. Wedlake, Sanjeeva J. Wijeyesakere, Dan Wilson, Zijun Xiao, Hongbin Yang, Gergely Zahoranszky-Kohalmi, Alexey V. Zakharov, Fagen F. Zhang, Zhen Zhang, Tongan Zhao, Hao Zhu, Kimberley M. Zorn, Warren Casey, Nicole C. Kleinstreuer
ENVIRONMENTAL HEALTH PERSPECTIVES
(2021)
Article
Biochemistry & Molecular Biology
Cosimo Toma, Claudia I. Cappelli, Alberto Manganaro, Anna Lombardo, Juergen Arning, Emilio Benfenati
Summary: This study developed predictive models for acute and chronic toxicities in Raphidocelis subcapitata, Daphnia magna, and fish, with the random forest machine learning approach yielding the best results. The models showed good statistical quality for all endpoints, and are freely available for use as individual models in the VEGA platform and for prioritization in JANUS software.
Article
Biochemistry & Molecular Biology
Domenico Gadaleta, Nicoleta Spinu, Alessandra Roncaglioni, Mark T. D. Cronin, Emilio Benfenati
Summary: Developmental and adult/ageing neurotoxicity is an important area for chemical risk assessment. This study proposes a screening method using multiple QSAR models and AOP networks to predict neurotoxicity. The results show that the predictive performances of the integrated computational approach are comparable to traditional methods based on chemical descriptors and structural fingerprints, making it suitable for large-scale screening and prioritization of chemicals.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Toxicology
Sylvia E. Escher, Alejandro Aguayo-Orozco, Emilio Benfenati, Annette Bitsch, Thomas Braunbeck, Katharina Brotzmann, Frederic Bois, Bart van der Burg, Jose Castel, Thomas Exner, Domenico Gadaleta, Iain Gardner, Daria Goldmann, Oliver Hatley, Nazanin Golbamaki, Rabea Graepel, Paul Jennings, Alice Limonciel, Anthony Long, Richard Maclennan, Enrico Mombelli, Ulf Norinder, Sankalp Jain, Liliana Santos Capinha, Olivier T. Taboureau, Laia Tolosa, Nanette G. Vrijenhoek, Barbara M. A. Van Vugt-Lussenburg, Paul Walker, Bob van de Water, Matthias Wehr, Andrew White, Barbara Zdrazil, Ciaran Fisher
Summary: Read-across approaches may not provide sufficient evidence on a common mode of action across category members. A case study on branched aliphatic carboxylic acids shows the potential to induce hepatic steatosis. By analyzing gene expression patterns and adverse outcome pathways, researchers were able to confirm biological similarity and design an in vitro testing battery to systematically investigate a common mode of action among the compounds.
TOXICOLOGY IN VITRO
(2022)
Article
Biochemistry & Molecular Biology
Gianluca Selvestrel, Giovanna J. Lavado, Alla P. Toropova, Andrey A. Toropov, Domenico Gadaleta, Marco Marzo, Diego Baderna, Emilio Benfenati
Summary: The risk characterization of chemicals depends on the determination of repeated-dose toxicity (RDT), which involves the identification of the no-observed-adverse-effect level (NOAEL) and the lowest-observed-adverse-effect level (LOAEL). In vivo tests for RDT are time-consuming and expensive, making in silico models an attractive and challenging alternative. This study developed and validated eight in silico models for predicting NOAEL and LOAEL, focusing on systemic and organ-specific toxicity.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2022)
Article
Pharmacology & Pharmacy
Pietro Delre, Giovanna J. Lavado, Giuseppe Lamanna, Michele Saviano, Alessandra Roncaglioni, Emilio Benfenati, Giuseppe Felice Mangiatordi, Domenico Gadaleta
Summary: This study developed highly predictive models of hERG-mediated cardiotoxicity using machine learning algorithms. The models were trained and validated using curated compounds from a freely accessible database. The study also proposed a new computational workflow for building such models. The results showed that these models outperformed commonly used models in the literature.
FRONTIERS IN PHARMACOLOGY
(2022)
Article
Biochemistry & Molecular Biology
Alberto Danieli, Erika Colombo, Giuseppa Raitano, Anna Lombardo, Alessandra Roncaglioni, Alberto Manganaro, Alessio Sommovigo, Edoardo Carnesecchi, Jean-Lou C. M. Dorne, Emilio Benfenati
Summary: A thorough assessment of in silico models and their applicability domain is crucial for utilizing new approach methodologies (NAMs) in chemical risk assessment and building users' confidence. The VEGA tool is examined in this study to evaluate the applicability domain of in silico models, demonstrating its efficiency in identifying less accurate predictions for various toxicological endpoints. The tool evaluates chemical structures and related features, providing valuable insights for both regression models and classifiers.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2023)
Article
Biochemistry & Molecular Biology
Ana Yisel Caballero Alfonso, Chayawan Chayawan, Domenico Gadaleta, Alessandra Roncaglioni, Emilio Benfenati
Summary: The reduction and replacement of in vivo tests have become crucial in terms of resources and animal benefits. The read-across approach reduces the number of substances to be tested, exploiting existing experimental data to predict the properties of untested substances. In this paper, a workflow is introduced to support analogue identification for read-across. The workflow combines multiple similarity metrics to improve the predictions of toxicity.
Article
Environmental Sciences
Kamel Mansouri, Agnes L. Karmaus, Jeremy Fitzpatrick, Grace Patlewicz, Prachi Pradeep, Domenico Alberga, Nathalie Alepee, Timothy E. H. Allen, Dave Allen, Vinicius M. Alves, Carolina H. Andrade, Tyler R. Auernhammer, Davide Ballabio, Shannon Bell, Emilio Benfenati, Sudin Bhattacharya, Joyce Bastos, Stephen Boyd, J. B. Brown, Stephen J. Capuzzi, Yaroslav Chushak, Heather Ciallella, Alex M. Clark, Viviana Consonni, Pankaj R. Daga, Sean Ekins, Sherif Farag, Maxim Fedorov, Denis Fourches, Domenico Gadaleta, Feng Gao, Jeffery M. Gearhart, Garett Goh, Jonathan M. Goodman, Francesca Grisoni, Christopher M. Grulke, Thomas Hartung, Matthew Hirn, Pavel Karpov, Alexandru Korotcov, Giovanna J. Lavado, Michael Lawless, Xinhao Li, Thomas Luechtefeld, Filippo Lunghini, Giuseppe F. Mangiatordi, Gilles Marcou, Dan Marsh, Todd Martin, Andrea Mauri, Eugene N. Muratov, Glenn J. Myatt, Dac-Trung Nguyen, Orazio Nicolotti, Reine Note, Paritosh Pande, Amanda K. Parks, Tyler Peryea, Ahsan H. Polash, Robert Rallo, Alessandra Roncaglioni, Craig Rowlands, Patricia Ruiz, Daniel P. Russo, Ahmed Sayed, Risa Sayre, Timothy Sheils, Charles Siegel, Arthur C. Silva, Anton Simeonov, Sergey Sosnin, Noel Southall, Judy Strickland, Yun Tang, Brian Teppen, Igor Tetko, Dennis Thomas, Valery Tkachenko, Roberto Todeschini, Cosimo Toma, Ignacio Tripodi, Daniela Trisciuzzi, Alexander Tropsha, Alexandre Varnek, Kristijan Vukovic, Zhongyu Wang, Liguo Wang, Katrina M. Waters, Andrew J. Wedlake, Sanjeeva J. Wijeyesakere, Dan Wilson, Zijun Xiao, Hongbin Yang, Gergely Zahoranszky-Kohalmi, Alexey Zakharov, Fagen F. Zhang, Zhen Zhang, Tongan Zhao, Hao Zhu, Kimberley M. Zorn, Warren Casey, Nicole C. Kleinstreuer
Summary: The international collaboration in developing in silico models for predicting acute oral toxicity, resulting in the CATMoS, has demonstrated high performance in terms of accuracy and robustness. This modeling suite is being evaluated by regulatory agencies as a potential replacement for in vivo rat acute oral toxicity studies.
ENVIRONMENTAL HEALTH PERSPECTIVES
(2021)
Article
Chemistry, Medicinal
Claudia Ileana Cappelli, Serena Manganelli, Cosimo Toma, Emilio Benfenati, Enrico Mombelli
Summary: The study developed QSAR models for adipose tissue:blood partition coefficient using rat in vivo data, and showed that an integrated model combining multiple single models outperformed the individual ones, with an external mean absolute error of 0.26 and 84% coverage, comparable to experimental variability.
MOLECULAR INFORMATICS
(2021)