Article
Multidisciplinary Sciences
Andrew K. C. Wong, Pei-Yuan Zhou, Zahid A. Butt
Summary: Machine Learning has made impressive advances across many applications, but relational datasets present challenges. The PDD system can discover explicit patterns from data, improving prediction accuracy and facilitating transparent interpretation of knowledge.
SCIENTIFIC REPORTS
(2021)
Article
Multidisciplinary Sciences
Taseef Hasan Farook, Saif Ahmed, Nafij Bin Jamayet, Farah Rashid, Aparna Barman, Preena Sidhu, Pravinkumar Patil, Awsaf Mahmood Lisan, Sumaya Zabin Eusufzai, James Dudley, Umer Daood
Summary: This study developed a 3D convolutional neural network to generate partial dental crowns for restorative dentistry. In phase 1, the effectiveness of desktop laser and intraoral scanners was evaluated, and intraoral scans were chosen for further analysis. In phase 2, tooth preparations were digitally synthesized and PDCs were designed using CAD workflows. The most accurate PDCs were then used to train the neural network in phase 3, leading to the development of a proof-of-concept 3D-CNN for generating PDCs in CAD.
SCIENTIFIC REPORTS
(2023)
Article
Chemistry, Multidisciplinary
Yuying Jia, Xuan Hou, Zhongwei Wang, Xiangang Hu
Summary: The article discusses the application of machine learning in nanomaterial research, emphasizing its importance in big data processing and high-throughput screening, as well as its application in prediction and interaction in nanobiology.
ACS SUSTAINABLE CHEMISTRY & ENGINEERING
(2021)
Article
Oncology
Ganggang Bai, Chuance Sun, Ziang Guo, Yangjing Wang, Xincheng Zeng, Yuhong Su, Qi Zhao, Buyong Ma
Summary: Therapeutic antibodies are a successful treatment for human diseases, but their design and discovery are challenging and time-consuming. Artificial intelligence has made significant advancements in these areas, particularly in computational predictors of antibody structure and developability. Machine learning offers new possibilities for fully computational antibody design.
SEMINARS IN CANCER BIOLOGY
(2023)
Article
Chemistry, Physical
Rui Ding, Yawen Chen, Ping Chen, Ran Wang, Jiankang Wang, Yiqin Ding, Wenjuan Yin, Yide Liu, Jia Li, Jianguo Liu
Summary: Machine learning is introduced to provide insights into catalyst design, revealing a strong relationship between pyridinic nitrogen species and catalytic performance. The synthesis level significance of pyrolysis time, which has not been extensively studied, is also highlighted.
Article
Biochemical Research Methods
Hao Lv, Lei Shi, Joshua William Berkenpas, Fu-Ying Dao, Hasan Zulfiqar, Hui Ding, Yang Zhang, Liming Yang, Renzhi Cao
Summary: AI and ML present promising solutions to combat the COVID-19 pandemic by accelerating the discovery and optimization of new antivirals. Despite challenges, they offer new insights and have the potential to effectively control the outbreak.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Chemistry, Medicinal
Alexander K. Hurben, Luke Erber
Summary: This article provides a broad overview of AI research in the field of chemical toxicology, focusing on its applications in drug design, development, and safety assessment.
CHEMICAL RESEARCH IN TOXICOLOGY
(2022)
Review
Cell Biology
Xiangxiang Zeng, Fei Wang, Yuan Luo, Seung-Gu Kang, Jian Tang, Felice C. Lightstone, Evandro F. Fang, Wendy Cornell, Ruth Nussinov, Feixiong Cheng
Summary: The recent advances of AI and deep generative models in medicinal applications, specifically in drug discovery and development, have proven their utility. This review provides an updated and accessible guide for the computational drug discovery and development community, discussing classical and newly developed AI approaches. The theoretical frameworks for representing chemical and biological structures and their applications are described, along with the challenges and future directions of multimodal deep generative models for accelerating drug discovery.
CELL REPORTS MEDICINE
(2022)
Article
Computer Science, Information Systems
Julien Meyer, April Khademi, Bernard Tetu, Wencui Han, Pria Nippak, David Remisch
Summary: This study aims to determine the reliance of pathologists on artificial intelligence (AI) and investigate whether providing information on AI influences this reliance. The results show that pathologists' accuracy is significantly higher with AI decision aids, and providing information on the algorithm does not significantly impact reliance. The study also finds that decisions are made faster when AI is provided.
JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION
(2022)
Review
Biochemistry & Molecular Biology
Sonal Priya, Garima Tripathi, Dev Bukhsh Singh, Priyanka Jain, Abhijeet Kumar
Summary: This review focuses on several machine learning approaches used in chemoinformatics, which have shown great potential in improving drug discovery. These approaches can effectively model various physicochemical properties of drugs and have achieved good accuracy in recent years.
CHEMICAL BIOLOGY & DRUG DESIGN
(2022)
Article
Automation & Control Systems
Peter Wang, Kui You, Yoong Hun Ong, Joe Ning Yeoh, Jerica Pang Qi Ong, Anh Thanh Lan Truong, Agata Blasiak, Edward Kai-Hua Chow, Dean Ho
Summary: The increase in global population and climate change pose challenges to global food security and supply chains. To sustainably improve food yield, the identification of compound combinations in peat moss that can enhance plant yield has been explored. The study found that combinations of 6-BAP/EDTA-Fe and HA/SWE significantly increased the yield of Amaranthus cruentus, and adjusting the concentration ratios of these combinations may further improve plant yield.
ADVANCED INTELLIGENT SYSTEMS
(2022)
Review
Environmental Studies
Dorota Kamrowska-Zaluska
Summary: This paper evaluates the potential application of urban big data analytics based on AI-related tools in city design and planning, discussing the implications of using artificial intelligence tools and geo-localised big data in solving research problems in urban planning and design as well as in planning practice.
Article
Computer Science, Hardware & Architecture
Dejan Milojicic, Phil Laplante
Summary: This special issue highlights the intersection of technology and sociopolitical factors, covering a wide range of topics from medicine and war to unmanned aircraft and software supply chains. It explores the interconnection of technologies in an increasingly complex world.
Article
Mathematics
Yujue Chen, He Hu
Summary: This paper proposes an artificial intelligence motion model based on the deep learning neural network instruction set architecture. By segmenting movements and recognizing the individual sub-movements, the model improves the accuracy of movement recognition. Experimental results demonstrate the feasibility and performance advantages of the proposed model.
JOURNAL OF MATHEMATICS
(2022)
Article
Optics
Mengwei Yuan, Gang Yang, Shijie Song, Luping Zhou, Robert Minasian, Xiaoke Yi
Summary: In this paper, a pre-trained-combined neural network (PTCN) is proposed as a comprehensive solution for the inverse design of an integrated photonic circuit. The PTCN model shows remarkable tolerance to the quantity and quality of the training data by utilizing both the initially pre-trained inverse and forward model with a joint training process.
Editorial Material
Chemistry, Medicinal
Atsushi Yoshimori, Hengwei Chen, Juergen Bajorath
FUTURE MEDICINAL CHEMISTRY
(2023)
Article
Biochemistry & Molecular Biology
Alec Lamens, Jurgen Bajorath
Summary: Compounds with multiple targets (MT-CPDs) are important in drug discovery, and computational approaches have been used to design or identify them. Machine learning models have been derived to distinguish between MT-CPDs and compounds with single-target activity (ST-CPDs). Surprisingly, it was found that models derived for ST-CPDs can accurately predict MT-CPDs, revealing a relationship between the two types of compounds.
Article
Biochemistry & Molecular Biology
Wojciech Pietrus, Rafal Kurczab, Dawid Warszycki, Andrzej J. J. Bojarski, Jurgen Bajorath
Summary: In this study, a total of 898 F-containing isomeric analog sets were identified and analyzed for structure-activity relationship (SAR) in the ChEMBL database. The results showed significant differences in affinity for some isomeric compounds against different aminergic GPCRs, and the change of fluorine position could lead to a significant change in potency. Additionally, a computational workflow was proposed to score the fluorine positions in the molecule.
Article
Pharmacology & Pharmacy
Jaidip Gill, Marie Moullet, Anton Martinsson, Filip Miljkovic, Beth Williamson, Rosalinda H. Arends, Venkatesh Pilla Reddy
Summary: This study investigated the use of regression-based machine learning to predict changes in drug exposure caused by pharmacokinetic drug-drug interactions. The results show that changes in drug exposure can be predicted with reasonable accuracy using this method, which has potential applications in drug-drug interaction risk assessment.
CPT-PHARMACOMETRICS & SYSTEMS PHARMACOLOGY
(2023)
Editorial Material
Chemistry, Medicinal
Juergen Bajorath
FUTURE MEDICINAL CHEMISTRY
(2023)
Article
Chemistry, Medicinal
Elena Xerxa, Filip Miljkovic, Juergen Bajorath
Summary: Large-scale analysis of public human and mouse protein kinase inhibitor (PKI) data revealed a significant number of human and mouse PKIs with reliable activity measurements. Human PKIs were found to exhibit coverage against a large number of kinases, with a substantial growth in the past years. Covalent PKIs containing acrylamide or heterocyclic urea warheads were particularly abundant, and they showed higher potency compared to structurally analogous PKIs. These findings have important implications for medicinal chemistry.
JOURNAL OF MEDICINAL CHEMISTRY
(2023)
Article
Biochemistry & Molecular Biology
Atsushi Yoshimori, Juergen Bajorath
Summary: In the field of drug design, very few studies have attempted the prediction of new active compounds from protein sequence data. This is mainly due to the challenging nature of this prediction task, as global protein sequence similarity has strong evolutionary and structural implications but is not directly related to ligand binding. However, the application of deep language models adapted from natural language processing provides new opportunities to attempt such predictions by linking amino acid sequences and chemical structures through textual molecular representations. In this study, a biochemical language model with a transformer architecture, named Motif2Mol, was introduced for the prediction of new active compounds based on sequence motifs of ligand binding sites. In a proof-of-concept application on inhibitors of more than 200 human kinases, Motif2Mol exhibited promising learning characteristics and an unprecedented ability to consistently reproduce known inhibitors of different kinases.
Article
Biochemistry & Molecular Biology
Tiago Janela, Kosuke Takeuchi, Juergen Bajorath
Summary: Prediction of potency of bioactive compounds is typically done using linear or nonlinear quantitative structure-activity relationship (QSAR) models. In this study, a novel approach called structure-potency fingerprint (SPFP) is introduced, which combines structural features and potency values into a single bit string representation. By using a conditional variational autoencoder (CVAE) with SPFPs, the potency module of test compounds can be accurately predicted using only their structure module. The SPFP-CVAE approach achieves comparable accuracy to support vector regression (SVR) and deep neural networks in predicting compounds' activity classes and potency values.
Article
Computer Science, Artificial Intelligence
Peizhen Bai, Filip Miljkovic, Bino John, Haiping Lu
Summary: DrugBAN is a deep bilinear attention network framework that explicitly learns the local interactions between drugs and targets, and adapts to out-of-distribution data. It achieves the best performance on three benchmark datasets compared to five state-of-the-art baseline models. The visualized bilinear attention map provides interpretable insights from prediction results.
NATURE MACHINE INTELLIGENCE
(2023)
Article
Chemistry, Medicinal
Nicola Gambacorta, Fulvio Ciriaco, Nicola Amoroso, Cosimo Damiano Altomare, Ju''rgen Bajorath, Orazio Nicolotti
Summary: In this study, a CIRCE compound prediction platform was developed based on explainable machine learning to support the design of selective CB1R and CB2R ligands. The platform achieved about 80% accuracy in test calculations and provided rationalized explanations for the predictions. CIRCE is freely available as a web-based prediction platform.
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2023)
Article
Biochemistry & Molecular Biology
Alec Lamens, Juergen Bajorath
Summary: In pharmaceutical research, black box predictions from machine learning models hinder their application in guiding experimental work. This study presents a test system that combines two explainable artificial intelligence methods to better understand prediction outcomes and provide chemically intuitive explanations for model decisions.
Article
Biochemistry & Molecular Biology
Elena Xerxa, Oliver Laufkoetter, Jurgen Bajorath
Summary: Protein kinase inhibitors (PKIs) are widely studied as drug candidates in drug discovery, with increasing interest in allosteric PKIs (APKIs) and covalent PKIs (CPKIs). The popularity of PKIs for therapeutic intervention has led to the accumulation of large volumes of activity data, enabling large-scale computational analysis. CPKIs with certain reactive groups showed significantly higher potency compared to non-covalent PKIs, but there was no general increase in promiscuity. Additionally, new APKIs have been identified, allowing for structure-based investigation of PK inhibition by covalent-allosteric mechanisms.
Review
Chemistry, Medicinal
Juergen Bajorath
Summary: This article discusses the opportunities and methods of applying chemical language models (CLMs) in drug discovery. CLMs can be developed using recurrent neural networks or transformer architectures, and attention mechanisms are used to improve predictive performance. CLMs can be used for constrained generative modeling and the prediction of chemical reactions or drug-target interactions. Since CLMs can learn mappings of different types of sequences and are applicable to any compound or target data presented in a sequential format and tokenized, they have a wide range of applications.
MOLECULAR INFORMATICS
(2023)
Article
Computer Science, Artificial Intelligence
Andrea Mastropietro, Giuseppe Pasculli, Juergen Bajorath
Summary: In drug design, graph neural networks (GNNs) are used to predict compound potency by analyzing graph representations of protein-ligand interactions. The study reveals that GNNs are influenced by ligand memorization during learning and certain GNN architectures prioritize interaction information for predicting high affinities. While GNNs do not comprehensively account for protein-ligand interactions and physical reality, they provide a helpful balance between ligand memorization and learning of interaction patterns.
NATURE MACHINE INTELLIGENCE
(2023)
