Review
Biochemistry & Molecular Biology
Marco Del Giudice, Serena Peirone, Sarah Perrone, Francesca Priante, Fabiola Varese, Elisa Tirtei, Franca Fagioli, Matteo Cereda
Summary: Artificial intelligence is used in cancer research to analyze large-scale RNA-sequencing datasets, disentangle inter- and intra-tumor heterogeneity, and contribute to personalized treatments.
INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES
(2021)
Article
Ethics
Charlotte Stix
Summary: This paper proposes a novel framework for the development of 'Actionable Principles for AI', drawing on elements from the development process of the European Commission's High Level Expert Group on AI's Ethics Guidelines for Trustworthy AI. The paper suggests three propositions for the formation of a prototype framework, including preliminary landscape assessments, multi-stakeholder participation and cross-sectoral feedback, and mechanisms to support implementation and operationalizability.
SCIENCE AND ENGINEERING ETHICS
(2021)
Article
Biochemistry & Molecular Biology
Mathieu J. Dupont, Francois Major
Summary: D-ORB is a system that builds non-pseudoknotted RNA family models by identifying overrepresented motifs in the secondary conformational landscapes of the family compared to unrelated sequences.
JOURNAL OF MOLECULAR BIOLOGY
(2023)
Article
Medical Informatics
Michaela Soellner, Joerg Koenigstorfer
Summary: The study assesses the impact of personal information request sources on individuals' willingness to disclose health information. It reveals that university hospitals prioritize altruism and are more appealing to individuals, while pharmaceutical companies prioritize egoism and individuals tend to conceal information. The appeal of the information and the credibility of the endorsers influence individuals' willingness to disclose personal information.
BMC MEDICAL INFORMATICS AND DECISION MAKING
(2022)
Article
Health Care Sciences & Services
Roman Zeleznik, Jakob Weiss, Jana Taron, Christian Guthier, Danielle S. Bitterman, Cindy Hancox, Benjamin H. Kann, Daniel W. Kim, Rinaa S. Punglia, Jeremy Bredfeldt, Borek Foldyna, Parastou Eslami, Michael T. Lu, Udo Hoffmann, Raymond Mak, Hugo J. W. L. Aerts
Summary: The study evaluated the use of a deep-learning system for heart segmentation on CT scans in radiation oncology treatment planning. The system, trained with multi-center data and validated in a real-world dataset, showed improved segmentation time and agreement compared to manual methods. The results indicate that deep-learning algorithms can be successfully applied across medical specialties to enhance clinical care.
NPJ DIGITAL MEDICINE
(2021)
Article
Biochemistry & Molecular Biology
Alexander H. H. Thieme, Yuanning Zheng, Gautam Machiraju, Chris Sadee, Mirja Mittermaier, Maximilian Gertler, Jorge L. Salinas, Krithika Srinivasan, Prashnna Gyawali, Francisco Carrillo-Perez, Angelo Capodici, Maximilian Uhlig, Daniel Habenicht, Anastassia Loeser, Maja Kohler, Maximilian Schuessler, David Kaul, Johannes Gollrad, Jackie Ma, Christoph Lippert, Kendall Billick, Isaac Bogoch, Tina Hernandez-Boussard, Pascal Geldsetzer, Olivier Gevaert
Summary: A deep-learning algorithm, MPXV-CNN, was developed to identify skin lesions caused by the mpox virus for early detection and mitigation. It demonstrated a sensitivity of 0.83-0.91 and a specificity of 0.965-0.898 across different datasets. The algorithm was robust in classifying lesions on various skin tones and body regions, and a web-based app was developed for patient guidance.
Article
Business
Waymond Rodgers, Robert Hudson, Fotini Economou
Summary: This paper introduces a new approach to understanding bankers' risk-taking behavior by using behavioral finance and a unique decision-making model. The results indicate that bankers' risk assessments differ in evaluating financial information regarding loans.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2023)
Article
Multidisciplinary Sciences
Boris B. Slavin
Summary: This study proposes an architectural approach for constructing a conceptual model of artificial general intelligence (AGI). The approach, commonly used for modeling enterprise information systems (IS), can also be applied to describe other complex open systems. The paper suggests a three-layer, five-level model of AGI, with two levels at the technological layer, two levels at the relationship layer, and the uppermost level representing general intelligence. The components of each higher layer are connected to components of the lower layers, forming the AGI model. The social layer emphasizes the subjectivity and decision-making abilities of AI, while the upper layer focuses on self-identification and understanding of AGI's place. The hypothesis suggests that limitation of the life cycle is an important condition for the actualization of intelligence.
Editorial Material
Biochemistry & Molecular Biology
Zachi I. Attia, Paul A. Friedman
Summary: By applying artificial intelligence to electrocardiograms recorded by patients using Apple watches, we conducted a prospective, digital, remote study to enable large-scale screening for left ventricular dysfunction, a serious and under-detected cardiac disease. The study found that patients engaged with the system and that the watch electrocardiograms effectively screened for the disease.
Editorial Material
Biochemistry & Molecular Biology
Eric Wu, Kevin Wu, Roxana Daneshjou, David Ouyang, Daniel E. Ho, James Zou
Summary: A comprehensive overview of medical AI devices approved by the US Food and Drug Administration sheds light on limitations of the evaluation process that may mask vulnerabilities of devices when deployed on patients.
Article
Chemistry, Multidisciplinary
Morgan Chandler, Sankalp Jain, Justin Halman, Enping Hong, Marina A. Dobrovolskaia, Alexey Zakharov, Kirill A. Afonin
Summary: Nucleic acid nanoparticles (NANPs) designed to interact with the human immune system can provide innovative therapeutic strategies. A computational model based on the transformer architecture has been developed to predict the immune activities of NANPs, which can aid in addressing public health challenges and promoting the development of novel biomedical tools.
Article
Medical Informatics
Lili Feng, Zhenyu Liu, Chaofeng Li, Zhenhui Li, Xiaoying Lou, Lizhi Shao, Yunlong Wang, Yan Huang, Haiyang Chen, Xiaolin Pang, Shuai Liu, Fang He, Jian Zheng, Xiaochun Meng, Peiyi Xie, Guanyu Yang, Yi Ding, Mingbiao Wei, Jingping Yun, Mien-Chie Hung, Weihua Zhou, Dantel R. Wahl, Ping Lan, Jie Tian, Xiangbo Wan
Summary: Accurate prediction of pathological complete response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer was achieved using an artificial intelligence radiopathomics integrated model based on pretreatment MRI and H&E-stained biopsy slides. The model, RAPIDS, showed high accuracy and outperformed single-modality prediction models, providing a novel tool for individualized management of locally advanced rectal cancer.
LANCET DIGITAL HEALTH
(2022)
Review
Biochemistry & Molecular Biology
Marcos Morgan, Lokesh Kumar, Yin Li, Marine Baptissart
Summary: Multiple RNA pathways are essential in producing functional sperm, with a particular focus on 3' end modifications. Studies have shown a correlation between RNA 3' end metabolism and male germ cell differentiation, as well as the importance of RNA pathways in maintaining genomic integrity.
CELLULAR AND MOLECULAR LIFE SCIENCES
(2021)
Article
Biochemical Research Methods
Natalia A. Szulc, Zuzanna Mackiewicz, Janusz M. Bujnicki, Filip Stefaniak
Summary: We developed a software called fingeRNAt for detecting non-covalent bonds formed within nucleic acid-ligand complexes. By using SIFts and machine learning methods, we were able to predict the binding of small molecules to RNA with higher accuracy compared to classic scoring functions. Additionally, we employed Explainable Artificial Intelligence (XAI) methods to better understand the decision-making process and quantitatively analyze the impact of interactions.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Construction & Building Technology
Mollaeiubli Takhmasib, Hyuk Jae Lee, Hwang Yi
Summary: This study presents the first on-site investigation of an artificial intelligence-integrated three-dimensionally movable kinetic facade. The results show that the adaptive facade controlled by AI models can improve indoor daylight probability in real time.
AUTOMATION IN CONSTRUCTION
(2023)
Article
Chemistry, Multidisciplinary
Sergio Cruz-Leon, Nadine Schwierz
Article
Chemistry, Physical
Nadine Schwierz
JOURNAL OF CHEMICAL PHYSICS
(2020)
Article
Chemistry, Physical
Sergio Cruz-Leon, Kara K. Grotz, Nadine Schwierz
Summary: This study optimizes the description of ion interactions with nucleic acids in simulations by adjusting combination rules, significantly improving agreement with experiments and offering a more accurate method for describing metal cations in biomolecular simulations.
JOURNAL OF CHEMICAL PHYSICS
(2021)
Article
Chemistry, Physical
Kara K. Grotz, Sergio Cruz-Leon, Nadine Schwierz
Summary: Improvements in accurately simulating the properties of magnesium ions have been made by optimizing parameters in a larger parameter space, resulting in the reproduction of experimental properties such as solvation free energy, hydration shell oxygens distance, water exchange rate, and ion-binding sites.
JOURNAL OF CHEMICAL THEORY AND COMPUTATION
(2021)
Article
Chemistry, Physical
Sebastian Falkner, Nadine Schwierz
Summary: This study investigates the water exchange mechanism between the hydration shells of Mg2+ through molecular dynamics simulations and transition path sampling. It reveals that the choice of water model and Mg2+ model influences the exchange kinetics, with different mechanisms observed depending on the force field used. The results provide insights into the impact of force field choice on exchange dynamics in biomolecular simulations.
JOURNAL OF CHEMICAL PHYSICS
(2021)
Article
Chemistry, Physical
Kara K. Grotz, Nadine Schwierz
Summary: This study provides accurate force field parameters for Mg2+ in combination with OPC water, showing the transferability of SPC/E parameters to OPC and presenting two optimal parameter sets, MicroMg and NanoMg, for different timescales and enhanced ion binding events observation.
JOURNAL OF CHEMICAL PHYSICS
(2022)
Article
Biochemistry & Molecular Biology
Christin Fuks, Sebastian Falkner, Nadine Schwierz, Martin Hengesbach
Summary: Riboswitch RNAs regulate gene expression through conformational changes induced by environmental conditions and specific ligand binding, which is of great significance for understanding the mechanism of RNA regulation.
FRONTIERS IN MOLECULAR BIOSCIENCES
(2022)
Article
Chemistry, Physical
Sergio Cruz-Leon, Nadine Schwierz
Summary: The distribution of cations around nucleic acids is crucial for various biological processes, but predicting it is challenging. This study uses molecular dynamics simulations to reveal the ion-specific distributions and binding patterns for DNA and RNA duplexes, shedding light on the opposing behavior of DNA and RNA in the same ionic conditions.
JOURNAL OF PHYSICAL CHEMISTRY B
(2022)
Article
Chemistry, Physical
Miriam Grava, Mohd Ibrahim, Akhil Sudarsan, Julio Pusterla, Julian Philipp, Joachim O. Raedler, Nadine Schwierz, Emanuel Schneck
Summary: The protonation degree and lipid packing of ionizable lipids play crucial roles in the performance of lipid-based nanoparticles, and a combination of molecular dynamics simulations and experimental measurements can provide valuable insights for further predictive modeling.
JOURNAL OF CHEMICAL PHYSICS
(2023)
Article
Biochemistry & Molecular Biology
Kartikay Sharma, Sambhasan Banerjee, Dilan Savran, Cedric Rajes, Sebastian Wiese, Amandeep Girdhar, Nadine Schwierz, Christopher Lee, James Shorter, Matthias Schmidt, Lin Guo, Marcus Faendrich
Summary: In this study, the three-dimensional structure of amyloid fibrils from the hnRNPA1 protein was investigated using cryo-electron microscopy. The fibril core was found to be composed of a 45-residue segment from the low-complexity domain of the protein, while the remaining parts formed a fuzzy coat around the core. The fibril exhibited a pseudo-21 screw symmetry and contained disease-associated mutation sites. These findings suggest that the structure of full-length protein amyloid fibrils may be more complex than currently believed.
JOURNAL OF MOLECULAR BIOLOGY
(2023)
Article
Chemistry, Multidisciplinary
Mohd Ibrahim, Christiane Wenzel, Max Lallemang, Bizan N. Balzer, Nadine Schwierz
Summary: Ion-mediated attraction between DNA and mica is crucial in biotechnological applications and molecular imaging. The specific adsorption of ions at the mica surface compensates or overcompensates its negative charge. Different types of contacts between ions, DNA phosphate oxygens, and mica result in low- and high-force pathways and a broad distribution of detachment forces. Cs+ and water-mediated contacts lead to low detachment forces and high mobility of DNA, while direct ion-DNA or ion-surface contacts result in higher forces. K+, Mg2+, and Ca2+ are the most promising cations for imaging under physiological conditions.
Article
Chemistry, Multidisciplinary
Mohd Ibrahim, Jennifer Gilbert, Marcel Heinz, Tommy Nylander, Nadine Schwierz
Summary: Ionizable lipids, such as MC3, are crucial for the design of LNPs as drug delivery agents. Combining molecular dynamics simulations with experimental data is necessary to understand the internal structure of LNPs. The choice of force field parameters is important for simulation accuracy, and high-quality experimental data is needed for parametrization validation. This study provides parameters for cationic and neutral MC3 compatible with the AMBER Lipid17 force field, and compares different force fields using neutron reflectivity experiments. Accurate force field parameters and experimental validation are essential for reliable simulations.
Article
Biochemistry & Molecular Biology
Marijana Ugrina, Ines Burkhart, Diana Mueller, Harald Schwalbe, Nadine Schwierz
Summary: In this study, the folding pathways of a G-quadruplex from the telomeric repeat-containing RNA were characterized using a combination of molecular dynamics simulations and circular dichroism experiments. The presence of ions stabilized the quadruplex fold, and the folding process was guided by the formation of an ion double layer surrounding the charged quadruplex. Coarse-grained simulations accurately captured the ionic double layer using a matching procedure based on all-atom simulations. The results showed that the folding progressed through a series of intermediate states, stabilized by transient Hoogsteen interactions, before reaching the final folded structure. The study also proposed that conformational entropy is a hallmark of rG4 folding, which was supported by the analysis of free energy landscapes and folding pathways of four rG4 systems with varying loop length.
NUCLEIC ACIDS RESEARCH
(2023)
Article
Chemistry, Physical
Sergio Cruz-Leon, Nadine Schwierz
Summary: The distribution of cations around nucleic acids is crucial for various biological processes, but predicting the exact distribution remains challenging. DNA and RNA may react differently to the same ionic conditions. This study aims to reveal the ion-specific distributions and binding patterns for DNA and RNA duplexes through molecular dynamics simulations.
JOURNAL OF PHYSICAL CHEMISTRY B
(2022)