Predicting Molecular Docking Affinity of Per- and Polyfluoroalkyl Substances (PFAs) Towards Human Blood Proteins Using Generative AI Algorithm DiffDock DOI Creative Commons
Dhan Lord Fortela, Ashley P. Mikolajczyk,

Miranda R. Carnes

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2023, Номер unknown

Опубликована: Авг. 6, 2023

Abstract This study computationally evaluates the molecular docking affinity of various perfluoroalkyl and polyfluoroalkyl substances (PFAs) using a generative machine learning algorithm, DiffDock, specialized in protein-ligand blind-docking prediction. Concerns about chemical pathways accumulation PFAs environment eventually human body has been rising due to empirical findings that levels blood rising. Though there is currently heightened need understand PFAs, studies on have relatively slow time-scale cost standard analysis such as those samples. The current demonstrates implementation DiffDock assesses prediction results relation findings. capability an advanced artificial intelligence (AI) algorithm designed for offers fast approach determining potential body.

Язык: Английский

Can AlphaFold’s breakthrough in protein structure help decode the fundamental principles of adaptive cellular immunity? DOI
Benjamin McMaster, Christopher J. Thorpe, Graham S. Ogg

и другие.

Nature Methods, Год журнала: 2024, Номер 21(5), С. 766 - 776

Опубликована: Апрель 23, 2024

Язык: Английский

Процитировано

15
Transferable deep generative modeling of intrinsically disordered protein conformations DOI Creative Commons
Giacomo Janson, Michael Feig

PLoS Computational Biology, Год журнала: 2024, Номер 20(5), С. e1012144 - e1012144

Опубликована: Май 23, 2024

Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use computational and experimental methods. Molecular simulations are valuable strategy for constructing structural but highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data emerged as efficient alternative generating ensembles. However, such methods currently suffer limited transferability when modeling sequences conformations absent in the training data. Here, we develop novel model achieves high levels intrinsically protein approach, named idpSAM, latent diffusion transformer neural networks. It combines autoencoder to representation geometry sample encoded space. IdpSAM was trained large dataset regions performed with ABSINTH implicit solvent model. Thanks expressiveness its networks stability, idpSAM faithfully captures 3D test no similarity set. Our study also demonstrates potential full datasets sampling underscores importance set size generalization. We believe represents significant progress transferable ensemble learning.

Язык: Английский

Процитировано

13
Mechanisms of myosin II force generation. Insights from novel experimental techniques and approaches DOI
Dilson E. Rassier, Alf Månsson

Physiological Reviews, Год журнала: 2024, Номер 105(1), С. 1 - 93

Опубликована: Март 7, 2024

Myosin II is a molecular motor that converts chemical energy derived from ATP hydrolysis into mechanical work. isoforms are responsible for muscle contraction and range of cell functions relying on the development force motion. When attaches to actin, hydrolyzed inorganic phosphate (P

Язык: Английский

Процитировано

7
Accelerating reliable multiscale quantum refinement of protein–drug systems enabled by machine learning DOI Creative Commons
Zeyin Yan,

Dacong Wei,

Xin Li

и другие.

Nature Communications, Год журнала: 2024, Номер 15(1)

Опубликована: Май 16, 2024

Biomacromolecule structures are essential for drug development and biocatalysis. Quantum refinement (QR) methods, which employ reliable quantum mechanics (QM) methods in crystallographic refinement, showed promise improving the structural quality or even correcting structure of biomacromolecules. However, vast computational costs complex mechanics/molecular (QM/MM) setups limit QR applications. Here we incorporate robust machine learning potentials (MLPs) multiscale ONIOM(QM:MM) schemes to describe core parts (e.g., drugs/inhibitors), replacing expensive QM method. Additionally, two levels MLPs combined first time overcome MLP limitations. Our unique MLPs+ONIOM-based achieve QM-level accuracy with significantly higher efficiency. Furthermore, our refinements provide evidence existence bonded nonbonded forms Food Drug Administration (FDA)-approved nirmatrelvir one SARS-CoV-2 main protease structure. This study highlights that powerful accelerate QRs protein-drug complexes, promote broader applications more atomistic insights into development.

Язык: Английский

Процитировано

7
Unveiling the role of BON domain-containing proteins in antibiotic resistance DOI Creative Commons
Shengwei Sun, Jinju Chen

Frontiers in Microbiology, Год журнала: 2025, Номер 15

Опубликована: Янв. 7, 2025

The alarming rise of antibiotic-resistant Gram-negative bacteria poses a global health crisis. Their unique outer membrane restricts antibiotic access. While diffusion porins are well-studied, the role BON domain-containing proteins (BDCPs) in resistance remains unexplored. We analyze protein databases, revealing widespread BDCP distribution across environmental bacteria. further describe their conserved core domain structure, key for understanding transport. Elucidating genetic and biochemical basis BDCPs offers novel target to combat restore bacterial susceptibility antibiotics.

Язык: Английский

Процитировано

1
Solution NMR goes big: Atomic resolution studies of protein components of molecular machines and phase-separated condensates DOI
Alexander I. M. Sever, Rashik Ahmed, Philip Rößler

и другие.

Current Opinion in Structural Biology, Год журнала: 2025, Номер 90, С. 102976 - 102976

Опубликована: Янв. 20, 2025

Язык: Английский

Процитировано

1
How did we get there? AI applications to biological networks and sequences DOI Creative Commons
Marco Anteghini, Francesco Gualdi,

Baldo Oliva

и другие.

Computers in Biology and Medicine, Год журнала: 2025, Номер 190, С. 110064 - 110064

Опубликована: Апрель 5, 2025

The rapidly advancing field of artificial intelligence (AI) has transformed numerous scientific domains, including biology, where a vast and complex volume data is available for analysis. This paper provides comprehensive overview the current state AI-driven methodologies in genomics, proteomics, systems biology. We discuss how machine learning algorithms, particularly deep models, have enhanced accuracy efficiency embedding sequences, motif discovery, prediction gene expression protein structure. Additionally, we explore integration AI analysis biological networks, protein-protein interaction networks multi-layered networks. By leveraging large-scale data, techniques enabled unprecedented insights into processes disease mechanisms. work underlines potential applying to highlighting applications suggesting directions future research further this evolving field.

Язык: Английский

Процитировано

1
Transferable deep generative modeling of intrinsically disordered protein conformations DOI Creative Commons
Giacomo Janson, Michael Feig

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Фев. 8, 2024

Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use computational and experimental methods. Molecular simulations are valuable strategy for constructing structural but highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data emerged as efficient alternative generating ensembles. However, such methods currently suffer limited transferability when modeling sequences conformations absent in the training data. Here, we develop novel model achieves high levels intrinsically protein approach, named idpSAM, latent diffusion transformer neural networks. It combines autoencoder to representation geometry sample encoded space. IdpSAM was trained large dataset regions performed with ABSINTH implicit solvent model. Thanks expressiveness its networks stability, idpSAM faithfully captures 3D test no similarity set. Our study also demonstrates potential full datasets sampling underscores importance set size generalization. We believe represents significant progress transferable ensemble learning.

Язык: Английский

Процитировано

4
Leveraging AI to Explore Structural Contexts of Post-Translational Modifications in Drug Binding DOI Creative Commons
Kirill E. Medvedev, R. Dustin Schaeffer,

Nick V. Grishin

и другие.

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Янв. 19, 2025

Post-translational modifications (PTMs) play a crucial role in allowing cells to expand the functionality of their proteins and adaptively regulate signaling pathways. Defects PTMs have been linked numerous developmental disorders human diseases, including cancer, diabetes, heart, neurodegenerative metabolic diseases. are important targets drug discovery, as they can significantly influence various aspects interactions binding affinity. The structural consequences PTMs, such phosphorylation-induced conformational changes or effects on ligand affinity, historically challenging study large scale, primarily due reliance experimental methods. Recent advancements computational power artificial intelligence, particularly deep learning algorithms protein structure prediction tools like AlphaFold3, opened new possibilities for exploring context between drugs. These AI-driven methods enable accurate modeling structures PTM-modified regions simulation ligand-binding dynamics scale. In this work, we identified small molecule binding-associated that across all listed DrugDomain database, which developed recently. 6,131 were mapped domains from Evolutionary Classification Protein Domains (ECOD) database. Scientific contribution. Using recent AI-based approaches (AlphaFold3, RoseTTAFold All-Atom, Chai-1), generated 14,178 models with docked ligands. Our results demonstrate these predict PTM binding, but precise evaluation accuracy requires much larger benchmarking set. We also found phosphorylation NADPH-Cytochrome P450 Reductase, observed cervical lung causes significant disruption pocket, potentially impairing function. All data available database v1.1 ( http://prodata.swmed.edu/DrugDomain/ ) GitHub https://github.com/kirmedvedev/DrugDomain ). This resource is first our knowledge offering

Язык: Английский

Процитировано

0
Enzymatic depolymerization of polyamides (nylons): current challenges and future directions DOI Creative Commons
Shengwei Sun

Polymer Degradation and Stability, Год журнала: 2025, Номер unknown, С. 111341 - 111341

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0