Pasar al contenido principal

POTENCIALES DE REDES NEURONALES PARA LA PROXIMA GENERACION DE SIMULACIONES MOLECULARES

PID2020-116564GB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2020
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POMPEU FABRA CCT

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Validation of the alchemical transfer method for the estimation of relative binding affinities of molecular series

  • Sabanés Zariquiey, Francesc
  • Pérez, Adrià
  • Majewski, Maciej
  • Gallicchio, Emilio
  • De Fabritiis, Gianni
The accurate prediction of protein-ligand binding affinities is crucial for drug discovery. Alchemical free energy calculations have become a popular tool for this purpose. However, the accuracy and reliability of these methods can vary depending on the methodology. In this study, we evaluate the performance of a relative binding free energy protocol based on the alchemical transfer method (ATM), a novel approach based on a coordinate transformation that swaps the positions of two ligands. The results show that ATM matches the performance of more complex free energy perturbation (FEP) methods in terms of Pearson correlation but with marginally higher mean absolute errors. This study shows that the ATM method is competitive compared to more traditional methods in speed and accuracy and offers the advantage of being applicable with any potential energy function., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 823712, and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033, the Torres-Quevedo Programme from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033). Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number GM140090. E.G. acknowledges support from the United States’ National Science Foundation (NSF CAREER 1750511).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

NNP/MM: Accelerating molecular dynamics simulations with machine learning potentials and molecular mechanics

  • Galvelis, Raimondas
  • Varela-Rial, Alejandro
  • Doerr, Stefan, 1987-
  • Fino, Roberto
  • Eastman, Peter
  • Markland, Thomas E.
  • Chodera, John D.
  • De Fabritiis, Gianni
Machine learning potentials have emerged as a means to enhance the accuracy of biomolecular simulations. However, their application is constrained by the significant computational cost arising from the vast number of parameters compared with traditional molecular mechanics. To tackle this issue, we introduce an optimized implementation of the hybrid method (NNP/MM), which combines a neural network potential (NNP) and molecular mechanics (MM). This approach models a portion of the system, such as a small molecule, using NNP while employing MM for the remaining system to boost efficiency. By conducting molecular dynamics (MD) simulations on various protein-ligand complexes and metadynamics (MTD) simulations on a ligand, we showcase the capabilities of our implementation of NNP/MM. It has enabled us to increase the simulation speed by ∼5 times and achieve a combined sampling of 1 μs for each complex, marking the longest simulations ever reported for this class of simulations., The authors thank the volunteers of GPUGRID.net for donating computing time. This project has received funding from the Torres-Quevedo Programme from the Spanish National Agency for Research (No. PTQ-17-09078/AEI/10.13039/501100011033) (R.G.); the European Union’s Horizon 2020 research and innovation programme, under Grant Agreement No. 823712 (R.G., A.V.-R., R.F.); the Industrial Doctorates Plan of the Secretariat of Universities and Research of the Department of Economy and Knowledge of the Generalitat of Catalonia (A.V.-R.); the Chan Zuckerberg Initiative DAF (Grant No. 2020-219414), an advised fund of Silicon Valley Community Foundation (S.D., P.E.); and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033. Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health, under Award No. GM140090 (P.E., T.E.M., J.D.C., G.D.F.). This research was funded in part through the NIH/NCI Cancer Center Support Grant P30 CA008748 (J.D.C.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Enhancing protein-ligand binding affinity predictions using neural network potentials

  • Sabanés Zariquiey, Francesc
  • Galvelis, Raimondas
  • Gallicchio, Emilio
  • Chodera, John D.
  • Markland, Thomas E.
  • De Fabritiis, Gianni
This letter gives results on improving protein-ligand binding affinity predictions based on molecular dynamics simulations using machine learning potentials with a hybrid neural network potential and molecular mechanics methodology (NNP/MM). We compute relative binding free energies with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2., The authors thank the volunteers of GPUGRID.net for donating computing time. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No. 823712, and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033; the Torres-Quevedo Programme from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033). Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under Award Number R01GM140090 to T.E.M., G.D.F., and J.D.C. E.G. acknowledges support from the United States National Science Foundation (NSF CAREER 1750511). J.D.C. also acknowledges support from NIH Grant P30CA008748 and the Sloan Kettering Institute. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Equivariant graph neural networks for toxicity prediction

  • Cremer, Julian
  • Medrano Sandonas, Leonardo
  • Tkatchenko, Alexandre
  • Clevert, Djork-Arné
  • De Fabritiis, Gianni
Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain., This research used computational resources provided by the High-Performance Center (HPC) at the University of Luxembourg. J.C. received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie Actions grant agreement “Advanced machine learning for Innovative Drug Discovery (AIDD)” No. 956832. L.M.S. thanks S. Goger for fruitful discussions about the influence of functional groups in toxicity prediction. G.D.F. acknowledges funding from the European Union’s Horizon 2020 research and innovation program under Grant Agreement No. 823712; and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033.
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Machine learning coarse-grained potentials of protein thermodynamics

  • Majewski, Maciej
  • Pérez, Adrià
  • Thölke, Philipp
  • Doerr, Stefan, 1987-
  • Charron, Nicholas E.
  • Giorgino, Toni
  • Husic, Brooke E.
  • Clementi, Cecilia
  • Noé, Frank
  • De Fabritiis, Gianni
A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics., The project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033 (G.D.F.) This project has received funding from the Torres-Quevedo Program from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033) (M.M.); the Torres-Quevedo Program from the Spanish National Agency for Research (PTQ2021-011669/AEI/10.13039/501100011033) (A.P.); the European Union’s Horizon 2020 research and innovation program under grant agreement No. 823712 (G.D.F.); NLM Training Program in Biomedical Informatics and Data Science (grant no. 5T15LM007093-27) (N.E.C.); Deutsche Forschungsgemeinschaft (DFG, GRK DAEDALUS, RTG 2433, Project Q05) (N.E.C.); National Science Foundation (CHE-1900374 and PHY-2019745) (C.C.); Einstein Foundation Berlin (Project 0420815101) (C.C.); Deutsche Forschungsgemeinschaft (DFG) SFB 1114 projects A04, B03, and B08, SFB/TRR 186 project A12, and SFB 1078 project C7 (C.C.); Deutsche Forschungsgemeinschaft (DFG) projects CRC1114/A04, CRC1114/C03 (F.N.); European Research Council (ERC) project ERG CoG 772230 (F.N.); Berlin Mathematics Center MATH+ project AA1-6 (F.N.); the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number GM140090 (G.D.F.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The authors thank the volunteers of GPUGRID.net for donating computing time. T.G. acknowledges the CINECA award under the ISCRA initiative, for the availability of high performance computing resources and support. This project has received funding from the Spoke 7 of the National Centre for HPC, Big Data and Quantum Computing (CN00000013) of the NextGenerationEU initiative (T.G.).
Repositorio Digital de la UPF
Publicación Artículo científico (JournalArticle)

Top-down machine learning of coarse-grained protein force fields

  • Navarro Ramírez, Carles
  • Majewski, Maciej
  • De Fabritiis, Gianni
Developing accurate and efficient coarse-grained representations of proteins is crucial for understanding their folding, function, and interactions over extended time scales. Our methodology involves simulating proteins with molecular dynamics and utilizing the resulting trajectories to train a neural network potential through differentiable trajectory reweighting. Remarkably, this method requires only the native conformation of proteins, eliminating the need for labeled data derived from extensive simulations or memory-intensive end-to-end differentiable simulations. Once trained, the model can be employed to run parallel molecular dynamics simulations and sample folding events for proteins both within and beyond the training distribution, showcasing its extrapolation capabilities. By applying Markov state models, native-like conformations of the simulated proteins can be predicted from the coarse-grained simulations. Owing to its theoretical transferability and ability to use solely experimental static structures as training data, we anticipate that this approach will prove advantageous for developing new protein force fields and further advancing the study of protein dynamics, folding, and interactions., The project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033 (G.D.F.). With the support of the Industrial Doctorates Plan of the Secretariat of Universities and Research of the Department of Economy and Knowledge of the Generalitat of Catalonia.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

NNP/MM: Accelerating molecular dynamics simulations with machine learning potentials and molecular mechanics

  • Galvelis, Raimondas
  • Varela-Rial, Alejandro
  • Doerr, Stefan, 1987-
  • Fino, Roberto
  • Eastman, Peter
  • Markland, Thomas E.
  • Chodera, John D.
  • De Fabritiis, Gianni
Machine learning potentials have emerged as a means to enhance the accuracy of biomolecular simulations. However, their application is constrained by the significant computational cost arising from the vast number of parameters compared with traditional molecular mechanics. To tackle this issue, we introduce an optimized implementation of the hybrid method (NNP/MM), which combines a neural network potential (NNP) and molecular mechanics (MM). This approach models a portion of the system, such as a small molecule, using NNP while employing MM for the remaining system to boost efficiency. By conducting molecular dynamics (MD) simulations on various protein-ligand complexes and metadynamics (MTD) simulations on a ligand, we showcase the capabilities of our implementation of NNP/MM. It has enabled us to increase the simulation speed by ∼5 times and achieve a combined sampling of 1 μs for each complex, marking the longest simulations ever reported for this class of simulations., The authors thank the volunteers of GPUGRID.net for donating computing time. This project has received funding from the Torres-Quevedo Programme from the Spanish National Agency for Research (No. PTQ-17-09078/AEI/10.13039/501100011033) (R.G.); the European Union’s Horizon 2020 research and innovation programme, under Grant Agreement No. 823712 (R.G., A.V.-R., R.F.); the Industrial Doctorates Plan of the Secretariat of Universities and Research of the Department of Economy and Knowledge of the Generalitat of Catalonia (A.V.-R.); the Chan Zuckerberg Initiative DAF (Grant No. 2020-219414), an advised fund of Silicon Valley Community Foundation (S.D., P.E.); and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033. Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health, under Award No. GM140090 (P.E., T.E.M., J.D.C., G.D.F.). This research was funded in part through the NIH/NCI Cancer Center Support Grant P30 CA008748 (J.D.C.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Validation of the alchemical transfer method for the estimation of relative binding affinities of molecular series

  • Sabanés Zariquiey, Francesc
  • Pérez, Adrià
  • Majewski, Maciej
  • Gallicchio, Emilio
  • De Fabritiis, Gianni
The accurate prediction of protein-ligand binding affinities is crucial for drug discovery. Alchemical free energy calculations have become a popular tool for this purpose. However, the accuracy and reliability of these methods can vary depending on the methodology. In this study, we evaluate the performance of a relative binding free energy protocol based on the alchemical transfer method (ATM), a novel approach based on a coordinate transformation that swaps the positions of two ligands. The results show that ATM matches the performance of more complex free energy perturbation (FEP) methods in terms of Pearson correlation but with marginally higher mean absolute errors. This study shows that the ATM method is competitive compared to more traditional methods in speed and accuracy and offers the advantage of being applicable with any potential energy function., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 823712, and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033, the Torres-Quevedo Programme from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033). Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number GM140090. E.G. acknowledges support from the United States’ National Science Foundation (NSF CAREER 1750511).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Enhancing protein-ligand binding affinity predictions using neural network potentials

  • Sabanés Zariquiey, Francesc
  • Galvelis, Raimondas
  • Gallicchio, Emilio
  • Chodera, John D.
  • Markland, Thomas E.
  • De Fabritiis, Gianni
This letter gives results on improving protein-ligand binding affinity predictions based on molecular dynamics simulations using machine learning potentials with a hybrid neural network potential and molecular mechanics methodology (NNP/MM). We compute relative binding free energies with the Alchemical Transfer Method and validate its performance against established benchmarks and find significant enhancements compared with conventional MM force fields like GAFF2., The authors thank the volunteers of GPUGRID.net for donating computing time. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under Grant Agreement No. 823712, and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033; the Torres-Quevedo Programme from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033). Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under Award Number R01GM140090 to T.E.M., G.D.F., and J.D.C. E.G. acknowledges support from the United States National Science Foundation (NSF CAREER 1750511). J.D.C. also acknowledges support from NIH Grant P30CA008748 and the Sloan Kettering Institute. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Equivariant graph neural networks for toxicity prediction

  • Cremer, Julian
  • Medrano Sandonas, Leonardo
  • Tkatchenko, Alexandre
  • Clevert, Djork-Arné
  • De Fabritiis, Gianni
Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain., This research used computational resources provided by the High-Performance Center (HPC) at the University of Luxembourg. J.C. received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie Actions grant agreement “Advanced machine learning for Innovative Drug Discovery (AIDD)” No. 956832. L.M.S. thanks S. Goger for fruitful discussions about the influence of functional groups in toxicity prediction. G.D.F. acknowledges funding from the European Union’s Horizon 2020 research and innovation program under Grant Agreement No. 823712; and the project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Machine learning coarse-grained potentials of protein thermodynamics

  • Majewski, Maciej
  • Pérez, Adrià
  • Thölke, Philipp
  • Doerr, Stefan, 1987-
  • Charron, Nicholas E.
  • Giorgino, Toni
  • Husic, Brooke E.
  • Clementi, Cecilia
  • Noé, Frank
  • De Fabritiis, Gianni
A generalized understanding of protein dynamics is an unsolved scientific problem, the solution of which is critical to the interpretation of the structure-function relationships that govern essential biological processes. Here, we approach this problem by constructing coarse-grained molecular potentials based on artificial neural networks and grounded in statistical mechanics. For training, we build a unique dataset of unbiased all-atom molecular dynamics simulations of approximately 9 ms for twelve different proteins with multiple secondary structure arrangements. The coarse-grained models are capable of accelerating the dynamics by more than three orders of magnitude while preserving the thermodynamics of the systems. Coarse-grained simulations identify relevant structural states in the ensemble with comparable energetics to the all-atom systems. Furthermore, we show that a single coarse-grained potential can integrate all twelve proteins and can capture experimental structural features of mutated proteins. These results indicate that machine learning coarse-grained potentials could provide a feasible approach to simulate and understand protein dynamics., The project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033 (G.D.F.) This project has received funding from the Torres-Quevedo Program from the Spanish National Agency for Research (PTQ2020-011145/AEI/10.13039/501100011033) (M.M.); the Torres-Quevedo Program from the Spanish National Agency for Research (PTQ2021-011669/AEI/10.13039/501100011033) (A.P.); the European Union’s Horizon 2020 research and innovation program under grant agreement No. 823712 (G.D.F.); NLM Training Program in Biomedical Informatics and Data Science (grant no. 5T15LM007093-27) (N.E.C.); Deutsche Forschungsgemeinschaft (DFG, GRK DAEDALUS, RTG 2433, Project Q05) (N.E.C.); National Science Foundation (CHE-1900374 and PHY-2019745) (C.C.); Einstein Foundation Berlin (Project 0420815101) (C.C.); Deutsche Forschungsgemeinschaft (DFG) SFB 1114 projects A04, B03, and B08, SFB/TRR 186 project A12, and SFB 1078 project C7 (C.C.); Deutsche Forschungsgemeinschaft (DFG) projects CRC1114/A04, CRC1114/C03 (F.N.); European Research Council (ERC) project ERG CoG 772230 (F.N.); Berlin Mathematics Center MATH+ project AA1-6 (F.N.); the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number GM140090 (G.D.F.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The authors thank the volunteers of GPUGRID.net for donating computing time. T.G. acknowledges the CINECA award under the ISCRA initiative, for the availability of high performance computing resources and support. This project has received funding from the Spoke 7 of the National Centre for HPC, Big Data and Quantum Computing (CN00000013) of the NextGenerationEU initiative (T.G.).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Top-down machine learning of coarse-grained protein force fields

  • Navarro Ramírez, Carles
  • Majewski, Maciej
  • De Fabritiis, Gianni
Developing accurate and efficient coarse-grained representations of proteins is crucial for understanding their folding, function, and interactions over extended time scales. Our methodology involves simulating proteins with molecular dynamics and utilizing the resulting trajectories to train a neural network potential through differentiable trajectory reweighting. Remarkably, this method requires only the native conformation of proteins, eliminating the need for labeled data derived from extensive simulations or memory-intensive end-to-end differentiable simulations. Once trained, the model can be employed to run parallel molecular dynamics simulations and sample folding events for proteins both within and beyond the training distribution, showcasing its extrapolation capabilities. By applying Markov state models, native-like conformations of the simulated proteins can be predicted from the coarse-grained simulations. Owing to its theoretical transferability and ability to use solely experimental static structures as training data, we anticipate that this approach will prove advantageous for developing new protein force fields and further advancing the study of protein dynamics, folding, and interactions., The project PID2020-116564GB-I00 has been funded by MCIN/AEI/10.13039/501100011033 (G.D.F.). With the support of the Industrial Doctorates Plan of the Secretariat of Universities and Research of the Department of Economy and Knowledge of the Generalitat of Catalonia.