arXiv subjects

Gianni De Fabritiis

Publications and source records attributed to Gianni De Fabritiis.

At least 37 records · Page 2Linked to original sources

arXiv2023

Navigating protein landscapes with a machine-learned transferable coarse-grained model

The most popular and universally predictive protein simulation models employ all-atom molecular dynamics (MD), but they come at extreme computational cost. The development of a universal, computationally efficient coarse-grained (CG) model with similar prediction performance has been a long-standing challenge. By combining recent deep learning methods with a large and diverse training set of all-atom protein simulations, we here develop a bottom-up CG force field with chemical transferability, which can be used for extrapolative molecular dynamics on new sequences not used during model parametrization. We demonstrate that the model successfully predicts folded structures, intermediates, metastable folded and unfolded basins, and the fluctuations of intrinsically disordered proteins while it is several orders of magnitude faster than an all-atom model. This showcases the feasibility of a universal and computationally efficient machine-learned CG model for proteins.

q-bio.BM↗

arXiv2023

A High-Throughput Steered Molecular Dynamics Study on the Free Energy Profile of Ion Permeation through Gramicidin A

Steered molecular dynamics (SMD) simulations for the calculation of free energies are well suited for high-throughput molecular simulations on a distributed infrastructure due to the simplicity of the setup and parallel granularity of the runs. However, so far, the computational cost limited the estimation of the free energy typically over just a few pullings, thus impeding the evaluation of statistical uncertainties involved. In this work, we performed two thousand pulls for the permeation of a potassium ion in the gramicidin A pore by all-atom molecular dynamics in order to assess the bidirectional SMD protocol with a proper amount of sampling. The estimated free energy profile still shows a statistical error of several kcal/mol, while the work distributions are estimated to be non-Gaussian at pulling speeds of 10 Å/ns. We discuss the methodology and the confidence intervals in relation to increasing amounts of computed trajectories and how different permeation pathways for the potassium ion, knock-on and sideways, affect the sampling and the free energy estimation.

physics.chem-ph↗

arXiv2023

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

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 to traditional molecular mechanics. To tackle this issue, we introduce an optimized implementation of the hybrid method (NNP/MM), which combines neural network potentials (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 one microsecond for each complex, marking the longest simulations ever reported for this class of simulation.

q-bio.BM↗

arXiv2023

Machine Learning Small Molecule Properties in Drug Discovery

Machine learning (ML) is a promising approach for predicting small molecule properties in drug discovery. Here, we provide a comprehensive overview of various ML methods introduced for this purpose in recent years. We review a wide range of properties, including binding affinities, solubility, and ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity). We discuss existing popular datasets and molecular descriptors and embeddings, such as chemical fingerprints and graph-based neural networks. We highlight also challenges of predicting and optimizing multiple properties during hit-to-lead and lead optimization stages of drug discovery and explore briefly possible multi-objective optimization techniques that can be used to balance diverse properties while optimizing lead candidates. Finally, techniques to provide an understanding of model predictions, especially for critical decision-making in drug discovery are assessed. Overall, this review provides insights into the landscape of ML models for small molecule property predictions in drug discovery. So far, there are multiple diverse approaches, but their performances are often comparable. Neural networks, while more flexible, do not always outperform simpler models. This shows that the availability of high-quality training data remains crucial for training accurate models and there is a need for standardized benchmarks, additional performance metrics, and best practices to enable richer comparisons between the different techniques and models that can shed a better light on the differences between the many techniques.

q-bio.BM↗

arXiv2023

Integrating Distributed Architectures in Highly Modular RL Libraries

Advancing reinforcement learning (RL) requires tools that are flexible enough to easily prototype new methods while avoiding impractically slow experimental turnaround times. To match the first requirement, the most popular RL libraries advocate for highly modular agent composability, which facilitates experimentation and development. To solve challenging environments within reasonable time frames, scaling RL to large sampling and computing resources has proved a successful strategy. However, this capability has been so far difficult to combine with modularity. In this work, we explore design choices to allow agent composability both at a local and distributed level of execution. We propose a versatile approach that allows the definition of RL agents at different scales through independent reusable components. We demonstrate experimentally that our design choices allow us to reproduce classical benchmarks, explore multiple distributed architectures, and solve novel and complex environments while giving full control to the user in the agent definition and training scheme definition. We believe this work can provide useful insights to the next generation of RL libraries.

cs.CV↗

arXiv2023

Validation of the Alchemical Transfer Method for the Estimation of Relative Binding Affinities of Molecular Series

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.

physics.chem-ph↗

arXiv2023

Binding-and-folding recognition of an intrinsically disordered protein using online learning molecular dynamics

Intrinsically disordered proteins participate in many biological processes by folding upon binding with other proteins. However, coupled folding and binding processes are not well understood from an atomistic point of view. One of the main questions is whether folding occurs prior to or after binding. Here we use a novel unbiased high-throughput adaptive sampling approach to reconstruct the binding and folding between the disordered transactivation domain of \mbox{c-Myb} and the KIX domain of the CREB-binding protein. The reconstructed long-term dynamical process highlights the binding of a short stretch of amino acids on \mbox{c-Myb} as a folded $α$-helix. Leucine residues, specially Leu298 to Leu302, establish initial native contacts that prime the binding and folding of the rest of the peptide, with a mixture of conformational selection on the N-terminal region with an induced fit of the C-terminal.

q-bio.BM↗

arXiv2022

Machine Learning Coarse-Grained Potentials of Protein Thermodynamics

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.

q-bio.BM↗

arXiv2022

SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.

physics.chem-ph↗

arXiv2022

TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials

The prediction of quantum mechanical properties is historically plagued by a trade-off between accuracy and speed. Machine learning potentials have previously shown great success in this domain, reaching increasingly better accuracy while maintaining computational efficiency comparable with classical force fields. In this work we propose TorchMD-NET, a novel equivariant transformer (ET) architecture, outperforming state-of-the-art on MD17, ANI-1, and many QM9 targets in both accuracy and computational efficiency. Through an extensive attention weight analysis, we gain valuable insights into the black box predictor and show differences in the learned representation of conformers versus conformations sampled from molecular dynamics or normal modes. Furthermore, we highlight the importance of datasets including off-equilibrium conformations for the evaluation of molecular potentials.

cs.LG↗

arXiv2021

Guided Exploration with Proximal Policy Optimization using a Single Demonstration

Solving sparse reward tasks through exploration is one of the major challenges in deep reinforcement learning, especially in three-dimensional, partially-observable environments. Critically, the algorithm proposed in this article uses a single human demonstration to solve hard-exploration problems. We train an agent on a combination of demonstrations and own experience to solve problems with variable initial conditions. We adapt this idea and integrate it with the proximal policy optimization (PPO). The agent is able to increase its performance and to tackle harder problems by replaying its own past trajectories prioritizing them based on the obtained reward and the maximum value of the trajectory. We compare different variations of this algorithm to behavioral cloning on a set of hard-exploration tasks in the Animal-AI Olympics environment. To the best of our knowledge, learning a task in a three-dimensional environment with comparable difficulty has never been considered before using only one human demonstration.

cs.AI↗

arXiv2020

TorchMD: A deep learning framework for molecular simulations

Molecular dynamics simulations provide a mechanistic description of molecules by relying on empirical potentials. The quality and transferability of such potentials can be improved leveraging data-driven models derived with machine learning approaches. Here, we present TorchMD, a framework for molecular simulations with mixed classical and machine learning potentials. All of force computations including bond, angle, dihedral, Lennard-Jones and Coulomb interactions are expressed as PyTorch arrays and operations. Moreover, TorchMD enables learning and simulating neural network potentials. We validate it using standard Amber all-atom simulations, learning an ab-initio potential, performing an end-to-end training and finally learning and simulating a coarse-grained model for protein folding. We believe that TorchMD provides a useful tool-set to support molecular simulations of machine learning potentials. Code and data are freely available at \url{github.com/torchmd}.

physics.chem-ph↗

arXiv2020

SkeleDock: A Web Application for Scaffold Docking in PlayMolecule

SkeleDock is a scaffold docking algorithm which uses the structure of a protein-ligand complex as a template to model the binding mode of a chemically similar system. This algorithm was evaluated in the D3R Grand Challenge 4 pose prediction challenge, where it achieved competitive performance. Furthermore, we show that, if crystallized fragments of the target ligand are available, SkeleDock can outperform rDock docking software at predicting the binding mode. This article also addresses the capacity of this algorithm to model macrocycles and deal with scaffold hopping. SkeleDock can be accessed at https://playmolecule.org/SkeleDock/.

q-bio.QM↗

arXiv2020

AdaptiveBandit: A multi-armed bandit framework for adaptive sampling in molecular simulations

Sampling from the equilibrium distribution has always been a major problem in molecular simulations due to the very high dimensionality of conformational space. Over several decades, many approaches have been used to overcome the problem. In particular, we focus on unbiased simulation methods such as parallel and adaptive sampling. Here, we recast adaptive sampling schemes on the basis of multi-armed bandits and develop a novel adaptive sampling algorithm under this framework, \UCB. We test it on multiple simplified potentials and in a protein folding scenario. We find that this framework performs similarly or better in every type of test potentials compared to previous methods. Furthermore, it provides a novel framework to develop new sampling algorithms with better asymptotic characteristics.

physics.comp-ph↗

arXiv2019

Machine learning for protein folding and dynamics

Many aspects of the study of protein folding and dynamics have been affected by the recent advances in machine learning. Methods for the prediction of protein structures from their sequences are now heavily based on machine learning tools. The way simulations are performed to explore the energy landscape of protein systems is also changing as force-fields are started to be designed by means of machine learning methods. These methods are also used to extract the essential information from large simulation datasets and to enhance the sampling of rare events such as folding/unfolding transitions. While significant challenges still need to be tackled, we expect these methods to play an important role on the study of protein folding and dynamics in the near future. We discuss here the recent advances on all these fronts and the questions that need to be addressed for machine learning approaches to become mainstream in protein simulation.

physics.bio-ph↗

arXiv2019

A Scalable Molecular Force Field Parameterization Method Based on Density Functional Theory and Quantum-Level Machine Learning

Fast and accurate molecular force field (FF) parameterization is still an unsolved problem. Accurate FFs are not generally available for all molecules, like novel druglike molecules. While methods based on quantum mechanics (QM) exist to parameterize them with better accuracy, they are computationally expensive and slow, which limits applicability to a small number of molecules. Here, we present an automated FF parameterization method which can utilize either DFT calculations or approximate QM energies produced by different neural network potentials (NNPs), to obtain improved parameters for molecules. We demonstrate that for the case of torchani-ANI-1x NNP, we can parameterize small molecules in a fraction of time compared with an equivalent parameterization using DFT QM calculations while producing more accurate parameters than FF (GAFF2). We expect our method to be of critical importance in computational structure-based drug discovery. The current version is available at PlayMolecule (www.playmolecule.org) and implemented in HTMD, allowing to parameterize molecules with different QM and NNP options.

physics.chem-ph↗

arXiv2018

Simulations meet Machine Learning in Structural Biology

Classical molecular dynamics (MD) simulations will be able to reach sampling in the second timescale within five years, producing petabytes of simulation data at current force field accuracy. Notwithstanding this, MD will still be in the regime of low-throughput, high-latency predictions with average accuracy. We envisage that machine learning (ML) will be able to solve both the accuracy and time-to-prediction problem by learning predictive models using expensive simulation data. The synergies between classical, quantum simulations and ML methods, such as artificial neural networks, have the potential to drastically reshape the way we make predictions in computational structural biology and drug discovery.

q-bio.BM↗

arXiv2017

Dimensionality reduction methods for molecular simulations

Molecular simulations produce very high-dimensional data-sets with millions of data points. As analysis methods are often unable to cope with so many dimensions, it is common to use dimensionality reduction and clustering methods to reach a reduced representation of the data. Yet these methods often fail to capture the most important features necessary for the construction of a Markov model. Here we demonstrate the results of various dimensionality reduction methods on two simulation data-sets, one of protein folding and another of protein-ligand binding. The methods tested include a k-means clustering variant, a non-linear auto encoder, principal component analysis and tICA. The dimension-reduced data is then used to estimate the implied timescales of the slowest process by a Markov state model analysis to assess the quality of the projection. The projected dimensions learned from the data are visualized to demonstrate which conformations the various methods choose to represent the molecular process.

stat.ML↗