Using a variant of parallel tempering, we study the changes in sampling within a simulation when the all-atom model is coupled to a Go-like potential. We find that the native structure is not the lowest-energy configuration in the all-atom force field. Adding a Go-term deforms the energy landscape in a way that the native configuration becomes the global minimum.
Recently, persistent homology has had tremendous success in biomolecular data analysis. It works by examining the topological relationship or connectivity of a group of atoms in a molecule at a variety of scales, then rendering a family of topological representations of the molecule. However, persistent homology is rarely {employed} for the analysis of atomic properties, such as biomolecular flexibility analysis or B factor prediction. This work introduces atom-specific persistent homology to provide a local atomic level representation of a molecule via a global topological tool. This is achie…
Potential function of simplified protein models for discriminating native proteins from decoys: Combining contact interaction and local sequence-dependent geometry
Despite recent advancements in deep learning methods for protein structure prediction and representation, little focus has been directed at the simultaneous inclusion and prediction of protein backbone and sidechain structure information. We present SidechainNet, a new dataset that directly extends the ProteinNet dataset. SidechainNet includes angle and atomic coordinate information capable of describing all heavy atoms of each protein structure. In this paper, we provide background information on the availability of protein structure data and the significance of ProteinNet. Thereafter, we arg…
Here we propose that the upper bound marginal stability of proteins (7.4 kcal/mol) is a universal property that includes macro-molecular complexes and is not affected by molecular changes such as mutations and Post-Translational Modifications. Its existence is, essentially, a consequence of the Anfinsen thermodynamic hypothesis rather than a result of an evolutive process. This result enables us to conjecture that neutral evolution should also be, with respect to protein stability, a universal phenomenon.
We inquire to what extent protein peptide plane and side chain dynamics can be reconstructed from knowledge of C-alpha dynamics. Due to lack of experimental data we analyze all atom molecular dynamics trajectories from Anton supercomputer, and for clarity we limit our attention to the peptide plane O atoms and side chain C-beta atoms. We try and reconstruct their dynamics using four different approaches. Three of these are the publicly available reconstruction programs Pulchra, Remo Scwrl4. The fourth, Statistical Method, builds entirely on statistical analysis of Protein Data Bank (PDB) struc…
Wayne State University（韦恩州立大学）；Univ. of Bari Aldo Moro（巴里大学阿尔多·莫罗分校）；National Research Council (CONICET)（国家研究委员会（CONICET））；Daruma Institute for Applied Intelligence（达摩应用智能研究所）
All-atom and coarse-grained molecular dynamics are two widely used computational tools to study the conformational states of proteins. Yet, these two simulation methods suffer from the fact that without access to supercomputing resources, the time and length scales at which these states become detectable are difficult to achieve. One alternative to such methods is based on encoding the atomistic trajectory of molecular dynamics as a shorthand version devoid of physical particles, and then learning to propagate the encoded trajectory through the use of artificial intelligence. Here we show that…
ESM All-Atom: Multi-scale Protein Language Model for Unified Molecular Modeling
Department of Computer Science, Tsinghua University（清华大学计算机系）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；PharMolix Inc（PharMolix公司）
We study the behavior of five proteins at the air-water and oil-water interfaces by all-atom molecular dynamics. The proteins are found to get distorted when pinned to the interface. This behavior is consistent with the phenomenological way of introducing the interfaces in a coarse-grained model through a force that depends on the hydropathy indices of the residues. Proteins couple to the oil-water interface stronger than to the air- water one. They diffuse slower at the oil-water interface but do not depin from it, whereas depinning events are observed at the other interface. The reduction of…
We present a simple, modular graph-based convolutional neural network that takes structural information from protein-ligand complexes as input to generate models for activity and binding mode prediction. Complex structures are generated by a standard docking procedure and fed into a dual-graph architecture that includes separate sub-networks for the ligand bonded topology and the ligand-protein contact map. This network division allows contributions from ligand identity to be distinguished from effects of protein-ligand interactions on classification. We show, in agreement with recent literatu…
One-Dimensional Structural Properties of Proteins in the Coarse-Grained CABS Model
尽管计算能力显著提高，但使用经典的全原子方法对蛋白质结构进行分子建模仍然效率低下，至少对于生物医学研究关注的大多数蛋白质靶点来说是如此。也许克服效率低下问题的最成功的策略是多尺度建模，以合并所有原子和粗粒度的模型。本章描述了一个成熟的CABS粗粒度蛋白质模型。CABS（C-Alpha，C-Beta and Side chains）模型假设氨基酸的2-4个联合原子表示、基于知识的力场（来自已知蛋白质序列和结构中的统计学数据）和有效的Monte Carlo采样方案（MC动力学、MC复制交换和组合）。特别强调的是CABS力场的独特设计，这在很大程度上是使用蛋白质的一维结构特性，包括蛋白质二级结构定义的。本章还介绍了基于CABS的建模方法，包括从头结构预测的多尺度工具，蛋白质动力学建模和蛋白质-肽复合物的预测。基于CABS的工具可在http://biocomp.chem.uw.edu.pl/tools上免费获得
Coarse-graining (CG) accelerates molecular simulations of protein dynamics by simulating sets of atoms as singular beads. Backmapping is the opposite operation of bringing lost atomistic details back from the CG representation. While machine learning (ML) has produced accurate and efficient CG simulations of proteins, fast and reliable backmapping remains a challenge. Rule-based methods produce poor all-atom geometries, needing computationally costly refinement through additional simulations. Recently proposed ML approaches outperform traditional baselines but are not transferable between prot…
Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings
Signal Processing Laboratory (LTS2), EPFL, Lausanne, Switzerland（信号处理实验室（LTS2），瑞士洛桑联邦理工学院）；Institute of Bioengineering, EPFL, Lausanne, Switzerland（生物工程研究所，瑞士洛桑联邦理工学院）；Bioinformatics Group, University & Research Wageningen, The Netherlands（生物信息学组，荷兰瓦赫宁根大学及研究学院）；Ludwig Institute for Cancer Research, Lausanne, Switzerland（癌症研究路易斯研究所，瑞士洛桑）
An Automatable Analytical Algorithm for Structure-Based Protein Functional Annotation via Detection of Specific Ligand 3D Binding Sites: Application to ATP (ser/thr Protein Kinases) and GTP (Small Ras-type G-Proteins) Binding Sites
Identifying novel functional protein structures is at the heart of molecular engineering and molecular biology, requiring an often computationally exhaustive search. We introduce the use of a Deep Convolutional Generative Adversarial Network (DCGAN) to classify protein structures based on their functionality by encoding each sample in a grid object structure using three features in each object: the generic atom type, the position atom type, and its occupancy relative to a given atom. We train DCGAN on 3-dimensional (3D) decoy and native protein structures in order to generate and discriminate …
ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning
Massachusetts Institute of Technology（麻省理工学院）；Laboratory for Atomistic and Molecular Mechanics (LAMM)（原子与分子力学实验室）；Center for Computational Science and Engineering（计算科学与工程中心）；Schwarzman College of Computing（施瓦茨曼计算学院）
Understanding and accurately predicting protein-ligand binding affinity are essential in the drug design and discovery process. At present, machine learning-based methodologies are gaining popularity as a means of predicting binding affinity due to their efficiency and accuracy, as well as the increasing availability of structural and binding affinity data for protein-ligand complexes. In biomolecular studies, graph theory has been widely applied since graphs can be used to model molecules or molecular complexes in a natural manner. In the present work, we upgrade the graph-based learners for …
