Enhancing Conformational Sampling for Intrinsically Disordered and Ordered Proteins by Variational Autoencoder

Abstract

Intrinsically disordered proteins (IDPs) account for more than 50% of the human proteome and are closely associated with tumors, cardiovascular diseases, and neurodegeneration, which have no fixed three-dimensional structure under physiological conditions. Due to the characteristic of conformational diversity, conventional experimental methods of structural biology, such as NMR, X-ray diffraction, and CryoEM, are unable to capture conformational ensembles. Molecular dynamics (MD) simulation can sample the dynamic conformations at the atomic level, which has become an effective method for studying the structure and function of IDPs. However, the high computational cost prevents MD simulations from being widely used for IDPs conformational sampling. In recent years, significant progress has been made in artificial intelligence, which makes it possible to solve the conformational reconstruction problem of IDP with fewer computational resources. Here, based on short MD simulations of different IDPs systems, we use variational autoencoders (VAEs) to achieve the generative reconstruction of IDPs structures and include a wider range of sampled conformations from longer simulations. Compared with the generative autoencoder (AEs), VAEs add an inference layer between the encoder and decoder in the latent space, which can cover the conformational landscape of IDPs more comprehensively and achieve the effect of enhanced sampling. Through experimental verification, the Cα RMSD between VAE-generated and MD simulation sampling conformations in the 5 IDPs test systems was significantly lower than that of AE. The Spearman correlation coefficient on the structure was higher than that of AE. VAE can also achieve excellent performance regarding structured proteins. In summary, VAEs can be used to effectively sample protein structures.

IoT Anomaly Detection to Strengthen Cybersecurity in the Critical Infrastructure of Smart Cities

“…Furthermore, RNNs have excelled at detecting temporal and sequential patterns in data, making them especially suitable for anomaly detection problems in time series [43]. Previous studies on VAEs have revealed their ability to capture the latent structure of high-dimensional data and detect significant deviations in these data [44]. These references support the choice of these algorithms and reinforce their applicability in the context of cybersecurity for critical infrastructure in a smart city [45].…”

Phanto-IDP: compact model for precise intrinsically disordered protein backbone generation and enhanced sampling

“…We compared Phanto-IDP with MD and previously developed deep learning models [ 16 , 17 ]. The models’ ability to reconstruct individual conformation in the trajectory was evaluated using average RMSD, which measured the level of fidelity in capturing conformational features and diversity at the conformational level.…”

“…Although these approaches do ensure more sufficient sampling, they still cost a lot of computational resources and time. On the other hand, in recent years, several deep learning–based enhanced sampling methods, such as the variational autoencoder (VAE), have been proposed [ 15 , 16 ]. These methods usually train a generative model on existing MD simulation trajectories to efficiently generate novel protein conformations.…”

Protein Language Model Supervised Precise and Efficient Protein Backbone Design Method

“…In addition to being pretrained on single-state protein structures, certain methods directly learn distributional ensembles from molecular dynamics simulation trajectories, which exhibit strong correlations with our proposed methods 7,61,62 . However, these models often show suboptimal performance when applied to structured proteins, while demonstrating relatively high sample fidelity in handling intrinsically disordered proteins (IDPs), which inherently possess greater flexibility compared to structured proteins 63,64 . All these methods show the promising aspects of deep learning, pretrained and fine-tuning fashion for this biology problems.…”