Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userPDBench: Evaluating Computational Methods for Protein Sequence Design
561
0
0.0
(
0
)
Ask ChatGPT about the research
No Arabic abstract
Proteins perform critical processes in all living systems: converting solar energy into chemical energy, replicating DNA, as the basis of highly performant materials, sensing and much more. While an incredible range of functionality has been sampled in nature, it accounts for a tiny fraction of the possible protein universe. If we could tap into this pool of unexplored protein structures, we could search for novel proteins with useful properties that we could apply to tackle the environmental and medical challenges facing humanity. This is the purpose of protein design. Sequence design is an important aspect of protein design, and many successful methods to do this have been developed. Recently, deep-learning methods that frame it as a classification problem have emerged as a powerful approach. Beyond their reported improvement in performance, their primary advantage over physics-based methods is that the computational burden is shifted from the user to the developers, thereby increasing accessibility to the design method. Despite this trend, the tools for assessment and comparison of such models remain quite generic. The goal of this paper is to both address the timely problem of evaluation and to shine a spotlight, within the Machine Learning community, on specific assessment criteria that will accelerate impact. We present a carefully curated benchmark set of proteins and propose a number of standard tests to assess the performance of deep learning based methods. Our robust benchmark provides biological insight into the behaviour of design methods, which is essential for evaluating their performance and utility. We compare five existing models with two novel models for sequence prediction. Finally, we test the designs produced by these models with AlphaFold2, a state-of-the-art structure-prediction algorithm, to determine if they are likely to fold into the intended 3D shapes.
rate research
Read More
Motivation: Bridging the exponentially growing gap between the number of unlabeled and labeled proteins, a couple of works have adopted semi-supervised learning for protein sequence modeling. They pre-train a model with a substantial amount of unlabeled data and transfer the learned representations to various downstream tasks. Nonetheless, the current pre-training methods mostly rely on a language modeling task and often show limited performances. Therefore, a complementary protein-specific task for pre-training is necessary to better capture the information contained within unlabeled protein sequences. Results: In this paper, we introduce a novel pre-training scheme called PLUS, which stands for Protein sequence representations Learned Using Structural information. PLUS consists of masked language modeling and a complementary protein-specific pre-training task, namely same family prediction. PLUS can be used to pre-train various model architectures. In this work, we mainly use PLUS to pre-train a recurrent neural network (RNN) and refer to the resulting model as PLUS-RNN. It advances state-of-the-art pre-training methods on six out of seven tasks, i.e., (1) three protein(-pair)-level classification, (2) two protein-level regression, and (3) two amino-acid-level classification tasks. Furthermore, we present results from our ablation studies and interpretation analyses to better understand the strengths of PLUS-RNN. Availability: The codes and pre-trained models are available at https://github.com/mswzeus/PLUS/
Background: Typically, proteins perform key biological functions by interacting with each other. As a consequence, predicting which protein pairs interact is a fundamental problem. Experimental methods are slow, expensive, and may be error prone. Many computational methods have been proposed to identify candidate interacting pairs. When accurate, they can serve as an inexpensive, preliminary filtering stage, to be followed by downstream experimental validation. Among such methods, sequence-based ones are very promising. Results: We present MPS(T&B) (Maximum Protein Similarity Topological and Biological), a new algorithm that leverages both topological and biological information to predict protein-protein interactions. We comprehensively compare MPS(T) and MPS(T&B) with state-of-the-art approaches on reliable PPIs datasets, showing that they have competitive or higher accuracy on biologically validated test sets. Conclusion: MPS(T) and MPS(T&B) are topological only and topological plus sequence-based computational methods that can effectively predict the entire human interactome.
The novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a major worldwide public health emergency that has infected over $1.5$ million people. The partially open state of S1 subunit in spike glycoprotein is considered vital for its infection with host cell and is represented as a key target for neutralizing antibodies. However, the mechanism elucidating the transition from the closed state to the partially open state still remains unclear. Here, we applied a combination of Markov state model, transition path theory and random forest to analyze the S1 motion. Our results explored a promising complete conformational movement of receptor-binding domain, from buried, partially open, to detached states. We also numerically confirmed the transition probability between those states. Based on the asymmetry in both the dynamics behavior and backbone C$alpha$ importance, we further suggested a relation between chains in the trimer spike protein, which may help in the vaccine design and antibody neutralization.
Normal mode analysis offers an efficient way of modeling the conformational flexibility of protein structures. Simple models defined by contact topology, known as elastic network models, have been used to model a variety of systems, but the validation is typically limited to individual modes for a single protein. We use anisotropic displacement parameters from crystallography to test the quality of prediction of both the magnitude and directionality of conformational variance. Normal modes from four simple elastic network model potentials and from the CHARMM forcefield are calculated for a data set of 83 diverse, ultrahigh resolution crystal structures. While all five potentials provide good predictions of the magnitude of flexibility, the methods that consider all atoms have a clear edge at prediction of directionality, and the CHARMM potential produces the best agreement. The low-frequency modes from different potentials are similar, but those computed from the CHARMM potential show the greatest difference from the elastic network models. This was illustrated by computing the dynamic correlation matrices from different potentials for a PDZ domain structure. Comparison of normal mode results with anisotropic temperature factors opens the possibility of using ultrahigh resolution crystallographic data as a quantitative measure of molecular flexibility. The comprehensive evaluation demonstrates the costs and benefits of using normal mode potentials of varying complexity. Comparison of the dynamic correlation matrices suggests that a combination of topological and chemical potentials may help identify residues in which chemical forces make large contributions to intramolecular coupling.
Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We train a 1.2B-parameter language model, ProGen, on ~280M protein sequences conditioned on taxonomic and keyword tags such as molecular function and cellular component. This provides ProGen with an unprecedented range of evolutionary sequence diversity and allows it to generate with fine-grained control as demonstrated by metrics based on primary sequence similarity, secondary structure accuracy, and conformational energy.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
