Significant research on deep neural networks, culminating in AlphaFold2, convincingly shows that deep learning can predict the na- tive structure of a given protein sequence with high accuracy. In contrast, work on deep learning frameworks that can account for the structural plasticity of protein molecules remains in its infancy. Many researchers are now investigating deep generative models to explore the structure space of a protein. Current models largely use 2D convolution, leveraging representations of protein structures as contact maps or distance matri- ces. The goal is exclusively to generate protein-like, sequence-agnostic tertiary structures, but no rigorous metrics are utilized to convincingly make this case. This paper makes several contributions. It builds on momentum in graph representation learning and formalizes a protein tertiary structure as a contact graph. It demonstrates that graph repre- sentation learning outperforms models based on image convolution. This work also equips graph-based deep latent variable models with the abil- ity to learn from experimentally-available tertiary structures of proteins of varying lengths. The resulting models are shown to outperform state- of-the-art ones on rigorous metrics that quantify both local and distal patterns in physically-realistic protein structures. We hope this work will spur further research in deep generative models for obtaining a broader view of the structure space of a protein molecule.
more »
« less
Guiding Protein Conformation Sampling with Conformation Space Maps
Deep learning research, from ResNet to AlphaFold2, convincingly shows that deep learning can predict the native conformation of a given protein sequence with high accu- racy. Accounting for the plasticity of protein molecules remains challenging, and powerful algorithms are needed to sample the conformation space of a given amino-acid sequence. In the complex and high-dimensional energy surface that accompanies this space, it is critical to explore a broad range of areas. In this paper, we present a novel evolutionary algorithm that guides its optimization process with a memory of the explored conformation space, so that it can avoid searching already explored regions and search in the unexplored regions. The algorithm periodically consults an evolving map that stores already sampled non- redundant conformations to enhance exploration during selection. Evaluation on diverse datasets shows superior performance of the algorithm over the state-of-the-art algorithms.
more » « less- PAR ID:
- 10342807
- Date Published:
- Journal Name:
- EPiC Series in Computing
- Volume:
- 83
- ISSN:
- 2398-7340
- Page Range / eLocation ID:
- 20 to 8
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
more » « less
Abstract Machine learning has been increasingly used for protein engineering. However, because the general sequence contexts they capture are not specific to the protein being engineered, the accuracy of existing machine learning algorithms is rather limited. Here, we report ECNet (evolutionary context-integrated neural network), a deep-learning algorithm that exploits evolutionary contexts to predict functional fitness for protein engineering. This algorithm integrates local evolutionary context from homologous sequences that explicitly model residue-residue epistasis for the protein of interest with the global evolutionary context that encodes rich semantic and structural features from the enormous protein sequence universe. As such, it enables accurate mapping from sequence to function and provides generalization from low-order mutants to higher-order mutants. We show that ECNet predicts the sequence-function relationship more accurately as compared to existing machine learning algorithms by using ~50 deep mutational scanning and random mutagenesis datasets. Moreover, we used ECNet to guide the engineering of TEM-1 β-lactamase and identified variants with improved ampicillin resistance with high success rates.
-
Knowles, David A ; Mostafavi, Sara (Ed.)Accurately modeling protein 3D structure is essential for the design of functional proteins. An important sub-task of structure modeling is protein side-chain packing: predicting the conformation of side-chains (rotamers) given the protein’s backbone structure and amino-acid sequence. Conventional approaches for this task rely on expensive sampling procedures over hand-crafted energy functions and rotamer libraries. Recently, several deep learning methods have been developed to tackle the problem in a data-driven way, albeit with vastly different formulations (from image-to-image translation to directly predicting atomic coordinates). Here, we frame the problem as a joint regression over the side-chains’ true degrees of freedom: the dihedral $\chi$ angles. We carefully study possible objective functions for this task, while accounting for the underlying symmetries of the task. We propose Holographic Packer (H-Packer), a novel two-stage algorithm for side-chain packing built on top of two light-weight rotationally equivariant neural networks. We evaluate our method on CASP13 and CASP14 targets. H-Packer is computationally efficient and shows favorable performance against conventional physics-based algorithms and is competitive against alternative deep learning solutions.more » « less
-
more » « less
A central challenge in template-free protein structure prediction is controlling the quality of computed tertiary structures also known as decoys. Given the size, dimensionality, and inherent characteristics of the protein structure space, this is non-trivial. The current mechanism employed by decoy generation algorithms relies on generating as many decoys as can be afforded. This is impractical and uninformed by any metrics of interest on a decoy dataset. In this paper, we propose to equip a decoy generation algorithm with an evolving map of the protein structure space. The map utilizes low-dimensional representations of protein structure and serves as a memory whose granularity can be controlled. Evaluations on diverse target sequences show that drastic reductions in storage do not sacrifice decoy quality, indicating the promise of the proposed mechanism for decoy generation algorithms in template-free protein structure prediction.
-
We have long known that characterizing protein structures structure is key to understanding protein function. Computational approaches have largely addressed a narrow formulation of the problem, seeking to compute one native structure from an amino-acid sequence. Now AlphaFold2 promises to reveal a high-quality native structure for possibly many proteins. However, researchers over the years have argued for broadening our view to account for the multiplicity of native structures. We now know that many protein molecules switch between different structures to regulate interactions with molecular partners in the cell. Elucidating such structures de novo is exceptionally difficult, as it requires exploration of possibly a very large structure space in search of competing, near-optimal structures. Here we report on a novel stochastic optimization method capable of revealing very different structures for a given protein from knowledge of its amino-acid sequence. The method leverages evolutionary search techniques and adapts its exploration of the search space to balance between exploration and exploitation in the presence of a computational budget. In addition to demonstrating the utility of this method for identifying multiple native structures, we additionally provide a benchmark dataset for researchers to continue work on this problem.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.29007/gfdc
