DeepPath: Overcoming data scarcity for protein transition pathway prediction using physics-based deep learning

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Март 2, 2025

The structural dynamics of proteins play a crucial role in their function, yet most experimental and deep learning methods produce only static models. While molecular (MD) simulations provide atomistic insight into conformational transitions, they remain computationally prohibitive, particularly for large-scale motions. Here, we introduce DeepPath, deep-learning-based framework that rapidly generates physically realistic transition pathways between known protein states. Unlike conventional supervised approaches, DeepPath employs active to iteratively refine its predictions, leveraging mechanical force fields as an oracle guide pathway generation. We validated on three biologically relevant test cases: SHP2 activation, CdiB H1 secretion, the BAM complex lateral gate opening. accurately predicted all cases, reproducing key intermediate structures transient interactions observed previous studies. Notably, also inwardand outward-open states closely aligns with experimentally hybrid-barrel structure (TMscore = 0.91). Across achieved accurate predictions within hours, showcasing efficient alternative MD exploring transitions.

Язык: Английский

AlphaFold2-Based Characterization of Apo and Holo Protein Structures and Conformational Ensembles Using Randomized Alanine Sequence Scanning Adaptation: Capturing Shared Signature Dynamics and Ligand-Induced Conformational Changes

International Journal of Molecular Sciences, Год журнала: 2024, Номер 25(23), С. 12968 - 12968

Опубликована: Дек. 2, 2024

Proteins often exist in multiple conformational states, influenced by the binding of ligands or substrates. The study these particularly apo (unbound) and holo (ligand-bound) forms, is crucial for understanding protein function, dynamics, interactions. In current study, we use AlphaFold2, which combines randomized alanine sequence masking with shallow alignment subsampling to expand diversity predicted structural ensembles capture changes between forms. Using several well-established datasets structurally diverse apo-holo pairs, proposed approach enables robust predictions structures ensembles, while also displaying notably similar dynamics distributions. These observations are consistent view that intrinsic allosteric proteins defined topology fold favor conserved motions driven soft modes. Our findings provide evidence AlphaFold2 combined can yield accurate results predicting moderate adjustments especially localized upon ligand binding. For large hinge-like domain movements, predict functional conformations characteristic both ligand-bound absence information. relevant using this AlphaFold adaptation probing selection mechanisms according adopt conformations, including those competent indicate modeling states may require more characterization flexible regions detection high-energy conformations. By incorporating a wider variety training datasets, model learn recognize occur

Язык: Английский

Assessing Structures and Conformational Ensembles of Apo and Holo Protein States Using Randomized Alanine Sequence Scanning Combined with Shallow Subsampling in AlphaFold2 : Insights and Lessons from Predictions of Functional Allosteric Conformations

bioRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 6, 2024

Abstract Proteins often exist in multiple conformational states, influenced by the binding of ligands or substrates. The study these particularly apo (unbound) and holo (ligand-bound) forms, is crucial for understanding protein function, dynamics, interactions. In current study, we use AlphaFold2 that combines randomized alanine sequence masking with shallow alignment subsampling to expand diversity predicted structural ensembles capture changes between forms. Using several well-established datasets structurally diverse apo-holo pairs, proposed approach enables robust predictions structures ensembles, while also displaying notably similar dynamics distributions. These observations are consistent view intrinsic allosteric proteins defined topology fold favors conserved motions driven soft modes. Our findings support notion approaches can yield reasonable accuracy predicting minor adjustments especially moderate localized upon ligand binding. However, large, hinge-like domain movements, tends predict most stable orientation which typically form rather than full range functional conformations characteristic ensemble. results indicate modeling states may require more accurate characterization flexible regions detection high energy conformations. By incorporating a wider variety training including both model learn recognize occur

Язык: Английский