Biology subjects

Janson, G.

Publications and source records attributed to Janson, G..

5 recordsLinked to original sources

bioRxiv2025

Deep generative modeling of temperature-dependent structural ensembles of proteins

Deep learning has revolutionized protein structure prediction, but capturing conformational ensembles and structural variability remains an open challenge. While molecular dynamics (MD) is the foundation method for simulating biomolecular dynamics, it is computationally expensive. Recently, deep learning models trained on MD have made progress in generating structural ensembles at reduced cost. However, they remain limited in modeling atomistic details and, crucially, incorporating the effect of environmental factors. Here, we present aSAM (atomistic structural autoencoder model), a latent diffusion model trained on MD to generate heavy atom protein ensembles. Unlike most methods, aSAM models atoms in a latent space, greatly facilitating accurate sampling of side chain and backbone torsion angle distributions. Additionally, we extended aSAM into the first reported transferable generator conditioned on temperature, named aSAMt. Trained on the large and open mdCATH dataset, aSAMt captures temperature-dependent ensemble properties and demonstrates generalization beyond training temperatures. By comparing aSAMt ensembles to long MD simulations of fast folding proteins, we find that high-temperature training enhances the ability of deep generators to explore energy landscapes. Finally, we also show that our MD-based aSAMt can already capture experimentally observed thermal behavior of proteins. Our work is a step towards generalizable ensemble generation to complement physics- based approaches.

biophysics↗

bioRxiv2024

Accurate Predictions of Molecular Properties of Proteins via Graph Neural Networks and Transfer Learning

Machine learning has emerged as a promising approach for predicting molecular properties of proteins, as it addresses limitations of experimental and traditional computational methods. Here, we introduce GSnet, a graph neural network (GNN) trained to predict physicochemical and geometric properties including solvation free energies, diffusion constants, and hydrodynamic radii, based on three-dimensional protein structures. By leveraging transfer learning, pre-trained GSnet embeddings were adapted to predict solvent-accessible surface area (SASA) and residue-specific pKa values, achieving high accuracy and generalizability. Notably, GSnet outperformed existing protein embeddings for SASA prediction, and a locally charge-aware variant, aLCnet, approached the accuracy of simulation-based and empirical methods for pKa prediction. Our GNN framework demonstrated robustness across diverse datasets, including intrinsically disordered peptides, and scalability for high-throughput applications. These results highlight the potential of GNN-based embeddings and transfer learning to advance protein structure analysis, providing a foundation for integrating predictive models into proteome-wide studies and structural biology pipelines.

biophysics↗

bioRxiv2024

Transferable deep generative modeling of intrinsically disordered protein conformations

Intrinsically disordered proteins have dynamic structures through which they play key biological roles. The elucidation of their conformational ensembles is a challenging problem requiring an integrated use of computational and experimental methods. Molecular simulations are a valuable computational strategy for constructing structural ensembles of disordered proteins but are highly resource-intensive. Recently, machine learning approaches based on deep generative models that learn from simulation data have emerged as an efficient alternative for generating structural ensembles. However, such methods currently suffer from limited transferability when modeling sequences and conformations absent in the training data. Here, we develop a novel generative model that achieves high levels of transferability for intrinsically disordered protein ensembles. The approach, named idpSAM, is a latent diffusion model based on transformer neural networks. It combines an autoencoder to learn a representation of protein geometry and a diffusion model to sample novel conformations in the encoded space. IdpSAM was trained on a large dataset of simulations of disordered protein regions performed with the ABSINTH implicit solvent model. Thanks to the expressiveness of its neural networks and its training stability, idpSAM faithfully captures 3D structural ensembles of test sequences with no similarity in the training set. Our study also demonstrates the potential for generating full conformational ensembles from datasets with limited sampling and underscores the importance of training set size for generalization. We believe that idpSAM represents a significant progress in transferable protein ensemble modeling through machine learning. AUTHOR SUMMARYProteins are essential molecules in living organisms and some of them have highly dynamical structures, which makes understanding their biological roles challenging. Disordered proteins can be studied through a combination of computer simulations and experiments. Computer simulations are often resource-intensive. Recently, machine learning has been used to make this process more efficient. The strategy is to learn from previous simulations to model the heterogenous conformations of proteins. However, such methods still suffer from poor transferability, meaning that they tend to make incorrect predictions on proteins not seen in training data. In this study, we present idpSAM, a method based on generative artificial intelligence for modeling the structures of disordered proteins. The model was trained using a vast dataset and, thanks to its architecture and training procedure, it performs well on not just proteins in the training set but achieves high levels transferability to proteins unseen in training. This advancement is a step forward in modeling biologically relevant disordered proteins. It shows how the combination of generative modeling and large training sets and can aid us understand how dynamical proteins behave.

bioinformatics↗

bioRxiv2022

Direct Generation of Protein Conformational Ensembles via Machine Learning

Dynamics and conformational sampling are essential for linking protein structure to biological function. While challenging to probe experimentally, computer simulations are widely used to describe protein dynamics, but at significant computational costs that continue to limit the systems that can be studied. Here, we demonstrate that machine learning can be trained with simulation data to directly generate physically realistic conformational ensembles of proteins without the need for any sampling and at negligible computational cost. As a proof-of-principle a generative adversarial network based on a transformer architecture with self-attention was trained on coarse-grained simulations of intrinsically disordered peptides. The resulting model, idpGAN, can predict sequence-dependent ensembles for any sequence demonstrating that transferability can be achieved beyond the limited training data. idpGAN was also retrained on atomistic simulation data to show that the approach can be extended in principle to higher-resolution conformational ensemble generation.

biophysics↗

bioRxiv2022

Revisiting degron motifs in human AURKA required for its targeting by APC/C-FZR1

Mitotic kinase Aurora A (AURKA) diverges from other kinases in its multiple active conformations that may explain its interphase roles and association with cancer, and the limited efficacy of drugs targeting the kinase pocket. Regulation of AURKA activity by the cell is critically dependent on destruction mediated by the Anaphase-Promoting Complex (APC/CFZR1) during mitotic exit and G1 phase and requires an atypical N-terminal degron in AURKA called the A-box in addition to a reported canonical D-box degron in the C-terminus. Here we find that the proposed C-terminal D-box of AURKA does not act as a degron and instead mediates essential structural features of the protein. In living cells, as previously reported in vitro, the N-terminal intrinsically disordered region (IDR) of AURKA containing the A-box is sufficient to confer FZR1-dependent mitotic degradation. Both in silico and in cellulo assays predict the QRVL Short Linear Interacting Motif (SLiM) of the A-box to be a phospho-regulated D-box. We propose that degradation of full-length AURKA additionally depends on an intact C-terminal domain because of critical conformational parameters permissive for both activity and mitotic degradation of AURKA. Summary blurbAURKA degron motifs are redefined to show that the so-called N-terminal A-box is in fact a D-box, and the so-called D-box in the C-terminus is not a degron but a motif critical for the active, degradable conformation of AURKA

cell biology↗