Stockinger, P. | Search bioRxiv

bioRxiv2024

GEMS: A Generalizable GNN Framework For Protein-Ligand Binding Affinity Prediction Through Robust Data Filtering and Language Model Integration

The field of computational drug design requires accurate scoring functions to predict binding affinities for protein-ligand interactions. However, train-test data leakage between the PDBbind database and the CASF benchmark datasets has significantly inflated the performance metrics of currently available deep-learning-based binding affinity prediction models, leading to overestimation of their generalization capabilities. We address this issue by proposing PDBbind CleanSplit, a training dataset curated by a novel structure-based filtering algorithm that eliminates train-test data leakage as well as redundancies within the training set. Retraining current top-performing models on CleanSplit caused their benchmark performance to drop significantly, indicating that the performance of existing models is largely driven by data leakage. In contrast, our graph neural network model for efficient molecular scoring (GEMS) maintains high benchmark performance when trained on CleanSplit. Leveraging a sparse graph modeling of protein-ligand interactions and transfer learning from language models, GEMS is able to generalize to strictly independent test datasets.

bioinformatics↗

bioRxiv2024

Chromatin Compaction Follows a Power Law Scaling with Cell Size from Interphase Through Mitosis

Coordination of mitotic chromosome compaction with cell size is crucial for proper genome segregation during mitosis. During development, DNA content remains constant but cell size evolves, necessitating a mechanism that scales chromosome compaction with cell size. In this study, we examined chromatin compaction in the developing Drosophila nervous system by analyzing the large neuronal stem cells and their smaller progeny, the ganglion mother cells. Using super-resolution 3D Stochastic Optical Reconstruction Microscopy and quantitative time-lapse fluorescence microscopy, we observed that nanoscale chromatin density during interphase scales with nuclear volume according to a power law. This scaling relationship is disrupted by inhibiting histone deacetylase activity, indicating that molecular cues rather than mechanical constraints primarily regulate chromatin compaction. Notably, this power law dependency is maintained into mitosis but the scaling exponent decreases, suggesting phase separation of chromatin events during mitotic compaction. We propose that the scaling of mitotic chromosome size relative to cell size depends on the power law behaviour of interphase chromatin volume, and that scaling of mitotic chromatin compaction is an emergent property of linear polymers undergoing phase separation with their solvent. Statement of SignificanceUnderstanding how chromatin compaction changes with cell size is essential for understanding the mechanisms ensuring accurate genome segregation during cell division. In this study, we combine Voronoi tessellation analysis of Stochastic Optical Reconstruction Microscopy and image processing methods based on fluorescence intensity spectrum analysis of live confocal images to measure chromatin volume in interphase and mitosis in cells of different sizes. This work reveals that chromatin density in Drosophila neuronal cells follows a power law relationship with nuclear volume from interphase through mitosis, suggesting a fundamental principle underlying chromosome scaling across different cell sizes. We show that this scaling is regulated by molecular cues, such as histone deacetylase activity, and is conserved through a potential phase separation during mitosis, providing new insights into the biophysical processes that govern chromatin organization. This work broadens our understanding of chromosome biology and will have implications for understanding size-dependent chromatin dynamics in other organisms.

cell biology↗