In situ structure of actin remodeling during glucose-stimulated insulin secretion using cryo-electron tomography

Actin mediates insulin secretion in pancreatic β-cells through remodeling. Hampered by limited resolution, previous studies have offered an ambiguous depiction as depolymerization and repolymerization. We report the in situ structure of actin remodeling in INS-1E β-cells during glucose-stimulated insulin secretion at nanoscale resolution. After remodeling, the actin filament network at the cell periphery exhibits three marked differences: 12% of actin filaments reorient quasi-orthogonally to the ventral membrane; the filament network mainly remains as cell-stabilizing bundles but partially reconfigures into a less compact arrangement; actin filaments anchored to the ventral membrane reorganize from a "netlike" to a "blooming" architecture. Furthermore, the density of actin filaments and microtubules around insulin secretory granules decreases, while actin filaments and microtubules become more densely packed. The actin filament network after remodeling potentially precedes the transport and release of insulin secretory granules. These findings advance our understanding of actin remodeling and its role in glucose-stimulated insulin secretion.

TEFDTA: a transformer encoder and fingerprint representation combined prediction method for bonded and non-bonded drug-target affinities

MOTIVATION

The prediction of binding affinity between drug and target is crucial in drug discovery. However, the accuracy of current methods still needs to be improved. On the other hand, most deep learning methods focus only on the prediction of non-covalent (non-bonded) binding molecular systems, but neglect the cases of covalent binding, which has gained increasing attention in the field of drug development.

RESULTS

In this work, a new attention-based model, A Transformer Encoder and Fingerprint combined Prediction method for Drug-Target Affinity (TEFDTA) is proposed to predict the binding affinity for bonded and non-bonded drug-target interactions. To deal with such complicated problems, we used different representations for protein and drug molecules, respectively. In detail, an initial framework was built by training our model using the datasets of non-bonded protein-ligand interactions. For the widely used dataset Davis, an additional contribution of this study is that we provide a manually corrected Davis database. The model was subsequently fine-tuned on a smaller dataset of covalent interactions from the CovalentInDB database to optimize performance. The results demonstrate a significant improvement over existing approaches, with an average improvement of 7.6% in predicting non-covalent binding affinity and a remarkable average improvement of 62.9% in predicting covalent binding affinity compared to using BindingDB data alone. At the end, the potential ability of our model to identify activity cliffs was investigated through a case study. The prediction results indicate that our model is sensitive to discriminate the difference of binding affinities arising from small variances in the structures of compounds.

AVAILABILITY AND IMPLEMENTATION

The codes and datasets of TEFDTA are available at https://github.com/lizongquan01/TEFDTA.