Search

The rational design of PROTACs is difficult due to their obscure structure-activity relationship. This study introduces a deep neural network model - DeepPROTACs to help design potent PROTACs molecules. It can predict the degradation capacity of a proposed PROTAC molecule based on structures of given target protein and E3 ligase. The experimental dataset is mainly collected from PROTAC-DB and appropriately labeled according to the DC50 and Dmax values. In the model of DeepPROTACs, the ligands as well as the ligand binding pockets are generated and represented with graphs and fed into Graph Convolutional Networks for feature extraction. While SMILES representations of linkers are fed into a Bidirectional Long Short-Term Memory layer to generate the features. Experiments show that DeepPROTACs model achieves 77.95% average prediction accuracy and 0.8470 area under receiver operating characteristic curve on the test set. DeepPROTACs is available online at a web server (https://bailab.siais.shanghaitech.edu.cn/services/deepprotacs/) and at github (https://github.com/fenglei104/DeepPROTACs).

Binder jet 3D printing (BJ3DP) is one of the most promising 3D printing technologies, due to its ability of printing large-scale complex parts with high efficiency and low cost. The powder particle size is crucial for the sintering quality of BJ3DP. In this work, on the basis of the constitutive model of viscoplastic theory, the shape evolution (shrinkage and relative density) of cubes produced by BJ3DP using 316L stainless steel powders (normal distribution of powder sizes) with different mean particle sizes (i.e., 20, 30, 40, 50, 60, and 70 μm) was studied via finite element numerical simulation during sintering. It revealed that the volumetric shrinkage, relative density, and maximum sintering stress decreased with increasing the mean particle size. The maximum sintering stress of the sample with mean particle size of 70 μm was 0.0492 MPa, with the volumetric shrinkage of ~40% and the relative density of ~89%. In the meantime, the maximum sintering stress of the sample with mean particle size of 20 μm was 0.1789 MPa, with the volumetric shrinkage of ~48% and the relative density of ~97%. In addition, the simulated results of the relative density of assumed samples agreed well with the experimental results from the literature.