Generative deep learning models have emerged as a powerful approach for de novo drug design as they aid researchers in finding new molecules with desired properties. Despite continuous improvements... Show moreGenerative deep learning models have emerged as a powerful approach for de novo drug design as they aid researchers in finding new molecules with desired properties. Despite continuous improvements in the field, a subset of the outputs that sequence-based de novo generators produce cannot be progressed due to errors. Here, we propose to fix these invalid outputs post hoc. In similar tasks, transformer models from the field of natural language processing have been shown to be very effective. Therefore, here this type of model was trained to translate invalid Simplified Molecular-Input Line-Entry System (SMILES) into valid representations. The performance of this SMILES corrector was evaluated on four representative methods of de novo generation: a recurrent neural network (RNN), a target-directed RNN, a generative adversarial network (GAN), and a variational autoencoder (VAE). This study has found that the percentage of invalid outputs from these specific generative models ranges between 4 and 89%, with different models having different error-type distributions. Post hoc correction of SMILES was shown to increase model validity. The SMILES corrector trained with one error per input alters 60-90% of invalid generator outputs and fixes 35-80% of them. However, a higher error detection and performance was obtained for transformer models trained with multiple errors per input. In this case, the best model was able to correct 60-95% of invalid generator outputs. Further analysis showed that these fixed molecules are comparable to the correct molecules from the de novo generators based on novelty and similarity. Additionally, the SMILES corrector can be used to expand the amount of interesting new molecules within the targeted chemical space. Introducing different errors into existing molecules yields novel analogs with a uniqueness of 39% and a novelty of approximately 20%. The results of this research demonstrate that SMILES correction is a viable post hoc extension and can enhance the search for better drug candidates. Show less
A drawback of the current mRNA-lipid nanoparticle (LNP) COVID-19 vaccines is that they have to be stored at (ultra)low temperatures. Understanding the root cause of the instability of these... Show moreA drawback of the current mRNA-lipid nanoparticle (LNP) COVID-19 vaccines is that they have to be stored at (ultra)low temperatures. Understanding the root cause of the instability of these vaccines may help to rationally improve mRNA-LNP product stability and thereby ease the temperature conditions for storage. In this review we discuss proposed structures of mRNA-LNPs, factors that impact mRNA-LNP stability and strategies to optimize mRNA-LNP product stability. Analysis of mRNA-LNP structures reveals that mRNA, the ionizable cationic lipid and water are present in the LNP core. The neutral helper lipids are mainly positioned in the outer, encapsulating, wall. mRNA hydrolysis is the determining factor for mRNA-LNP instability. It is currently unclear how water in the LNP core interacts with the mRNA and to what extent the degradation prone sites of mRNA are protected through a coat of ionizable cationic lipids. To improve the stability of mRNA-LNP vaccines, optimization of the mRNA nucleotide composition should be prioritized. Secondly, a better understanding of the milieu the mRNA is exposed to in the core of LNPs may help to rationalize adjustments to the LNP structure to preserve mRNA integrity. Moreover, drying techniques, such as lyophilization, are promising options still to be explored. Show less
