Leveraging attention-enhanced variational autoencoders: Novel approach for investigating latent space of aptamer sequences.

Aptamers are increasingly recognized as potent alternatives to antibodies for diagnostic and therapeutic applications. The application of deep learning, particularly attention-based models, for aptamer (DNA/RNA) sequences is an innovative field. The ongoing advancements in aptamer sequencing technologies coupled with machine learning algorithms have resulted in novel developments. Further research is required to investigate the full potential of deep learning models and address the challenges associated with the generation of sequences, like the large search space of possible sequences. In this study, we propose a workflow that integrates an attention mechanism within a framework of a generative variational autoencoder, to generate novel sequences by expanding latent memory. They show 100 % novelty compared with the dataset, and approximately 88 % of them show negative values for the minimum free energy, which may indicate the likelihood of an RNA sequence folding into a functional structure. Because the field of aptamer discovery is affected by data scarcity, advanced strategies that facilitate the generation of diverse and superior sequences are necessitated. The utilization of our workflow can result in novel aptamers. Thus, investigations such as the present study can address the abovementioned challenge. Our research is anticipated to facilitate further discoveries and advancements in aptamer fields.

The use of machine learning modeling, virtual screening, molecular docking, and molecular dynamics simulations to identify potential VEGFR2 kinase inhibitors.

Targeting the signaling pathway of the Vascular endothelial growth factor receptor-2 is a promising approach that has drawn attention in the quest to develop novel anti-cancer drugs and cardiovascular disease treatments. We construct a screening pipeline using machine learning classification integrated with similarity checks of approved drugs to find new inhibitors. The statistical metrics reveal that the random forest approach has slightly better performance. By further similarity screening against several approved drugs, two candidates are selected. Analysis of absorption, distribution, metabolism, excretion, and toxicity, along with molecular docking and dynamics are performed for the two candidates with regorafenib as a reference. The binding energies of molecule1, molecule2, and regorafenib are - 89.1, - 95.3, and - 87.4 (kJ/mol), respectively which suggest candidate compounds have strong binding to the target. Meanwhile, the median lethal dose and maximum tolerated dose for regorafenib, molecule1, and molecule2 are predicted to be 800, 1600, and 393 mg/kg, and 0.257, 0.527, and 0.428 log mg/kg/day, respectively. Also, the inhibitory activity of these compounds is predicted to be 7.23 and 7.31, which is comparable with the activity of pazopanib and sorafenib drugs. In light of these findings, the two compounds could be further investigated as potential candidates for anti-angiogenesis therapy.

BoostSweet: Learning molecular perceptual representations of sweeteners.

The development of safe artificial sweeteners has attracted considerable interest in the food industry. Previous machine learning (ML) studies based on quantitative structure-activity relationships have provided some molecular principles for predicting sweetness, but these models can be improved via the chemical recognition of sweetness active factors. Our ML model, a soft-vote ensemble model that has a light gradient boosting machine and uses both layered fingerprints and alvaDesc molecular descriptor features, demonstrates state-of-the-art performance, with an AUROC score of 0.961. Based on an analysis of feature importance and dataset, we identified that the number of nitrogen atoms that serve as hydrogen bond donors in molecules can play an essential role in determining sweetness. These results potentially provide an advanced understanding of the relationship between molecular structure and sweetness, which can be used to design new sweeteners based on molecular structural dependence.

Frustrated molecular packing in highly ordered smectic phase of side-chain liquid crystalline polymer with rigid polyacetylene backbone.

Using poly(5-{[(4'-heptoxy-4-biphenylyl)carbonyl]oxy}-1-pentyne) as an example, we demonstrate the incorporative accommodation of the rigid polyacetylene backbones and the mesogenic pendants, which leads to a highly ordered smectic (Sm) phase with a frustrated structure. The polymer exhibits a recognizable sheetlike molecular shape due to its rigid backbone and relatively short spacer (three methylene units), and the building block of the liquid crystalline (LC) phase is the whole molecule. In the LC phase, five layers of the molecules stack as a smectic A (SmA) block, and adjacent SmA blocks glide halfway of the molecular width from one to another. In scanning tunneling microscopy (STM) experiments, the STM tip scrape is found to generate a regular nanopattern with periodic electron conductivity, of which the spacing is determined by the side-chain length.

Binuclear homoleptic manganese carbonyls: Mn2(CO)x (x = 10, 9, 8, 7).

The unsaturated homoleptic manganese carbonyls Mn(2)(CO)(n)() (n = 7, 8, 9) are characterized by their equilibrium geometries, thermochemistry, and vibrational frequencies using methods from density functional theory (DFT). The computed metal-metal distances for global minima range from 3.01 A for the unbridged Mn(2)(CO)(10) with a Mn-Mn single bond to 2.14 A for a monobridged Mn(2)(CO)(7) formulated with a metal-metal quadruple bond. The global minimum for Mn(2)(CO)(9) has a four-electron bridging mu-eta(2)-CO group and a 2.96 A Mn-Mn distance suggestive of the single bond required for 18-electron configurations for both metal atoms. This structure is closely related to an experimentally realized structure for the isolated and structurally characterized stable phosphine complex [R(2)PCH(2)PR(2)](2)Mn(2)(CO)(4)(mu-eta(2)-CO). An unbridged (OC)(4)Mn-Mn(CO)(5) structure for Mn(2)(CO)(9) has only slightly (<6 kcal/mol) higher energy with a somewhat shorter metal-metal distance of 2.77 A. For Mn(2)(CO)(8) the lowest energy structure is a D(2)(d)() unbridged structure with a 2.36 A metal-metal distance suggesting the triple bond required for the favored 18-electron configuration for both metal atoms. However, the unbridged unsymmetrical (CO)(3)Mn-Mn(CO)(5) structure with a metal-metal bond distance of 2.40 A lies only 1 to 3 kcal/mol above this global minimum. The lowest energy structure of Mn(2)(CO)(7) is an unbridged C(s)() structure with a short metal-metal distance of 2.26 A. This is followed energetically by another C(s)() unbridged Mn(2)(CO)(7) structure with a somewhat longer metal-metal distance of 2.38 A.