Current drug discovery processes can cost billions of dollars and usually take five to ten years. People have been researching and implementing various computational approaches to search for molecules and compounds from the chemical space, which can be on the order of 1060 molecules. One solution involves deep generative models, which are artificial intelligence models that learn from nonlinear data by modeling the probability distribution of chemical structures and creating similar data points from the trends it identifies. Aiming for faster runtime and greater robustness when analyzing high-dimensional data, we designed and implemented a Hybrid Quantum-Classical Generative Adversarial Network (QGAN) to synthesize molecules.

Ischemic stroke occurs when blood flow to the brain is interrupted, causing brain damage. This study investigated the effectiveness of different NOX inhibitors as treatments for ischemic stroke in silico. The results help corroborate previous in vivo and in vitro studies in an in silico format, and can be used towards developing drugs to treat ischemic stroke.

Social media is widely used and easily accessible for adolescents, it has the potential to increase STEM (Science, Technology, Engineering, and Math) identity in girls. We aimed to investigate the effects of exposure to counter-stereotypical portrayals of women in STEM on social media on the STEM identity of adolescent girls. The study concluded that social media alone may not be an effective tool to increase STEM identity in girls. Social media can still be used as a complementary tool to support and encourage women in STEM, but it should not be relied upon solely to address the gender disparity in STEM fields.

Crumpling is the process whereby a sheet of paper undergoes deformation to yield a three-dimensional structure comprising a random network of ridges and facets with variable density. The authors hypothesized that the more times a paper sheet is crumpled, the greater its compressive strength. Their results show a relatively strong linear relationship between the number of times a paper sheet is crumpled and its compressive strength.

The authors looked at how a 3D bioprinter could be used to model the blood brain barrier.

The authors use pictures of candy wrappers and neural networks to improve nutritional accuracy of diet-tracking apps.

Recurrent neural networks (RNNs) are useful for text generation since they can generate outputs in the context of previous ones. Baroque music and language are similar, as every word or note exists in context with others, and they both follow strict rules. The authors hypothesized that if we represent music in a text format, an RNN designed to generate language could train on it and create music structurally similar to Bach’s. They found that the music generated by our RNN shared a similar structure with Bach’s music in the input dataset, while Bachbot’s outputs are significantly different from this experiment’s outputs and thus are less similar to Bach’s repertoire compared to our algorithm.

In this study, the authors investigated the time-dependent cytokine secretion ability of phyto-hemagglutinin (PHA)-activated T cells derived from human peripheral (PB) and cord blood (CB). They hypothesized that the anti-inflammatory cytokine, IL-10, and pro-inflammatory cytokine, TNFα, levels would be higher in PHA-activated T cells obtained from PB as compared to the levels obtained from CB and would decrease over time. Upon PHA-activation, the IL-10 levels were relatively high while the TNFα levels decreased, making these findings applicable in therapeutic treatments e.g., rheumatoid arthritis, psoriasis, and organ transplantation.

Human intelligence is correlated with variation in the protein neuroplastin-65, which is encoded by the NPTN gene. The authors examine the evolution of this gene across different animal species.

Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.