Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron

Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compound and a known target ligand have been established in ligand-based virtual screens (LBVSs). However, despite the good performances of the above methods compared to their predecessors, especially when dealing with molecules that have structurally homogenous active elements, they are not satisfied when dealing with molecules that are structurally heterogeneous. The main aim of this study is to improve the performance of similarity searching, especially with molecules that are structurally heterogeneous. The Siamese network will be used due to its capability to deal with complicated data samples in many fields. The Siamese multi-layer perceptron architecture will be enhanced by using two similarity distance layers with one fused layer, then multiple layers will be added after the fusion layer, and then the nodes of the model that contribute less or nothing during inference according to their signal-to-noise ratio values will be pruned. Several benchmark datasets will be used, which are: the MDL Drug Data Report (MDDR-DS1, MDDR-DS2, and MDDR-DS3), the Maximum Unbiased Validation (MUV), and the Directory of Useful Decoys (DUD). The results show the outperformance of the proposed method on standard Tanimoto coefficient (TAN) and other methods. Additionally, it is possible to reduce the number of nodes in the Siamese multilayer perceptron model while still keeping the effectiveness of recall on the same level.

Alignment Effects in Spatial Perspective Taking from an External Vantage Point

In three experiments, we examined, using a perceptual task, the difficulties of spatial perspective taking. Participants imagined adopting perspectives around a table and pointed from them towards the positions of a target. Depending on the condition, the scene was presented on a virtual screen in Virtual Reality or projected on an actual screen in the real world (Experiment 1), or viewed as immediate in Virtual Reality (Experiment 2). Furthermore, participants pointed with their arm (Experiments 1 and 2) vs. a joystick (Experiment 3). Results showed a greater alignment effect (i.e., a larger difference in performance between trials with imagined perspectives that were aligned vs. misaligned with the orientation of the participant) when executing the task in a virtual rather than in the real environment, suggesting that visual access to body information and room geometry, which is typically lacking in Virtual Reality, influences perspective taking performance. The alignment effect was equal across the Virtual Reality conditions of Experiment 1 and Experiment 2, suggesting that being an internal (compared to an external) observer to the scene induces no additional difficulties for perspective taking. Equal alignment effects were also found when pointing with the arm vs. a joystick, indicating that a body-dependent response mode such as pointing with the arm creates no further difficulties for reasoning from imagined perspectives.

An Android Mobile-based Measurement Application – Object and Interior Room Measurement App

The conventional and most common way to measure the interior of a room is using a measuring tape and other similar tools. However, it is not productive and often more than one worker is required to assist the measurement process. The goal of this study is to discuss the acceptability and usability of Android-based measurement mobile app designed for interior designers, civil engineer designers and water pipe workers. The user can take the measurement of the traditional form of the interior room from the image captured and to give the result of the area of space from the measurement taken from the image. The developed mobile app includes a virtual screen ruler to measure the approximate length and width of the room. This can be achieved by having a reference scale from the user and the camera lens must be focused at the study points. The result is then calculated from the video stream through the camera. The data obtained is then formulated in the area in order to obtain the result of the space area. The user will receive the results on the display screen as soon as the calculation is carried out. Later, the results revealed that, while not part of the original research goal, the applications can also be used to calculate the height and length of an object. Finally, an extended review of the mobile app is provided, which shows its high applicability and user acceptability.

Recent Progress in the Drug Development Targeting SARS-CoV-2 Main Protease as Treatment for COVID-19

The sudden outbreak of 2019 novel coronavirus (2019-nCoV, later named SARS-CoV-2) rapidly turned into an unprecedented pandemic of coronavirus disease 2019 (COVID-19). This global healthcare emergency marked the third occurrence of a deadly coronavirus (CoV) into the human society after entering the new millennium, which overwhelmed the worldwide healthcare system and affected the global economy. However, therapeutic options for COVID-19 are still very limited. Developing drugs targeting vital proteins in viral life cycle is a feasible approach to overcome this dilemma. Main protease (Mpro) plays a dominant role in processing CoV-encoded polyproteins which mediate the assembly of replication-transcription machinery and is thus recognized as an ideal antiviral target. Here we summarize the recent progress in the discovery of anti-SARS-CoV-2 agents against Mpro. Combining structural study, virtual screen, and experimental screen, numerous therapeutic candidates including repurposed drugs and ab initio designed compounds have been proposed. Such collaborative effort from the scientific community would accelerate the pace of developing efficacious treatment for COVID-19.

Virtual Screening Identifies Chebulagic Acid as an Inhibitor of the M2(S31N) Viral Ion Channel and Influenza A Virus

The increasing prevalence of drug-resistant influenza viruses emphasizes the need for new antiviral countermeasures. The M2 protein of influenza A is a proton-gated, proton-selective ion channel, which is essential for influenza replication and an established antiviral target. However, all currently circulating influenza A virus strains are now resistant to licensed M2-targeting adamantane drugs, primarily due to the widespread prevalence of an M2 variant encoding a serine to asparagine 31 mutation (S31N). To identify new chemical leads that may target M2(S31N), we performed a virtual screen of molecules from two natural product libraries and identified chebulagic acid as a candidate M2(S31N) inhibitor and influenza antiviral. Chebulagic acid selectively restores growth of M2(S31N)-expressing yeast. Molecular modeling also suggests that chebulagic acid hydrolysis fragments preferentially interact with the highly-conserved histidine residue within the pore of M2(S31N) but not adamantane-sensitive M2(S31). In contrast, chebulagic acid inhibits in vitro influenza A replication regardless of M2 sequence, suggesting that it also acts on other influenza targets. Taken together, results implicate chebulagic acid and/or its hydrolysis fragments as new chemical leads for M2(S31N) and influenza-directed antiviral development.

2-amino-1,3-benzothiazole-6-carboxamide Preferentially Binds the Tandem Mismatch Motif r(UY:GA)

RNA helices are often punctuated with non-Watson-Crick features that can be the target of chemical compounds, but progress towards identifying small molecules specific for non-canonical elements has been slow. We have used a tandem UU:GA mismatch motif (5’-UG-3’:5’-AU-3’) embedded within the helix of an RNA hairpin as a model to identify compounds that bind the motif specifically. The three-dimensional structure of the RNA hairpin and its interaction with a small molecule compound identified through a virtual screen are presented. The G-A of the mismatch forms a sheared pair upon which the U-U base pair stacks. The hydrogen bond configuration of the U-U pair involves the O2 of the U adjacent to the G and the O4 of the U adjacent to the A. The G-A and U-U pairs are flanked by A-U and G-C base pairs, respectively, and the mismatch exhibits greater stability than when the motif is within the context of other flanking base pairs or when the 5’-3’ orientation of the G-A and U-U is swapped. Residual dipolar coupling constants were used to generate an ensemble of structures against which a virtual screen of 64,480 small molecules was performed to identify candidate compounds that the motif specifically binds. The tandem mismatch was found to be specific for one compound, 2-amino-1,3-benzothiazole-6-carboxamide, which binds with moderate affinity but extends the motif to include the flanking A-U and G-C base pairs. The finding that affinity for the UU:GA mismatch is flanking sequence dependent emphasizes the importance of motif context and potentially increases the number of small non-canonical features within RNA that can be specifically targeted by small molecules.