Drug–Target Interaction Deep Learning-Based Model Identifies the Flavonoid Troxerutin as a Candidate TRPV1 Antagonist

Based on the advances made by artificial intelligence (AI) technologies in drug discovery, including target identification, hit molecule identification, and lead optimization, this study investigated natural compounds that could act as transient receptor potential vanilloid 1 (TRPV1) channel protein antagonists. Using a molecular transformer drug–target interaction (MT-DTI) model, troxerutin was predicted to be a TRPV1 antagonist at IC50 582.73 nM. In a TRPV1-overexpressing HEK293T cell line, we found that troxerutin antagonized the calcium influx induced by the TRPV1 agonist capsaicin in vitro. A structural modeling and docking experiment of troxerutin and human TRPV1 confirmed that troxerutin could be a TRPV1 antagonist. A small-scale clinical trial consisting of 29 participants was performed to examine the efficacy of troxerutin in humans. Compared to a vehicle lotion, both 1% and 10% w/v troxerutin lotions reduced skin irritation, as measured by skin redness induced by capsaicin, suggesting that troxerutin could ameliorate skin sensitivity in clinical practice. We concluded that troxerutin is a potential TRPV1 antagonist based on the deep learning MT-DTI model prediction. The present study provides a useful reference for target-based drug discovery using AI technology and may provide useful information for the integrated research field of AI technology and biology.

Drug Discovery in Real Life: An Online Learning Activity for Bioinformatics Students

During COVID-19 lockdowns, online learning activities had to be developed for the Undergraduate and Masters by Coursework Bioinformatics students at RMIT University. Therefore, we designed an integrative, industry-based research assignment, which guided the students through a drug discovery project from target identification to lead optimization. The students were able to utilize this real-life scenario to apply multiple diverse but complementary bioinformatic principles to analyze biological and chemical data leading to meaningful predictions. This activity was utilized as a final assessment of the students' knowledge.

Research on Intelligent Fingertip Blood Collection Robot

At present, fingertip blood sampling is mainly done manually by medical workers. Under the COVID-19 epidemic, medical workers are easily infected, in addition, the finger needs to be squeezed to increase the amount of bleeding during the blood collection process, which will cause the cell fluid to enter the blood and cause the test results to be inaccurate. This paper presents a kind of design about an intelligent fingertip blood sampling robot. We get the finger vein image through the near-infrared imaging module, and select the vein intersection area as the blood collection point after image segmentation, which will be helpful in improving the amount of bleeding. We use the laser to guide the end of the blood collection robot puncture needle and blood collection vessels to achieve rapid and accurate blood puncture and blood collection operation. The experimental results show that the maximum deviation between the blood sampling needle and the blood sampling point does not exceed 0.15mm and the longest time from fingertip blood sampling point selection to guide the blood sampling needle to the blood sampling point is less than 9.8 seconds. © 2021 ACM.

Recognition efficiency of atypical cardiovascular readings on ECG devices through fogged goggles.

In their continuing battle against the COVID-19 pandemic, medical workers in hospitals worldwide need to wear safety glasses and goggles to protect their eyes from the possible transmission of the virus. However, they work for long hours and need to wear a mask and other personal protective equipment, which causes their protective eye wear to fog up. This fogging up of eye wear, in turn, has a substantial impact in the speed and accuracy of reading information on the interface of electrocardiogram (ECG) machines. To gain a better understanding of the extent of the impact, this study experimentally simulates the fogging of protective goggles when viewing the interface with three variables: the degree of fogging of the goggles, brightness of the screen, and color of the font of the cardiovascular readings. This experimental study on the target recognition of digital font is carried out by simulating the interface of an ECG machine and readability of the ECG machine with fogged eye wear. The experimental results indicate that the fogging of the lenses has a significant impact on the recognition speed and the degree of fogging has a significant correlation with the font color and brightness of the screen. With a reduction in screen brightness, its influence on recognition speed shows a v-shaped trend, and the response time is the shortest when the screen brightness is 150 cd/m2. When eyewear is fogged, yellow and green font colors allow a quicker response with a higher accuracy. On the whole, the subjects show a better performance with the use of green font, but there are inconsistencies. In terms of the interaction among the three variables, the same results are also found and the same conclusion can be made accordingly. This research study can act as a reference for the interface design of medical equipment in events where medical staff wear protective eyewear for a long period of time.

Identifying the Structure of CSCL Conversations Using String Kernels

Computer-Supported Collaborative Learning tools are exhibiting an increased popularity in education, as they allow multiple participants to easily communicate, share knowledge, solve problems collaboratively, or seek advice. Nevertheless, multi-participant conversation logs are often hard to follow by teachers due to the mixture of multiple and many times concurrent discussion threads, with different interaction patterns between participants. Automated guidance can be provided with the help of Natural Language Processing techniques that target the identification of topic mixtures and of semantic links between utterances in order to adequately observe the debate and continuation of ideas. This paper introduces a method for discovering such semantic links embedded within chat conversations using string kernels, word embeddings, and neural networks. Our approach was validated on two datasets and obtained state-of-the-art results on both. Trained on a relatively small set of conversations, our models relying on string kernels are very effective for detecting such semantic links with a matching accuracy larger than 50% and represent a better alternative to complex deep neural networks, frequently employed in various Natural Language Processing tasks where large datasets are available.