Search

The prevalence of autism spectrum disorder (ASD) has risen rapidly in recent decades. Owing to its success across disciplines, the use of artificial intelligence (AI) in the screening of ASD has emerged as a prominent solution. We conducted a bibliometric analysis on AI-powered ASD screening research with a unit of 2090 publications retrieved from Scopus database in the period 2010–2021. Our findings show, among other things, that the annual growth rate of publications was 33.05% and scientific production drastically increased 23-fold from 22 in 2010 to 509 in 2021 with nearly two thirds (1307; 62,54%) of the retrieved documents being published between 2019–2021. The USA was the global leader in terms of scientific output with 730 publications followed by China (255), and India (251). Stanford university, the scientific journal NeuroImage, and Dennis P. Wall were the most globally prolific institution, publication source, and author, respectively. Using VOSviewer's clustering algorithms, keyword and topic analysis identified neuroimaging techniques and genetic research as hot and emerging research trends. Interestingly, three of the top ten prolific authors were women, indicating a significant milestone for gender rebalancing efforts in the AI workforce. The findings will help both experienced and aspiring scientists better understand the structure and current state of knowledge, uncover patterns of collaboration, and identify emerging trends in ASD research using AI. [ABSTRACT FROM AUTHOR]

DNA data storage is a rapidly developing technology with great potential due to its high density, long-term durability, and low maintenance cost. The major technical challenges include various errors, such as strand breaks, rearrangements, and indels that frequently arise during DNA synthesis, amplification, sequencing, and preservation. In this study, a de novo strand assembly algorithm (DBGPS) is developed using de Bruijn graph and greedy path search to meet these challenges. DBGPS shows substantial advantages in handling DNA breaks, rearrangements, and indels. The robustness of DBGPS is demonstrated by accelerated aging, multiple independent data retrievals, deep error-prone PCR, and large-scale simulations. Remarkably, 6.8 MB of data is accurately recovered from a severely corrupted sample that has been treated at 70 °C for 70 days. With DBGPS, we are able to achieve a logical density of 1.30 bits/cycle and a physical density of 295 PB/g. DNA data storage is a rapidly developing technology with great potential due to its high density, long-term durability, and low maintenance cost. Here the authors present a strand assembly algorithm (DBGPS) using de Bruijn graph and greedy path search. [ABSTRACT FROM AUTHOR]

Accurate identification of protein-nucleotide binding residues is crucial for the study of drug structure and protein functional annotation. The study of protein-nucleotide binding residues is a typical problem of sample imbalance. The minority class (binding residues) are far less than the majority class (non-binding residues). The traditional machine learning algorithm is not universal for this kind of research, the results will be seriously biased to majority class. To deal with the serious imbalance problem, we propose a new computational method to identify protein-nucleotide binding residues via Graph Regularized k-local Hyperplane Distance Nearest Neighbor (GHKNN). On the training set, we compare the performance of the basic classifier, the ensemble classifier and the single classifier. On the independent test sets, we compare the performance with other existing models. The experimental results prove that our proposed method has higher accuracy in the identification of protein-nucleotide binding residues and is more prominent than other existing models. The data and material are freely available at https://github.com/guofei-tju/GHKNN. [ABSTRACT FROM AUTHOR]

RNA-binding proteins play an important role in the biological process. However, the traditional experiment technology to predict RNA-binding residues is time-consuming and expensive, so the development of an effective computational approach can provide a strategy to solve this issue. In recent years, most of the computational approaches are constructed on protein sequence information, but the protein structure has not been considered. In this paper, we use a novel computational model of RNA-binding residues prediction, using protein sequence and structure information. Our hybrid features are encoded by local sequence and structure feature extraction models. Our predictor is built by employing the Granular Multiple Kernel Support Vector Machine with Repetitive Under-sampling (GMKSVM-RU). In order to evaluate our method, we use fivefold cross-validation on the RBP129, our method achieves better experimental performance with MCC of 0.3367 and accuracy of 88.84%. In order to further evaluate our model, an independent data set (RBP60) is employed, and our method achieves MCC of 0.3921 and accuracy of 87.52%. Above results demonstrate that integrating sequence and structure information is beneficial to improve the prediction ability of RNA-binding residues. [ABSTRACT FROM AUTHOR]

Retinal diseases can be found timely by observing retinal fundus images. So extracting blood vessels from retinal images is an important part because it is the way to show the changes of vessels. However, most of the previous methods based on deep learning cared more about accuracy and ignored the complexity of the model for segmenting retinal vessels, which makes these methods difficult to apply to medical equipment. Besides, due to the great differences in the width of retinal vessels, some methods cannot well-extract all blood vessels at the same time. Based on above limitations, we propose a new lightweight network, called Res2Unet. It applies a multi-scale strategy to extract blood vessels of different widths and integrates the strategy into the channels to greatly reduce parameters and computation resources. Res2Unet also uses channel-attention mechanism to promote the communication between channels and recalibrate the relationship of channel features. Then, we propose two post-processing methods. One called the local threshold method(LTM) uses a lower local threshold to excavate hidden blood vessels in discontinuous blood vessels of the probability maps. The other named weighted correction method (WCM) combines the probability maps of Unet and Res2Unet to remove false positive and false negative samples. On the DRIVE dataset, the Dice, IOU and AUC of our Res2Unet reach 0.8186, 0.6926 and 0.9772, respectively, which are better than that of Unet with 0.8109, 0.6817 and 0.9751. Importantly, the number of parameters of Res2Unet are about one-third of Unet. It means that Res2Unet has less hardware requirements. [ABSTRACT FROM AUTHOR]