Search

Abstract Diagnosing Parkinson's disease (PD) in its early stages is a significant challenge in medicine. Hand tremors and dysgraphia, which are typical early motor symptoms of PD, can manifest for decades before a formal diagnosis is made. Therefore, handwriting analysis has become an important tool for detecting PD. While many machine learning algorithms have been applied in this area, they struggle to capture the subtle changes in handwriting and must describe features from various perspectives. To address these issues, this paper proposes a Coordinate Attention Enhanced Swin Transformer (CAS Transformer) model for PD handwriting recognition. It establishes the long‐term dependence of features on the joint coordinate attention application, which enables the model to more accurately localize the important features of handwriting data and also extract the fuzzy edge features of handwriting images.These characteristics of the CAS Transformer enable it to outperform current advanced deep learning methods in classification, with an accuracy of 92.68% in experiments conducted on two handwritten datasets.

Glycans are an important group of natural biopolymers, which not only play the role of a major biological energy resource but also as signaling molecules. As a result, structural characterization or sequencing of glycans, as well as targeted synthesis of glycans, is of great interest for understanding their structure–function relationship. However, this generally involves tedious manual operations and high reagent consumptions, which are the main technical bottlenecks retarding the advances of both automatic glycan sequencing and synthesis. Until now, automated enzymatic glycan sequencers or synthesizers are still not available on the market. In this study, to promote the development of automation in glycan sequencing or synthesis, first, programmed degradation and synthesis of glycans catalyzed by enzymes were successfully conducted on a digital microfluidic (DMF) device by using microdroplets as microreactors. In order to develop automatic glycan synthesizers and sequencers, a strategy integrating enzymatic oligosaccharide degradation or synthesis and magnetic manipulation to realize the separation and purification process after enzymatic reactions was designed and performed on DMF. An automatic process for enzymatic degradation of tetra-N-acetyl chitotetraose was achieved. Furthermore, the two-step enzymatic synthesis of lacto-N-tetraose was successfully and efficiently completed on the DMF platform. This work demonstrated here would open the door to further develop automatic enzymatic glycan synthesizers or sequencers based on DMF.

Abstract A novel expansin-like protein (CxEXL22) has been identified and characterized from newly isolated Arthrobotrys sp. CX1 that can cause cellulose decrystallization. Unlike previously reported expansin-like proteins from microbes, CxEXL22 has a parallel β-sheet domain at the N terminal, containing many hydrophobic residues to form the hydrophobic surface as part of the groove. The direct phylogenetic relationship implied the genetic transfers occurred from nematode to nematicidal fungal Arthrobotrys sp. CX1. CxEXL22 showed strong activity for the hydrolysis of hydrogen bonds between cellulose molecules, especially when highly crystalline cellulose was used as substrate. The hydrolysis efficiency of Avicel was increased 7.9-fold after pretreating with CxEXL22. The rupture characterization of crystalline region indicated that CxEXL22 strongly binds cellulose and breaks up hydrogen bonds in the crystalline regions of cellulose to split cellulose chains, causing significant depolymerization to expose much more microfibrils and enhances cellulose accessibility.