ChemReco: automated recognition of hand-drawn carbon-hydrogen-oxygen structures using deep learning.

Chemical molecular structures are a direct and convenient means of expressing chemical knowledge, playing a vital role in academic communication. In chemistry, hand drawing is a common task for students and researchers. If we can convert hand-drawn chemical molecular structures into machine-readable formats, like SMILES encoding, computers can efficiently process and analyze these structures, significantly enhancing the efficiency of chemical research. Furthermore, with the progress of educational technology, automated grading is gaining popularity. When machines automatically recognize chemical molecular structures and assess the correctness of the drawings, it offers great convenience to teachers. We created ChemReco, a tool designed to identify chemical molecular structures involving three atoms: C, H, and O, providing convenience for chemical researchers. Currently, there are limited studies on hand-drawn chemical molecular structures. Therefore, the primary focus of this paper is constructing datasets. We propose a synthetic image method to rapidly generate images resembling hand-drawn chemical molecular structures, enhancing dataset acquisition efficiency. Regarding model selection, the hand-drawn chemical molecule structural recognition model developed in this article achieves a final recognition accuracy of 96.90%. This model employs the encoder-decoder architecture of EfficientNet + Transformer, demonstrating superior performance compared to other encoder-decoder combinations.

Subnano-Fe (Co, Ni) clusters anchored on halloysite nanotubes: an efficient Fenton-like catalyst for the degradation of tetracycline.

Iron-based catalysts are environmentally friendly, and iron minerals are abundant in the earth's crust, with great potential advantages for PMS-based advanced oxidation process applications. However, homogeneous Fe2+/PMS systems suffer from side reactions and are challenging to reuse. Therefore, developing catalysts with improved stability and activity is a long-term goal for practical Fe-based catalyst applications. In this study, we prepared Fe-HNTs nanoreactors by encapsulating a nitrogen-doped carbon layer with one-dimensional halloysite nanotubes (HNTs) using the molten salt-assisted method. Subsequently, Fe (Co, Ni) nanoclusters were anchored onto the nitrogen-doped carbon layer at a relatively low temperature (550℃), resulting in stable and uniform distribution of metal nanoclusters on the surface of HNTs carriers in the form of Fe-Nx coordination. The results showed that the dissolution of the molten salt and leaching of post-treated metal oxides generated numerous mesopores within the Fe-HNTs nanoreactor, leading to a specific surface area more than 10 times that of HNTs. This enhanced mass transfer capability facilitates rapid pollutant removal while exposing more active sites. Remarkably, Fe-HNTs adsorbed up to 97% of tetracycline within 60 min. In the Fe-HNTs/PMS system, the predominant reactive oxygen species has been shown to be 1O2, and the added tetracycline was degraded by more than 98% within 5 min. The removal of tetracycline was maintained above 96% in the presence of interfering factors such as wide pH (3-11) and inorganic anions (5 mM Cl-, HCO3-, NO3-, and SO42-). The investigated mechanism suggests that efficient degradation and interference resistance of the Fe-HNTs/PMS system is attributed to the synergistic effect between the rapid adsorption of porous structure and the non-radical (1O2)-dominated degradation pathway.

Development of high-resolution multiple-SNP arrays for genetic analyses and molecular breeding through genotyping by target sequencing and liquid chip.

Genotyping platforms, as critical supports for genomics, genetics, and molecular breeding, have been well implemented at national institutions/universities in developed countries and multinational seed companies that possess high-throughput, automatic, large-scale, and shared facilities. In this study, we integrated an improved genotyping by target sequencing (GBTS) system with capture-in-solution (liquid chip) technology to develop a multiple single-nucleotide polymorphism (mSNP) approach in which mSNPs can be captured from a single amplicon. From one 40K maize mSNP panel, we developed three types of markers (40K mSNPs, 251K SNPs, and 690K haplotypes), and generated multiple panels with various marker densities (1K-40K mSNPs) by sequencing at different depths. Comparative genetic diversity analysis was performed with genic versus intergenic markers and di-allelic SNPs versus non-typical SNPs. Compared with the one-amplicon-one-SNP system, mSNPs and within-mSNP haplotypes are more powerful for genetic diversity detection, linkage disequilibrium decay analysis, and genome-wide association studies. The technologies, protocols, and application scenarios developed for maize in this study will serve as a model for the development of mSNP arrays and highly efficient GBTS systems in animals, plants, and microorganisms.

The high diversity of SARS-CoV-2-related coronaviruses in pangolins alerts potential ecological risks.

Understanding the zoonotic origin and evolution history of SARS-CoV-2 will provide critical insights for alerting and preventing future outbreaks. A significant gap remains for the possible role of pangolins as a reservoir of SARS-CoV-2 related coronaviruses (SC2r-CoVs). Here, we screened SC2r-CoVs in 172 samples from 163 pangolin individuals of four species, and detected positive signals in muscles of four Manis javanica and, for the first time, one M. pentadactyla. Phylogeographic analysis of pangolin mitochondrial DNA traced their origins from Southeast Asia. Using in-solution hybridization capture sequencing, we assembled a partial pangolin SC2r-CoV (pangolin-CoV) genome sequence of 22 895 bp (MP20) from the M. pentadactyla sample. Phylogenetic analyses revealed MP20 was very closely related to pangolin-CoVs that were identified in M. javanica seized by Guangxi Customs. A genetic contribution of bat coronavirus to pangolin-CoVs via recombination was indicated. Our analysis revealed that the genetic diversity of pangolin-CoVs is substantially higher than previously anticipated. Given the potential infectivity of pangolin-CoVs, the high genetic diversity of pangolin-CoVs alerts the ecological risk of zoonotic evolution and transmission of pathogenic SC2r-CoVs.

The Novel Sensor Network Structure for Classification Processing Based on the Machine Learning Method of the ACGAN.

To address the problem of unstable training and poor accuracy in image classification algorithms based on generative adversarial networks (GAN), a novel sensor network structure for classification processing using auxiliary classifier generative adversarial networks (ACGAN) is proposed in this paper. Firstly, the real/fake discrimination of sensor samples in the network has been canceled at the output layer of the discriminative network and only the posterior probability estimation of the sample tag is outputted. Secondly, by regarding the real sensor samples as supervised data and the generative sensor samples as labeled fake data, we have reconstructed the loss function of the generator and discriminator by using the real/fake attributes of sensor samples and the cross-entropy loss function of the label. Thirdly, the pooling and caching method has been introduced into the discriminator to enable more effective extraction of the classification features. Finally, feature matching has been added to the discriminative network to ensure the diversity of the generative sensor samples. Experimental results have shown that the proposed algorithm (CP-ACGAN) achieves better classification accuracy on the MNIST dataset, CIFAR10 dataset and CIFAR100 dataset than other solutions. Moreover, when compared with the ACGAN and CNN classification algorithms, which have the same deep network structure as CP-ACGAN, the proposed method continues to achieve better classification effects and stability than other main existing sensor solutions.