ABSTRACT. MSP130-related-2 is thought to play a role in biomineralization as revealed in Crassostrea gigas and sea urchins. In this study, an MSP130-related-2 gene was isolated from Hyriopsis cumingii (HcMSP130-related-2) and characterized for the first time. The HcMSP130-related-2 cDNA was 2307 bp in length and consisted of a 572-bp 5'-untranslated region (5'-UTR), a 1239-bp open reading frame encoding 430-amino acid residues, and a 439-bp 3'-UTR. The molecular weight of the peptide was predicted to be 48551.3 Da, with a theoretical isoelectric point of 4.78 and instability index of 32.74, indicating that the protein is stable. The HcMSP130-related-2 amino acid residues included a signal peptide and several potential N-glycosylation sites. NCBI BLAST analysis indicated that this full-length amino acid sequence showed the highest similarity with HcMSP130-related-2 from C. gigas (45%) and about 38% identity with that from SpMSP130-rel-2 and Strongylocentrotus purpuratus. A phylogenetic tree showed that HcMSP130-rel-2 clustered with MSP130 from C. gigas. HcMSP130-related-2 was expressed in various tissues, including the mantle, blood, gill, foot, liver, kidney, intestine, and muscle, with the highest transcripts found in the mantle. Quantitative real-time polymerase chain reaction was used to analyze the expression of the HcMSP130-related-2 gene in grass carp after inducing shell damage. HcMSP130-related-2 expression was upregulated significantly in the mantle within 7 days (P < 0.05) after damage; however, the expression remained unchanged in the adductor muscle tissues (P > 0.05). These data suggest that HcMSP130-related-2 might be involved in shell formation in H. cumingii.

Sedimentary microfacies division is the basis of oil and gas exploration research. The traditional sedimentary microfacies division mainly depends on human experience, which is greatly influenced by human factor and is low in efficiency. Although deep learning has its advantage in solving complex nonlinear problems, there is no effective deep learning method to solve sedimentary microfacies division so far. Therefore, this paper proposes a deep learning method based on DMC-BiLSTM for intelligent division of well-logging&mdash;sedimentary microfacies. First, the original curve is reconstructed multi-dimensionally by trend decomposition and median filtering, and spatio-temporal correlation clustering features are extracted from the reconstructed matrix by Kmeans. Then, taking reconstructed features, original curve features and clustering features as input, the prediction types of sedimentary microfacies at current depth are obtained based on BiLSTM. Experimental results show that this method can effectively classify sedimentary microfacies with its recognition efficiency reaching 96.84%.