Search

With the development of online educational platforms, numerous research works have focused on the knowledge tracing task, which relates to the problem of diagnosing the changing knowledge proficiency of learners. Deep-neural-network-based models are used to explore the interaction information between students and their answer logs in the current field of knowledge tracing studies. However, those models ignore the impact of previous interactions, including the exercise relation, forget factor, and student behaviors (the slipping factor and the guessing factor). Those models also do not consider the importance of the Q-matrix, which relates exercises to knowledge points. In this paper, we propose a novel relational attention knowledge tracing (RAKT) to track the students’ knowledge proficiency in exercises. Specifically, the RAKT model incorporates the students’ performance data with corresponding interaction information, such as the context of exercises and the different time intervals between exercises. The RAKT model also takes into account the students’ interaction behaviors, including the slipping factor and the guessing factor. Moreover, consider the relationship between exercise sets and knowledge sets and the relationship between different knowledge points in the same exercise. An extension model of RAKT is called the Calibrated Q-matrix relational attention knowledge tracing model (QRAKT), which was developed using a Q-matrix calibration method based on the hierarchical knowledge levels. Experiments were conducted on two public educational datasets, ASSISTment2012 and Eedi. The results of the experiments indicated that the RAKT model and the QRAKT model outperformed the four baseline models.

Residue solvent accessibility is closely related to the spatial arrangement and packing of residues. Predicting the solvent accessibility of a protein is an important step to understand its structure and function. In this work, we present a deep learning method to predict residue solvent accessibility, which is based on a stacked deep bidirectional recurrent neural network applied to sequence profiles. To capture more long-range sequence information, a merging operator was proposed when bidirectional information from hidden nodes was merged for outputs. Three types of merging operators were used in our improved model, with a long short-term memory network performing as a hidden computing node. The trained database was constructed from 7361 proteins extracted from the PISCES server using a cut-off of 25% sequence identity. Sequence-derived features including position-specific scoring matrix, physical properties, physicochemical characteristics, conservation score and protein coding were used to represent a residue. Using this method, predictive values of continuous relative solvent-accessible area were obtained, and then, these values were transformed into binary states with predefined thresholds. Our experimental results showed that our deep learning method improved prediction quality relative to current methods, with mean absolute error and Pearson’s correlation coefficient values of 8.8% and 74.8%, respectively, on the CB502 dataset and 8.2% and 78%, respectively, on the Manesh215 dataset.

Copy number variation (CNV) is an important structural variation used to elucidate complex economic traits. In this study, we sequenced 25 Wannan spotted pigs (WSPs) to detect their CNVs and identify their selection signatures compared with those of 10 Asian wild boars. A total of 14,161 CNVs were detected in the WSPs, accounting for 0.72% of the porcine genome. The fixation index (Fst) was used to identify the selection signatures, and 195 CNVs with the top 1% of the Fst value were selected. Eighty genes were identified in the selected CNV regions. Functional GO and KEGG analyses revealed that the genes within these selected CNVs are associated with key traits such as reproduction (GAL3ST1 and SETD2), fatty acid composition (PRKG1, ACACA, ACSL3, UGT8), immune system (LYZ), ear size (WIF1), and feed efficiency (VIPR2). The findings of this study contribute novel insights into the genetic CNVs underlying WSP characteristics and provide essential information for the protection and utilization of WSP populations.

Macroalgae provide food for microbial, meio- and macro-faunal communities in coastal ecosystems, thus mediating nutrient dynamics and functions in these ecosystems. Because of this vital role, it is important to clarify physiological information about macroalgae as it reflects their growth potential in the field. In this study, we examined the biomass, pigment content, and photosynthetic O2 evolution rate versus irradiance curves of 18 macroalgal species from the intertidal zone of the Guangdong–Hong Kong–Macao Greater Bay Area, China, and investigated their photosynthetic patterns in relation to phyla characteristics, morphology, and growth locations. The results showed that green algae had the highest maximum photosynthetic O2 evolution rate (Pmax), light utilization efficiency (α), and dark respiration (Rd) among the three macroalgal phyla; the sheet-like macroalgal species had the highest Pmax, α, and Rd among the four morphological categories. The macroalgal species in the upper intertidal zone showed higher Pmax and α and lower saturation irradiance (EK) and compensation irradiance (EC) than those species in the lower intertidal location. The PCA results showed that the biomass of sheet-like macroalgal species was positively correlated with factor PC1 (50.34%), and that of finely branched species was negatively correlated with factor PC2 (25.17%). In addition, our results indicate that the light absorption and utilization capabilities of macroalgae could determine whether they could dominate the intertidal zone and that their photosynthetic characteristics could be used as a potential indicator of their biomass distribution in the Greater Bay Area.

In the preparation of ready-mixed concrete, it is inevitable to produce waste fresh concrete (WFC). An efficient, low-cost and environmentally friendly recycling scheme is the key to WFC recycling. In this work, we directly added some unhardened WFC to fresh concrete to prepare recycled fresh concrete (RFC); on this basis, fly ash (FA) and nano-silica (NS) were added as supplementary cementitious material (SCM) to obtain modified recycled fresh concrete (RFC-SF). Then, the mechanical properties, slump, freeze–thaw resistance, phase structure of the hydration products and hydration process in RFC were studied. The results show that the addition of FA and NS significantly improved the comprehensive performance of RFC. Compared with RFC, the compressive strength of RFC-SF with 15% FA and 3% NS increased by 15.2% and 50.3% at 7 d and 90 d, respectively, and the splitting tensile strength increased by 20.5% and 76.4%, respectively. The slump remained above 155 mm, and the mass loss rate decreased by 42.6% after freeze–thaw cycles. XRD and FTIR analysis showed that the addition of FA and NS accelerated the hydration reaction process of RFC-SF, reduced the content of calcium hydroxide (CH) and refined the grain size of CH. RFC-SF had a denser microstructure and a lower calcium-silicon ratio in SEM and EDS tests.

Wanbei pig (WBP) is one of the indigenous pig resources in China and has many germplasm characteristics. However, research on its genome is lacking. To assess the genomic variation, population structure, and selection signatures, we resequenced 18 WBP for the first time and performed a comprehensive analysis with resequenced data of 10 Asian wild boars. In total, 590.03 Gb of data and approximately 41 million variants were obtained. Polymorphism level (θπ) ratio and genetic differentiation (fixation index)-based cross approaches were applied, and 539 regions, which harbored 176 genes, were selected. Functional analysis of the selected genes revealed that they were associated with lipid metabolism (SCP2, APOA1, APOA4, APOC3, CD36, BCL6, ADCY8), backfat thickness (PLAG1, CACNA2D1), muscle (MYOG), and reproduction (CABS1). Overall, our results provide a valuable resource for characterizing the uniqueness of WBP and a basis for future breeding.

Intramuscular fat (IMF) deposition is an important determinant of pork quality and a complex process facilitated by non-coding ceRNAs. In this study, 52 Berkshire × Anqing Sixwhite crossbred pigs were slaughtered to measure eight carcass and pork quality traits. Whole-transcriptome sequencing analysis was performed using longissimus dorsi samples of six low- and high-IMF samples; 34 ceRNA networks, based on 881, 394, 158 differentially expressed (DE) lncRNAs, miRNAs, and mRNAs, were constructed. Following weighted gene co-expression network analysis between the low and high IMF, only one ceRNA, lncRNA4789/miR-381-3p/FABP3, that showed similar DE trend in longissimus dorsi tissue was retained. Dual-luciferase reporter assays further indicated that FABP3 was a direct, functional target of miR-381-3p, where miR-381-3p overexpression inhibited the mRNA and protein expression of FABP3. In addition, overexpressed lncRNA4789 attenuated the effect of miR-381-3p on FABP3 by sponging miR-381-3p. Cell function verification experiment demonstrated that miR-381-3p suppressed IMF deposition by inhibiting preadipocyte cell differentiation and lipid droplet deposition via the suppression of FABP3 expression in the peroxisome proliferator-activated receptor signalling pathway, whereas lncRNA4789 rescued FABP3 expression by sponging miR-381-3p. Our study may aid in identifying novel molecular markers for its optimization in IMF which is of importance in breeding for improving pork quality.

Selective laser melting (SLM) is a layer by layer process of melting and solidifying of metal powders. The surface quality of the previous layer directly affects the uniformity of the next layer. If the surface roughness value of the previous layer is large, there is the possibility of not being able to complete the layering process such that the entire process has to be abandoned. At least, it may result in long term durability problem and the inhomogeneity, may even make the processed structure not be able to be predicted. In the present study, the ability of a fiber laser to in-situ polish the rough surfaces of four typical additive-manufactured alloys, namely, Ti6Al4V, AlSi10Mg, 316L and IN718 was demonstrated. The results revealed that the surface roughness of the as-received alloys could be reduced to about 3 μm through the application of the laser-polishing process, and the initial surfaces had roughness values of 8.80−16.64 μm. Meanwhile, for a given energy density, a higher laser power produced a laser-polishing effect that was often more obvious, with the surface roughness decreasing with an increase in the laser power. Further, the polishing strategy will be optimized by simulation in our following study.

Solanesol, an aliphatic terpene alcohol composed of nine isoprene units, is mainly found in solanaceous plants. Particularly, tobacco (Nicotiana tabacum), belonging to the Solanaceae family, is the richest plant source of solanesol, and its leaves have been regarded as the ideal material for solanesol extraction. Since the discovery of solanesol in tobacco, significant progress has been achieved in research on solanesol’s bioactivities, medicinal value, accumulation, extraction technology, and determination methods. Solanesol possesses strong free radical absorption ability and antioxidant activity owing to the presence of several non-conjugated double bonds. Notably, solanesol’s anti-inflammatory, neuroprotective, and antimicrobial activities have been previously demonstrated. Solanesol is a key intermediate in the synthesis of coenzyme Q10, vitamin K2, and the anticancer agent synergiser N-solanesyl-N,N′-bis(3,4-dimethoxybenzyl) ethylenediamine. Other applications of solanesol include solanesol derivative micelles for hydrophobic drug delivery, solanesol-derived scaffolds for bioactive peptide multimerization, and solanesol-anchored DNA for mediating vesicle fusion. Solanesol accumulation in plants is influenced by genetic and environmental factors, including biotic stresses caused by pathogen infections, temperature, illumination, and agronomic measures. Seven extraction technologies and seven determination methods of solanesol are also systematically summarized in the present review. This review can serve as a reference for solanesol’s comprehensive application.