Body Weight Estimation for Pigs Based on 3D Hybrid Filter and Convolutional Neural Network.

The measurement of pig weight holds significant importance for producers as it plays a crucial role in managing pig growth, health, and marketing, thereby facilitating informed decisions regarding scientific feeding practices. On one hand, the conventional manual weighing approach is characterized by inefficiency and time consumption. On the other hand, it has the potential to induce heightened stress levels in pigs. This research introduces a hybrid 3D point cloud denoising approach for precise pig weight estimation. By integrating statistical filtering and DBSCAN clustering techniques, we mitigate weight estimation bias and overcome limitations in feature extraction. The convex hull technique refines the dataset to the pig's back, while voxel down-sampling enhances real-time efficiency. Our model integrates pig back parameters with a convolutional neural network (CNN) for accurate weight estimation. Experimental analysis indicates that the mean absolute error (MAE), mean absolute percent error (MAPE), and root mean square error (RMSE) of the weight estimation model proposed in this research are 12.45 kg, 5.36%, and 12.91 kg, respectively. In contrast to the currently available weight estimation methods based on 2D and 3D techniques, the suggested approach offers the advantages of simplified equipment configuration and reduced data processing complexity. These benefits are achieved without compromising the accuracy of weight estimation. Consequently, the proposed method presents an effective monitoring solution for precise pig feeding management, leading to reduced human resource losses and improved welfare in pig breeding.

Instance Segmentation and Ensemble Learning for Automatic Temperature Detection in Multiparous Sows.

The core body temperature serves as a pivotal physiological metric indicative of sow health, with rectal thermometry prevailing as a prevalent method for estimating core body temperature within sow farms. Nonetheless, employing contact thermometers for rectal temperature measurement proves to be time-intensive, labor-demanding, and hygienically suboptimal. Addressing the issues of minimal automation and temperature measurement accuracy in sow temperature monitoring, this study introduces an automatic temperature monitoring method for sows, utilizing a segmentation network amalgamating YOLOv5s and DeepLabv3+, complemented by an adaptive genetic algorithm-random forest (AGA-RF) regression algorithm. In developing the sow vulva segmenter, YOLOv5s was synergized with DeepLabv3+, and the CBAM attention mechanism and MobileNetv2 network were incorporated to ensure precise localization and expedited segmentation of the vulva region. Within the temperature prediction module, an optimized regression algorithm derived from the random forest algorithm facilitated the construction of a temperature inversion model, predicated upon environmental parameters and vulva temperature, for the rectal temperature prediction in sows. Testing revealed that vulvar segmentation IoU was 91.50%, while the predicted MSE, MAE, and R2 for rectal temperature were 0.114 °C, 0.191 °C, and 0.845, respectively. The automatic sow temperature monitoring method proposed herein demonstrates substantial reliability and practicality, facilitating an autonomous sow temperature monitoring.

CAT-CBAM-Net: An Automatic Scoring Method for Sow Body Condition Based on CNN and Transformer.

Sow body condition scoring has been confirmed as a vital procedure in sow management. A timely and accurate assessment of the body condition of a sow is conducive to determining nutritional supply, and it takes on critical significance in enhancing sow reproductive performance. Manual sow body condition scoring methods have been extensively employed in large-scale sow farms, which are time-consuming and labor-intensive. To address the above-mentioned problem, a dual neural network-based automatic scoring method was developed in this study for sow body condition. The developed method aims to enhance the ability to capture local features and global information in sow images by combining CNN and transformer networks. Moreover, it introduces a CBAM module to help the network pay more attention to crucial feature channels while suppressing attention to irrelevant channels. To tackle the problem of imbalanced categories and mislabeling of body condition data, the original loss function was substituted with the optimized focal loss function. As indicated by the model test, the sow body condition classification achieved an average precision of 91.06%, the average recall rate was 91.58%, and the average F1 score reached 91.31%. The comprehensive comparative experimental results suggested that the proposed method yielded optimal performance on this dataset. The method developed in this study is capable of achieving automatic scoring of sow body condition, and it shows broad and promising applications.

Visible-Light-Promoted C(sp3 )-H Alkylation by Intermolecular Charge Transfer: Preparation of Unnatural α-Amino Acids and Late-Stage Modification of Peptides.

Disclosed herein is the visible-light-promoted deaminative C(sp3 )-H alkylation of glycine and peptides using Katritzky salts as electrophiles. Simple reaction conditions and excellent functional-group tolerance provide a general strategy for the efficient preparation of unnatural α-amino acids and precise modification of peptides with unnatural α-amino-acid residues. Mechanistic studies suggest that visible-light-promoted intermolecular charge transfer within a glycine-Katritzky salt electron donor-acceptor (EDA) complex induces a single-electron transfer process without the assistance of photocatalyst.

Estimation of Weight and Body Measurement Model for Pigs Based on Back Point Cloud Data.

Pig farming is a crucial sector in global animal husbandry. The weight and body dimension data of pigs reflect their growth and development status, serving as vital metrics for assessing their progress. Presently, pig weight and body dimensions are predominantly measured manually, which poses challenges such as difficulties in herding, stress responses in pigs, and the control of zoonotic diseases. To address these issues, this study proposes a non-contact weight estimation and body measurement model based on point cloud data from pig backs. A depth camera was installed above a weighbridge to acquire 3D point cloud data from 258 Yorkshire-Landrace crossbred sows. We selected 200 Yorkshire-Landrace sows as the research subjects and applied point cloud filtering and denoising techniques to their three-dimensional point cloud data. Subsequently, a K-means clustering segmentation algorithm was employed to extract the point cloud corresponding to the pigs' backs. A convolutional neural network with a multi-head attention was established for pig weight prediction and added RGB information as an additional feature. During the data processing process, we also measured the back body size information of the pigs. During the model evaluation, 58 Yorkshire-Landrace sows were specifically selected for experimental assessment. Compared to manual measurements, the weight estimation exhibited an average absolute error of 11.552 kg, average relative error of 4.812%, and root mean square error of 11.181 kg. Specifically, for the MACNN, incorporating RGB information as an additional feature resulted in a decrease of 2.469 kg in the RMSE, a decrease of 0.8% in the MAPE, and a decrease of 1.032 kg in the MAE. Measurements of shoulder width, abdominal width, and hip width yielded corresponding average relative errors of 3.144%, 3.798%, and 3.820%. In conclusion, a convolutional neural network with a multi-head attention was established for pig weight prediction, and incorporating RGB information as an additional feature method demonstrated accuracy and reliability for weight estimation and body dimension measurement.

Visible-light-mediated catalyst-free synthesis of unnatural α-amino acids and peptide macrocycles.

The visible light induced, photocatalysts or photoabsorbing EDA complexes mediated cleavage of pyridinium C-N bond were reported in the past years. Here, we report an ionic compound promote homolytic cleavage of pyridinium C-N bond by exploiting the photonic energy from visible light. This finding is successfully applied in deaminative hydroalkylation of a series of alkenes including naturally occurring dehydroalanine, which provides an efficient way to prepare ß-alkyl substituted unnatural amino acids under mild and photocatalyst-free conditions. Importantly, by using this protocol, the deaminative cyclization of peptide backbone N-terminals is realized. Furthermore, the use of Et3N or PPh3 as reductants and H2O as hydrogen atom source is a practical advantage. We anticipate that our protocol will be useful in peptide synthesis and modern peptide drug discovery.

Discovery of pentapeptide-inhibitor hits targeting FKBP51 by combining computational modeling and X-ray crystallography.

FKBP51 is well-known as a cochaperone of Hsp90 machinery and implicated in many human diseases including stress-related diseases, tau-mediated neurodegeneration and cancers, which makes FKBP51 an attractive drug target for the therapy of FKBP51-associated diseases. However, it has been reported that only nature product rapamycin, cyclosporine A, FK506 and its derivatives exhibit good binding affinities when bound to FKBP51 by now. Given the advantages of peptide-inhibitors, we designed and obtained 20 peptide-inhibitor hits through structure-based drug design. We further characterized the interaction modes of the peptide-inhibitor hits on the FK1 domain of FKBP51 by biochemical and structural biology methods. Structural analysis revealed that peptide-inhibitor hits form U-shaped conformations and occupy the FK506 binding pocket and share similar interaction modes with FK506. Using molecular dynamics simulations, we delved into the interaction dynamics and found that hits are anchored to the FK506 binding pocket in a quite stable conformation. Meanwhile, it was shown that interactions between FK1 and peptide-inhibitor hits are mainly attributed to the hydrogen bond networks comprising I87 and Y113 and FPF cores of peptide-inhibitors involved extensive hydrophobic interactions. We presumed that the peptide design strategy based on the small molecule structure probably shed new lights on the peptide-inhibitor discovery of other targets. The findings presented here could also serve as a structural basis and starting point facilitating the optimization and generation of FKBP51 peptide-inhibitors with better bio-activities.

Intranasal MMI-0100 Attenuates Aß1-42- and LPS-Induced Neuroinflammation and Memory Impairments via the MK2 Signaling Pathway.

Background: Accumulating evidence suggests inhibiting neuroinflammation as a potential target in therapeutic or preventive strategies for Alzheimer's disease (AD). MAPK-activated protein kinase II (MK2), downstream kinase of p38 mitogen activated protein kinase (MAPK) p38 MAPK, was unveiled as a promising option for the treatment of AD. Increasing evidence points at MK2 as involved in neuroinflammatory responses. MMI-0100, a cell-penetrating peptide inhibitor of MK2, exhibits anti-inflammatory effects and is in current clinical trials for the treatment of pulmonary fibrosis. Therefore, it is important to understand the actions of MMI-0100 in neuroinflammation. Methods: The mouse memory function was evaluated using novel object recognition (NOR) and object location recognition (OLR) tasks. Brain hippocampus tissue samples were analyzed by quantitative PCR, Western blotting, and immunostaining. Near-infrared fluorescent and confocal microscopy experiments were used to detect the brain uptake and distribution after intranasal MMI-0100 application. Results: Central MMI-0100 was able to ameliorate the memory deficit induced by Aß1-42 or LPS in novel object and location memory tasks. MMI-0100 suppressed LPS-induced activation of astrocytes and microglia, and dramatically decreased a series of pro-inflammatory cytokines such as TNF-α, IL-6, IL-1ß, COX-2, and iNOS via inhibiting phosphorylation of MK2, but not ERK, JNK, and p38 in vivo and in vitro. Importantly, one of the reasons for the failure of macromolecular protein or peptide drugs in the treatment of AD is that they cannot cross the blood-brain barrier. Our data showed that intranasal administration of MMI-0100 significantly ameliorates the memory deficit induced by Aß1-42 or LPS. Near-infrared fluorescent and confocal microscopy experiment results showed that a strong fluorescent signal, coming from mouse brains, was observed at 2 h after nasal applications of Cy7.5-MMI-0100. However, brains from control mice treated with saline or Cy7.5 alone displayed no significant signal. Conclusions: MMI-0100 attenuates Aß1-42- and LPS-induced neuroinflammation and memory impairments via the MK2 signaling pathway. Meanwhile, these data suggest that the MMI-0100/MK2 system may provide a new potential target for treatment of AD.