Ming Liu

Dr. Ming Liu


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 February 2020 in Genes
Verified
Journal Article
Open access
PDF file
MLMing Liu
Ming Liu
TYTing Yu
Ting Yu
PSPuneet Kumar Singh
Puneet Kumar Singh
QLQinjian Liu
Qinjian Liu
HLHao Liu
Hao Liu
HHhuanqing he
huanqing he
The edible straw mushroom, Volvariella volvacea, is one of the most important cultivated mushrooms in tropical and sub-tropical regions. Strain improvement for V. volvacea is difficult because of the unknown mechanisms involved in its growth regulation and substrate utilization. A comparative physiological and transcriptomic study was conducted between two commercially available straw mushroom strains (v9 and v26) to explore their fast-growth regulation mechanism(s). The physiological study showed that V. volvacea v9 had a shorter growth cycle and higher biological efficiency (4% higher) than that in v26. At least 14,556 unigenes were obtained from the four cDNA libraries (two replicates per strain). Among them, the expression of 1597 unigenes was up-regulated while 1352 were down-regulated. Four heat-shock proteins were highly expressed in v9, showing that v9 has the better ability to handle stresses and/or environmental changes. Moreover, up to 14 putative transporter genes were expressed at a higher level in v9 than those in v26, implying that v9 has a better ability to transport nutrients or export xenobiotics efficiently. Our report allows to identify the candidate genes involved in the fast growth requirement of V. volvacea, which represents a valuable resource for strain improvement in this commercially important edible mushroom.

29 November 2022 in Horticulturae
Verified
Journal Article
Open access
PDF file
TLTongkai Li
Tongkai Li
HHHuamao Huang
Huamao Huang
YPYangyang Peng
Yangyang Peng
HZHui Zhou
Hui Zhou
HHHaiying Hu
Haiying Hu
MLMing Liu
Ming Liu
As a traditional edible and medicinal fungus in China, Oudemansiella raphanipes has high economic benefits. In order to achieve the automatic classification of Oudemansiella raphanipes into four quality levels using their image dataset, a quality grading algorithm based on neural network models was proposed. At first, the transfer learning strategy and six typical convolution neural network models, e.g., VGG16, ResNet50, InceptionV3, NasNet-Mobile, EfficientNet, and MobileNetV2, were used to train the datasets. Experiments show that MobileNetV2 has good performance considering both testing accuracy and detection time. MobileNetV2 only needs 37.5 ms to classify an image, which is shorter by 11.76%, 28.57%, 46.42%, 59.45%, and 79.73%, respectively, compared with the classification times of InceptionV3, EfficientNetB0, ResNet50, NasNet-Mobile, and VGG16. Based on the original MobileNetV2 model, four optimization methods, including data augmentation, hyperparameter selecting, an overfitting control strategy, and a dynamic learning rate strategy, were adopted to improve the accuracy. The final classification accuracy can reach as high as 98.75%, while the detection time for one image is only 22.5 ms and the model size is only 16.48 MB. This quality grading algorithm based on an improved MobileNetV2 model is feasible and effective for Oudemansiella raphanipes, satisfying the needs in the production line.

22 February 2024 in Horticulturae
Verified
Journal Article
Open access
PDF file
ZLZhu Liu
Zhu Liu
JWJianhao Wang
Jianhao Wang
LKLinzhi Kang
Linzhi Kang
YPYangyang Peng
Yangyang Peng
LYLuyao Ye
Luyao Ye
MLMing Liu
Ming Liu
As one of the most nutritious and delicious mushroom varieties, Volvariella volvacea has always been popular among people around the world. Different from other artificially cultivated mushrooms, Volvariella volvacea is mostly planted on non-sterile substrates. As the cultivation time increases, the yield of mushroom houses continues to decrease. In our experiment, we selected two groups of samples from the old and new mushroom houses, environmental samples and substrate samples. The results showed that the diversity and abundance of microorganisms in the culture environment of the old mushroom room were consistent with that of the new mushroom room, but the proportion of actinomycetes in the former was significantly higher than that of the new mushroom room. The metabolic activity of microorganisms in the old mushroom room was enhanced compared with the new mushroom room. The microbial diversity in the growth substrate was investigated, and it was found that the structure and diversity of the microbial community in the substrate had changed. In conclusion, the interplay between mushrooms, the culture environment, and the host bacterial community may be the cause of the changes in the yield of Volvariella volvacea.

30 January 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
CHChen Haoxuan
Chen Haoxuan
HHHuamao Huang
Huamao Huang
YPYangyang Peng
Yangyang Peng
HZHui Zhou
Hui Zhou
HHHaiying Hu
Haiying Hu
MLMing Liu
Ming Liu
Oudemansiella raphanipes is valued for its rich nutritional content and medicinal properties, but traditional manual grading methods are time-consuming and labor-intensive. To address this, deep learning techniques are employed to automate the grading process, and knowledge distillation (KD) is used to enhance the accuracy of a small-parameter model while maintaining a low resource occupation and fast response speed in resource-limited devices. This study employs a three-teacher KD framework and investigates three cascaded structures: the parallel model, the standard series model, and the series model with residual connections (residual-series model). The student model used is a lightweight ShuffleNet V2 0.5x, while the teacher models are VGG16, ResNet50, and Xception. Our experiments show that the cascaded structures result in improved performance indices, compared with the traditional ensemble model with equal weights; in particular, the residual-series model outperforms the other models, achieving a grading accuracy of 99.7% on the testing dataset with an average inference time of 5.51 ms. The findings of this study have the potential for broader application of KD in resource-limited environments for automated quality grading.

29 November 2025 in Journal of Fungi
Verified
Journal Article
Open access
PDF file
ZLZhu Liu
Zhu Liu
LKLinzhi Kang
Linzhi Kang
YPYangyang Peng
Yangyang Peng
JWJianhao Wang
Jianhao Wang
LYLuyao Ye
Luyao Ye
MLMing Liu
Ming Liu
Integrative transcriptomic–metabolomic profiling across three developmental stages of Coprinus comatus revealed that a coherent, monotonic molecular program drives fruiting body maturation. Stage-resolved RNA-seq and untargeted metabolomics were carried out to cleanly separate samples, and results showed directional trends: glycerophospholipids and other lipid species declined steadily, whereas peptides and amino-acid derivatives accumulated. Early development was driven by cell cycle regulation and DNA damage repair, while later stages shifted toward amino acid, glutathione and cell wall metabolism. These coupled transcriptional and metabolic shifts delineate processes associated with maturation and autolysis from which actionable markers can be identified to refine cultivation practices and optimize harvesting time.

15 July 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
RFRunze Fang
Runze Fang
HHHuamao Huang
Huamao Huang
NGNuoyan Guo
Nuoyan Guo
HWHaichuan Wei
Haichuan Wei
SWShiyi Wang
Shiyi Wang
MLMing Liu
Ming Liu
Accurate identification of Oudemansiella raphanipes growth stages is crucial for understanding its development and optimizing cultivation. However, deep learning methods for this task remain unexplored. This paper introduces OR-FCOS, an enhanced fully convolutional one-stage (FCOS) approach designed to improve accuracy and efficiency in identifying these growth stages. We constructed the ORaph8K dataset, containing 8,000 images of Oudemansiella raphanipes at different growth stages, used for training and validation. The OR-FCOS uses the MobileNetV3-Large backbone with an efficient multi-scale attention (EMA) module, improving feature extraction efficiency without sacrificing accuracy. A neural architecture search (NAS)-enhanced FCOS decoder replaces both the traditional feature pyramid networks (FPN) and prediction head in FCOS, optimizing feature fusion and prediction. Integrating the complete intersection over union (CIoU) loss function addresses standard IoU limitations by factoring in aspect ratio and bounding box center distance. Channel pruning further reduces the decoder’s parameters, decreasing model size and computational requirements while maintaining precision. The enhanced algorithm achieved a mean average precision (mAP) of 89.4% (\(\hbox {mAP}_{50}\)) and 78.3% (\(\hbox {mAP}_{50:95}\)), while the number of model parameters was reduced to 9.9 M, the model size was reduced to 40.1 MB, and the number of floating point operations per second (FLOPs) was reduced to 31.2 G. These results show that OR-FCOS accurately and efficiently identifies the growth stages of Oudemansiella raphanipes. By installing cameras in cultivation facilities, our algorithm enables automated and real-time monitoring, thereby supporting large-scale factory-based production of the fungus.