Biology subjects

Meng, X.-H.

Publications and source records attributed to Meng, X.-H..

3 recordsLinked to original sources

bioRxiv2022

Multi-omics analyses of drug repurposing reveal Acebutolol and Amiloride for osteoporosis treatment

Osteoporosis is a metabolic bone disease that occurs during aging, characterized by low bone mineral density (BMD) and a high risk of trauma fracture. While current pharmacological interventions provide symptomatic benefits, they are unsatisfactory and have major side effects. In this study, we used multi-omics data and drug similarity to construct osteoporosis driver signaling networks (ODSN) and drug functional networks (DFN), respectively. By integrating ODSN and DFN with treatment transcriptional responses, we observed 8 drugs that demonstrated strong targeting effects on ODSN. Mendelian Randomization analysis determines the causal effect on BMD using cis-eQTLs of the drug targets and BMD GWAS data. The findings suggested Acebutolol and Amiloride may increase BMD, while Acenocoumarol, Aminocaproic acid and Armodafinil may enhance bone loss. Zebrafish experiments experimentally showed Acebutolol hydrochloride and Amiloride hydrochloride had significant protective effects on osteoporosis in zebrafish embryos induced by Dexamethasone. Also, Acenocoumarol reduced bone mineralization compared with the control group. The findings suggest that the hypertension drugs Acebutolol and Amiloride warrant further investigation in functional mechanistic experiments to evaluate their effectiveness for osteoporosis treatments.

systems biology↗

bioRxiv2020

Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images

BackgroundMachine-assisted recognition of colorectal cancer (CRC) has been mainly focused on supervised deep learning that suffers from a significant bottleneck of requiring massive labeled data. We hypothesize that semi-supervised deep learning leveraging a small amount of labeled data with abundant available unlabeled data can provide a powerful alternative strategy. MethodWe proposed a semi-supervised model based on the mean teacher architecture that provides pathological predictions at both patch- and patient-levels. We demonstrated the general utility of the model utilizing 13,111 CRC whole slide images from 8,803 subjects gathered from 13 independent centers. We compared our proposed method with the prevailing supervised learning and six pathologists. Two extended evaluations on 15,000 lung and 294,912 lymph node images were also performed to confirm the generality of utility of semi-supervised learning for different cancers. ResultsWith a small amount of labeled training patches ([~]3,150 labeled, [~]40,950 unlabeled or [~]6,300 labeled, [~]37,800 unlabeled), the semi-supervised learning (SSL) performed significantly better than the supervised learning (SL, which only used the labeled data) (area under the curve, AUC: 0.90 {+/-} 0.06 vs. 0.84 {+/-} 0.07, P value = 0.02 or AUC: 0.98 {+/-} 0.01 vs. 0.92 {+/-} 0.04, P value = 0.0004). Moreover, we found no significant difference between SL using massive [~]44,100 labeled patches and SSL ([~]6,300 labeled, [~]37,800 unlabeled) at patch-level diagnoses (AUC:0.98 {+/-} 0.01 vs. 0.987 {+/-} 0.01, P value = 0.134) and patient-level diagnoses (average AUC: 0.974 vs. 0.980, P value = 0.117). SSL was close to human pathologists in diagnosis performance (average AUC: 0.972 vs. 0.969). This extended evaluation on lung and lymph node also confirmed when a small amount of labeled data were used, SSL was better than SL, and achieved similar performance as that of SL with massive labeling. ConclusionsWe reported that SSL can achieve excellent performance through a multi-center study. Because SSL dramatically reduces the need and cost of pathological image annotation, it has great potential to effectively build pathological artificial intelligence (AI) platforms in practice.

pathology↗

bioRxiv2020

Accurate Diagnosis of Colorectal Cancer Based on Histopathology Images Using Artificial Intelligence

BackgroundAccurate and robust pathological image analysis for colorectal cancer (CRC) diagnosis is time-consuming and knowledge-intensive, but is essential for CRC patients treatment. The current heavy workload of pathologists in clinics/hospitals may easily lead to unconscious misdiagnosis of CRC based on their daily image analyses. MethodsBased on a state-of-the-art transfer-learned deep convolutional neural network in artificial intelligence (AI), we proposed a novel patch aggregation strategy for clinic CRC prediction/diagnosis using weakly labeled pathological whole slide image (WSI) patches. This approach was trained and validated using an unprecedented and enormously large number of 170,099 patches, >14,680 WSIs, from >9,631 subjects that covered diverse and representative clinical cases from multi-independent-sources across China, U.S., and Germany. ResultsOur innovative AI tool was consistently nearly perfectly agreed with (average Kappa-statistic 0.896) and even often better than most of the experienced expert pathologists when tested in diagnosing CRC WSIs from multi-centers. The average area under the receiver operating characteristics curve (AUC) of AI was greater than that of the pathologists (0.981 vs 0.970) and achieved the best performance among the application of other AI methods to CRC diagnosis. Our AI-generated heatmap highlights the image regions of cancer tissue/cells. ConclusionsThis first-ever generalizable AI system can handle large amounts of WSIs consistently and robustly without potential bias due to fatigue commonly experienced by clinical pathologists. Hence, it will drastically alleviate the heavy clinical burden of daily pathology diagnosis, and improve the treatment for CRC patients. This tool is generalizable to other cancer diagnosis based on image recognition.

pathology↗