Development of a screening system of gene sets for estimating the time of early skeletal muscle injury based on second-generation sequencing technology

The present study is aimed to address the challenge of wound age estimation in forensic science by identifying reliable genetic markers using low-cost and high-precision second-generation sequencing technology. A total of 54 Sprague-Dawley rats were randomly assigned to a control group or injury groups, with injury groups being further divided into time points (4 h, 8 h, 12 h, 16 h, 20 h, 24 h, 28 h, and 32 h after injury, n = 6) to establish rat skeletal muscle contusion models. Gene expression data were obtained using second-generation sequencing technology, and differential gene expression analysis, weighted gene co-expression network analysis (WGCNA) and time-dependent expression trend analysis were performed. A total of six sets of biomarkers were obtained: differentially expressed genes at adjacent time points (127 genes), co-expressed genes most associated with wound age (213 genes), hub genes exhibiting time-dependent expression (264 genes), and sets of transcription factors (TF) corresponding to the above sets of genes (74, 87, and 99 genes, respectively). Then, random forest (RF), support vector machine (SVM) and multilayer perceptron (MLP), were constructed for wound age estimation from the above gene sets. The results estimated by transcription factors were all superior to the corresponding hub genes, with the transcription factor group of WGCNA performed the best, with average accuracy rates of 96% for three models' internal testing, and 91.7% for the highest external validation. This study demonstrates the advantages of the indicator screening system based on second-generation sequencing technology and transcription factor level for wound age estimation.

Endometrial cancer in women with abnormal uterine bleeding: Data mining classification methods

Background

Over the last decade, artificial intelligence in medicine has been growing. Since endometrial cancer can be treated with early diagnosis, finding a non-invasive method for screening patients, especially high-risk ones, could have a particular value. Regarding the importance of this issue, we aimed to investigate the risk factors related to endometrial cancer and find a tool to predict it using machine learning.

Methods

In this cross-sectional study, 972 patients with abnormal uterine bleeding from January 2016 to January 2021 were studied, and the essential characteristics of each patient, along with the findings of curettage pathology, were analyzed using statistical methods and machine learning algorithms, including artificial neural networks, classification and regression trees, support vector machine, and logistic regression.

Results

Out of 972 patients with a mean age of 45.77 ± 10.70 years, 920 patients had benign pathology, and 52 patients had endometrial cancer. In terms of endometrial cancer prediction, the logistic regression model had the best performance (sensitivity of 100% and 98%, specificity of 98.83% and 98.7%, for trained and test data sets respectively,) followed by the classification and regression trees model.

Conclusion

Based on the results, artificial intelligence-based algorithms can be applied as a non-invasive screening method for predicting endometrial cancer.

Artificial Intelligence in De novo Drug Design: Are We Still There?

BACKGROUND

The artificial intelligence (AI)-assisted design of drug candidates with novel structures and desired properties has received significant attention in the recent past, so related areas of forward prediction that aim to discover chemical matters worth synthesizing and further experimental investigation.

OBJECTIVES

The purpose behind developing AI-driven models is to explore the broader chemical space and suggest new drug candidate scaffolds with promising therapeutic value. Moreover, it is anticipated that such AI-based models may not only significantly reduce the cost and time but also decrease the attrition rate of drug candidates that fail to reach the desirable endpoints at the final stages of drug development. In an attempt to develop AI-based models for de novo drug design, numerous methods have been proposed by various study groups by applying machine learning and deep learning algorithms to chemical datasets. However, there are many challenges in obtaining accurate predictions, and real breakthroughs in de novo drug design are still scarce.

METHODS

In this review, we explore the recent trends in developing AI-based models for de novo drug design to assess the current status, challenges, and opportunities in the field.

CONCLUSION

The consistently improved AI algorithms and the abundance of curated training chemical data indicate that AI-based de novo drug design should perform better than the current models. Improvements in the performance are warranted to obtain better outcomes in the form of potential drug candidates, which can perform well in in vivo conditions, especially in the case of more complex diseases.

Identification and validation of hypoxia-derived gene signatures to predict clinical outcomes and therapeutic responses in stage I lung adenocarcinoma patients

Rationale: The current tumour-node-metastasis (TNM) staging system is insufficient for precise treatment decision-making and accurate survival prediction for patients with stage I lung adenocarcinoma (LUAD). Therefore, more reliable biomarkers are urgently needed to identify the high-risk subset in stage I patients to guide adjuvant therapy. Methods: This study retrospectively analysed the transcriptome profiles and clinical parameters of 1,400 stage I LUAD patients from 14 public datasets, including 13 microarray datasets from different platforms and 1 RNA-Seq dataset from The Cancer Genome Atlas (TCGA). A series of bioinformatic and machine learning approaches were combined to establish hypoxia-derived signatures to predict overall survival (OS) and immune checkpoint blockade (ICB) therapy response in stage I patients. In addition, enriched pathways, genomic and copy number alterations were analysed in different risk subgroups and compared to each other. Results: Among various hallmarks of cancer, hypoxia was identified as a dominant risk factor for overall survival in stage I LUAD patients. The hypoxia-related prognostic risk score (HPRS) exhibited more powerful capacity of survival prediction compared to traditional clinicopathological features, and the hypoxia-related immunotherapeutic response score (HIRS) outperformed conventional biomarkers for ICB therapy. An integrated decision tree and nomogram were generated to optimize risk stratification and quantify risk assessment. Conclusions: In summary, the proposed hypoxia-derived signatures are promising biomarkers to predict clinical outcomes and therapeutic responses in stage I LUAD patients.

Artificial intelligence solution to classify pulmonary nodules on CT

PURPOSE

The purpose of this study was to create an algorithm to detect and classify pulmonary nodules in two categories based on their volume greater than 100 mm³ or not, using machine learning and deep learning techniques.

MATERIALS AND METHOD

The dataset used to train the model was provided by the organization team of the SFR (French Radiological Society) Data Challenge 2019. An asynchronous and parallel 3-stages pipeline was developed to process all the data (a data "pre-processing" stage; a "nodule detection" stage; a "classifier" stage). Lung segmentation was achieved using 3D U-NET algorithm; nodule detection was done using 3D Retina-UNET and classifier stage with a support vector machine algorithm on selected features. Performances were assessed using area under receiver operating characteristics curve (AUROC).

RESULTS

The pipeline showed good performance for pathological nodule detection and patient diagnosis. With the preparation dataset, an AUROC of 0.9058 (95% confidence interval [CI]: 0.8746-0.9362) was obtained, 87% yielding accuracy (95% CI: 84.83%-91.03%) for the "nodule detection" stage, corresponding to 86% specificity (95% CI: 82%-92%) and 89% sensitivity (95% CI: 84.83%-91.03%).

CONCLUSION

A fully functional pipeline using 3D U-NET, 3D Retina-UNET and classifier stage with a support vector machine algorithm was developed, resulting in high capabilities for pulmonary nodule classification.