GANSamples-ac4C: Enhancing ac4C site prediction via generative adversarial networks and transfer learning

RNA modification, N4-acetylcytidine (ac4C), is enzymatically catalyzed by N-acetyltransferase 10 (NAT10) and plays an essential role across tRNA, rRNA, and mRNA. It influences various cellular functions, including mRNA stability and rRNA biosynthesis. Wet-lab detection of ac4C modification sites is highly resource-intensive and costly. Therefore, various machine learning and deep learning techniques have been employed for computational detection of ac4C modification sites. The known ac4C modification sites are limited for training an accurate and stable prediction model. This study introduces GANSamples-ac4C, a novel framework that synergizes transfer learning and generative adversarial network (GAN) to generate synthetic RNA sequences to train a better ac4C modification site prediction model. Comparative analysis reveals that GANSamples-ac4C outperforms existing state-of-the-art methods in identifying ac4C sites. Moreover, our result underscores the potential of synthetic data in mitigating the issue of data scarcity for biological sequence prediction tasks. Another major advantage of GANSamples-ac4C is its interpretable decision logic. Multi-faceted interpretability analyses detect key regions in the ac4C sequences influencing the discriminating decision between positive and negative samples, a pronounced enrichment of G in this region, and ac4C-associated motifs. These findings may offer novel insights for ac4C research. The GANSamples-ac4C framework and its source code are publicly accessible at http://www.healthinformaticslab.org/supp/.

Dynamic contrast-enhanced magnetic resonance imaging in cervical cancer: correlation between quantitative parameters and molecular markers hypoxia-inducible factors-1-alpha, vascular endothelial growth factor, and Ki-67

AIM

To investigate whether dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) has the potential to non-invasively detect microenvironmental condition by quantitatively measuring blood perfusion, vessel wall permeability, and vascularity, and to elucidate the possible correlations between DCE-MRI quantitative parameters and the expression level of hypoxia, vascularity, and cell proliferation related molecular biomarkers.

MATERIALS AND METHODS

In this prospective single center clinical study, 58 patients diagnosed with cervical cancer underwent DCE-MRI before anticancer treatment were enrolled. Ktrans, Kep, Ve, and Vp were generated from Extended Toft's model. Then patients conducted colposcopy biopsy within 1 week after DCE-MRI. Pretreatment expression levels of HIF-1α, VEGF and Ki-67 were assessed and scored by immunohistochemistry on colposcopy obtained tumor specimens.

RESULTS

In HIF-1α low-expression group, Ktrans (p=0.031) and Kep (p=0.012) values were significantly higher than the high-expression group. In VEGF high-expression group, Ktrans (p=0.044) and Ve values (p=0.021) were significantly higher than the low-expression group. In Ki-67 high-expression group, Ktrans (p=0.026) and Kep (p=0.033) were significantly higher than the low-expression group. Multiple linear regression analyses and Pearson correlation revealed that Ktrans independently negatively correlated with HIF-1α expression, Ve independently positively correlated with VEGF, and Kep independently positively correlated with Ki-67. The area under the ROC curves of Ktrans for HIF-1α, Ve for VEGF, and Kep for Ki-67 were 0.728, 0.743, 0.730, respectively.

CONCLUSION

Our results suggest that DCE-MRI quantitative parameters could be potentially used as imaging markers for non-invasively detecting microenvironmental hypoxia, vascularity and proliferation in cervical cancer patients.

Machine Learning-Based Integrated Multiomics Characterization of Colorectal Cancer Reveals Distinctive Metabolic Signatures

The metabolic signature identification of colorectal cancer is critical for its early diagnosis and therapeutic approaches that will significantly block cancer progression and improve patient survival. Here, we combined an untargeted metabolic analysis strategy based on internal extractive electrospray ionization mass spectrometry and the machine learning approach to analyze metabolites in 173 pairs of cancer samples and matched normal tissue samples to build robust metabolic signature models for diagnostic purposes. Screening and independent validation of metabolic signatures from colorectal cancers via machine learning methods (Logistic Regression_L1 for feature selection and eXtreme Gradient Boosting for classification) was performed to generate a panel of seven signatures with good diagnostic performance (the accuracy of 87.74%, sensitivity of 85.82%, and specificity of 89.66%). Moreover, seven signatures were evaluated according to their ability to distinguish between cancer and normal tissues, with the metabolic molecule PC (30:0) showing good diagnostic performance. In addition, genes associated with PC (30:0) were identified by multiomics analysis (combining metabolic data with transcriptomic data analysis) and our results showed that PC (30:0) could promote the proliferation of colorectal cancer cell SW480, revealing the correlation between genetic changes and metabolic dysregulation in cancer. Overall, our results reveal potential determinants affecting metabolite dysregulation, paving the way for a mechanistic understanding of altered tissue metabolites in colorectal cancer and design interventions for manipulating the levels of circulating metabolites.

Energy-Conversion Device Using a Quantum Engine with the Work Medium of Two-Atom Entanglement

Although entanglement is considered as an essential resource for quantum information processing, whether entanglement helps for energy conversion or output in the quantum regime is still lack of experimental witness. Here, we report on an energy-conversion device operating as a quantum engine with the working medium acted by two entangled ions confined in a harmonic potential. The two ions are entangled by virtually coupling to one of the vibrational modes shared by the two ions, and the quantum engine couples to a quantum load, which is another shared vibrational mode. We explore the energy conversion efficiency of the quantum engine and investigate the useful energy (i.e., the maximum extractable work) stored in the quantum load by tuning the two ions in different degrees of entanglement as well as detecting the change of the phonons in the load. Our observation provides, for the first time, quantitative evidence that entanglement fuels the useful energy produced by the quantum engine, but not helpful for the energy conversion efficiency. We consider that our results may be useful to the study of quantum batteries for which one of the most indexes is the maximum extractable energy.

[Exercise promotes irisin expression to ameliorate renal injury in type 2 diabetic rats]

OBJECTIVE

To investigate the role of irisin in exercise-induced improvement of renal function in type 2 diabetic rats.

METHODS

Forty male SD rats aged 4-6 weeks were randomized into normal control group, type 2 diabetes mellitus model group, diabetic exercise (DE) group and diabetic irisin (DI) group (n=8). The rats in DE group were trained with treadmill running for 8 weeks, and those in DI group were given scheduled irisin injections for 8 weeks. After the treatments, blood biochemical parameters of the rats were examined, and renal histopathology was observed with HE, Masson and PAS staining. Western blotting was used to detect the protein expression levels in the rats'kidneys.

RESULTS

The diabetic rats showed significantly increased levels of fasting insulin, total cholesterol, triglyceride, serum creatinine and blood urea nitrogen with lowered serum irisin level (all P < 0.05). Compared with those in DM group, total cholesterol, triglyceride, serum creatinine and blood urea nitrogen levels were decreased and serum irisin levels were increased in both DE and DI groups (all P < 0.05). The rats in DM group showed obvious structural disorders and collagen fiber deposition in the kidneys, which were significantly improved in DE group and DI group. Both regular exercises and irisin injections significantly ameliorated the reduction of FNDC5, LC3-II/I, Atg7, Beclin-1, p-AMPK, AMPK and SIRT1 protein expressions and lowered of p62 protein expression in the kidneys of the diabetic rats (all P < 0.05).

CONCLUSION

Both exercise and exogenous irisin treatment improve nephropathy in type 2 diabetic rats possibly due to irisin-mediated activation of the AMPK/SIRT1 pathway in the kidneys to promote renal autophagy.

A probabilistic knowledge graph for target identification

Early identification of safe and efficacious disease targets is crucial to alleviating the tremendous cost of drug discovery projects. However, existing experimental methods for identifying new targets are generally labor-intensive and failure-prone. On the other hand, computational approaches, especially machine learning-based frameworks, have shown remarkable application potential in drug discovery. In this work, we propose Progeni, a novel machine learning-based framework for target identification. In addition to fully exploiting the known heterogeneous biological networks from various sources, Progeni integrates literature evidence about the relations between biological entities to construct a probabilistic knowledge graph. Graph neural networks are then employed in Progeni to learn the feature embeddings of biological entities to facilitate the identification of biologically relevant target candidates. A comprehensive evaluation of Progeni demonstrated its superior predictive power over the baseline methods on the target identification task. In addition, our extensive tests showed that Progeni exhibited high robustness to the negative effect of exposure bias, a common phenomenon in recommendation systems, and effectively identified new targets that can be strongly supported by the literature. Moreover, our wet lab experiments successfully validated the biological significance of the top target candidates predicted by Progeni for melanoma and colorectal cancer. All these results suggested that Progeni can identify biologically effective targets and thus provide a powerful and useful tool for advancing the drug discovery process.

MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning

MOTIVATION

Predicting molecular properties is a pivotal task in various scientific domains, including drug discovery, material science, and computational chemistry. This problem is often hindered by the lack of annotated data and imbalanced class distributions, which pose significant challenges in developing accurate and robust predictive models.

RESULTS

This study tackles these issues by employing pretrained molecular models within a few-shot learning framework. A novel dynamic contrastive loss function is utilized to further improve model performance in the situation of class imbalance. The proposed MolFeSCue framework not only facilitates rapid generalization from minimal samples, but also employs a contrastive loss function to extract meaningful molecular representations from imbalanced datasets. Extensive evaluations and comparisons of MolFeSCue and state-of-the-art algorithms have been conducted on multiple benchmark datasets, and the experimental data demonstrate our algorithm's effectiveness in molecular representations and its broad applicability across various pretrained models. Our findings underscore MolFeSCues potential to accelerate advancements in drug discovery.

AVAILABILITY AND IMPLEMENTATION

We have made all the source code utilized in this study publicly accessible via GitHub at http://www.healthinformaticslab.org/supp/ or https://github.com/zhangruochi/MolFeSCue. The code (MolFeSCue-v1-00) is also available as the supplementary file of this paper.

Generating the Transcriptional Regulation View of Transcriptomic Features for Prediction Task and Dark Biomarker Detection on Small Datasets

Transcriptome represents the expression levels of many genes in a sample and has been widely used in biological research and clinical practice. Researchers usually focused on transcriptomic biomarkers with differential representations between a phenotype group and a control group of samples. This study presented a multitask graph-attention network (GAT) learning framework to learn the complex inter-genic interactions of the reference samples. A demonstrative reference model was pre-trained on the healthy samples (HealthModel), which could be directly used to generate the model-based quantitative transcriptional regulation (mqTrans) view of the independent test transcriptomes. The generated mqTrans view of transcriptomes was demonstrated by prediction tasks and dark biomarker detection. The coined term "dark biomarker" stemmed from its definition that a dark biomarker showed differential representation in the mqTrans view but no differential expression in its original expression level. A dark biomarker was always overlooked in traditional biomarker detection studies due to the absence of differential expression. The source code and the manual of the pipeline HealthModelPipe can be downloaded from http://www.healthinformaticslab.org/supp/resources.php.

ACPPfel: Explainable deep ensemble learning for anticancer peptides prediction based on feature optimization

Background: Cancer is a significant global health problem that continues to cause a high number of deaths worldwide. Traditional cancer treatments often come with risks that can compromise the functionality of vital organs. As a potential alternative to these conventional therapies, Anticancer peptides (ACPs) have garnered attention for their small size, high specificity, and reduced toxicity, making them as a promising option for cancer treatments. Methods: However, the process of identifying effective ACPs through wet-lab screening experiments is time-consuming and requires a lot of labor. To overcome this challenge, a deep ensemble learning method is constructed to predict anticancer peptides (ACPs) in this study. To evaluate the reliability of the framework, four different datasets are used in this study for training and testing. During the training process of the model, integration of feature selection methods, feature dimensionality reduction measures, and optimization of the deep ensemble model are carried out. Finally, we explored the interpretability of features that affected the final prediction results and built a web server platform to facilitate anticancer peptides prediction, which can be used by all researchers for further studies. This web server can be accessed at http://lmylab.online:5001/. Results: The result of this study achieves an accuracy rate of 98.53% and an AUC (Area under Curve) value of 0.9972 on the ACPfel dataset, it has improvements on other datasets as well.

CAGI, the Critical Assessment of Genome Interpretation, establishes progress and prospects for computational genetic variant interpretation methods

BACKGROUND

The Critical Assessment of Genome Interpretation (CAGI) aims to advance the state-of-the-art for computational prediction of genetic variant impact, particularly where relevant to disease. The five complete editions of the CAGI community experiment comprised 50 challenges, in which participants made blind predictions of phenotypes from genetic data, and these were evaluated by independent assessors.

RESULTS

Performance was particularly strong for clinical pathogenic variants, including some difficult-to-diagnose cases, and extends to interpretation of cancer-related variants. Missense variant interpretation methods were able to estimate biochemical effects with increasing accuracy. Assessment of methods for regulatory variants and complex trait disease risk was less definitive and indicates performance potentially suitable for auxiliary use in the clinic.

CONCLUSIONS

Results show that while current methods are imperfect, they have major utility for research and clinical applications. Emerging methods and increasingly large, robust datasets for training and assessment promise further progress ahead.

[Study of the effects of dietary patterns on glycemic control in community type 2 diabetic mellitus patients]

Objective: To understand the impact of diet on glycemic control in community-managed patients with type 2 diabetes mellitus (T2DM) and provide evidence for implementing prevention strategies and measures for diabetes patients. Methods: Eight communities were randomly selected from Changshu and Wuhan in 2015, and T2DM patients managed in the community were selected to conduct questionnaire surveys, physical measurements, and blood glucose testing. Factor analysis was used to obtain dietary patterns. A binary logistic regression model was used to analyze the factors affecting glycemic control. Results: Finally, 1 818 T2DM patients were included, and the control rate of FPG was 57.59% (95%CI: 55.30%-59.86%), and the control rate of 2 h postprandial blood glucose (2 h PBG) was 24.90% (95%CI: 22.93%- 26.91%). Five dietary patterns were obtained by factor analysis: animal food pattern, fruit-aquatic products-potato patterns, vegetable-grain pattern, egg-milk-bean pattern, and oil-salt patterns. No-conditional multivariate logistic regression analysis showed that after adjusting for confounding factors, the reduced probability of FPG control was related to animal food pattern (OR=0.71, 95%CI: 0.52-0.98) and fruit-aquatic products-potato patterns (OR=0.71, 95%CI: 0.51-0.97). The decrease in the 2 h PBG control probability was related to fruit-aquatic products-potato patterns (OR=0.60, 95%CI: 0.40-0.90). The increased probability of FPG and 2 h postprandial glucose control were both related to vegetable-grain pattern (OR=1.41, 95%CI: 1.03-1.94; OR=1.68, 95%CI: 1.13-2.51) and egg-milk-bean pattern (OR=1.75, 95%CI: 1.25-2.46; OR=1.56, 95%CI: 1.00-2.42). Compared with the Q4 group of egg-milk-bean pattern, the FPG control rate of the combination of "fruit-aquatic products-potato pattern (Q4 group), vegetable-grain pattern (Q2 group), egg-milk-bean pattern (Q3 group)" was higher (OR=6.79, 95%CI: 1.15-40.23, P=0.035). Compared with the Q4 group of vegetable-grain pattern, the combination of "fruit-aquatic products-potato pattern (Q4 group), vegetable-grain pattern (Q3 group), egg-milk-bean pattern (Q2 group), oil-salt pattern (Q2 group)" had higher control rate of 2 h PBG (OR=12.78, 95%CI: 1.26-130.05, P=0.031). Conclusions: A proper combination of dietary patterns and dietary patterns are more conducive to the control of FPG and 2 h PBG in T2DM patients managed in the communities of Wuhan and Changshu. Patient nutrition education should be strengthened, and the food-matching ability of patients should be improved.

Computational Characterization of Undifferentially Expressed Genes with Altered Transcription Regulation in Lung Cancer

A transcriptome profiles the expression levels of genes in cells and has accumulated a huge amount of public data. Most of the existing biomarker-related studies investigated the differential expression of individual transcriptomic features under the assumption of inter-feature independence. Many transcriptomic features without differential expression were ignored from the biomarker lists. This study proposed a computational analysis protocol (mqTrans) to analyze transcriptomes from the view of high-dimensional inter-feature correlations. The mqTrans protocol trained a regression model to predict the expression of an mRNA feature from those of the transcription factors (TFs). The difference between the predicted and real expression of an mRNA feature in a query sample was defined as the mqTrans feature. The new mqTrans view facilitated the detection of thirteen transcriptomic features with differentially expressed mqTrans features, but without differential expression in the original transcriptomic values in three independent datasets of lung cancer. These features were called dark biomarkers because they would have been ignored in a conventional differential analysis. The detailed discussion of one dark biomarker, GBP5, and additional validation experiments suggested that the overlapping long non-coding RNAs might have contributed to this interesting phenomenon. In summary, this study aimed to find undifferentially expressed genes with significantly changed mqTrans values in lung cancer. These genes were usually ignored in most biomarker detection studies of undifferential expression. However, their differentially expressed mqTrans values in three independent datasets suggested their strong associations with lung cancer.

Undifferentially Expressed CXXC5 as a Transcriptionally Regulatory Biomarker of Breast Cancer

This work hypothesizes that some genes undergo radically changed transcription regulations (TRs) in breast cancer (BC), but don't show differential expressions for unknown reasons. The TR of a gene is quantitatively formulated by a regression model between the expression of this gene and multiple transcription factors (TFs). The difference between the predicted and real expression levels of a gene in a query sample is defined as the mqTrans value of this gene, which quantitatively reflects its regulatory changes. This work systematically screens the undifferentially expressed genes with differentially expressed mqTrans values in 1036 samples across five datasets and three ethnic groups. This study calls the 25 genes satisfying the above hypothesis in at least four datasets as dark biomarkers, and the strong dark biomarker gene CXXC5 (CXXC Finger Protein 5) is even supported by all the five independent BC datasets. Although CXXC5 does not show differential expressions in BC, its transcription regulations show quantitative associations with BCs in diversified cohorts. The overlapping long noncoding RNAs (lncRNAs) may have contributed their transcripts to the expression miscalculations of dark biomarkers. The mqTrans analysis serves as a complementary view of the transcriptome-based detections of biomarkers that are ignored by many existing studies.

Multi-view progression diagnosis of thyroid cancer by integrating platelet transcriptomes and blood routine tests

Thyroid cancer is the most common type of endocrine system cancer. The pre-cancer and early stages are usually benign or slowly growing, and do not need invasive treatments. This study investigated the challenging classification task of four classes of samples, i.e., normal controls (N), thyroid adenomas (TA), papillary thyroid cancers (PTC) and metastasized papillary thyroid cancers (MPTC). We proposed a multi-view progression diagnosis framework ThyroidBloodTest to integrate the two views of RNAseq platelet transcriptomes (View-T) and blood routine (View-B) features. Platelet transcriptome represented the molecular-level information, while the blood routine features were easy to obtain in the clinical practice. Eleven feature selection algorithms and seven classifiers were evaluated for both views. The experimental data suggested the importance of choosing appropriate data analysis algorithms and feature engineering techniques like principal component analysis (PCA). The best ThyroidBloodTest model achieved Acc = 0.8750 for the four-class classification of the N/TA/PTC/MPTC samples based on the integrated feature space of View-T and View-B. The cellular localization cytosol and three post-translational modification types acetylation/phosphorylation/ubiquitination were observed to be enriched in the proteins encoded by the View-T biomarkers. The numbers of different immune cells also contributed positively to the progression diagnosis of thyroid cancer. The proposed multi-view prediction model demonstrated the necessity of integrating both platelet transcriptomes and blood routine tests for the progression diagnosis of thyroid cancer.

High Dose Hyperfractionated Thoracic Radiotherapy vs. Standard Dose for Limited Stage Small-Cell Lung Cancer: A Multicenter, Open-Label Randomized, Phase 3 Trial

PURPOSE/OBJECTIVE(S)

Limited stage small-cell lung cancer (LS-SCLC) is associated with poor prognosis. We aimed to assess the efficacy and safety of high-dose, hyperfractionated thoracic radiotherapy of 54 Gy in 30 fractions compared with standard dose (45 Gy in 30 fractions) as a first-line treatment for LS-SCLC.

MATERIALS/METHODS

The study was an open-label, randomized, phase 3 trial, done at 16 public hospitals in China. Key inclusion criteria were patients aged 18-70 years, with previously histologically or cytologically confirmed LS-SCLC, previously untreated or received 1-2 courses of intravenous cisplatin (75 mg/m²of body-surface area, on day 1 or divided into two days of each cycle) or carboplatin (area under the curve of 5 mg/mL per min, day 1 of each cycle)and intravenous etoposide (100 mg/m²of body-surface area, on days 1-3 of each cycle), and an Eastern Cooperative Oncology Group (ECOG) performance status of 0-1.Eligible patients were randomly assigned (1:1) to receive volumetric-modulated arc radiotherapy (VMAT) of 45 Gy in 30 fractions or the simultaneous integrated boost VMAT (SIB-VMAT) of 54 Gy in 30 fractions to the primary lung tumor and lymph node metastases starting 0-42 days after the first chemotherapy course. Both groups of patients received thoracic radiotherapy twice per day and 10 fractions per week. Prophylactic cranial radiation (PCI, 25 Gy in 10 fractions) was implemented to patients with responsive disease. The primary endpoint was overall survival. Safety was analyzed in the as-treated population.

RESULTS

Between June 30, 2017, and April 6, 2021, 224 eligible patients were enrolled and randomly assigned to 54 Gy (n = 108) or 45 Gy (n = 116). Median follow-up for the primary analysis was 45 months (IQR 41-48). Median overall survival was significantly improved in the 54 Gy group (62.4 months) compared with the 45 Gy group (43.1 months; p = 0.001). Median progression-free survival was significantly improved in the 54 Gy group (30.5 months) compared with the 45 Gy group (16.7 months; p = 0.044). The most common grade 3-4 adverse events were neutropenia (30 [28%] of 108 patients in the 54 Gy group vs 27 [23%] of 116 patients in the 45 Gy group), neutropenic infections (6 [6%] vs 2 [2%]), thrombocytopenia (13 [12%] vs 12 [10%]), anemia (6 [6%] vs 4 [3%]), and esophagitis (1 [1%] vs 3 [3%]). Treatment-related serious adverse events occurred in 9 [8%] patients in the 54 Gy group and 16 [14%] patients in the 45 Gy group. There were one treatment-related deaths in 54 Gy group (myocardial infarction).

CONCLUSION

Compared with standard thoracic radiotherapy dose of 45 Gy, the high dose of 54 Gy improved overall survival and progression-free survival without increasing toxicities in patients with LS-SCLC, supporting twice-daily hyperfractionated thoracic radiotherapy of 54 Gy with concurrent chemotherapy is an alternative treatment option for LS-SCLC. This study is complete and registered with ClinicalTrials.gov, NCT03214003.

Deep Learning and GAN-Synthesis for Auto-Segmentation of Pancreatic Cancer by Non-Enhanced CT for Adaptive Radiotherapy

PURPOSE/OBJECTIVE(S)

In conventional adaptive radiotherapy (ART) for pancreatic cancer, contrast-enhanced CT (CECT) helps to more precisely delineate primary gross tumor volume (GTV) than non-enhanced CT (NECT). However, frequent use of contrast medium can damage kidneys and prolong treatment time. Moreover, traditional manual delineation is labor-intensive and highly dependent on the experience of oncologists. Currently, automatic delineation based on deep learning with Generative Adversarial Networks (GAN)-based CT synthesis is one of the most feasible solutions to these problems.

MATERIALS/METHODS

A dataset of 35 pancreatic cancer patients was retrospectively collected from May 2021 to December 2022. All patients consist of a pair of NECT and CECT. We designed and developed an automatic delineation framework (Proposed) for GTV of pancreatic cancer based on Trans-cycleGAN and a modified 3D U-Net. TranscycleGAN can not only synthesize CECT from NECT, but can also augment the amount of CT images; then all real and synthesized CT images were used to train the modified 3D U-Net for automatic delineation of GTV; finally, our framework was able to automatically delineate GTV by NECT, but not only by CECT. Our framework was evaluated by dice similarity coefficient (DSC), 95% Harsdorff distance (95HD) and average surface distance (ASD) with oncologists' manual delineation ("gold standard").

RESULTS

The evaluation results were summarized in Table 1. The proposed framework achieved the best automatic delineation results by NECT, which was superior to that of CECT: 0.917 & 0.903 of DSC, 2.498mm & 3.029mm of HD95, 0.481mm & 0.534mm of ASD, p < 0.05 for DSC and HD95. Specifically, it is significantly superior to the automatic delineation results using U-Net by CECT 0.917 & 0.818 of DSC, 2.498mm & 13.228mm of HD95, 0.481mm & 3.633mm of ASD, p < 0.05 for DSC.

CONCLUSION

We proposed an automatic delineation framework for contouring GTV in ART of pancreatic cancer based on deep learning and Trans-cycleGAN network. This framework could automatically delineate GTV and achieve better performance with NECT compared to CECT. Our method could not only reduce the use of contrast medium, but also increase the precision and effectiveness of tumor delineation, which could have a positive impact on precision radiotherapy.

Reconstructing the cytokine view for the multi-view prediction of COVID-19 mortality

BACKGROUND

Coronavirus disease 2019 (COVID-19) is a rapidly developing and sometimes lethal pulmonary disease. Accurately predicting COVID-19 mortality will facilitate optimal patient treatment and medical resource deployment, but the clinical practice still needs to address it. Both complete blood counts and cytokine levels were observed to be modified by COVID-19 infection. This study aimed to use inexpensive and easily accessible complete blood counts to build an accurate COVID-19 mortality prediction model. The cytokine fluctuations reflect the inflammatory storm induced by COVID-19, but their levels are not as commonly accessible as complete blood counts. Therefore, this study explored the possibility of predicting cytokine levels based on complete blood counts.

METHODS

We used complete blood counts to predict cytokine levels. The predictive model includes an autoencoder, principal component analysis, and linear regression models. We used classifiers such as support vector machine and feature selection models such as adaptive boost to predict the mortality of COVID-19 patients.

RESULTS

Complete blood counts and original cytokine levels reached the COVID-19 mortality classification area under the curve (AUC) values of 0.9678 and 0.9111, respectively, and the cytokine levels predicted by the feature set alone reached the classification AUC value of 0.9844. The predicted cytokine levels were more significantly associated with COVID-19 mortality than the original values.

CONCLUSIONS

Integrating the predicted cytokine levels and complete blood counts improved a COVID-19 mortality prediction model using complete blood counts only. Both the cytokine level prediction models and the COVID-19 mortality prediction models are publicly available at http://www.healthinformaticslab.org/supp/resources.php .

OCMR: A comprehensive framework for optical chemical molecular recognition

Artificial intelligence (AI) has achieved significant progress in the field of drug discovery. AI-based tools have been used in all aspects of drug discovery, including chemical structure recognition. We propose a chemical structure recognition framework, Optical Chemical Molecular Recognition (OCMR), to improve the data extraction capability in practical scenarios compared with the rule-based and end-to-end deep learning models. The proposed OCMR framework enhances the recognition performances via the integration of local information in the topology of molecular graphs. OCMR handles complex tasks like non-canonical drawing and atomic group abbreviation and substantially improves the current state-of-the-art results on multiple public benchmark datasets and one internally curated dataset.

Orchestrating information across tissues via a novel multitask GAT framework to improve quantitative gene regulation relation modeling for survival analysis

Survival analysis is critical to cancer prognosis estimation. High-throughput technologies facilitate the increase in the dimension of genic features, but the number of clinical samples in cohorts is relatively small due to various reasons, including difficulties in participant recruitment and high data-generation costs. Transcriptome is one of the most abundantly available OMIC (referring to the high-throughput data, including genomic, transcriptomic, proteomic and epigenomic) data types. This study introduced a multitask graph attention network (GAT) framework DQSurv for the survival analysis task. We first used a large dataset of healthy tissue samples to pretrain the GAT-based HealthModel for the quantitative measurement of the gene regulatory relations. The multitask survival analysis framework DQSurv used the idea of transfer learning to initiate the GAT model with the pretrained HealthModel and further fine-tuned this model using two tasks i.e. the main task of survival analysis and the auxiliary task of gene expression prediction. This refined GAT was denoted as DiseaseModel. We fused the original transcriptomic features with the difference vector between the latent features encoded by the HealthModel and DiseaseModel for the final task of survival analysis. The proposed DQSurv model stably outperformed the existing models for the survival analysis of 10 benchmark cancer types and an independent dataset. The ablation study also supported the necessity of the main modules. We released the codes and the pretrained HealthModel to facilitate the feature encodings and survival analysis of transcriptome-based future studies, especially on small datasets. The model and the code are available at http://www.healthinformaticslab.org/supp/.

Efficient Fe(III)/Fe(II) cycling mediated by L-cysteine functionalized zero-valent iron for enhancing Cr(VI) removal

Herein, L-cysteine (Cys) was modified on zero-valent iron (C-ZVI^bm) by using a mechanical ball-milling method to improve the surface functionality and the Cr(VI) removal efficiency. Characterization results indicated that Cys was modified on the surface of ZVI by the specific adsorption of Cys on the oxide shell to form a -COO-Fe complex. The Cr(VI) removal efficiency of C-ZVI^bm (99.6%) was much higher than that of ZVI^bm (7.3%) in 30 min. The attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR) analysis inferred that Cr(VI) was more likely to be adsorbed on the surface of C-ZVI^bm to form bidentate binuclear inner-sphere complexes. The adsorption process was well-matched to the Freundlich isotherm and the pseudo-second-order kinetic model. Electrochemical analysis and electron paramagnetic resonance (ESR) spectroscopy revealed that Cys on the C-ZVI^bm lowered the redox potential of Fe(III)/Fe(II), and favored the surface Fe(III)/Fe(II) cycling mediated by the electrons from Fe⁰ core. These electron transfer processes were beneficial to the surface reduction of Cr(VI) to Cr(III). Our findings provide new understandings into the surface modification of ZVI with a low-molecular weight amino acid to promote in-situ Fe(III)/Fe(II) cycling, and have great potential for the construction of efficient systems for Cr(VI) removal.

Transcriptional Dysregulations of Seven Non-Differentially Expressed Genes as Biomarkers of Metastatic Colon Cancer

Background: Colon cancer (CC) is common, and the mortality rate greatly increases as the disease progresses to the metastatic stage. Early detection of metastatic colon cancer (mCC) is crucial for reducing the mortality rate. Most previous studies have focused on the top-ranked differentially expressed transcriptomic biomarkers between mCC and primary CC while ignoring non-differentially expressed genes. Results: This study proposed that the complicated inter-feature correlations could be quantitatively formulated as a complementary transcriptomic view. We used a regression model to formulate the correlation between the expression levels of a messenger RNA (mRNA) and its regulatory transcription factors (TFs). The change between the predicted and real expression levels of a query mRNA was defined as the mqTrans value in the given sample, reflecting transcription regulatory changes compared with the model-training samples. A dark biomarker in mCC is defined as an mRNA gene that is non-differentially expressed in mCC but demonstrates mqTrans values significantly associated with mCC. This study detected seven dark biomarkers using 805 samples from three independent datasets. Evidence from the literature supports the role of some of these dark biomarkers. Conclusions: This study presented a complementary high-dimensional analysis procedure for transcriptome-based biomarker investigations with a case study on mCC.

Expert consensus of management of adverse drug reactions with anaplastic lymphoma kinase tyrosine kinase inhibitors

Anaplastic lymphoma kinase (ALK) rearrangements occur in ∼3%-6% of patients with advanced non-small-cell lung cancer (NSCLC). Small molecular drugs that effectively inhibit ALK gene have revolutionized the therapeutic paradigm for patients with ALK rearrangements, resulting in significant improvements in objective response rate, progression-free survival, and overall survival compared with classical platinum-based chemotherapy. Several ALK tyrosine kinase inhibitors (ALK-TKIs), including crizotinib, alectinib, ceritinib, brigatinib, ensartinib, and lorlatinib, have been recommended as standard first-line treatment for advanced NSCLC patients with ALK rearrangements. Patients with ALK rearrangements typically exhibit long-term durable responses to ALK-TKIs; therefore, the management of adverse drug reactions (ADRs) with ALK-TKIs is crucial in clinical practice to maximize clinical benefits, prevent an adverse impact on quality of life, and improve patient compliance. In general, ALK-TKIs are well tolerated. There are, however, a number of serious toxicities that may necessitate dose modification or even discontinuation of treatment and the management of ADRs with ALK-TKIs has grown in importance. The therapeutic use of this class of medications still carries some risk because there are currently no pertinent guidelines or consensus recommendations for managing ADRs caused by ALK-TKIs in China. In order to improve the clinical management of ADRs with ALK-TKIs, the Chinese Society of Clinical Oncology (CSCO) Non-small Cell Lung Cancer Professional Committee led the discussion and summary of the incidence, diagnosis and grading standards, and prevention and treatment of ADRs caused by ALK-TKIs.

FoxO1/NLRP3 Inflammasome Promotes Age-Related Alveolar Bone Resorption

Periodontitis is the utmost common chronic oral disease that exhibits intense susceptibility to aging. Aging is characterized by persistent sterile low-grade inflammation, leading to age-related periodontal complications represented by alveolar bone loss. Currently, forkhead transcription factor O1 (FoxO1) is generally believed to have a significant role in body development, senescence, cell viability, and oxidative stress in numerous organs and cells. However, the role of this transcription factor in mediating age-related alveolar bone resorption has not been examined. In this study, FoxO1 deficiency was discovered to have a beneficial correlation with halting the progression of alveolar bone resorption in aged mice. To further investigate the function of FoxO1 in age-related alveolar bone resorption, osteoblastic-specific FoxO1 knockout mice were generated, leading to an amelioration in alveolar bone loss compared to aged-matched wild-type mice, manifested as enhanced osteogenic potential. Mechanistically, we identified enhancement of the NLRP3 inflammasome signaling in FoxO1-deficient osteoblasts in the high dose of reactive oxygen species. Concordant with our study, MCC950, a specific inhibitor of NLRP3 inflammasome, greatly rescued osteoblast differentiation under oxidative stress. Our data shed light on the manifestations of FoxO1 depletion in osteoblasts and propose a possible mechanism for the therapy of age-related alveolar bone loss.

EpiTEAmDNA: Sequence feature representation via transfer learning and ensemble learning for identifying multiple DNA epigenetic modification types across species

Methylation is a major DNA epigenetic modification for regulating the biological processes without altering the DNA sequence, and multiple types of DNA methylations have been discovered, including 6mA, 5hmC, and 4mC. Multiple computational approaches were developed to automatically identify the DNA methylation residues using machine learning or deep learning algorithms. The machine learning (ML) based methods are difficult to be transferred to the other predicting tasks of the DNA methylation sites using additional knowledge. Deep learning (DL) may facilitate the transfer learning of knowledge from similar tasks, but they are often ineffective on small datasets. This study proposes an integrated feature representation framework EpiTEAmDNA based on the strategies of transfer learning and ensemble learning, which is evaluated on multiple DNA methylation types across 15 species. EpiTEAmDNA integrates convolutional neural network (CNN) and conventional machine learning methods, and shows improved performances than the existing DL-based methods on small datasets when no additional knowledge is available. The experimental data suggests that the EpiTEAmDNA models may be further improved via transfer learning based on additional knowledge. The evaluation experiments on the independent test datasets also suggest that the proposed EpiTEAmDNA framework outperforms the existing models in most prediction tasks of the 3 DNA methylation types across 15 species. The source code, pre-trained global model, and the EpiTEAmDNA feature representation framework are freely available at http://www.healthinformaticslab.org/supp/.

[Diagnosis and treatment of 26 cases of adenovirus infection after allogeneic hematopoietic stem cell transplantation]

Objective: To analyze the clinical characteristics and prognosis of adenovirus infection after allogeneic hematopoietic stem cell transplantation. Methods: A total of 26 patients with adenovirus infection admitted to the posttransplant ward of the First Affiliated Hospital of Soochow University from 2018 to 2022 were enrolled. Their data on baseline and clinical characteristics, treatment, and follow-up were analyzed. Results: The median patient age was 30 (22, 44) years. Twenty-two patients received related haploid stem cell transplantation, three received unrelated stem cell transplantation, and one received umbilical cord stem cell transplantation. Antithymocyte globulin was included in the conditioning regimen in 25 patients. The median time of adenovirus infection was +95 (+44, +152) days. The median peripheral blood lymphocyte count was 0.30 (0.11, 0.69) × 10(9)/L. Twelve patients had acute graft-versus-host disease. Twenty-four patients received antirejection therapies at diagnosis. Sixteen cases had combined infection with other pathogens with adenovirus infection. Eight cases were diagnosed as asymptomatic infection, and 18 were diagnosed as adenovirus disease, including pneumonia (38.89% ) , gastrointestinal disease (38.89% ) , encephalitis (33.33% ) , hepatitis (5.56% ) , and urinary tract inflammation (5.56% ) . The age of >30 years was a risk factor for adenovirus disease (P=0.03) . Eighteen patients received tapering of immunosuppression, and all 26 patients received at least one antiviral drug. Other treatments included high-dose gamma globulin and donor lymphocyte infusion. Adenovirus infection improved in 10 cases and progressed in 16 cases. The median follow-up time was 30 (7, 237) days. Twenty-two patients died. The all-cause mortality rate was (88.5±7.1) % , and the attributable mortality rate was 45.5% . There was no significant difference in the 100 d survival rate between asymptomatic infected patients and patients diagnosed with adenovirus disease (37.5% vs 22.2% , HR=1.83, 95% CI 0.66-5.04, P=0.24) . Conclusion: The age of >30 years was a risk factor for adenovirus disease. Mortality was high in patients with adenovirus infection after allogeneic hematopoietic stem cell transplantation.

Gender-specific dysregulations of nondifferentially expressed biomarkers of metastatic colon cancer

Colon cancer is a common cancer type in both sexes and its mortality rate increases at the metastatic stage. Most studies exclude nondifferentially expressed genes from biomarker analysis of metastatic colon cancers. The motivation of this study is to find the latent associations of the nondifferentially expressed genes with metastatic colon cancers and to evaluate the gender specificity of such associations. This study formulates the expression level prediction of a gene as a regression model trained for primary colon cancers. The difference between a gene's predicted and original expression levels in a testing sample is defined as its mqTrans value (model-based quantitative measure of transcription regulation), which quantitatively measures the change of the gene's transcription regulation in this testing sample. We use the mqTrans analysis to detect the messenger RNA (mRNA) genes with nondifferential expression on their original expression levels but differentially expressed mqTrans values between primary and metastatic colon cancers. These genes are referred to as dark biomarkers of metastatic colon cancer. All dark biomarker genes were verified by two transcriptome profiling technologies, RNA-seq and microarray. The mqTrans analysis of a mixed cohort of both sexes could not recover gender-specific dark biomarkers. Most dark biomarkers overlap with long non-coding RNAs (lncRNAs), and these lncRNAs might have contributed their transcripts to calculating the dark biomarkers' expression levels. Therefore, mqTrans analysis serves as a complementary approach to identify dark biomarkers generally ignored by conventional studies, and it is essential to separate the female and male samples into two analysis experiments. The dataset and mqTrans analysis code are available at https://figshare.com/articles/dataset/22250536.

Enhancement of Quantum Heat Engine by Encircling a Liouvillian Exceptional Point

Quantum heat engines are expected to outperform the classical counterparts due to quantum coherences involved. Here we experimentally execute a single-ion quantum heat engine and demonstrate, for the first time, the dynamics and the enhanced performance of the heat engine originating from the Liouvillian exceptional points (LEPs). In addition to the topological effects related to LEPs, we focus on thermodynamic effects, which can be understood by the Landau-Zener-Stückelberg process under decoherence. We witness a positive net work from the quantum heat engine if the heat engine cycle dynamically encircles a LEP. Further investigation reveals that a larger net work is done when the system is operated closer to the LEP. We attribute the enhanced performance of the quantum heat engine to the Landau-Zener-Stückelberg process, enabled by the eigenenergy landscape in the vicinity of the LEP, and the exceptional point-induced topological transition. Therefore, our results open new possibilities toward LEP-enabled control of quantum heat engines and of thermodynamic processes in open quantum systems.

A90 IMPLEMENTATION OF NATIONAL GUIDELINES ON THE MANAGEMENT OF VACCINE PREVENTABLE ILLNESS IN PATIENTS WITH INFLAMMATORY BOWEL DISEASE: PERCEIVED BARRIERS AND INTERVENTION FUNCTIONS AMONGST GASTROENTEROLOGISTS

Background

Vaccination uptake amongst patients with IBD remains suboptimal. Studies evaluating effectiveness of interventions designed to improve vaccine uptake have not assessed perceived barriers and solutions related to implementation of evidence-based guidelines for vaccine preventable illness (VPI).

Purpose

The aim of this study was to identify barriers and facilitators for evidence-based management of VPI in IBD.

Method

A semi-structured interview was conducted with gastroenterologists. Interview questions were developed and guided by the COM-B and TDF evidence-based implementation science frameworks. A brief intake questionnaire was administered to collect participant demographic and clinical practice information. Gastroenterologists were recruited through direct local contact via email by the investigators. Sixty minute interviews were recorded and transcribed for data analysis. Using thematic analysis, codes from the study data will be generated to identify themes. The data will be categorized into the coding scheme and themes created using an inductive coding approach.

Result(s)

As of October 2022, 5 interviews were conducted. Mean participant age was 47.8 years, with 60% identifying practice in an urban/academic setting compared to a rural/community setting (20%). Preliminary major themes included 1) assessing vaccination status and recommending appropriate vaccines are the responsibility of the gastroenterologist 2) gastroenterologists need more support to administer vaccines in clinical practice 3) barriers to implementation of VPI guidelines include lack of access to a family physician, limited time, vaccine hesitancy, and incomplete understanding of coverage/access to vaccines and 4) intervention themes include use of clinical decision support tools embedded into the workflow of healthcare providers, need for support from allied healthcare providers, increased need for third party support, and more education/CME relating to management of VPI in clinical practice. Specific knowledge gaps include 1) uncertainty relating to what vaccines are covered financially 2) lack of knowledge of risk factors for specific VPI such as pneumococcus and meningococcus and 3) how to administer live vaccines in patients already on immunosuppressants.

Conclusion(s)

Preliminary qualitative themes suggest that although gastroenterologists acknowledge the importance of managing VPI in patients with IBD, perceived resource, policy, and educational barriers exist. The qualitative data from this study will be used to design and implement customized, evidence-based implementation strategies for managing VPI that are sensitive to the local environment.

Please acknowledge all funding agencies by checking the applicable boxes below

None

Disclosure of Interest

None Declared

FMGNN: A Method to Predict Compound-Protein Interaction With Pharmacophore Features and Physicochemical Properties of Amino Acids

Identifying interactions between compounds and proteins is an essential task in drug discovery. To recommend compounds as new drug candidates, applying the computational approaches has a lower cost than conducting the wet-lab experiments. Machine learning-based methods, especially deep learning-based methods, have advantages in learning complex feature interactions between compounds and proteins. However, deep learning models will over-generalize and lead to the problem of predicting less relevant compound-protein pairs when the compound-protein feature interactions are high-dimensional sparse. This problem can be overcome by learning both low-order and high-order feature interactions. In this paper, we propose a novel hybrid model with Factorization Machines and Graph Neural Network called FMGNN to extract the low-order and high-order features, respectively. Then, we design a compound-protein interactions (CPIs) prediction method with pharmacophore features of compound and physicochemical properties of amino acids. The pharmacophore features can ensure that the prediction results much more fit the expectation of biological experiment and the physicochemical properties of amino acids are loaded into the embedding layer to improve the convergence speed and accuracy of protein feature learning. The experimental results on several datasets, especially on an imbalanced large-scale dataset, showed that our proposed method outperforms other existing methods for CPI prediction. The western blot experiment results on wogonin and its candidate target proteins also showed that our proposed method is effective and accurate for finding target proteins. The computer program of implementing the model FMGNN is available at https://github.com/tcygxu2021/FMGNN.

[Analysis of reproductive outcomes in the first IVF-ET cycle after laparoscopic treatment in patients with endometriosis]

Objective: To explore the effect of endometriosis (EM) on reproductive outcomes of young patient with EM after laparoscopic treatment in the first in vitro fertilization-embryo transfer (IVF-ET) cycle. Methods: The clinical data and reproductive outcomes of 394 infertile patients with EM after laparoscopic treatment (EM group) and 3 242 infertile patients caused by gamete transport disorder (control group) in the first IVF-ET cycle were collected in Chongqing Health Center for Women and Children from January 2016 to June 2021. The information included baseline characteristics, oocyte retrieval, embryo development, clinical pregnancy, miscarriage, and live birth. Propensity score matching (PSM) method was used to perform 1∶2 matching between EM group and control group. The impact of EM on reproductive outcomes was analyzed in the retrospective observational study. Results: In the initial data, compared with control group, the number of two pronucleus (2PN) zygotes (9.7±4.8 vs 9.0±4.4), the number of transferable embryos (6.2±3.6 vs 5.5±3.4) and the rate of transferable embryos (64.0% vs 60.8%) on the third day were significantly lower in EM group, and the differences were statistically significant (all P<0.05). After PSM was performed, there were 394 and 787 cases in EM group and control group, respectively. Compared with control group, the number of 2PN zygotes (9.7±4.9 vs 9.0±4.4), the 2PN fertility rate (77.1% vs 75.3%), the number of transferable embryos on the third day (6.2±3.6 vs 5.5±3.4), the transferable embryos rate on the third day (63.8% vs 60.8%) were significantly lower in EM group, and the differences were statically significant (all P<0.05). The study did not find the effect of EM on embryo implantation rate, pregnancy rate, early miscarriage rate, live birth rate and preterm birth rate (all P>0.05). Conclusions: EM might interfere with the development of oocytes and embryos. Obtaining top-quality embryos may be an effective way to improve the prognosis of patients with EM after laparoscopic treatment.

[Reproducibility evaluation of air-charged catheter for rest urethral pressure profilometry]

We retrospectively included 53 (9 males, 44 females) patients who underwent rest urethral pressure profilometry (RUPP) due to lower urinary tract symptoms (LUTS) in Beijing Chaoyang Hospital from May 2021 to March 2022. The age of patients was (55±16) (25-76) years old. The clinical diagnoses of the included patients with lower urinary tract symptoms were classified as: benign prostatic hyperplasia in 9 cases, interstitial cystitis in 1 case, stress urinary incontinence in 11 cases and non-obstructive dysuria in 32 cases. The full set of urodynamic examination was composed of bladder pressure measurement during the filling period, pressure flow study (PFS) and RUPP. All the urodynamic examination was performed by air-charged catheter (ACC) and corresponding equipment. All patients underwent RUPP measurements twice. The vesical pressure (Pves) values were (35.30±6.15), (35.81±5.91) cmH₂O (1 cmH₂O=0.098 kPa); the Pura@max were (141.91±36.53), (145.02±38.85) cmH₂O; functional urethral length were (41.70±16.34), (42.55±16.40) mm; the maximum urethral closure pressure for the two RUPP measurements were (106.57±36.44), (109.41±39.27) cmH₂O. There was no statistical difference between the two RUPP measurements (P>0.05). The reproducibility of the RUPP measurements obtained by ACC is good and deserves further study.

Conservative versus liberal oxygen therapy in relation to all-cause mortality among patients in the intensive care unit: a systematic review of randomized controlled trials with meta-analysis and trial sequential analysis

OBJECTIVE

To evaluate the benefits and harmful effects of conservative versus liberal oxygen therapy in patients admitted to the Intensive Care Unit (ICU).

DESIGN

A systematic review and meta-analysis was carried out.

SETTING

ICU.

PARTICIPANTS

Adult patients (aged 18 years or older) were randomized to either a lower oxygenation target strategy (conservative oxygen therapy) or a higher oxygenation target strategy (liberal oxygen therapy) in the ICU.

INTERVENTIONS

Patients received different oxygenation target strategies.

RESULTS

Ten studies involving 5429 adult patients admitted to the ICU were included in the meta-analysis. The pooled results showed no decreased all-cause mortality at 28 days (RR 0.90; 95%CI 0.75-1.09; p = 0.28), 90 days (RR 1.02; 95%CI 0.92-1.13; p = 0.71) or longest follow-up (RR 0.97; 95%CI 0.88-1.08; p = 0.63) among patients administered conservative oxygen therapy. Secondary outcomes were comparable between the two groups. The results of sensitivity analyses and subgroup analyses were consistent with the main analyses.

CONCLUSION

No beneficial or harmful effects of conservative oxygen therapy were found compared to liberal oxygen therapy in relation to all-cause mortality among adult patients in the ICU. Conservative oxygen therapy did not reduce all-cause mortality at 28 days, 90 days or longest follow-up. Other important clinical outcomes were also comparable between the two groups.

Seven non-differentially expressed 'dark biomarkers' show transcriptional dysregulation in chronic lymphocytic leukemia

Aim: Transcriptional regulation is actively involved in the onset and progression of various diseases. This study used the feature-engineering approach model-based quantitative transcription regulation to quantitatively measure the correlation between mRNA and transcription factors in a reference dataset of chronic lymphocytic leukemia (CLL) transcriptomes. Methods: A comprehensive investigation of transcriptional regulation changes in CLL was conducted using 973 samples in six independent datasets. Results & conclusion: Seven mRNAs were detected to have significantly differential model-based quantitative transcription regulation values but no differential expression between CLL patients and controls. We called these genes 'dark biomarkers' because their original expression levels did not show differential changes in the CLL patients. The overlapping lncRNAs might have contributed their transcripts to the expression miscalculations of these dark biomarkers.

Energy Expenditure Estimation From Respiratory Magnetometer Plethysmography: A Comparison Study

Physical activity (PA) quantification by estimating energy expenditure (EE) is essential to health. Reference methods for EE estimation often involve expensive and cumbersome systems to wear. To address these problems, light-weighted and cost-effective portable devices are developed. Respiratory magnetometer plethysmography (RMP) is among such devices, based on the measurements of thoraco-abdominal distances. The aim of this study was to conduct a comparative study on EE estimation with low to high PA intensity with portable devices including the RMP. Fifteen healthy subjects aged 23.84±4.36 years were equipped with an accelerometer, a heart rate (HR) monitor, a RMP device and a gas exchange system, while performing 9 sedentary and physical activities: sitting, standing, lying, walking at 4 and 6 km/h, running at 9 and 12 km/h, biking at 90 and 110 W. An artificial neural network (ANN) as well as a support vector regression algorithm were developed using features derived from each sensor separately and jointly. We compared also three validation approaches for the ANN model: leave one out subject, 10 fold cross-validation, and subject-specific. Results showed that 1. for portable devices the RMP provided better EE estimation compared to accelerometer and HR monitor alone; 2. combining the RMP and HR data further improved the EE estimation performances; and 3. the RMP device was also reliable in EE estimation for various PA intensities.

AcneTyper: An automatic diagnosis method of dermoscopic acne image via self-ensemble and stacking

BACKGROUND

Acne is a skin lesion type widely existing in adolescents, and poses computational challenges for automatic diagnosis. Computer vision algorithms are utilized to detect and determine different subtypes of acne. Most of the existing acne detection algorithms are based on the facial natural images, which carry noisy factors like illuminations.

OBJECTIVE

In order to tackle this issue, this study collected a dataset ACNEDer of dermoscopic acne images with annotations. Deep learning methods have demonstrated powerful capabilities in automatic acne diagnosis, and they usually release the training epoch with the best performance as the delivered model.

METHODS

This study proposes a novel self-ensemble and stacking-based framework AcneTyper for diagnosing the acne subtypes. Instead of delivering the best epoch, AcneTyper consolidates the prediction results of all training epochs as the latent features and stacks the best subset of these latent features for distinguishing different acne subtypes.

RESULTS

The proposed AcneTyper framework achieves a promising detection performance of acne subtypes and even outperforms a clinical dermatologist with two-year experiences by 6.8% in accuracy.

CONCLUSION

The method we proposed is used to determine different subtypes of acne and outperforms inexperienced dermatologists and contributes to reducing the probability of misdiagnosis.

[The prevalence and risk factors of diabetic peripheral artery disease in Chinese communities]

Objective: To investigate the prevalence and risk factors of diabetic peripheral artery disease (PAD) in patients with type 2 diabetes mellitus (T2DM) managed in primary health care in China. Methods: A total of 2 528 T2DM patients were selected using a two-stage cluster random sampling method based on the baseline survey of the "China Diabetic Foot Prevention Model Project." The study was conducted in 2015 among T2DM patients in 8 primary healthcare centers in Changshu county and Jiang'an district of Wuhan, China. Data collection methods included a questionnaire, body measurement, and blood glucose detection. The Ankle-Brachial Index (ABI) is the most widely used noninvasive vascular test. A binary logistic regression model was used to analyze the influence factors. Results: The prevalence of PAD was 11.2% among the diabetic patients managed in primary health care in the two cities. The prevalence of PAD under 55 years old, 55- years old, 65- years old, and ≥75 years old were 7.8%, 6.0%, 12.9% and 22.5%, respectively. Multivariate stepwise logistic regression identified influence factors included older age, higher education level, smoking, drinking, postprandial glucose uncontrol, and prior myocardial infarction or angina. Compared to age <55 years, the odds ratio for PAD were 0.74 for 55- years (95%CI: 0.43-1.28), 1.72 for 65- years (95%CI: 1.05-2.81), 3.56 for 75 years and above (95%CI: 2.07-6.11), respectively. Compared to patients with education in primary school and below, the odds ratio was 1.37 (95%CI: 0.97-1.94), 2.48 (95%CI: 1.73-3.55), 1.99 (95%CI: 1.26-3.13) for those with education levels of junior high school, senior high school, and college, respectively. Current smoking (OR=1.49, 95%CI: 1.02-2.17), current drinking (OR=0.45, 95%CI: 0.28-0.71), postprandial glucose uncontrol (2 h postprandial plasma glucose >10.0 mmol/L: OR=1.72, 95%CI: 1.22-2.43), and prior myocardial infarction or angina (OR=2.32, 95%CI: 1.50-3.61) were influencing factors of PAD. Conclusions: Despite the high prevalence of PAD in diabetes managed in primary health care; multiple risk factors are not effectively aware of and under control. It is urgent to promote ABI screening and standardized management for diabetes, especially in primary health care.

[Progress in research and development of soft tissue three-dimensional bioprinting and its supporting equipment]

As a cutting-edge technology of tissue engineering, three-dimensional bioprinting can accurately fabricate biomimetic tissue, which has made great progress in the field of hard tissue printing such as bones and teeth. Meanwhile, the research on soft tissue bioprinting is also developing rapidly. This article mainly discussed the development progress in various bioprinting technologies and supporting equipment including printing software, printing hardware, supporting consumables, and bioreactors for soft tissue three-dimensional bioprinting, and made a prospect for the future research and development direction of soft tissue three-dimensional bioprinting.

Integration of lncRNAs, Protein-Coding Genes and Pathology Images for Detecting Metastatic Melanoma

Melanoma is a lethal skin disease that develops from moles. This study aimed to integrate multimodal data to predict metastatic melanoma, which is highly aggressive and difficult to treat. The proposed EnsembleSKCM method evaluated the prediction performances of long noncoding RNAs (lncRNAs), protein-coding messenger genes (mRNAs) and pathology images (images) for metastatic melanoma. Feature selection was used to screen for metastatic biomarkers in the lncRNA and mRNA datasets. The integrated EnsembleSKCM model was built based on the weighted results of the lncRNA-, mRNA- and image-based models. EnsembleSKCM achieved 0.9444 in the prediction accuracy of metastatic melanoma and outperformed the single-modal prediction models based on the lncRNA, mRNA and image data. The experimental data suggest the importance of integrating the complementary information from the three data modalities. WGCNA was used to analyze the relationship of molecular-level features and image features, and the results show connections between them. Another cohort was used to validate our prediction.

[Expression characteristics and diagnostic value of angiogenic molecules in intravenous leiomyomatosis]

Objective: This study aims to analyze the clinicopathological characteristics of patients with intravenous leiomyoma (IVL), and to explore the expression characteristics and diagnostic value of angiogenesis related molecules in IVL. Methods: The clinicopathological data of 40 patients with IVL at Women's Hospital, School of Medicine, Zhejiang University from January 2013 to April 2021 were reviewed. Log-rank test was performed to compare the difference in recurrence-free survival (RFS) rates among patients with different clinicopathological characteristics. Immunohistochemistry (IHC) staining was performed on 10 angiogenesis related molecules to analyze their expression characteristics in IVL. The sensitivity and specificity of molecules with high expression rates in the diagnosis of IVL were calculated, the receiver operating characteristic curve (ROC) was plotted and the area under ROC (AUC) was calculated to evaluate the diagnostic value. Results: Median age of the 40 patients was 47 (43, 50) years. The clinical manifestations of IVL were atypical with the diagnostic accuracy of preoperative ultrasound was 12.5% (5/40), CT and/or MRI was 26.7% (8/30), and intraoperative frozen section was 30.0% (12/40). The overall recurrence rate of IVL was 10.0% (4/40). The Log-rank test showed that the cumulative recurrence-free survival rate of IVL patients with previous cesarean section (40.9%) was lower than that of those without cesarean section (96.4%) (P<0.05); and their median RFS time was shorter than those without cesarean section (16.4 months vs 22.2 months). The overall positive rates of adrenomedullin (ADM), fibroblast growth factor receptor 1 (FGFR1), vascular endothelial growth factor receptor 3 (VEGFR3) and angiogenin receptor tyrosine kinase receptor 1 (TIE1) were 65.0% (26/40), 75.0% (30/40), 57.5% (23/40) and 50.0% (20/40), respectively. FGFR1 expression intensity and positive rate were higher in tumors with a maximum diameter greater than 5 cm than in tumors with a maximum diameter smaller than 5 cm (P<0.05). The AUC of FGFR1 combined with ADM, VEGFR3, and TIE1 was 0.876 (95%CI: 0.788-0.964, P<0.001). Conclusions: There was no typical clinical manifestation of IVL. A history of the previous cesarean section indicated a lower cumulative recurrence-free survival rate and shorter recurrence interval. It was hard to diagnose IVL by sonography, radiography, or frozen section pathology. FGFR1, ADM, VEGFR3, and TIE1 were all highly expressed in IVL, and the efficacy of the combination of the four molecules in diagnosing IVL was higher than that of imaging and classical vascular endothelial markers, which are expected to be promising molecular diagnostic markers.

A polygenic stacking classifier revealed the complicated platelet transcriptomic landscape of adult immune thrombocytopenia

Immune thrombocytopenia (ITP) is an autoimmune disease with the typical symptom of a low platelet count in blood. ITP demonstrated age and sex biases in both occurrences and prognosis, and adult ITP was mainly induced by the living environments. The current diagnosis guideline lacks the integration of molecular heterogenicity. This study recruited the largest cohort of platelet transcriptome samples. A comprehensive procedure of feature selection, feature engineering, and stacking classification was carried out to detect the ITP biomarkers using RNA sequencing (RNA-seq) transcriptomes. The 40 detected biomarkers were loaded to train the final ITP detection model, with an overall accuracy 0.974. The biomarkers suggested that ITP onset may be associated with various transcribed components, including protein-coding genes, long intergenic non-coding RNA (lincRNA) genes, and pseudogenes with apparent transcriptions. The delivered ITP detection model may also be utilized as a complementary ITP diagnosis tool. The code and the example dataset is freely available on http://www.healthinformaticslab.org/supp/resources.php

POS0397 SSD6453, A NOVEL AND HIGHLY SELECTIVE BTK/JAK3 DUAL INHIBITOR IS EFFICACIOUS IN MULTIPLE PRE-CLINICAL MODELS OF INFLAMMATION

Background

The mechanism of inflammatory diseases is complicated and dysfunction of multiple immune cells is thought to be directly related to the pathogenesis. Targeting either JAK-STAT or BCR signaling has been proved solid clinical efficacy in multiple inflammatory diseases, such as rheumatoid arthritis (RA) and multiple sclerosis (MS). And the combination of BTK and JAK inhibitors demonstrated synergistic effects for the treatment of inflammation models in pre-clinic. JAK3 expression is largely restricted to leukocytes and involves functions in JAK1/JAK3 heterodimer in signal transduction, it might be a more effective and safer target. Meanwhile, both BTK and JAK3 possess a cysteine residue in their active site and this feature makes it possible to design a dual inhibitor. SSD6453 is a highly selective and irreversible JAK3/BTK dual inhibitor which may have synergistic effects for the treatment of RA and other inflammatory diseases such as MS.

Objectives

To develop a potent, oral, highly selective JAK3/BTK inhibitor for treatment of multiple inflammatory diseases.

Methods

ADP-GLO based biochemical assays were performed to determine the enzymatic inhibitory effect and selectivity for JAK family. The target engagement was evaluated by IgM induced pBTK and IL-2 induced pSTAT5 in human PBMCs. In vivo efficacy was evaluated by rat collagen-induced arthritic (CIA) model and mice experimental autoimmune encephalomyelitis (EAE) models induced by MOG1-125 or MOG35-55, respectively. BTK occupancy in spleens post last dose 24h and IL-2 induced pSTAT5 in whole blood post last dose 0.5h were used to evaluate targets inhibitions. Osteoclast was stained by IHC in pathological section of rat paws.

Results

In biochemical assays, SSD6453 inhibited BTK and JAK3 with the IC50 values of 3.4 nM and 1.1 nM, respectively. Notably, SSD6453 displayed high selectivity against JAK1 (510 fold), JAK2 (75 fold) and TYK2 (525 fold). In cellular assays, SSD6453 inhibited anti-IgM induced pBTK and IL-2 induced pSTAT5 in human PBMCs with the IC50 values of 18.8 nM and 168.8 nM, respectively. SSD6453 demonstrated favorable PK properties in broad pre-clinical species. Single oral administration of SSD6453 in rat or mouse, resulted in dose-dependent inhibition of BTK and JAKs concurrently. In the rat CIA model in which disease development was accompanied by a robust T-cell and B-cell inflammation response to collagen, SSD6453 dose-dependently inhibited paw edema. And SSD6453 at 10mpk achieved complete (95%) BTK occupancy and JAK3 inhibition and superior efficacy in comparison of tofacitinib (JAK@10 mpk) or evobrutinib (BTK @30mpk) alone, suggesting that concurrent inhibition of JAK3 and BTK lead to synergistic anti-inflammation effects. In addition, ED-1+ osteoclast count decrease was observed in paws, suggesting the prevention of SSD6453 in joint destruction. In two EAE models either induced by MOG1-125 or MOG35-55, which represented T or B dominant inflammation model, respectively, SSD6453 robustly ameliorated disease in both two models. In comparison, BTK inhibitor is efficacious only in the MOG1-125 induced model.

Conclusion

SSD6453 is a novel and high selective BTK/JAK3 dual inhibitor, and demonstrated synergistic efficacy in multiple pre-clinic inflammation models. SSD6453 showed good pharmacokinetic characteristics and well-tolerant in multiple pre-clinical species, and is moving to IND in 2022.

Disclosure of Interests

Feng Zhou Shareholder of: I own the shares of Simcere, Grant/research support from: The work is financially support by Simcere, Employee of: Simcere, Lei Jiang Shareholder of: I own the shares of Simcere, Grant/research support from: The work is financially supported by Simcere, Employee of: I am employee of Simcere, Yuxi Yan Grant/research support from: The work is financially supported by Simcere, Employee of: I am employee of Simcere, Wenqing Yang Shareholder of: I own the shares of Simcere, Grant/research support from: the work is financially supported by Simcere, Employee of: I am employee of Simcere, Feng Tang Shareholder of: I own the shares of Simcere, Grant/research support from: The work is financially supported by Simcere, Employee of: I am employee of simcere, Ping Chen Shareholder of: I own the shares of Simcere, Grant/research support from: The work is financially supported by Simcere, Employee of: I am employee of Simcere, Renhong Tang Shareholder of: I own the shares of Simcere, Grant/research support from: The work is financially supported by Simcere, Employee of: I am employee of Simcere.