Construction of Immune Infiltration-Related LncRNA Signatures Based on Machine Learning for the Prognosis in Colon Cancer.

Colon cancer is one of the malignant tumors with high morbidity, lethality, and prevalence across global human health. Molecular biomarkers play key roles in its prognosis. In particular, immune-related lncRNAs (IRL) have attracted enormous interest in diagnosis and treatment, but less is known about their potential functions. We aimed to investigate dysfunctional IRL and construct a risk model for improving the outcomes of patients. Nineteen immune cell types were collected for identifying house-keeping lncRNAs (HKLncRNA). GSE39582 and TCGA-COAD were treated as the discovery and validation datasets, respectively. Four machine learning algorithms (LASSO, Random Forest, Boruta, and Xgboost) and a Gaussian mixture model were utilized to mine the optimal combination of lncRNAs. Univariate and multivariate Cox regression was utilized to construct the risk score model. We distinguished the functional difference in an immune perspective between low- and high-risk cohorts calculated by this scoring system. Finally, we provided a nomogram. By leveraging the microarray, sequencing, and clinical data for immune cells and colon cancer patients, we identified the 221 HKLncRNAs with a low cell type-specificity index. Eighty-seven lncRNAs were up-regulated in the immune compared to cancer cells. Twelve lncRNAs were beneficial in improving performance. A risk score model with three lncRNAs (CYB561D2, LINC00638, and DANCR) was proposed with robust ROC performance on an independent dataset. According to immune-related analysis, the risk score is strongly associated with the tumor immune microenvironment. Our results emphasized IRL has the potential to be a powerful and effective therapy for enhancing the prognostic of colon cancer.

Deep transfer learning for clinical decision-making based on high-throughput data: comprehensive survey with benchmark results.

The rapid growth of omics-based data has revolutionized biomedical research and precision medicine, allowing machine learning models to be developed for cutting-edge performance. However, despite the wealth of high-throughput data available, the performance of these models is hindered by the lack of sufficient training data, particularly in clinical research (in vivo experiments). As a result, translating this knowledge into clinical practice, such as predicting drug responses, remains a challenging task. Transfer learning is a promising tool that bridges the gap between data domains by transferring knowledge from the source to the target domain. Researchers have proposed transfer learning to predict clinical outcomes by leveraging pre-clinical data (mouse, zebrafish), highlighting its vast potential. In this work, we present a comprehensive literature review of deep transfer learning methods for health informatics and clinical decision-making, focusing on high-throughput molecular data. Previous reviews mostly covered image-based transfer learning works, while we present a more detailed analysis of transfer learning papers. Furthermore, we evaluated original studies based on different evaluation settings across cross-validations, data splits and model architectures. The result shows that those transfer learning methods have great potential; high-throughput sequencing data and state-of-the-art deep learning models lead to significant insights and conclusions. Additionally, we explored various datasets in transfer learning papers with statistics and visualization.

Machine learning in metastatic cancer research: Potentials, possibilities, and prospects.

Cancer has received extensive recognition for its high mortality rate, with metastatic cancer being the top cause of cancer-related deaths. Metastatic cancer involves the spread of the primary tumor to other body organs. As much as the early detection of cancer is essential, the timely detection of metastasis, the identification of biomarkers, and treatment choice are valuable for improving the quality of life for metastatic cancer patients. This study reviews the existing studies on classical machine learning (ML) and deep learning (DL) in metastatic cancer research. Since the majority of metastatic cancer research data are collected in the formats of PET/CT and MRI image data, deep learning techniques are heavily involved. However, its black-box nature and expensive computational cost are notable concerns. Furthermore, existing models could be overestimated for their generality due to the non-diverse population in clinical trial datasets. Therefore, research gaps are itemized; follow-up studies should be carried out on metastatic cancer using machine learning and deep learning tools with data in a symmetric manner.

GILoop: Robust chromatin loop calling across multiple sequencing depths on Hi-C data.

Graph and image are two common representations of Hi-C cis-contact maps. Existing computational tools have only adopted Hi-C data modeled as unitary data structures but neglected the potential advantages of synergizing the information of different views. Here we propose GILoop, a dual-branch neural network that learns from both representations to identify genome-wide CTCF-mediated loops. With GILoop, we explore the combined strength of integrating the two view representations of Hi-C data and corroborate the complementary relationship between the views. In particular, the model outperforms the state-of-the-art loop calling framework and is also more robust against low-quality Hi-C libraries. We also uncover distinct preferences for matrix density by graph-based and image-based models, revealing interesting insights into Hi-C data elucidation. Finally, along with multiple transfer-learning case studies, we demonstrate that GILoop can accurately model the organizational and functional patterns of CTCF-mediated looping across different cell lines.

Analysis of propagating wave structures of the cold bosonic atoms in a zig-zag optical lattice via comparison with two different analytical techniques.

The wave propagation has the significant role in the field of coastal engineering and ocean. In the geographical fields, waves are primary source of environmental process owed to energy conveyance on floating structure. This study aims to investigate the system of cold bosonic atoms in zig-zag optics lattices. The solitonic patterns of the considered model successfully surveyed by using two integrated analytical techniques new extended direct algebraic and G ' G 2 expansion method. The exact solutions are presented by rational, trigonometric, hyperbolic and exponential functions. On the basis of solitons, we need to show that which one is more integrated and robust scheme. These solutions will help to understood the dynamics of cold bosonic atoms in zig-zag optical lattices and the several other systems. Three dimensional as well as two dimensional comparison presented for a cold bosonic atoms model solutions which are revealed diagrammatically for appropriate parameters by using Mathematica. This study will help physicists to predict some new hypothesis and theories in the field of mathematical physics.

A study on sustainable air travel behavior under the possible remedy of risk knowledge: A mediating perspective of risk perception during COVID-19.

The aviation industry is the center of gravity for tourism-dependent countries seeking to uplift their economic activities. The COVID-19 pandemic in the early part of 2020 threatened people and the air industry to the maximum extent. This paper investigated the sustainable air travel behavior of passengers under the risk knowledge path. The mediating role of risk perception, i.e., physical risk, psychological risk, and service quality, was also tested for the risk knowledge-air travel behavior association. We surveyed 339 travelers at six airports in Thailand from January to June 2021 to record their responses. We applied covariance-variance-based structural equation modeling (CB-SEM), and the study results revealed a direct effect of risk knowledge with an indirect impact via risk perception paths on air travel behavior. This paper highlights knowledge as a remedial response to the perceptual makeup of air services sustainability. The study has solid managerial implications for aviation management in the design of ideal pathways for retaining air services during the current public emergency of COVID-19.

Inspirational Leadership and Innovative Communication in Sustainable Organizations: A Mediating Role of Mutual Trust.

The possibility of accomplishing sustainable objectives is largely connected to the management and flourishing of an organizational system which keeps human capital engaged and committed. Our study investigated the association of inspirational leadership and innovative communication with employee engagement and commitment under the lens of leader member exchange theory. Specifically, we emphasized the mediating role of mutual trust in connection to social sustainability facets. A survey of data from employees in the manufacturing sector of Yunnan, China was utilized to test the hypothesized model. The study findings reported a significant association and came to the conclusion that a leader's inspirational behavior coupled with innovative communication is a significant predictor of engagement and commitment in socially sustainable organizations. Moreover, mutual trust significantly mediated the relationship of innovative communication and inspirational leadership with employee engagement and commitment reaching the social perspective of sustainability. The current study added to the literature of sustainable organization by pointing out the social dimensions of sustainability.

Reducing healthcare disparities using multiple multiethnic data distributions with fine-tuning of transfer learning.

Healthcare disparities in multiethnic medical data is a major challenge; the main reason lies in the unequal data distribution of ethnic groups among data cohorts. Biomedical data collected from different cancer genome research projects may consist of mainly one ethnic group, such as people with European ancestry. In contrast, the data distribution of other ethnic races such as African, Asian, Hispanic, and Native Americans can be less visible than the counterpart. Data inequality in the biomedical field is an important research problem, resulting in the diverse performance of machine learning models while creating healthcare disparities. Previous researches have reduced the healthcare disparities only using limited data distributions. In our study, we work on fine-tuning of deep learning and transfer learning models with different multiethnic data distributions for the prognosis of 33 cancer types. In previous studies, to reduce the healthcare disparities, only a single ethnic cohort was used as the target domain with one major source domain. In contrast, we focused on multiple ethnic cohorts as the target domain in transfer learning using the TCGA and MMRF CoMMpass study datasets. After performance comparison for experiments with new data distributions, our proposed model shows promising performance for transfer learning schemes compared to the baseline approach for old and new data distributation experiments.

Visual analysis of environmental research progress in Germany linking Development Anthropology: A sustainable approach based on the Web of Science.

Environmental devaluation is a major concern for European countries as they seek to scrutinize strategies for development anthropology. Germany holds diversified ties with the socioeconomic and environmental development of the region. In accordance with global obligations, Germany's research on environmental issues, protection laws and actions, and universities and scientific research institutions in the field of environmental protection are progressing toward the development of a sustainable future securing the development anthropology. However, Germany's research on environmental issues is unclear to the rest of the world. Chinese scholars also lack effective countermeasures and suggestions for implementing environmental protection cooperation between China and Germany under the Belt and Road Initiative to draw a sustainable global drain. Understanding the current situation and frontier trend of environmental research in German academic circles is essential and irreplaceable for relying on research results data and quantitative analysis theory to carry out the research process. The methodology of this paper established a quantitative analysis based on "institutions," "scholars," "research objects," and "frequency of keywords" among the research results on environmental issues in Germany. It constructs a digital portrait of the field of environmental research in Germany. Knowledge mapping is extensively used in this study as the primary research tool to show the development of environmental research in Germany. The standard deviation of social science research has roughly doubled in that time. CiteSpace, a visual tool for document statistical analysis, is used to analyze the research results on environmental protection published by German scholars from 2008 to 2018. The study results include Web of Science Network, and finally, a visual map is drawn. This study analyzes the status quo, research institutions, keywords, research hotspots, and research trends of international cooperation in environmental research in Germany. The findings are in supportive position of environment study that is the key to human existence and societal development. Leading to this Germans are in concern of human anthropology being reflected in scholarly published work. In response to practical challenges, "global warming" and "sustainable development" became the most frequently used keywords. It provides sustainable thoughts and countermeasures to strengthen Sino-German environmental protection exchange and cooperation further.

Comparative clinical evaluation on herbal formulation Pepsil, Safoof-e-Katira and Omeprazole in gastro esophageal reflux disease.

This study was conducted to evaluate the role of Unani herbal drugs Pepsil and Safoof-e-katira on the gastro esophageal reflux disease (GERD). This was multicentre randomized case control study conducted at Matab Hakeem Muhammad Noor-ud-din, Burewala; Aziz Muhammad din Medical and Surgical Centre, Burewala and Shifa-ul-mulk Memorial Hospital, Hamdard University Karachi. The patients were selected according to inclusion and exclusion criteria. In test group-1 the male female ratio was 40%, 60%; test group-2 was 42%, 58% and in control group was 44%, 56% respectively. The observed symptoms in the study were increased appetite (TG-1-95%, TG-2-95% and CG-89%), difficulty in swallowing (TG-1-93%, TG-2-96% and TC-94%), belching/burping (TG-1-97%, TG-2-97% and CG-95%), vomiting (TG-1-90%, TG-2-96% and CG-89%), heart burn (TG-1-100%, TG-2-100% and CG-98%), palpitation (TG-1-100%, TG-2-100% and CG-97%), epigastric pain (TG-1-97%, TG-2-97% and CG-90%), abdominal cramps (TG-1-97%, TG-2-98% and CG-95%), tenesmus (TG-1-100%, TG-2-100% and CG-97%), flatulence (TG-1-100%, TG-2-75% and CG-95%), wakeup during sleep (TG-1-94%, TG-2-87% and CG-94%). The p-value of the results of the symptoms was 0.000 except flatulence where the value was 0.001. The statistical results of the study prescribed that all the drugs studied (Pepsil, Safoof-e-katira and Omeprazole) are highly significant. The herbal coded drug Pepsil showed no side effects and unani herbal drug safoof-e-katira showed minimum result of 75% in the patients while Omeprazole resulted with some side effects. In the result it can be concluded that the herbal coded drug Pepsil is a potent herbal drug for gastro esophageal reflux disease.