An Optimized Cloud Computing Method for Extracting Molecular Descriptors.

Extracting molecular descriptors from chemical compounds is an essential preprocessing phase for developing accurate classification models. Supervised machine learning algorithms offer the capability to detect "hidden" patterns that may exist in a large dataset of compounds, which are represented by their molecular descriptors. Assuming that molecules with similar structure tend to share similar physicochemical properties, large chemical libraries can be screened by applying similarity sourcing techniques in order to detect potential bioactive compounds against a molecular target. However, the process of generating these compound features is time-consuming. Our proposed methodology not only employs cloud computing to accelerate the process of extracting molecular descriptors but also introduces an optimized approach to utilize the computational resources in the most efficient way.

Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy.

Diabetic retinopathy (DR) is a common complication of long-term diabetes, affecting the human eye and potentially leading to permanent blindness. The early detection of DR is crucial for effective treatment, as symptoms often manifest in later stages. The manual grading of retinal images is time-consuming, prone to errors, and lacks patient-friendliness. In this study, we propose two deep learning (DL) architectures, a hybrid network combining VGG16 and XGBoost Classifier, and the DenseNet 121 network, for DR detection and classification. To evaluate the two DL models, we preprocessed a collection of retinal images obtained from the APTOS 2019 Blindness Detection Kaggle Dataset. This dataset exhibits an imbalanced image class distribution, which we addressed through appropriate balancing techniques. The performance of the considered models was assessed in terms of accuracy. The results showed that the hybrid network achieved an accuracy of 79.50%, while the DenseNet 121 model achieved an accuracy of 97.30%. Furthermore, a comparative analysis with existing methods utilizing the same dataset revealed the superior performance of the DenseNet 121 network. The findings of this study demonstrate the potential of DL architectures for the early detection and classification of DR. The superior performance of the DenseNet 121 model highlights its effectiveness in this domain. The implementation of such automated methods can significantly improve the efficiency and accuracy of DR diagnosis, benefiting both healthcare providers and patients.

Multiclass sentiment analysis on COVID-19-related tweets using deep learning models.

COVID-19 is an infectious disease with its first recorded cases identified in late 2019, while in March of 2020 it was declared as a pandemic. The outbreak of the disease has led to a sharp increase in posts and comments from social media users, with a plethora of sentiments being found therein. This paper addresses the subject of sentiment analysis, focusing on the classification of users' sentiment from posts related to COVID-19 that originate from Twitter. The period examined is from March until mid-April of 2020, when the pandemic had thus far affected the whole world. The data is processed and linguistically analyzed with the use of several natural language processing techniques. Sentiment analysis is implemented by utilizing seven different deep learning models based on LSTM neural networks, and a comparison with traditional machine learning classifiers is made. The models are trained in order to distinguish the tweets between three classes, namely negative, neutral and positive.

Attitudes and Awareness Toward Pharmacogenomics and Personalized Medicine Adoption Among Health Sciences Trainees: Experience from Greece and Lessons for Europe.

The increasing incorporation of genomics in clinical practice underscores the need to improve genomics knowledge and familiarity among future health care providers. To this end, it is important to consider both the "push" and the "pull" factors that shape or determine the transition of new personalized medicine (PM) discoveries to clinical practice. One of the pull factors involves the attitudes, values, and education of the user communities such as patients, physicians, and scientists who are poised to use the PM diagnostics. Among the push factors are often health scientists who contribute to PM science and development efforts. Seen in this light, health sciences trainees represent both the push and pull factors, not to mention the next generation of stakeholders and innovation actors who will make PM a reality in mainstream medical practice in the future. Τhis study aimed at investigating and comparing awareness and attitudes (ethical and other) on pharmacogenomics (PGx) and PM adoption among undergraduate students from the school of health sciences and other students. A convenience sample was used in this survey in two groups of students: 205 students from the School of Health Sciences and 141 students from other schools (e.g., biology, computer engineering, and business administration) of the University of Patras, Greece, and mostly at undergraduate education level. We observed that despite the relatively low level of awareness about genetics, PGx, and relevant notions, both groups of students were very optimistic about the genetic testing usefulness and professed their positive anticipations about PGx on disease management. Thus, health sciences students and those in other faculties appeared to be avid proponents of genetics testing and in favor of public endorsement of the concepts of individually tailored medicine. This case study in Greece is one of the first studies on perceptions and attitudes toward PGx testing and PM in Southern Europe. Of importance, the study informs the prospects and challenges on the push and pull factors of PM innovation while offering potential lessons for future PM curriculum needs in health sciences in other countries in Europe.

Improving the Run-Time of Space-Efficient n-Gram Data Structures Using Apache Spark.

Storing information in memory efficiently is one of the most significant challenges in computer science. The two main factors that consist an efficient data structure is the reduction of space and time consumption. There is a plethora of different tools able to reduce the run-time of a process, and Apache Spark is one of these; it is a computing framework that is using clusters to execute a process. There are two key features in this software, a directed acyclic graph (DAG) that maps the execution process and the resilient distributed datasets (RDD), which allow large in-memory computations. In order to construct a data structure, which is space- and time-efficient, we have to utilize the corresponding framework. A comparison of the run-time improvement with the use of Spark is also provided. Finally, to prove the efficacy of this software tool, we construct a space-efficient data structure and compare the run-time with and without its use.

An Improved Self-Labeled Algorithm for Cancer Prediction.

Nowadays, cancer constitutes the second leading cause of death globally. The application of an efficient classification model is considered essential in modern diagnostic medicine in order to assist experts and physicians to make more accurate and early predictions and reduce the rate of mortality. Machine learning techniques are being broadly utilized for the development of intelligent computational systems, exploiting the recent advances in digital technologies and the significant storage capabilities of electronic media. Ensemble learning algorithms and semi-supervised algorithms have been independently developed to build efficient and robust classification models from different perspectives. The former attempts to achieve strong generalization by using multiple learners, while the latter attempts to achieve strong generalization by exploiting unlabeled data. In this work, we propose an improved semi-supervised self-labeled algorithm for cancer prediction, based on ensemble methodologies. Our preliminary numerical experiments illustrate the efficacy and efficiency of the proposed algorithm, proving that reliable and robust prediction models could be developed by the adaptation of ensemble techniques in the semi-supervised learning framework.

Apache Spark Implementations for String Patterns in DNA Sequences.

The availability of numerical data grows from 1 day to another in a remarkable way. New technologies of high-throughput Next-Generation Sequencing (NGS) are producing DNA sequences. Next-Generation Sequencing describes a DNA sequencing technology which has revolutionized genomic research. In this paper, we perform some experiments using a cloud infrastructure framework, namely, Apache Spark, in some sequences derived from the National Center for Biotechnology Information (NCBI). The problems we examine are some of the most popular ones, namely, Longest Common Prefix, Longest Common Substring, and Longest Common Subsequence.

Documentation of clinically relevant genomic biomarker allele frequencies in the next-generation FINDbase worldwide database.

FINDbase (http://www.findbase.org) is a comprehensive data resource recording the prevalence of clinically relevant genomic variants in various populations worldwide, such as pathogenic variants underlying genetic disorders as well as pharmacogenomic biomarkers that can guide drug treatment. Here, we report significant new developments and technological advancements in the database architecture, leading to a completely revamped database structure, querying interface, accompanied with substantial extensions of data content and curation. In particular, the FINDbase upgrade further improves the user experience by introducing responsive features that support a wide variety of mobile and stationary devices, while enhancing computational runtime due to the use of a modern Javascript framework such as ReactJS. Data collection is significantly enriched, with the data records being divided in a Public and Private version, the latter being accessed on the basis of data contribution, according to the microattribution approach, while the front end was redesigned to support the new functionalities and querying tools. The abovementioned updates further enhance the impact of FINDbase, improve the overall user experience, facilitate further data sharing by microattribution, and strengthen the role of FINDbase as a key resource for personalized medicine applications and personalized public health.