In Silico Models to Validate Novel Blood-Based Biomarkers

Biological validation of preliminary findings is a key prerequisite in biomarker discovery. In recent years, the development of advanced large-scale sequencing technologies combined with high-throughput computational analysis methods led to the extraction of considerable amount of data from healthy and diseased tissues. Stored in large open-access repositories, these data can be accessed and interrogated by researchers aiming at understanding the biological rationale behind their results. These so called in silico analyses, in opposite to in vitro analyses, have gained increasing importance in recent years, becoming a major component of research projects and publications. However, making sense of the large amount of data available can be challenging and may lead to a misinterpretation of the data. To reduce the dimensionality of this data, recent years have seen the development of statistical m\ethods and advanced graph analytics which help researchers summarize the available data and draw appropriate conclusions. In this chapter we will describe three in silico methods to investigate the biological underpinnings of a panel of seven blood-based biomarkers of Alzheimer's disease.

Towards Using Graph Analytics for Tracking Covid-19

Graph analytics are now considered the state-of-the-art in many applications of communities detection. The combination between the graph's definition in mathematics and the graphs in computer science as an abstract data structure is the key behind the success of graph-based approaches in machine learning. Based on graphs, several approaches have been developed such as shortest path first (SPF) algorithms, subgraphs extraction, social media analytics, transportation networks, bioinformatic algorithms, etc. While SPF algorithms are widely used in optimization problems, Spectral clustering (SC) algorithms have overcome the limits of the most state-of-art approaches in communities detection. The purpose of this paper is to introduce a graph-based approach of communities detection in the novel coronavirus Covid-19 countries' datasets. The motivation behind this work is to overcome the limitations of multiclass classification, as SC is an unsupervised clustering algorithm, there is no need to predefine the output clusters as a preprocessing step. Our proposed approach is based on a previous contribution on an automatic estimation of the k number of the output clusters. Based on dynamic statistical data for more than 200 countries, each cluster is supposed to group countries having similar behaviors of Covid-19 propagation.

Modeling association detection in order to discover compounds to inhibit oral cancer

In the past, algorithms exploiting varying semantics in interactions between biological objects such as genes and diseases have been used in bioinformatics to uncover latent relationships within biological datasets. In this paper, we consider the algorithm Medusa in parallel with binary classification in order to find potential compounds to inhibit oral cancer. Oral cancer affects the mouth and pharynx and has a high mortality rate due to its late discovery. Current methods of oral cancer treatment, such as chemoradiation and surgery, fail to provide better chances for survival, warranting an alternative approach. By running Medusa on a data fusion graph consisting of biological objects, we incorporate binary classification to model the algorithm's association detection to discover compounds with the potential to mitigate the effects of oral cancer.