Mandrake: visualising microbial population structure by embedding millions of genomes into a low-dimensional representation

In less than a decade, population genomics of microbes has progressed from the effort of sequencing dozens of strains to thousands, or even tens of thousands of strains in a single study. There are now hundreds of thousands of genomes available even for a single bacterial species and the number of genomes is expected to continue to increase at an accelerated pace given the advances in sequencing technology and widespread genomic surveillance initiatives. This explosion of data calls for innovative methods to enable rapid exploration of the structure of a population based on different data modalities, such as multiple sequence alignments, assemblies and estimates of gene content across different genomes. Here we present Mandrake, an efficient implementation of a dimensional reduction method tailored for the needs of large-scale population genomics. Mandrake is capable of visualising population structure from millions of whole genomes and we illustrate its usefulness with several data sets representing major pathogens. Our method is freely available both as an analysis pipeline (https://github.com/johnlees/mandrake) and as a browser-based interactive application (https://gtonkinhill.github.io/mandrake-web/).

Dimension Reduction Using New Bond Graph Algorithm and Deep Learning Pooling on EEG Signals for BCI

One of the main challenges in studying brain signals is the large size of the data due to the use of many electrodes and the time-consuming sampling. Choosing the right dimensional reduction method can lead to a reduction in the data processing time. Evolutionary algorithms are one of the methods used to reduce the dimensions in the field of EEG brain signals, which have shown better performance than other common methods. In this article, (1) a new Bond Graph algorithm (BGA) is introduced that has demonstrated better performance on eight benchmark functions compared to genetic algorithm and particle swarm optimization. Our algorithm has fast convergence and does not get stuck in local optimums. (2) Reductions of features, electrodes, and the frequency range have been evaluated simultaneously for brain signals (left-handed and right-handed). BGA and other algorithms are used to reduce features. (3) Feature extraction and feature selection (with algorithms) for time domain, frequency domain, wavelet coefficients, and autoregression have been studied as well as electrode reduction and frequency interval reduction. (4) First, the features/properties (algorithms) are reduced, the electrodes are reduced, and the frequency range is reduced, which is followed by the construction of new signals based on the proposed formulas. Then, a Common Spatial Pattern is used to remove noise and feature extraction and is classified by a classifier. (5) A separate study with a deep sampling method has been implemented as feature selection in several layers with functions and different window sizes. This part is also associated with reducing the feature and reducing the frequency range. All items expressed in data set IIa from BCI competition IV (the left hand and right hand) have been evaluated between one and three channels, with better results for similar cases (in close proximity). Our method demonstrated an increased accuracy by 5 to 8% and an increased kappa by 5%.

Cancer Detection based on Microarray Data Classification Using FLNN and Hybrid Feature Selection

Cancer is one of the second deadliest diseases in the world after heart disease. Citing from the WHO's report on cancer, in 2018 there were around 18.1 million cases of cancer in the world with a total of 9.6 million deaths. Now that bioinformatics technology is growing and based on WHO’s report on cancer, an early detection is needed where bioinformatics technology can be used to diagnose cancer and to help to reduce the number of deaths from cancer by immediately treating the person. Microarray DNA data as one of the bioinformatics technology is becoming popular for use in the analysis and diagnosis of cancer in the medical world. Microarray DNA data has a very large number of genes, so a dimensional reduction method is needed to reduce the use of features for the classification process by selecting the most influential features. After the most influential features are selected, these features are going to be used for the classification and predict whether a person has cancer or not. In this research, hybridization is carried out by combining Information Gain as a filtering method and Genetic Algorithm as a wrapping method to reduce dimensions, and lastly FLNN as a classification method. The test results get colon cancer data to get the highest accuracy value of 90.26%, breast cancer by 85.63%, lung cancer and ovarian cancer by 100%, and prostate cancer by 94.10%.

Three-dimensional reduction method with a modified C2 isthmus screw in irreducible atlantoaxial dislocation: a technical note

Background Three-dimensional reduction plays a vital role in surgical reduction of irreversible atlantoaxial dislocation (IAAD). However, the most commonly used combination of C1 pedicle screw (PS) or lateral mass screw (LMS) and C2 PS or isthmus screw often fails to achieve satisfactory reduction at one time. The difficulty is usually caused by short anteroposterior and vertical distance between heads of C1 and C2 screws, which lack enough space for reduction operation. The objective of this study is to describe a three-dimensional reduction method with a modified C2 isthmus screw and to illustrate its advantage and effectiveness for IAAD. Methods Twelve patients with IAAD underwent reduction and fixation with modified C2 isthmus screw combined with C1 PS or LMS, fusion with autologous bone graft. The insertion point was lateral to the intersection of caudal edge of C2 lamina and lateral mass, with a trajectory towards C2 isthmus, via lateral mass. The three-dimensional reduction was achieved through pulling and distracting. Radiographic evaluation included anteroposterior and direct distance between different insertion points, the occipitoaxial angle (O-C2A), clivus-canal angle (CCA) and cervicomedullary angle (CMA). Clinical outcomes evaluation included the Japanese Orthopaedic Association (JOA) score, Visual analog scale (VAS) and Neck Disability Index (NDI). Results All the patients maintained effective reduction during the follow-up. The anteroposterior and direct distance was significantly higher in modified C2 isthmus screw than C2 PS whether combined with C1 PS or LMS (P < 0.05). The degree of O-C2A, CCA and CMA, JOA score, NDI, and VAS were significantly improved after the surgery (P < 0.05). Conclusions Three-dimensional reduction method with a modified C2 isthmus screw is effective and safe in managing IAAD. It can increase the anteroposterior and vertical distance between the heads of C1 and C2 screws, which is benefit for the three-dimensional reduction operation of IAAD.

A Roadmap towards Breast Cancer Therapies Supported by Explainable Artificial Intelligence

In recent years personalized medicine reached an increasing importance, especially in the design of oncological therapies. In particular, the development of patients’ profiling strategies suggests the possibility of promising rewards. In this work, we present an explainable artificial intelligence (XAI) framework based on an adaptive dimensional reduction which (i) outlines the most important clinical features for oncological patients’ profiling and (ii), based on these features, determines the profile, i.e., the cluster a patient belongs to. For these purposes, we collected a cohort of 267 breast cancer patients. The adopted dimensional reduction method determines the relevant subspace where distances among patients are used by a hierarchical clustering procedure to identify the corresponding optimal categories. Our results demonstrate how the molecular subtype is the most important feature for clustering. Then, we assessed the robustness of current therapies and guidelines; our findings show a striking correspondence between available patients’ profiles determined in an unsupervised way and either molecular subtypes or therapies chosen according to guidelines, which guarantees the interpretability characterizing explainable approaches to machine learning techniques. Accordingly, our work suggests the possibility to design data-driven therapies to emphasize the differences observed among the patients.

Sparse Graph Embedding Based on the Fuzzy Set for Image Classification

In recent years, many face image feature extraction and dimensional reduction algorithms have been proposed for linear and nonlinear data, such as local-based graph embedding algorithms or fuzzy set algorithms. However, the aforementioned algorithms are not very effective for face images because they are always affected by overlaps (outliers) and sparsity points in the database. To solve the problems, a new and effective dimensional reduction method for face recognition is proposed—sparse graph embedding with the fuzzy set for image classification. The aim of this algorithm is to construct two new fuzzy Laplacian scattering matrices by using the local graph embedding and fuzzy k-nearest neighbor. Finally, the optimal discriminative sparse projection matrix is obtained by adding elastic network regression. Experimental results and analysis indicate that the proposed algorithm is more effective than other algorithms in the UCI wine dataset and ORL, Yale, and AR standard face databases.