Early breast cancer detection and differentiation tool based on tissue impedance characteristics and machine learning.

During Basic screening, it is challenging, if not impossible to detect breast cancer especially in the earliest stage of tumor development. However, measuring the electrical impedance of biological tissue can detect abnormalities even before being palpable. Thus, we used impedance characteristics data of various breast tissue to develop a breast cancer screening tool guided and augmented by a deep learning (DL). A DL algorithm was trained to ideally classify six classes of breast cancer based on electrical impedance characteristics data of the breast tissue. The tool correctly predicted breast cancer in data of patients whose breast tissue impedance was reported to have been measured when other methods detected no anomaly in the tissue. Furthermore, a DL-based approach using Long Short-Term Memory (LSTM) effectively classified breast tissue with an accuracy of 96.67%. Thus, the DL algorithm and method we developed accurately augmented breast tissue classification using electrical impedance and enhanced the ability to detect and differentiate cancerous tissue in very early stages. However, more data and pre-clinical is required to improve the accuracy of this early breast cancer detection and differentiation tool.

New methodology for repetitive sequences identification in human X and Y chromosomes.

Repetitive DNA sequences occupy the major proportion of DNA in the human genome and even in the other species' genomes. The importance of each repetitive DNA type depends on many factors: structural and functional roles, positions, lengths and numbers of these repetitions are clear examples. Conserving such DNA sequences or not in different locations in the chromosome remains a challenge for researchers in biology. Detecting their location despite their great variability and finding novel repetitive sequences remains a challenging task. To side-step this problem, we developed a new method based on signal and image processing tools. In fact, using this method we could find repetitive patterns in DNA images regardless of the repetition length. This new technique seems to be more efficient in detecting new repetitive sequences than bioinformatics tools. In fact, the classical tools present limited performances especially in case of mutations (insertion or deletion). However, modifying one or a few numbers of pixels in the image doesn't affect the global form of the repetitive pattern. As a consequence, we generated a new repetitive patterns database which contains tandem and dispersed repeated sequences. The highly repetitive sequences, we have identified in X and Y chromosomes, are shown to be located in other human chromosomes or in other genomes. The data we have generated is then taken as input to a Convolutional neural network classifier in order to classify them. The system we have constructed is efficient and gives an average of 94.4% as recognition score.

Comparative genomic signature representations of the emerging COVID-19 coronavirus and other coronaviruses: High identity and possible recombination between Bat and Pangolin coronaviruses.

Coronaviruses are responsible on respiratory diseases in animal and human. The combination of numerical encoding techniques and digital signal processing methods are becoming increasingly important in handling large genomic data. In this paper, we propose to analyze the SARS-CoV-2 genomic signature using the combination of different nucleotide representations and signal processing tools in the aim to identify its genetic origin. The sequence of SARS-CoV-2 was compared with 21 relevant sequences including Bat, Yak and Pangolin coronavirus sequences. In addition, we developed a new algorithm to locate the nucleotide modifications. The results show that the Bat and Pangolin coronaviruses were the most related to SARS-CoV-2 with 96% and 86% of identity all along the genome. Within the S gene sequence, the Pangolin sequence presents local highest nucleotide identity. Those findings suggest genesis of SARS-Cov-2 through evolution from Bat and Pangolin strains. This study offers new ways to automatically characterize viruses.

Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction.

In unsupervised learning, there is no apparent straightforward cost function that can capture the significant factors of variations and similarities. Since natural systems have smooth dynamics, an opportunity is lost if an unsupervised objective function remains static. The absence of concrete supervision suggests that smooth dynamics should be integrated during the training process. Compared to classical static cost functions, dynamic objective functions allow to better make use of the gradual and uncertain knowledge acquired through pseudo-supervision. In this paper, we propose Dynamic Autoencoder (DynAE), a novel model for deep clustering that addresses a clustering-reconstruction trade-off, by gradually and smoothly eliminating the reconstruction objective function in favor of a construction one. Experimental evaluations on benchmark datasets show that our approach achieves state-of-the-art results compared to the most relevant deep clustering methods.

The Helitron family classification using SVM based on Fourier transform features applied on an unbalanced dataset.

Helitrons are mobile sequences which belong to the class 2 of eukaryotic transposons. Their specificity resides in their mechanism of transposition: the rolling circle mechanism. They play an important role in remodeling proteomes due to their ability to modify existing genes and introducing new ones. A major difficulty in identifying and classifying Helitron families comes from the complex structure, the unspecified length, and the unbalanced appearance number of each Helitron type. The Helitron's recognition is still not solved in literature. The purpose of this paper is to characterize and classify Helitron types using spectral features and support vector machine (SVM) classification technique. Thus, the helitronic DNA is transformed into a numerical form using the FCGS2 coding technique. Then, a set of spectral features is extracted from the smoothed Fourier transform applied on the FCGS2 signals. Based on the spectral signature and the classification's confusion matrix, we demonstrated that some specific classes which do not show similarities, such as HelitronY2 and NDNAX3, are easily discriminated with important accuracy rates exceeding 90%. However, some Helitron types have great similarities such as the following: Helitron1, HelitronY1, HelitronY1A, and HelitronY4. Our system is also able to predict them with promising values reaching 70%. Graphical abstract The Helitron recognizer based on features extracted from smoothed Fourier transform.

A new way to visualize DNA's base succession: the Caenorhabditis elegans chromosome landscapes.

In the eukaryotic genomes, the genetic diseases are generally associated with the tandem repeats. These repeats seem to appear frequently. In this paper, we are describing a wavelet transform technique which provides a new way to represent the DNA succession bases as a DNA progression images. These images offer DNA landscapes, visualizing and following up periodicities through genomes. We investigated in a structural coding technique the Pnuc. Then, we illustrated, with time-frequency representation, the existence and the superposition of the periodicities in some biological features, their locations and the different ways in which they appear. The representations generated showed that one periodicity can sometimes be alone, but generally, it is incorporated to others. These periodicities associations create, in the Caenorhabditis elegans chromosome, a precise structural image of biological features, such as CeRep, Helitrons, repeats and satellites.

Wavelet analysis of frequency chaos game signal: a time-frequency signature of the C. elegans DNA.

Challenging tasks are encountered in the field of bioinformatics. The choice of the genomic sequence's mapping technique is one the most fastidious tasks. It shows that a judicious choice would serve in examining periodic patterns distribution that concord with the underlying structure of genomes. Despite that, searching for a coding technique that can highlight all the information contained in the DNA has not yet attracted the attention it deserves. In this paper, we propose a new mapping technique based on the chaos game theory that we call the frequency chaos game signal (FCGS). The particularity of the FCGS coding resides in exploiting the statistical properties of the genomic sequence itself. This may reflect important structural and organizational features of DNA. To prove the usefulness of the FCGS approach in the detection of different local periodic patterns, we use the wavelet analysis because it provides access to information that can be obscured by other time-frequency methods such as the Fourier analysis. Thus, we apply the continuous wavelet transform (CWT) with the complex Morlet wavelet as a mother wavelet function. Scalograms that relate to the organism Caenorhabditis elegans (C. elegans) exhibit a multitude of periodic organization of specific DNA sequences.

Building Specific Signals from Frequency Chaos Game and Revealing Periodicities Using a Smoothed Fourier Analysis.

Investigating the roles and functions of DNA within genomes is becoming a primary focus of genomic research. Thus, the research works are moving towards cooperation between different scientific disciplines which aims at facilitating the interpretation of genetic information. In order to characterize the DNA of living organisms, signal processing tools appear to be very suitable for such study. However, a DNA sequence must be converted into a numerical sequence before processing; which defines the concept of DNA coding. In line with this, we propose a new one dimensional model based on the chaos game representation theory called Frequency Chaos Game Signal: FCGS. Then, we perform a Smoothed Fourier Transform to enhance hidden periodicities in the C.elegans DNA sequences. Through this study, we demonstrate the performance of our coding approach in highlighting characteristic periodicities. Indeed, several periodicities are shown to be involved in the 1D spectra and the 2D spectrograms of FCGSs. To investigate further about the contribution of our method in the enhancement of characteristic spectral attributes, a comparison with a range of binary indicators is established.

Detecting particular features in C. elegans genomes using synchronous analysis based on wavelet transform.

In this paper, synchronous analysis based on wavelet transform is applied to genomic sequences. To focus on the particular feature of periodicity 3 in the protein-coding region of genes, a coding method is applied on the sequence, which will be segmented to form a pitch synchronous representation. This modelling concept captures period of period fluctuation of signals. The wavelet transform enhances the periodicity, and a given threshold is used to make decision about exon's positions. The algorithm simulation shows the accuracy of the method in simultaneously locating exons and revealing the reading frame associated.