Genomic object detection: An improved approach for transposable elements detection and classification using convolutional neural networks.

Analysis of eukaryotic genomes requires the detection and classification of transposable elements (TEs), a crucial but complex and time-consuming task. To improve the performance of tools that accomplish these tasks, Machine Learning approaches (ML) that leverage computer resources, such as GPUs (Graphical Processing Unit) and multiple CPU (Central Processing Unit) cores, have been adopted. However, until now, the use of ML techniques has mostly been limited to classification of TEs. Herein, a detection-classification strategy (named YORO) based on convolutional neural networks is adapted from computer vision (YOLO) to genomics. This approach enables the detection of genomic objects through the prediction of the position, length, and classification in large DNA sequences such as fully sequenced genomes. As a proof of concept, the internal protein-coding domains of LTR-retrotransposons are used to train the proposed neural network. Precision, recall, accuracy, F1-score, execution times and time ratios, as well as several graphical representations were used as metrics to measure performance. These promising results open the door for a new generation of Deep Learning tools for genomics. YORO architecture is available at https://github.com/simonorozcoarias/YORO.

InpactorDB: A Plant LTR Retrotransposon Reference Library.

LTR retrotransposons (LTR-RT) are major components of plant genomes. These transposable elements participate in the structure and evolution of genes and genomes through their mobility and their copy number amplification. For example, they are commonly used as evolutionary markers in genetic, genomic, and cytogenetic approaches. However, the plant research community is faced with the near absence of free availability of full-length, curated, and lineage-level classified LTR retrotransposon reference sequences. In this chapter, we will introduce InpactorDB, an LTR retrotransposon sequence database of 181 plant species representing 98 plant families for a total of 67,241 non-redundant elements. We will introduce how to use newly sequenced genomes to identify and classify LTR-RTs in a similar way with a standardized procedure using the Inpactor tool. InpactorDB is freely available at https://inpactordb.github.io .

Inpactor2: a software based on deep learning to identify and classify LTR-retrotransposons in plant genomes.

LTR-retrotransposons are the most abundant repeat sequences in plant genomes and play an important role in evolution and biodiversity. Their characterization is of great importance to understand their dynamics. However, the identification and classification of these elements remains a challenge today. Moreover, current software can be relatively slow (from hours to days), sometimes involve a lot of manual work and do not reach satisfactory levels in terms of precision and sensitivity. Here we present Inpactor2, an accurate and fast application that creates LTR-retrotransposon reference libraries in a very short time. Inpactor2 takes an assembled genome as input and follows a hybrid approach (deep learning and structure-based) to detect elements, filter partial sequences and finally classify intact sequences into superfamilies and, as very few tools do, into lineages. This tool takes advantage of multi-core and GPU architectures to decrease execution times. Using the rice genome, Inpactor2 showed a run time of 5 minutes (faster than other tools) and has the best accuracy and F1-Score of the tools tested here, also having the second best accuracy and specificity only surpassed by EDTA, but achieving 28% higher sensitivity. For large genomes, Inpactor2 is up to seven times faster than other available bioinformatics tools.

Automatic curation of LTR retrotransposon libraries from plant genomes through machine learning.

Transposable elements are mobile sequences that can move and insert themselves into chromosomes, activating under internal or external stimuli, giving the organism the ability to adapt to the environment. Annotating transposable elements in genomic data is currently considered a crucial task to understand key aspects of organisms such as phenotype variability, species evolution, and genome size, among others. Because of the way they replicate, LTR retrotransposons are the most common transposable elements in plants, accounting in some cases for up to 80% of all DNA information. To annotate these elements, a reference library is usually created, a curation process is performed, eliminating TE fragments and false positives and then annotated in the genome using the homology method. However, the curation process can take weeks, requires extensive manual work and the execution of multiple time-consuming bioinformatics software. Here, we propose a machine learning-based approach to perform this process automatically on plant genomes, obtaining up to 91.18% F1-score. This approach was tested with four plant species, obtaining up to 93.6% F1-score (Oryza granulata) in only 22.61 s, where bioinformatics methods took approximately 6 h. This acceleration demonstrates that the ML-based approach is efficient and could be used in massive sequencing projects.

Sensitivity of deep learning applied to spatial image steganalysis.

In recent years, the traditional approach to spatial image steganalysis has shifted to deep learning (DL) techniques, which have improved the detection accuracy while combining feature extraction and classification in a single model, usually a convolutional neural network (CNN). The main contribution from researchers in this area is new architectures that further improve detection accuracy. Nevertheless, the preprocessing and partition of the database influence the overall performance of the CNN. This paper presents the results achieved by novel steganalysis networks (Xu-Net, Ye-Net, Yedroudj-Net, SR-Net, Zhu-Net, and GBRAS-Net) using different combinations of image and filter normalization ranges, various database splits, different activation functions for the preprocessing stage, as well as an analysis on the activation maps and how to report accuracy. These results demonstrate how sensible steganalysis systems are to changes in any stage of the process, and how important it is for researchers in this field to register and report their work thoroughly. We also propose a set of recommendations for the design of experiments in steganalysis with DL.

K-mer-based machine learning method to classify LTR-retrotransposons in plant genomes.

Every day more plant genomes are available in public databases and additional massive sequencing projects (i.e., that aim to sequence thousands of individuals) are formulated and released. Nevertheless, there are not enough automatic tools to analyze this large amount of genomic information. LTR retrotransposons are the most frequent repetitive sequences in plant genomes; however, their detection and classification are commonly performed using semi-automatic and time-consuming programs. Despite the availability of several bioinformatic tools that follow different approaches to detect and classify them, none of these tools can individually obtain accurate results. Here, we used Machine Learning algorithms based on k-mer counts to classify LTR retrotransposons from other genomic sequences and into lineages/families with an F1-Score of 95%, contributing to develop a free-alignment and automatic method to analyze these sequences.

Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain.

In recent years, Deep Learning techniques applied to steganalysis have surpassed the traditional two-stage approach by unifying feature extraction and classification in a single model, the Convolutional Neural Network (CNN). Several CNN architectures have been proposed to solve this task, improving steganographic images' detection accuracy, but it is unclear which computational elements are relevant. Here we present a strategy to improve accuracy, convergence, and stability during training. The strategy involves a preprocessing stage with Spatial Rich Models filters, Spatial Dropout, Absolute Value layer, and Batch Normalization. Using the strategy improves the performance of three steganalysis CNNs and two image classification CNNs by enhancing the accuracy from 2% up to 10% while reducing the training time to less than 6 h and improving the networks' stability.

InpactorDB: A Classified Lineage-Level Plant LTR Retrotransposon Reference Library for Free-Alignment Methods Based on Machine Learning.

Long terminal repeat (LTR) retrotransposons are mobile elements that constitute the major fraction of most plant genomes. The identification and annotation of these elements via bioinformatics approaches represent a major challenge in the era of massive plant genome sequencing. In addition to their involvement in genome size variation, LTR retrotransposons are also associated with the function and structure of different chromosomal regions and can alter the function of coding regions, among others. Several sequence databases of plant LTR retrotransposons are available for public access, such as PGSB and RepetDB, or restricted access such as Repbase. Although these databases are useful to identify LTR-RTs in new genomes by similarity, the elements of these databases are not fully classified to the lineage (also called family) level. Here, we present InpactorDB, a semi-curated dataset composed of 130,439 elements from 195 plant genomes (belonging to 108 plant species) classified to the lineage level. This dataset has been used to train two deep neural networks (i.e., one fully connected and one convolutional) for the rapid classification of these elements. In lineage-level classification approaches, we obtain up to 98% performance, indicated by the F1-score, precision and recall scores.

Lower methane emissions were associated with higher abundance of ruminal Prevotella in a cohort of Colombian buffalos.

BACKGROUND: Ruminants burp massive amounts of methane into the atmosphere and significantly contribute to the deposition of greenhouse gases and the consequent global warming. It is therefore urgent to devise strategies to mitigate ruminant's methane emissions to alleviate climate change. Ruminal methanogenesis is accomplished by a series of methanogen archaea in the phylum Euryarchaeota, which piggyback into carbohydrate fermentation by utilizing residual hydrogen to produce methane. Abundance of methanogens, therefore, is expected to affect methane production. Furthermore, availability of hydrogen produced by cellulolytic bacteria acting upstream of methanogens is a rate-limiting factor for methane production. The aim of our study was to identify microbes associated with the production of methane which would constitute the basis for the design of mitigation strategies. RESULTS: Moderate differences in the abundance of methanogens were observed between groups. In addition, we present three lines of evidence suggesting an apparent higher abundance of a consortium of Prevotella species in animals with lower methane emissions. First, taxonomic classification revealed increased abundance of at least 29 species of Prevotella. Second, metagenome assembly identified increased abundance of Prevotella ruminicola and another species of Prevotella. Third, metabolic profiling of predicted proteins uncovered 25 enzymes with homology to Prevotella proteins more abundant in the low methane emissions group. CONCLUSIONS: We propose that higher abundance of ruminal Prevotella increases the production of propionic acid and, in doing so, reduces the amount of hydrogen available for methanogenesis. However, further experimentation is required to ascertain the role of Prevotella on methane production and its potential to act as a methane production mitigator.

Retrotransposons in Plant Genomes: Structure, Identification, and Classification through Bioinformatics and Machine Learning.

Transposable elements (TEs) are genomic units able to move within the genome of virtually all organisms. Due to their natural repetitive numbers and their high structural diversity, the identification and classification of TEs remain a challenge in sequenced genomes. Although TEs were initially regarded as "junk DNA", it has been demonstrated that they play key roles in chromosome structures, gene expression, and regulation, as well as adaptation and evolution. A highly reliable annotation of these elements is, therefore, crucial to better understand genome functions and their evolution. To date, much bioinformatics software has been developed to address TE detection and classification processes, but many problematic aspects remain, such as the reliability, precision, and speed of the analyses. Machine learning and deep learning are algorithms that can make automatic predictions and decisions in a wide variety of scientific applications. They have been tested in bioinformatics and, more specifically for TEs, classification with encouraging results. In this review, we will discuss important aspects of TEs, such as their structure, importance in the evolution and architecture of the host, and their current classifications and nomenclatures. We will also address current methods and their limitations in identifying and classifying TEs.

A systematic review of the application of machine learning in the detection and classification of transposable elements.

BACKGROUND: Transposable elements (TEs) constitute the most common repeated sequences in eukaryotic genomes. Recent studies demonstrated their deep impact on species diversity, adaptation to the environment and diseases. Although there are many conventional bioinformatics algorithms for detecting and classifying TEs, none have achieved reliable results on different types of TEs. Machine learning (ML) techniques can automatically extract hidden patterns and novel information from labeled or non-labeled data and have been applied to solving several scientific problems. METHODOLOGY: We followed the Systematic Literature Review (SLR) process, applying the six stages of the review protocol from it, but added a previous stage, which aims to detect the need for a review. Then search equations were formulated and executed in several literature databases. Relevant publications were scanned and used to extract evidence to answer research questions. RESULTS: Several ML approaches have already been tested on other bioinformatics problems with promising results, yet there are few algorithms and architectures available in literature focused specifically on TEs, despite representing the majority of the nuclear DNA of many organisms. Only 35 articles were found and categorized as relevant in TE or related fields. CONCLUSIONS: ML is a powerful tool that can be used to address many problems. Although ML techniques have been used widely in other biological tasks, their utilization in TE analyses is still limited. Following the SLR, it was possible to notice that the use of ML for TE analyses (detection and classification) is an open problem, and this new field of research is growing in interest.

Netlang: A software for the linguistic analysis of corpora by means of complex networks.

To date there is no software that directly connects the linguistic analysis of a conversation to a network program. Networks programs are able to extract statistical information from data basis with information about systems of interacting elements. Language has also been conceived and studied as a complex system. However, most proposals do not analyze language according to linguistic theory, but use instead computational systems that should save time at the price of leaving aside many crucial aspects for linguistic theory. Some approaches to network studies on language do apply precise linguistic analyses, made by a linguist. The problem until now has been the lack of interface between the analysis of a sentence and its integration into the network that could be managed by a linguist and that could save the analysis of any language. Previous works have used old software that was not created for these purposes and that often produced problems with some idiosyncrasies of the target language. The desired interface should be able to deal with the syntactic peculiarities of a particular language, the options of linguistic theory preferred by the user and the preservation of morpho-syntactic information (lexical categories and syntactic relations between items). Netlang is the first program able to do that. Recently, a new kind of linguistic analysis has been developed, which is able to extract a complexity pattern from the speaker's linguistic production which is depicted as a network where words are inside nodes, and these nodes connect each other by means of edges or links (the information inside the edge can be syntactic, semantic, etc.). The Netlang software has become the bridge between rough linguistic data and the network program. Netlang has integrated and improved the functions of programs used in the past, namely the DGA annotator and two scripts (ToXML.pl and Xml2Pairs.py) used for transforming and pruning data. Netlang allows the researcher to make accurate linguistic analysis by means of syntactic dependency relations between words, while tracking record of the nature of such syntactic relationships (subject, object, etc). The Netlang software is presented as a new tool that solve many problems detected in the past. The most important improvement is that Netlang integrates three past applications into one program, and is able to produce a series of file formats that can be read by a network program. Through the Netlang software, the linguistic network analysis based on syntactic analyses, characterized for its low cost and the completely non-invasive procedure aims to evolve into a sufficiently fine grained tool for clinical diagnosis in potential cases of language disorders.

Passiflora quadrangularis L. prevents experimental hypertension and vascular remodelling in rats exposed to nitric oxide deficit / Passiflora quadrangularis L. previene la hipertensión experimental y el remodelado vascular en ratas expuestas a déficit de óxido nítrico

Background: Passiflora quadrangularis L. is among the species used in Colombian folk medicine for hypertension, but until now it has not been studied in experimental models. Objectives: To assess the capacity of P. quadrangularis L. EtOH extract to prevent the hypertension and vascular remodelling induced by nitric oxide (NO) deficit in Wistar rats. Methods: The nitric oxide (NO) synthase inhibitor L-NAME (10 mg/kg, i.p (intraperitoneal), every 48h) was administered for seven weeks to the following groups of rats: P. quadrangularis L.75, 150 and 300 mg/kg/d, p.o. (oral route); enalapril as reference agent, 10 mg/kg/d, p.o. and vehicle as control (mixture of propylene glycol 10%, glycerine 10% and polysorbate 2%). Arterial blood pressure (BP) and heart rate (HR) were measured twice a week. After sacrifice, the aortic rings were isolated, contraction was triggered with phenylephrine (PE 10-6 M) and then the relaxant response achieved with cumulative concentrations of acetylcholine (ACh, 10-10 ­ 10-5 M) or sodium nitroprusside (SNP, 10-10 ­ 10-5 M) was assessed. Histopathologic measures of thickness/lumen ratio from both the left ventricle and aorta walls, as well as phytochemical screening, were also performed. Results: As for enalapril, all doses of P. quadrangularis L. prevented the hypertension induced by L-NAME (122±1.2 versus 155±1.3 mmHg at seventh week). P. quadrangularis L. significantly increased the relaxant effect induced by ACh in isolated aorta and decreased the thickness/lumen ratio of aorta wall specimens. Conclusions: P. quadrangularis L. prevents experimental hypertension induced in rats with nitric oxide deficits improving the endothelium vasodilatation response and protecting against vascular remodelling.

Antecedentes: Passiflora quadrangularis L. es una de las especies utilizadas en medicina tradicional en Colombia para la hipertensión pero hasta el momento no se ha evaluado en modelos experimentales. Objetivos: Evaluar la capacidad del extracto etanólico de P. quadrangularis L. para prevenir la hipertensión y el remodelado vascular inducidos por déficit de óxido nítrico (NO) en ratas Wistar. Métodos: El inhibidor de la óxido nítrico (NO) sintasa L-NAME (10 mg/kg, i.p, cada 48 h) se administró durante siete semanas a los siguientes grupos de tratamiento: P. quadrangularis L. 75, 150 y 300 mg/kg/d, p.o; Enalapril como agente de referencia, 10 mg/kg/d, p.o., y vehículo como control (mezcla de propilenglicol 10%, glicerina 10% y polisorbato 2%). Se midió la presión arterial (BP) y la frecuencia cardiaca (HR) dos veces por semana. Después del sacrificio, se aislaron los anillos aórticos, se desencadenó la contracción con fenilefrina (PE 10-6 M) y la respuesta relajante con concentraciones acumulativas de acetilcolina (ACh, 10-10 ­ 10-5 M) o nitroprusiato de sodio (SNP, 10-10 ­ 10-5 M). También se realizaron estudios histopatológicos de la relación entre el espesor y el lumen tanto en el ventrículo izquierdo como en las paredes de la aorta, así como un cribado fitoquímico. Resultados: Enalapril y todas las dosis de P. quadrangularis L. evitaron la hipertensión inducida por L-NAME (122 ± 1,2 frente a 155 ± 1,3 mm Hg a la séptima semana). P. quadrangularis L. aumentó significativamente el efecto relajante inducido por ACh en la aorta aislada y disminuyó la relación entre el espesor y la luz de los especímenes en la pared de la aorta. Conclusiones: P. quadrangularis L. previene la hipertensión experimental inducida por déficit de óxido nítrico en ratas, mejorando la respuesta del endotelio y protegiendo frente al remodelado vascular.

GITIRBio: A Semantic and Distributed Service Oriented-Architecture for Bioinformatics Pipeline.

The need to process large quantities of data generated from genomic sequencing has resulted in a difficult task for life scientists who are not familiar with the use of command-line operations or developments in high performance computing and parallelization. This knowledge gap, along with unfamiliarity with necessary processes, can hinder the execution of data processing tasks. Furthermore, many of the commonly used bioinformatics tools for the scientific community are presented as isolated, unrelated entities that do not provide an integrated, guided, and assisted interaction with the scheduling facilities of computational resources or distribution, processing and mapping with runtime analysis. This paper presents the first approximation of a Web Services platform-based architecture (GITIRBio) that acts as a distributed front-end system for autonomous and assisted processing of parallel bioinformatics pipelines that has been validated using multiple sequences. Additionally, this platform allows integration with semantic repositories of genes for search annotations. GITIRBio is available at: http://c-head.ucaldas.edu.co:8080/gitirbio.

Construction of coffee transcriptome networks based on gene annotation semantics.

Gene annotation is a process that encompasses multiple approaches on the analysis of nucleic acids or protein sequences in order to assign structural and functional characteristics to gene models. When thousands of gene models are being described in an organism genome, construction and visualization of gene networks impose novel challenges in the understanding of complex expression patterns and the generation of new knowledge in genomics research. In order to take advantage of accumulated text data after conventional gene sequence analysis, this work applied semantics in combination with visualization tools to build transcriptome networks from a set of coffee gene annotations. A set of selected coffee transcriptome sequences, chosen by the quality of the sequence comparison reported by Basic Local Alignment Search Tool (BLAST) and Interproscan, were filtered out by coverage, identity, length of the query, and e-values. Meanwhile, term descriptors for molecular biology and biochemistry were obtained along the Wordnet dictionary in order to construct a Resource Description Framework (RDF) using Ruby scripts and Methontology to find associations between concepts. Relationships between sequence annotations and semantic concepts were graphically represented through a total of 6845 oriented vectors, which were reduced to 745 non-redundant associations. A large gene network connecting transcripts by way of relational concepts was created where detailed connections remain to be validated for biological significance based on current biochemical and genetics frameworks. Besides reusing text information in the generation of gene connections and for data mining purposes, this tool development opens the possibility to visualize complex and abundant transcriptome data, and triggers the formulation of new hypotheses in metabolic pathways analysis.

Efecto de algunas especies vegetales antiinflamatorias sobre la actividad enzimática de elastasa y mieloperoxidasa / Effect of some antiinflammatory plant species on elastase and myeloperoxidase enzyme activity

Se evaluó el efecto de extractos metanólicos y acuosos de las especies vegetales Critoniella acuminata, Salvia rubescens, Phenax rugosus (Poir.) Wedd y Tabebuia chrysanta G. Nicholson sobre las enzimas elastasa y mieloperoxidasa, relacionadas con el proceso de desgranulación leucocitaria, y se determinó el potencial efecto inhibitorio directo sobre la enzima o la inhibición de la desgranulación de los neutrófilos polimorfonucleares. Los extractos de Critoniella acuminata y Salvia rubescens presentaron efectos sobre el proceso de desgranulación y la actividad de las enzimas mieloperoxidasa y elastasa; en el caso de los extractos de Phenax rugosus, estos no mostraron un efecto significativo sobre ninguna de las enzimas. De la especie Tabebuia chrysanta solamente el extracto metanólico mostró efecto sobre la inhibición de la actividad elastasa.

In this work, the effect of aqueous and methanolic extracts of the plants species Critoniella acuminata, Salvia rubescens, Phenax rugosus (Poir.) Wedd and Tabebuia chrysanta G. on the enzymes elastase and myeloperoxidase, involved in degranulation leukocyte process, was evaluated, identifying the potential direct inhibitory effect on the enzyme and/or inhibition of the desgranulation of polymorphonuclear neutrophils. Extracts of Critoniella acuminata and Salvia rubescens presented effects on the degranulation process and the inhibition of the enzyme elastase and myeloperoxidase; the extracts of Phenax rugosus do not showed significant effect. Tabebuia chrysanta methanolic extract only showed effect on inhibition of elastase activity.