Genomics enters the deep learning era

Routhier, Etienne; Mozziconacci, Julien

doi:10.7717/peerj.13613

Cited by 22 publications

(19 citation statements)

References 136 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The different GC content values of Mmyco and Mpneumo prompted us to investigate if the GC content could explain the establishment of Y and U chromatin. To do so, we turned to convolution neural networks (CNN), a computational approach increasingly used in genomics to learn genome annotations from the underlying DNA sequence 25,26 ( Supplementary Figure 1d) . We trained CNNs to learn MNase-seq, and Scc1 or PolII ChIP-seq profiles using yeast chromosomes I to XV sequences (Methods) 27 .…”

Section: Resultsmentioning

confidence: 99%

Exogenous chromosomes reveal how sequence composition drives chromatin assembly, activity, folding and compartmentalization

Chapard

Meneu

Serizay

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Genomic sequences co-evolve with DNA-associated proteins to ensure the orderly folding of long DNA molecules into functional chromosomes. In eukaryotes, this multiscale folding involves several molecular complexes and structures, ranging from nucleosomes to large cohesin-mediated DNA loops. To directly explore the causal relationships between the DNA sequence composition and the spontaneous loading and activity of these complexes in the absence of co-evolution, we used and characterized yeast strains carrying exogenous bacterial chromosomes that diverged from eukaryotic sequences over 1.5 billion years ago. By combining this synthetic approach with deep learning-based in silico analysis, we show that sequence composition drives chromatin assembly, transcriptional activity, folding, and compartmentalization in this cellular context. These results are also a step forward in understanding the molecular events at play following natural horizontal gene transfers, and could also be considered in synthetic genomic engineering projects.

show abstract

Section: Resultsmentioning

confidence: 99%

Exogenous chromosomes reveal how sequence composition drives chromatin assembly, activity, folding and compartmentalization

Chapard

Meneu

Serizay

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Number of layers [1,6] Number of units per layer [4,50] Dropout rate [0. the estimation of the optimal cut-off: The final DL architecture estimated for each LASSO penalty was applied to classify the test data set. For each individual, the output from the last layer, resulting from the sigmoid activation function, was expressed as a probability of being mastitis-susceptible.…”

Section: Sampled Hyperparameters Rangementioning

confidence: 99%

“…Due to the development of high-throughput technology, the past few decades have seen a considerable increase in the availability of genomic data [1,2]. Among them, the most common data structure is the whole genome sequence (WGS) that is nowadays available for thousands of individuals representing various species e.g.…”

Section: Introductionmentioning

confidence: 99%

An explainable deep learning classifier of bovine mastitis based on whole genome sequence data - circumventing the p>>>n problem

Kotlarz

Mielczarek

Biecek

et al. 2023

Preprint

View full text Add to dashboard Cite

The most serious drawback underlying the biological annotation of Whole Genome Sequence data is the p>>n problem, meaning that the number of polymorphic variants (p) is much larger than the number of available phenotypic records (n). Therefore, the major aim of the study was to propose a way to circumvent the problem by combining a LASSO logistic regression model with Deep Learning (DL). That was illustrated by a practical biological problem of classification of cows into mastitis-susceptible or mastitis-resistant, based on genotypes of Single Nucleotide Polymorphisms (SNPs) identified in their WGS. Among several DL architectures proposed via optimisation of DL hyperparameters using the Optuna software, imposed on different SNP sub-sets defined by LASSO logistic regressions with different penalty values, the architecture with 204,642 SNPs was selected as the best one. This architecture was composed of 2 layers with respectively 7 and 46 units per layer as well as respective drop-out rates of 0.210 and 0.358. The classification of the test data set resulted in the AUC=0.750, accuracy=0.650, sensitivity=0.600, and specificity=0.700 was selected as the best model and thus proceeded to genomic and functional annotations. Significant SNPs were selected based on the SHapley Additive exPlanation values transformed to Z-scores to assess the underlying type I-error. These SNPs were annotated to genes. As a final result, a single GO term related to the biological process and thirteen GO terms related to the molecular function were significantly enriched in the gene set that corresponded to the significant SNPs.

show abstract

“…In this scenario of rare and complex genetic disorders where a diagnosis is not reached or a prognosis is not accurate enough, more sophisticated methods should be applied to analyze large-scale genomic data. The use of artificial intelligence (AI) and, particularly, machine learning (ML) algorithms has raised great interest in recent years due to its potential to uncover complex patterns in genomic data 8 . These ML algorithms have shown the capacity to learn from and act on large, heterogeneous datasets to extract new biological insights, improving the accuracy of the diagnosis of RDs [9][10][11][12] .…”

Section: Introductionmentioning

confidence: 99%

A systematic review on machine learning approaches in the diagnosis of rare genetic diseases

Roman‐Naranjo

Parra-Perez

López-Escámez

2023

Preprint

View full text Add to dashboard Cite

Background: The diagnosis of rare genetic diseases is often challenging due to the complexity of the genetic underpinnings of these conditions and the limited availability of diagnostic tools. Machine learning (ML) algorithms have the potential to improve the accuracy and speed of diagnosis by analyzing large amounts of genomic data and identifying complex multiallelic patterns that may be associated with specific diseases. In this systematic review, we aimed to identify the methodological trends and the ML application areas in rare genetic diseases. Methods: We performed a systematic review of the literature following the PRISMA guidelines to search studies that used ML approaches to enhance the diagnosis of rare genetic diseases. Studies that used DNA-based sequencing data and a variety of ML algorithms were included, summarized, and analyzed using bibliometric methods, visualization tools, and a feature co-occurrence analysis. Findings: Our search identified 22 studies that met the inclusion criteria. We found that exome sequencing was the most frequently used sequencing technology (59%), and rare neoplastic diseases were the most prevalent disease scenario (59%). In rare neoplasms, the most frequent applications of ML models were the differential diagnosis or stratification of patients (38.5%) and the identification of somatic mutations (30.8%). In other rare diseases, the most frequent goals were the prioritization of rare variants or genes (55.5%) and the identification of biallelic or digenic inheritance (33.3%). The most employed method was the random forest algorithm (54.5%). In addition, the features of the datasets needed for training these algorithms were distinctive depending on the goal pursued, including the mutational load in each gene for the differential diagnosis of patients, or the combination of genotype features and sequence-derived features (such as GC-content) for the identification of somatic mutations. Conclusions: ML algorithms based on sequencing data are mainly used for the diagnosis of rare neoplastic diseases, with random forest being the most common approach. We identified key features in the datasets used for training these ML models according to the objective pursued. These features can support the development of future ML models in the diagnosis of rare genetic diseases. Keywords: artificial intelligence, rare diseases, precision medicine, rare variants, DNA-sequencing, genomics

show abstract

Genomics enters the deep learning era

Cited by 22 publications

References 136 publications

Exogenous chromosomes reveal how sequence composition drives chromatin assembly, activity, folding and compartmentalization

Exogenous chromosomes reveal how sequence composition drives chromatin assembly, activity, folding and compartmentalization

An explainable deep learning classifier of bovine mastitis based on whole genome sequence data - circumventing the p>>>n problem

A systematic review on machine learning approaches in the diagnosis of rare genetic diseases

Contact Info

Product

Resources

About