ForestQC: Quality control on genetic variants from next-generation sequencing data using random forest

Machine learning-based prediction model for brain metastasis in patients with extensive-stage small cell lung cancer

Brain metastases (BMs) in extensive-stage small cell lung cancer (ES-SCLC) are often associated with poor survival rates and quality of life, making the timely identification of high-risk patients for BMs in ES-SCLC crucial. Patients diagnosed with ES-SCLC between 2010 and 2018 were screened from the Surveillance, Epidemiology, and End Results (SEER) database. Four different machine learning (ML) algorithms were used to create prediction models for BMs in ES-SCLC patients. The accuracy, sensitivity, specificity, AUROC, and AUPRC were compared among these models and traditional logistic regression (LR). The random forest (RF) model demonstrated the best performance and was chosen for further analysis. The AUROC and AUPRC were calculated and compared. The findings from the RF model were utilized to identify the risk factors linked to BMs in patients diagnosed with ES-SCLC. Examining 4,716 instances of ES-SCLC, the research conducted an analysis, with brain metastases arising in 1,900 cases. Through evaluation of the ROC curve and PRC concerning the RF Model, results depicted an AUROC of 0.896 (95% CI: 0.889-0.899) and AUPRC of 0.900 (95% CI: 0.895-0.904). Test accuracy measured at 0.810 (95% CI: 0.784-0.833), sensitivity at 0.797 (95% CI: 0.756-0.841), and specificity at 0.819 (95% CI: 0.754-0.879). Based on the SHAP analysis of the RF predictive model, the top 10 most relevant features were identified and ranked in order of relative importance: bone metastasis, liver metastasis, radiation, age, tumor size, primary tumor location, N-stage, race, T-stage, and chemotherapy. The research developed and validated a predictive RF model using clinical and pathological data to predict the risk of BMs in patients with ES-SCLC. This model may assist physicians in making clinical decisions that could delay the onset of BMs and improve patient survival rates.

Generative haplotype prediction outperforms statistical methods for small variant detection in next-generation sequencing data

MOTIVATION

Detection of germline variants in next-generation sequencing data is an essential component of modern genomics analysis. Variant detection tools typically rely on statistical algorithms such as de Bruijn graphs or Hidden Markov models, and are often coupled with heuristic techniques and thresholds to maximize accuracy. Despite significant progress in recent years, current methods still generate thousands of false-positive detections in a typical human whole genome, creating a significant manual review burden.

RESULTS

We introduce a new approach that replaces the handcrafted statistical techniques of previous methods with a single deep generative model. Using a standard transformer-based encoder and double-decoder architecture, our model learns to construct diploid germline haplotypes in a generative fashion identical to modern large language models. We train our model on 37 whole genome sequences from Genome-in-a-Bottle samples, and demonstrate that our method learns to produce accurate haplotypes with correct phase and genotype for all classes of small variants. We compare our method, called Jenever, to FreeBayes, GATK HaplotypeCaller, Clair3, and DeepVariant, and demonstrate that our method has superior overall accuracy compared to other methods. At F1-maximizing quality thresholds, our model delivers the highest sensitivity, precision, and the fewest genotyping errors for insertion and deletion variants. For single nucleotide variants, our model demonstrates the highest sensitivity but at somewhat lower precision, and achieves the highest overall F1 score among all callers we tested.

AVAILABILITY AND IMPLEMENTATION

Jenever is implemented as a python-based command line tool. Source code is available at https://github.com/ARUP-NGS/jenever/.

A CC-NB-ARC-LRR Gene Regulates Bract Morphology in Cotton

Bracts are leaf-like structures in flowering plants. They serve multiple functions such as attracting pollinators, aiding tolerance of abiotic stressors, and conducting photosynthesis. While previous studies extensively examine bract function, the molecular mechanisms underlying bract growth remain unknown. Here, the map-based isolation and characterization of a crucial factor responsible for cotton bract development, identified from a mutant known as frego bract (fg), discovered by Frego in 1945 are presented. This gene, named Ghfg, encodes a CC-NB-ARC-LRR (CNL) family protein. Through analysis of bract form in plants with virus-induced gene silencing (VIGS) and transgenic plants, this gene is confirmed to be the causal gene under the fg locus. Furthermore, high-resolution single-cell transcriptomic landscape of cotton bracts is generated, which reveals differences related to auxin in proliferating cells from TM-1 and T582; differences in auxin distribution and ROS accumulation are experimentally verified. These findings suggest that GhFG is in a self-activated state in the fg mutant, and its activity leads to ROS accumulation that impacts auxin distribution and transport. Finally, an island cotton variety with the frego bract trait is developed, demonstrating a novel solution for reducing the high impurity rate caused by bract remnants.

[Artificial intelligence and acute kidney injury]

Digitalization is increasingly finding its way into intensive care units and with it artificial intelligence (AI) for critically ill patients. One promising area for the use of AI is in the field of acute kidney injury (AKI). The use of AI is primarily focused on the prediction of AKI, but further approaches are also being used to classify existing AKI into different phenotypes. Different AI models are used for prediction. The area under the receiver operating characteristic curve values (AUROC) achieved with these models vary and are influenced by several factors, such as the prediction time and the definition of AKI. Most models have an AUROC between 0.650 and 0.900, with lower values for predictions further into the future and when applying Acute Kidney Injury Network (AKIN) instead of KDIGO criteria. Classification into phenotypes already makes it possible to categorize patients into groups with different risks of mortality or requirement of renal replacement therapy (RRT), but the etiologies or therapeutic consequences derived from this are still lacking. However, all the models suffer from AI-specific shortcomings. The use of large databases does not make it possible to promptly include recent changes in therapy and the implementation of new biomarkers in a relevant proportion. For this reason, serum creatinine and urinary output, with their known limitations, dominate current AI models for prediction impairing the performance of the current models. On the other hand, the increasingly complex models no longer allow physicians to understand the basis on which the warning of a threatening AKI is calculated and subsequent initiation of therapy should take place. The successful use of AIs in routine clinical practice will be highly determined by the trust of the physicians in the systems and overcoming the aforementioned weaknesses. However, the clinician will remain irreplaceable as the decisive authority for critically ill patients by combining measurable and nonmeasurable parameters.

From Data to Insights: Machine Learning Empowers Prognostic Biomarker Prediction in Autism

Autism Spectrum Disorder (ASD) poses significant challenges to society and science due to its impact on communication, social interaction, and repetitive behavior patterns in affected children. The Autism and Developmental Disabilities Monitoring (ADDM) Network continuously monitors ASD prevalence and characteristics. In 2020, ASD prevalence was estimated at 1 in 36 children, with higher rates than previous estimates. This study focuses on ongoing ASD research conducted by Erciyes University. Serum samples from 45 ASD patients and 21 unrelated control participants were analyzed to assess the expression of 372 microRNAs (miRNAs). Six miRNAs (miR-19a-3p, miR-361-5p, miR-3613-3p, miR-150-5p, miR-126-3p, and miR-499a-5p) exhibited significant downregulation in all ASD patients compared to healthy controls. The current study endeavors to identify dependable diagnostic biomarkers for ASD, addressing the pressing need for non-invasive, accurate, and cost-effective diagnostic tools, as current methods are subjective and time-intensive. A pivotal discovery in this study is the potential diagnostic value of miR-126-3p, offering the promise of earlier and more accurate ASD diagnoses, potentially leading to improved intervention outcomes. Leveraging machine learning, such as the K-nearest neighbors (KNN) model, presents a promising avenue for precise ASD diagnosis using miRNA biomarkers.

Glucocorticoid Receptor Gene (NR3C1) Polymorphisms and Metabolic Syndrome: Insights from the Mennonite Population

The regulation of the hypothalamic-pituitary-adrenal (HPA) axis is associated with polymorphisms and the methylation degree of the glucocorticoid receptor gene (NR3C1) and is potentially involved in the development of metabolic syndrome (MetS). In order to evaluate the association between MetS with the polymorphisms, methylation, and gene expression of the NR3C1 in the genetically isolated Brazilian Mennonite population, we genotyped 20 NR3C1 polymorphisms in 74 affected (MetS) and 138 unaffected individuals without affected first-degree relatives (Co), using exome sequencing, as well as five variants from non-exonic regions, in 70 MetS and 166 Co, using mass spectrometry. The methylation levels of 11 1F CpG sites were quantified using pyrosequencing (66 MetS and 141 Co), and the NR3C1 expression was evaluated via RT-qPCR (14 MetS and 25 Co). Age, physical activity, and family environment during childhood were associated with MetS. Susceptibility to MetS, independent of these factors, was associated with homozygosity for rs10482605*C (OR = 4.74, pcorr = 0.024) and the haplotype containing TTCGTTGATT (rs3806855*T_ rs3806854*T_rs10482605*C_rs10482614*G_rs6188*T_rs258813*T_rs33944801*G_rs34176759*A_rs17209258*T_rs6196*T, OR = 4.74, pcorr = 0.048), as well as for the CCT haplotype (rs41423247*C_ rs6877893*C_rs258763*T), OR = 6.02, pcorr = 0.030), but not to the differences in methylation or gene expression. Thus, NR3C1 polymorphisms seem to modulate the susceptibility to MetS in Mennonites, independently of lifestyle and early childhood events, and their role seems to be unrelated to DNA methylation and gene expression.

Genome-Wide SNP and Indel Discovery in Abaca (Musa textilis Née) and among Other Musa spp. for Abaca Genetic Resources Management

Abaca (Musa textilis Née) is an economically important fiber crop in the Philippines. Its economic potential, however, is hampered by biotic and abiotic stresses, which are exacerbated by insufficient genomic resources for varietal identification vital for crop improvement. To address these gaps, this study aimed to discover genome-wide polymorphisms among abaca cultivars and other Musa species and analyze their potential as genetic marker resources. This was achieved through whole-genome Illumina resequencing of abaca cultivars and variant calling using BCFtools, followed by genetic diversity and phylogenetic analyses. A total of 20,590,381 high-quality single-nucleotide polymorphisms (SNP) and DNA insertions/deletions (InDels) were mined across 16 abaca cultivars. Filtering based on linkage disequilibrium (LD) yielded 130,768 SNPs and 13,620 InDels, accounting for 0.396 ± 0.106 and 0.431 ± 0.111 of gene diversity across these cultivars. LD-pruned polymorphisms across abaca, M. troglodytarum, M. acuminata and M. balbisiana enabled genetic differentiation within abaca and across the four Musa spp. Phylogenetic analysis revealed the registered varieties Abuab and Inosa to accumulate a significant number of mutations, eliciting further studies linking mutations to their advantageous phenotypes. Overall, this study pioneered in producing marker resources in abaca based on genome-wide polymorphisms vital for varietal authentication and comparative genotyping with the more studied Musa spp.

Discordant calls across genotype discovery approaches elucidate variants with systematic errors

Large-scale high-throughput sequencing data sets have been transformative for informing clinical variant interpretation and for use as reference panels for statistical and population genetic efforts. Although such resources are often treated as ground truth, we find that in widely used reference data sets such as the Genome Aggregation Database (gnomAD), some variants pass gold-standard filters, yet are systematically different in their genotype calls across genotype discovery approaches. The inclusion of such discordant sites in study designs involving multiple genotype discovery strategies could bias results and lead to false-positive hits in association studies owing to technological artifacts rather than a true relationship to the phenotype. Here, we describe this phenomenon of discordant genotype calls across genotype discovery approaches, characterize the error mode of wrong calls, provide a list of discordant sites identified in gnomAD that should be treated with caution in analyses, and present a metric and machine learning classifier trained on gnomAD data to identify likely discordant variants in other data sets. We find that different genotype discovery approaches have different sets of variants at which this problem occurs, but there are characteristic variant features that can be used to predict discordant behavior. Discordant sites are largely shared across ancestry groups, although different populations are powered for the discovery of different variants. We find that the most common error mode is that of a variant being heterozygous for one approach and homozygous for the other, with heterozygous in the genomes and homozygous reference in the exomes making up the majority of miscalls.

Validation of genetic variants from NGS data using deep convolutional neural networks

Accurate somatic variant calling from next-generation sequencing data is one most important tasks in personalised cancer therapy. The sophistication of the available technologies is ever-increasing, yet, manual candidate refinement is still a necessary step in state-of-the-art processing pipelines. This limits reproducibility and introduces a bottleneck with respect to scalability. We demonstrate that the validation of genetic variants can be improved using a machine learning approach resting on a Convolutional Neural Network, trained using existing human annotation. In contrast to existing approaches, we introduce a way in which contextual data from sequencing tracks can be included into the automated assessment. A rigorous evaluation shows that the resulting model is robust and performs on par with trained researchers following published standard operating procedure.

FVC as an adaptive and accurate method for filtering variants from popular NGS analysis pipelines

The quality control of variants from whole-genome sequencing data is vital in clinical diagnosis and human genetics research. However, current filtering methods (Frequency, Hard-Filter, VQSR, GARFIELD, and VEF) were developed to be utilized on particular variant callers and have certain limitations. Especially, the number of eliminated true variants far exceeds the number of removed false variants using these methods. Here, we present an adaptive method for quality control on genetic variants from different analysis pipelines, and validate it on the variants generated from four popular variant callers (GATK HaplotypeCaller, Mutect2, Varscan2, and DeepVariant). FVC consistently exhibited the best performance. It removed far more false variants than the current state-of-the-art filtering methods and recalled ~51-99% true variants filtered out by the other methods. Once trained, FVC can be conveniently integrated into a user-specific variant calling pipeline.

FVC is a method for calling specific gene variants from whole genome data, for potential use in clinical diagnosis and human genetics research.

A quality control portal for sequencing data deposited at the European genome-phenome archive

Since its launch in 2008, the European Genome-Phenome Archive (EGA) has been leading the archiving and distribution of human identifiable genomic data. In this regard, one of the community concerns is the potential usability of the stored data, as of now, data submitters are not mandated to perform any quality control (QC) before uploading their data and associated metadata information. Here, we present a new File QC Portal developed at EGA, along with QC reports performed and created for 1 694 442 files [Fastq, sequence alignment map (SAM)/binary alignment map (BAM)/CRAM and variant call format (VCF)] submitted at EGA. QC reports allow anonymous EGA users to view summary-level information regarding the files within a specific dataset, such as quality of reads, alignment quality, number and type of variants and other features. Researchers benefit from being able to assess the quality of data prior to the data access decision and thereby, increasing the reusability of data (https://ega-archive.org/blog/data-upcycling-powered-by-ega/).

Artificial Intelligence and Cardiovascular Genetics

Polygenic diseases, which are genetic disorders caused by the combined action of multiple genes, pose unique and significant challenges for the diagnosis and management of affected patients. A major goal of cardiovascular medicine has been to understand how genetic variation leads to the clinical heterogeneity seen in polygenic cardiovascular diseases (CVDs). Recent advances and emerging technologies in artificial intelligence (AI), coupled with the ever-increasing availability of next generation sequencing (NGS) technologies, now provide researchers with unprecedented possibilities for dynamic and complex biological genomic analyses. Combining these technologies may lead to a deeper understanding of heterogeneous polygenic CVDs, better prognostic guidance, and, ultimately, greater personalized medicine. Advances will likely be achieved through increasingly frequent and robust genomic characterization of patients, as well the integration of genomic data with other clinical data, such as cardiac imaging, coronary angiography, and clinical biomarkers. This review discusses the current opportunities and limitations of genomics; provides a brief overview of AI; and identifies the current applications, limitations, and future directions of AI in genomics.

What makes a good prediction? Feature importance and beginning to open the black box of machine learning in genetics

Genetic data have become increasingly complex within the past decade, leading researchers to pursue increasingly complex questions, such as those involving epistatic interactions and protein prediction. Traditional methods are ill-suited to answer these questions, but machine learning (ML) techniques offer an alternative solution. ML algorithms are commonly used in genetics to predict or classify subjects, but some methods evaluate which features (variables) are responsible for creating a good prediction; this is called feature importance. This is critical in genetics, as researchers are often interested in which features (e.g., SNP genotype or environmental exposure) are responsible for a good prediction. This allows for the deeper analysis beyond simple prediction, including the determination of risk factors associated with a given phenotype. Feature importance further permits the researcher to peer inside the black box of many ML algorithms to see how they work and which features are critical in informing a good prediction. This review focuses on ML methods that provide feature importance metrics for the analysis of genetic data. Five major categories of ML algorithms: k nearest neighbors, artificial neural networks, deep learning, support vector machines, and random forests are described. The review ends with a discussion of how to choose the best machine for a data set. This review will be particularly useful for genetic researchers looking to use ML methods to answer questions beyond basic prediction and classification.

Machine learning random forest for predicting oncosomatic variant NGS analysis

Since 2017, we have used IonTorrent NGS platform in our hospital to diagnose and treat cancer. Analyzing variants at each run requires considerable time, and we are still struggling with some variants that appear correct on the metrics at first, but are found to be negative upon further investigation. Can any machine learning algorithm (ML) help us classify NGS variants? This has led us to investigate which ML can fit our NGS data and to develop a tool that can be routinely implemented to help biologists. Currently, one of the greatest challenges in medicine is processing a significant quantity of data. This is particularly true in molecular biology with the advantage of next-generation sequencing (NGS) for profiling and identifying molecular tumors and their treatment. In addition to bioinformatics pipelines, artificial intelligence (AI) can be valuable in helping to analyze mutation variants. Generating sequencing data from patient DNA samples has become easy to perform in clinical trials. However, analyzing the massive quantities of genomic or transcriptomic data and extracting the key biomarkers associated with a clinical response to a specific therapy requires a formidable combination of scientific expertise, biomolecular skills and a panel of bioinformatic and biostatistic tools, in which artificial intelligence is now successful in developing future routine diagnostics. However, cancer genome complexity and technical artifacts make identifying real variants challenging. We present a machine learning method for classifying pathogenic single nucleotide variants (SNVs), single nucleotide polymorphisms (SNPs), multiple nucleotide variants (MNVs), insertions, and deletions detected by NGS from different types of tumor specimens, such as: colorectal, melanoma, lung and glioma cancer. We compared our NGS data to different machine learning algorithms using the k-fold cross-validation method and to neural networks (deep learning) to measure the performance of the different ML algorithms and determine which one is a valid model for confirming NGS variant calls in cancer diagnosis. We trained our machine learning with 70% of our data samples, extracted from our local database (our data structure had 7 parameters: chromosome, position, exon, variant allele frequency, minor allele frequency, coverage and protein description) and validated it with the 30% remaining data. The model offering the best accuracy was chosen and implemented in the NGS analysis routine. Artificial intelligence was developed with the R script language version 3.6.0. We trained our model on 70% of 102,011 variants. Our best error rate (0.22%) was found with random forest machine learning (ntree = 500 and mtry = 4), with an AUC of 0.99. Neural networks achieved some good scores. The final trained model with the neural network achieved an accuracy of 98% and an ROC-AUC of 0.99 with validation data. We tested our RF model to interpret more than 2000 variants from our NGS database: 20 variants were misclassified (error rate < 1%). The errors were nomenclature problems and false positives. After adding false positives to our training database and implementing our RF model routinely, our error rate was always < 0.5%. The RF model shows excellent results for oncosomatic NGS interpretation and can easily be implemented in other molecular biology laboratories. AI is becoming increasingly important in molecular biomedical analysis and can be very helpful in processing medical data. Neural networks show a good capacity in variant classification, and in the future, they may be useful in predicting more complex variants.

Efficient collection of a large number of mutations by mutagenesis of DNA damage response defective animals

With the development of massive parallel sequencing technology, it has become easier to establish new model organisms that are ideally suited to the specific biological phenomena of interest. Considering the history of research using classical model organisms, we believe that the efficient construction and sharing of gene mutation libraries will facilitate the progress of studies using these new model organisms. Using C. elegans, we applied the TMP/UV mutagenesis method to animals lacking function in the DNA damage response genes atm-1 and xpc-1. This method produces genetic mutations three times more efficiently than mutagenesis of wild-type animals. Furthermore, we confirmed that the use of next-generation sequencing and the elimination of false positives through machine learning could automate the process of mutation identification with an accuracy of over 95%. Eventually, we sequenced the whole genomes of 488 strains and isolated 981 novel mutations generated by the present method; these strains have been made available to anyone who wants to use them. Since the targeted DNA damage response genes are well conserved and the mutagens used in this study are also effective in a variety of species, we believe that our method is generally applicable to a wide range of animal species.

seqQscorer: automated quality control of next-generation sequencing data using machine learning

Controlling quality of next-generation sequencing (NGS) data files is a necessary but complex task. To address this problem, we statistically characterize common NGS quality features and develop a novel quality control procedure involving tree-based and deep learning classification algorithms. Predictive models, validated on internal and external functional genomics datasets, are to some extent generalizable to data from unseen species. The derived statistical guidelines and predictive models represent a valuable resource for users of NGS data to better understand quality issues and perform automatic quality control. Our guidelines and software are available at https://github.com/salbrec/seqQscorer.