Extreme Gradient Boosting Tuned with Metaheuristic Algorithms for Predicting Myeloid NGS Onco-Somatic Variant Pathogenicity.

The advent of next-generation sequencing (NGS) technologies has revolutionized the field of bioinformatics and genomics, particularly in the area of onco-somatic genetics. NGS has provided a wealth of information about the genetic changes that underlie cancer and has considerably improved our ability to diagnose and treat cancer. However, the large amount of data generated by NGS makes it difficult to interpret the variants. To address this, machine learning algorithms such as Extreme Gradient Boosting (XGBoost) have become increasingly important tools in the analysis of NGS data. In this paper, we present a machine learning tool that uses XGBoost to predict the pathogenicity of a mutation in the myeloid panel. We optimized the performance of XGBoost using metaheuristic algorithms and compared our predictions with the decisions of biologists and other prediction tools. The myeloid panel is a critical component in the diagnosis and treatment of myeloid neoplasms, and the sequencing of this panel allows for the identification of specific genetic mutations, enabling more accurate diagnoses and tailored treatment plans. We used datasets collected from our myeloid panel NGS analysis to train the XGBoost algorithm. It represents a data collection of 15,977 mutations variants composed of a collection of 13,221 Single Nucleotide Variants (SNVs), 73 Multiple Nucleoid Variants (MNVs), and 2683 insertion deletions (INDELs). The optimal XGBoost hyperparameters were found with Differential Evolution (DE), with an accuracy of 99.35%, precision of 98.70%, specificity of 98.71%, and sensitivity of 1.

Comparison between Immunocytochemistry, FISH and NGS for ALK and ROS1 Rearrangement Detection in Cytological Samples.

The detection of ROS1 and ALK rearrangements is performed for advanced-stage non-small cell lung cancer. Several techniques can be used on cytological samples, such as immunocytochemistry (ICC), fluorescence in situ hybridization (FISH) and, more recently, next-generation sequencing (NGS), which is gradually becoming the gold standard. We performed a retrospective study to compare ALK and ROS1 rearrangement results from immunocytochemistry, FISH and NGS methods from 131 cytological samples. Compared to NGS, the sensitivity and specificity of ICC were 0.79 and 0.91, respectively, for ALK, and 1 and 0.87 for ROS1. Regarding FISH, the sensitivity and specificity were both at 1 for ALK and ROS1 probes. False-positive cases obtained by ICC were systematically corrected by FISH. When using ICC and FISH techniques, results are very close to NGS. The false-positive cases obtained by ICC are corrected by FISH, and the true-positive cases are confirmed. NGS has the potential to improve the detection of ALK and ROS1 rearrangements in cytological samples; however, the cost of this technique is still much higher than the sequential use of ICC and FISH.

Molecular characterization of fast-growing melanomas.

BACKGROUND: The rate of growth of primary melanoma is a robust predictor of aggressiveness, but the mutational profile of fast-growing melanomas (FGMM) and the potential to stratify patients at high risk of death has not been comprehensively studied. OBJECTIVE: To investigate the epidemiologic, clinical, and mutational profile of primary cutaneous melanomas with a thickness ≥ 1 mm, stratified by rate of growth. METHODS: Observational prospective study. Deep-targeted sequencing of 40 melanoma driver genes on formalin fixed, paraffin-embedded primary melanoma samples. Comparison of FGMM (rate of growth > 0.5 mm/month) and nonFGMM (rate of growth ≤ 0.5 mm/month). RESULTS: Two hundred patients were enrolled, among wom 70 had FGMM. The relapse-free survival was lower in the FGMM group (P = .014). FGMM had a higher number of predicted deleterious mutations within the 40 genes than nonFGMM (P = .033). Ulceration (P = .032), thickness (P = .006), lower sun exposure (P = .049), and fibroblast growth factor receptor 2 (FGFR2) mutations (P = .037) were significantly associated with fast growth. LIMITATIONS: Single-center study, cohort size, potential memory bias, number of investigated genes. CONCLUSION: Fast growth is linked to specific tumor biology and environmental factors. Ulceration, thickness, and FGFR2 mutations are associated with fast growth. Screening for FGFR2 mutations might provide an additional tool to better identify FGMM, which are probably good candidates for adjuvant therapies.

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.

Comparative genomic analysis of primary tumors and paired brain metastases in lung cancer patients by whole exome sequencing: a pilot study.

Lung cancer brain metastases (BMs) are frequent and associated with poor prognosis despite a better knowledge of lung cancer biology and the development of targeted therapies. The inconstant intracranial response to systemic treatments is partially due to tumor heterogeneity between the primary lung tumor (PLT) and BMs. There is therefore a need for a better understanding of lung cancer BMs biology to improve treatment strategies for these patients. We conducted a study of whole exome sequencing of paired BM and PLT samples. The number of somatic variants and chromosomal alterations was higher in BM samples. We identified recurrent mutations in BMs not found in PLT. Phylogenic trees and lollipop plots were designed to describe their functional impact. Among the 13 genes mutated in ≥ 1 BM, 7 were previously described to be associated with invasion process, including 3 with recurrent mutations in functional domains which may be future targets for therapy. We provide with some insights about the mechanisms leading to BMs. We found recurrent mutations in BM samples in 13 genes. Among these genes, 7 were previously described to be associated with cancer and 3 of them (CCDC178, RUNX1T1, MUC2) were described to be associated with the metastatic process.