Summary Assessing the pathogenicity of genetic variants can be a complex and challenging task. Spliceogenic variants, which alter mRNA splicing, may yield mature transcripts that encode non-functional protein products, an important predictor of Mendelian disease risk. However, most variant annotation tools do not adequately assess spliceogenicity outside the native splice site and thus the disease-causing potential of variants in other intronic and exonic regions is often overlooked. Here, we present a plugin for the Ensembl Variant Effect Predictor that packages MaxEntScan and extends its functionality to provide splice site predictions using a maximum entropy model. The plugin incorporates a sliding window algorithm to predict splice site loss or gain for any variant that overlaps a transcript feature. We also demonstrate the utility of the plugin by comparing our predictions to two mRNA splicing datasets containing several cancer-susceptibility genes. Availability and implementation Source code is freely available under the Apache License, Version 2.0: https://github.com/Ensembl/VEP_plugins. Supplementary information Supplementary data are available at Bioinformatics online.

Endometrial cancer is the most common gynecological cancer, but is nevertheless uncommon enough to have value as a signature cancer for some hereditary cancer syndromes. Commercial multigene testing panels include up to 13 different genes annotated for germline DNA testing of patients with endometrial cancer. Many other genes have been reported as relevant to familial endometrial cancer from directed genome-wide sequencing studies or multigene panel testing, or research. This review assesses the evidence supporting association with endometrial cancer risk for 32 genes implicated in hereditary endometrial cancer, and presents a summary of rare germline variants in these 32 genes detected by analysis of quasi-population-based endometrial cancer patients from The Cancer Genome Atlas project. This comprehensive investigation has led to the conclusion that convincing evidence currently exists to support clinical testing of only six of these genes for diagnosis of hereditary endometrial cancer. Testing of endometrial cancer patients for the remaining genes should be considered in the context of research studies, as a means to better establish the level of endometrial cancer risk, if any, associated with genetic variants that are deleterious to gene or protein function. It is acknowledged that clinical testing of endometrial cancer patients for several genes included on commercial panels may provide actionable findings in relation to risk of other cancers, but these should be considered secondary or incidental findings and not conclusive evidence for diagnosis of inherited endometrial cancer. In summary, this review and analysis provides a comprehensive report of current evidence to guide the selection of genes for clinical and research gene testing of germline DNA from endometrial cancer patients.

The Li-Fraumeni syndrome (LFS) and its variant form (LFL) is a familial predisposition to multiple forms of childhood, adolescent, and adult cancers associated with germ-line mutation in the TP53 tumor suppressor gene. Individual disparities in tumor patterns are compounded by acceleration of cancer onset with successive generations. It has been suggested that this apparent anticipation pattern may result from germ-line genomic instability in TP53 mutation carriers, causing increased DNA copy-number variations (CNVs) with successive generations. To address the genetic basis of phenotypic disparities of LFS/LFL, we performed whole-genome sequencing (WGS) of 13 subjects from two generations of an LFS kindred. Neither de novo CNV nor significant difference in total CNV was detected in relation with successive generations or with age at cancer onset. These observations were consistent with an experimental mouse model system showing that trp53 deficiency in the germ line of father or mother did not increase CNV occurrence in the offspring. On the other hand, individual records on 1,771 TP53 mutation carriers from 294 pedigrees were compiled to assess genetic anticipation patterns (International Agency for Research on Cancer TP53 database). No strictly defined anticipation pattern was observed. Rather, in multigeneration families, cancer onset was delayed in older compared with recent generations. These observations support an alternative model for apparent anticipation in which rare variants from noncarrier parents may attenuate constitutive resistance to tumorigenesis in the offspring of TP53 mutation carriers with late cancer onset.Li-Fraumeni syndrome | whole genome sequencing | genetic anticipation | p53 mutation | copy number variation

Type of cancer and age of onset in individuals with inherited aberrations in the tumour suppressor gene TP53 are variable, possibly influenced by genetic modifiers and different environmental exposure. Since 2009, the modified Chompret criteria (MCC) have been used to identify individuals for TP53 mutation screening. Using the TP53 mutation database maintained by the International Agency for Research on Cancer (IARC), we investigated if the MCC, mainly developed for a Caucasian population, was also applicable in Asia. We identified several differences in Asian families compared with similar Caucasian cohorts, suggesting that identification and management of Li-Fraumeni syndrome in Asia do not completely mirror that of North America and Western Europe. Early gastric cancer (<40 years) may be considered a new addition to the MCC especially for Asian families.

Amyotrophic lateral sclerosis (ALS) is a prototypical neurodegenerative disease characterized by progressive degeneration of motor neurons to severely effect the functionality to control voluntary muscle movement. Most of the non-additive genetic aberrations responsible for ALS make its molecular classification very challenging along with limited sample size, curse of dimensionality, class imbalance and noise in the data. Deep learning methods have been successful in many other related areas but have low minority class accuracy and suffer from the lack of explainability when used directly with RNA expression features for ALS molecular classification. In this paper, we propose a deep-learning-based molecular ALS classification and interpretation framework. Our framework is based on training a convolution neural network (CNN) on images obtained from converting RNA expression values into pixels based on DeepInsight similarity technique. Then, we employed Shapley additive explanations (SHAP) to extract pixels with higher relevance to ALS classifications. These pixels were mapped back to the genes which made them up. This enabled us to classify ALS samples with high accuracy for a minority class along with identifying genes that might be playing an important role in ALS molecular classifications. Taken together with RNA expression images classified with CNN, our preliminary analysis of the genes identified by SHAP interpretation demonstrate the value of utilizing Machine Learning to perform molecular classification of ALS and uncover disease-associated genes.