Somatic variants act as critical players during cancer occurrence and development. Thus, an accurate and robust method to identify them is the foundation of cutting-edge cancer genome research. However, due to low accessibility and high individual-/sample-specificity of the somatic variants in tumor samples, the detection is, to date, still crammed with challenges, particularly when lacking paired normal samples as control. To solve this burning issue, we developed a tumor-only somatic and germline variant identification method (TSomVar) using the random forest algorithm established on sample-specific variant datasets derived from genotype imputation, reads-mapping level annotation and functional annotation. We trained TSomVar by using genomic variant datasets of three major cancer types: colorectal cancer, hepatocellular carcinoma and skin cutaneous melanoma. Compared with existing tumor-only somatic variant identification tools, TSomVar shows excellent performances in somatic variant detection with higher accuracy and better capability of recalling for test datasets from colorectal cancer and skin cutaneous melanoma. In addition, TSomVar is equipped with the competence of accurately identifying germline variants in tumor samples. Taken together, TSomVar will undoubtedly facilitate and revolutionize somatic variant explorations in cancer research.

Genotype imputation is a statistical method for estimating missing genotypes from a denser haplotype reference panel. Existing methods usually performed well on common variants, but they may not be ideal for low-frequency and rare variants. Previous studies showed that the population similarity between study and reference panels is one of the key factors influencing the imputation accuracy. Here, we developed an imputation reference panel reconstruction method (RefRGim) using convolutional neural networks (CNNs), which can generate a study-specified reference panel for each input data based on the genetic similarity of individuals from current study and references. The CNNs were pretrained with single nucleotide polymorphism data from the 1000 Genomes Project. Our evaluations showed that genotype imputation with RefRGim can achieve higher accuracies than original reference panel, especially for low-frequency and rare variants. RefRGim will serve as an efficient reference panel reconstruction method for genotype imputation. RefRGim is freely available via GitHub: https://github.com/shishuo16/RefRGim.