Search

Background It remains an important challenge to predict the functional consequences or clinical impacts of genetic variants in human diseases, such as cancer. An increasing number of genetic variants in cancer have been discovered and documented in public databases such as COSMIC, but the vast majority of them have no functional or clinical annotations. Some databases, such as CiVIC are available with manual annotation of functional mutations, but the size of the database is small due to the use of human annotation. Since the unlabeled data (millions of variants) typically outnumber labeled data (thousands of variants), computational tools that take advantage of unlabeled data may improve prediction accuracy. Result To leverage unlabeled data to predict functional importance of genetic variants, we introduced a method using semi-supervised generative adversarial networks (SGAN), incorporating features from both labeled and unlabeled data. Our SGAN model incorporated features from clinical guidelines and predictive scores from other computational tools. We also performed comparative analysis to study factors that influence prediction accuracy, such as using different algorithms, types of features, and training sample size, to provide more insights into variant prioritization. We found that SGAN can achieve competitive performances with small labeled training samples by incorporating unlabeled samples, which is a unique advantage compared to traditional machine learning methods. We also found that manually curated samples can achieve a more stable predictive performance than publicly available datasets. Conclusions By incorporating much larger samples of unlabeled data, the SGAN method can improve the ability to detect novel oncogenic variants, compared to other machine-learning algorithms that use only labeled datasets. SGAN can be potentially used to predict the pathogenicity of more complex variants such as structural variants or non-coding variants, with the availability of more training samples and informative features.

Widespread in public databases, foreign contaminant sequences pose a substantial obstacle in genomic analyses. Such contamination in viral genome databases is also notorious but more complicated and often causes questionable results in various applications, particularly in virome-based virus detection. Here, we conducted comprehensive screening and identification of the foreign sequences hidden in the largest eukaryotic viral genome collections of GenBank and UniProt using a scrutiny pipeline, which enables us to rigorously detect those problematic viral sequences (PVSs) with origins in hosts, vectors, and laboratory components. As a result, a total of 766 nucleotide PVSs and 276 amino acid PVSs with lengths up to 6,605 bp were determined, which were widely distributed in 39 families with many involving highly public health-concerning viruses, such as hepatitis C virus, Crimean-Congo hemorrhagic fever virus, and filovirus. The majority of these PVSs are genomic fragments of hosts including humans and bacteria. However, they cannot simply be regarded as foreign contaminants, since parts of them are results of natural occurrence or artificial engineering of viruses. Nevertheless, they severely disturb such sequence-based analyses as genome annotation, taxonomic assignment, and virome profiling. Therefore, we provide a clean version of the eukaryotic viral reference data set by the removal of these PVSs, which allows more accurate virome analysis with less time consumed than with other comprehensive databases.