Model performance and interpretability of semi-supervised generative adversarial networks to predict oncogenic variants with unlabeled data.

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.

CancerVar: An artificial intelligence-empowered platform for clinical interpretation of somatic mutations in cancer.

Several knowledgebases are manually curated to support clinical interpretations of thousands of hotspot somatic mutations in cancer. However, discrepancies or even conflicting interpretations are observed among these databases. Furthermore, many previously undocumented mutations may have clinical or functional impacts on cancer but are not systematically interpreted by existing knowledgebases. To address these challenges, we developed CancerVar to facilitate automated and standardized interpretations for 13 million somatic mutations based on the AMP/ASCO/CAP 2017 guidelines. We further introduced a deep learning framework to predict oncogenicity for these variants using both functional and clinical features. CancerVar achieved satisfactory performance when compared to several independent knowledgebases and, using clinically curated datasets, demonstrated practical utility in classifying somatic variants. In summary, by integrating clinical guidelines with a deep learning framework, CancerVar facilitates clinical interpretation of somatic variants, reduces manual work, improves consistency in variant classification, and promotes implementation of the guidelines.

Antibacterial Cyclic Tripeptides from Antarctica-Sponge-Derived Fungus Aspergillus insulicola HDN151418.

Three new aspochracin-type cyclic tripeptides, sclerotiotides M-O (1-3), together with three known analogues, sclerotiotide L (4), sclerotiotide F (5), and sclerotiotide B (6), were obtained from the ethyl acetate extract of the fungus Aspergillus insulicola HDN151418, which was isolated from an unidentified Antarctica sponge. Spectroscopic and chemical approaches were used to elucidate their structures. The absolute configuration of the side chain in compound 4 was elucidated for the first time. Compounds 1 and 2 showed broad antimicrobial activity against a panel of pathogenic strains, including Bacillus cereus, Proteus species, Mycobacterium phlei, Bacillus subtilis, Vibrio parahemolyticus, Edwardsiella tarda, MRCNS, and MRSA, with MIC values ranging from 1.56 to 25.0 µM.