A Novel System for Functional Determination of Variants of Uncertain Significance using Deep Convolutional Neural Networks

Immunofluorescence analyses of respiratory epithelial cells aid the diagnosis of nephronophthisis

BACKGROUND

Nephronophthisis (NPH) comprises a heterogeneous group of inherited renal ciliopathies clinically characterized by progressive kidney failure. So far, definite diagnosis is based on molecular testing only. Here, we studied the feasibility of NPHP1 and NPHP4 immunostaining of nasal epithelial cells to secure and accelerate the diagnosis of NPH.

METHODS

Samples of 86 individuals with genetically determined renal ciliopathies were analyzed for NPHP1 localization using immunofluorescence microscopy (IF). A sub-cohort of 35 individuals was also analyzed for NPHP4 localization. Western blotting was performed to confirm IF results.

RESULTS

NPHP1 and NPHP4 were both absent in all individuals with disease-causing NPHP1 variants including one with a homozygous missense variant (c.1027G > A; p.Gly343Arg) formerly classified as a "variant of unknown significance." In individuals with an NPHP4 genotype, we observed a complete absence of NPHP4 while NPHP1 was severely reduced. IF results were confirmed by immunoblotting. Variants in other genes related to renal ciliopathies did not show any impact on NPHP1/NPHP4 expression. Aberrant immunostaining in two genetically unsolved individuals gave rise for a further genetic workup resulting in a genetic diagnosis for both with disease-causing variants in NPHP1 and NPHP4, respectively.

CONCLUSIONS

IF of patient-derived respiratory epithelial cells may help to secure and accelerate the diagnosis of nephronophthisis-both by verifying inconclusive genetic results and by stratifying genetic diagnostic approaches. Furthermore, we provide in vivo evidence for the interaction of NPHP1 and NPHP4 in a functional module.

Actionability classification of variants of unknown significance correlates with functional effect

Genomically-informed therapy requires consideration of the functional impact of genomic alterations on protein expression and/or function. However, a substantial number of variants are of unknown significance (VUS). The MD Anderson Precision Oncology Decision Support (PODS) team developed an actionability classification scheme that categorizes VUS as either "Unknown" or "Potentially" actionable based on their location within functional domains and/or proximity to known oncogenic variants. We then compared PODS VUS actionability classification with results from a functional genomics platform consisting of mutant generation and cell viability assays. 106 (24%) of 438 VUS in 20 actionable genes were classified as oncogenic in functional assays. Variants categorized by PODS as Potentially actionable (N = 204) were more likely to be oncogenic than those categorized as Unknown (N = 230) (37% vs 13%, p = 4.08e-09). Our results demonstrate that rule-based actionability classification of VUS can identify patients more likely to have actionable variants for consideration with genomically-matched therapy.

Analysis of Novel Variants Associated with Three Human Ovarian Cancer Cell Lines

Background:

Identification of mutations is of great significance in cancer research, as it can contribute to development of therapeutic strategies and prevention of cancer formation. Ovarian cancer is one of the leading cancer-related causes of death in Taiwan. Accumulation of genetic mutations can lead to cancer.

Objective:

We utilized whole-exome sequencing to explore cancer-associated missense variants in three human ovarian cancer cell lines derived from Taiwanese patients.

Methods:

We use (i) cell line whole-exome sequencing data, (ii) 188 patients’ whole-exome sequencing data, and (iii) use of in vitro experiments to verify predicted variant results. We establish an effective analysis workflow for discovery of novel ovarian cancer variants, comprising three steps: (i) use of public databases and in-house hospital data to select novel variants (ii) investigation of protein structural stability caused by genetic mutations, and (iii) use of in vitro experiments to verify predictions.

Results:

Our study enumerated 296 novel variants by imposing specific criteria and using sophisticated bioinformatics tools for further analysis. Eleven and 54 missense novel variants associated with cancerous and non-cancerous genes, respectively, were identified. We show that 13 missense mutations affect the stability of protein 3D structure, while 11 disease-causing novel variants were confirmed by PCR sequencing. Among these, ten variants were predicted to be pathogenic, while the pathogenicity of one was uncertain.

Conclusion:

We confirm that novel variant genes play a crucial role in ovarian cancer patients, with 11 novel variants that may promote progression and development of ovarian cancer.

Artificial Intelligence and Mapping a New Direction in Laboratory Medicine: A Review

BACKGROUND

Modern artificial intelligence (AI) and machine learning (ML) methods are now capable of completing tasks with performance characteristics that are comparable to those of expert human operators. As a result, many areas throughout healthcare are incorporating these technologies, including in vitro diagnostics and, more broadly, laboratory medicine. However, there are limited literature reviews of the landscape, likely future, and challenges of the application of AI/ML in laboratory medicine.

CONTENT

In this review, we begin with a brief introduction to AI and its subfield of ML. The ensuing sections describe ML systems that are currently in clinical laboratory practice or are being proposed for such use in recent literature, ML systems that use laboratory data outside the clinical laboratory, challenges to the adoption of ML, and future opportunities for ML in laboratory medicine.

SUMMARY

AI and ML have and will continue to influence the practice and scope of laboratory medicine dramatically. This has been made possible by advancements in modern computing and the widespread digitization of health information. These technologies are being rapidly developed and described, but in comparison, their implementation thus far has been modest. To spur the implementation of reliable and sophisticated ML-based technologies, we need to establish best practices further and improve our information system and communication infrastructure. The participation of the clinical laboratory community is essential to ensure that laboratory data are sufficiently available and incorporated conscientiously into robust, safe, and clinically effective ML-supported clinical diagnostics.

Functional measurement of mitogen-activated protein kinase pathway activation predicts responsiveness of RAS-mutant cancers to MEK inhibitors

BACKGROUND

RAS variant-related functional impact on the mitogen-activated protein kinase (MAPK) pathway, and correlation between MAPK activation and MAPK/ERK kinase (MEK) inhibitor responsiveness, is not established.

PATIENTS AND METHODS

Of 1,693 tumours sequenced, 576 harboured a RAS alteration; 62 patients received an MEK inhibitor (MEKi) and had RAS mutations that were functionally characterised. We report that RAS mutants have variable levels of MAPK activity, as measured by a functional cell-based assay that quantified MAPK pathway activation after transfection with a variety of RAS mutations.

RESULTS

Patients with tumours harbouring RAS alterations with high versus low MAPK activity who were treated with an MEKi showed significantly longer median progression-free survival (PFS) (5.0 vs. 2.3 months; p = 0.0034) and overall survival (20.0 vs. 5.0 months; p = 0.0146) and a trend towards higher rates of clinical benefit (stable disease ≥6 months or partial/complete remission) (38% versus 15%; p = 0.095) (p-values as per univariate analysis). PFS remained statistically significant after the multivariate analysis (p = 0.003).

CONCLUSIONS

These results support a correlation between RAS-mutant cancers with greater MAPK signalling and PFS after MEKi treatment.