Reducing Sanger confirmation testing through false positive prediction algorithms

Purpose Clinical genome sequencing (cGS) followed by orthogonal confirmatory testing is standard practice. While orthogonal testing significantly improves specificity, it also results in increased turnaround time and cost of testing. The purpose of this study is to evaluate machine learning models trained to identify false positive variants in cGS data to reduce the need for orthogonal testing. Methods We sequenced five reference human genome samples characterized by the Genome in a Bottle Consortium (GIAB) and compared the results with an established set of variants for each genome referred to as a truth set. We then trained machine learning models to identify variants that were labeled as false positives. Results After training, the models identified 99.5% of the false positive heterozygous single-nucleotide variants (SNVs) and heterozygous insertions/deletions variants (indels) while reducing confirmatory testing of nonactionable, nonprimary SNVs by 85% and indels by 75%. Employing the algorithm in clinical practice reduced overall orthogonal testing using dideoxynucleotide (Sanger) sequencing by 71%. Conclusion Our results indicate that a low false positive call rate can be maintained while significantly reducing the need for confirmatory testing. The framework that generated our models and results is publicly available at https://github.com/HudsonAlpha/STEVE.

Serum S100 Protein Is a Reliable Predictor of Brain Injury After Out-of-Hospital Cardiac Arrest: A Cohort Study

Purpose: To evaluate serum S100 protein at hospital admission and after 48 h in early neuroprognostication of comatose survivors of out-of-hospital cardiac arrest (OHCA).Methods: The study included 48 consecutive patients after OHCA, who survived for at least 72 h after the event. The patients were divided based on their best cerebral performance category (CPC) achieved over a 30 day follow-up period: favorable neurological outcome (CPC 1–2) vs. unfavorable neurological outcome (CPC 3–4). Predictors of an unfavorable neurological outcome were identified by multivariable regression analysis. Analysis of the receiver operating characteristic curve (ROC) was used to determine the cut-off value for S100, having a 0% false-positive prediction rate.Results: Of the 48 patients, 30 (63%) had a favorable and 18 (38%) had an unfavorable neurological outcome. Eleven patients (23%) died over the 30 day follow-up. Increased S100 levels at 48 h after OHCA, but not the baseline S100 levels, were independently associated with unfavorable neurological outcome, with an area under the ROC curve of 0.85 (confidence interval 0.74–0.96). A 48 h S100 value ≥0.37 μg/L had a specificity of 100% and sensitivity of 39% in predicting an unfavorable 30 day neurological outcome.Conclusion: This study showed that S100 values assessed 48 h after an OHCA could independently predict an unfavorable neurological outcome at 30 days.

Reducing Sanger Confirmation Testing through False Positive Prediction Algorithms

PurposeClinical genome sequencing (cGS) followed by orthogonal confirmatory testing is standard practice. While orthogonal testing significantly improves specificity it also results in increased turn-around-time and cost of testing. The purpose of this study is to evaluate machine learning models trained to identify false positive variants in cGS data to reduce the need for orthogonal testing.MethodsWe sequenced five reference human genome samples characterized by the Genome in a Bottle Consortium (GIAB) and compared the results to an established set of variants for each genome referred to as a ‘truth-set’. We then trained machine learning models to identify variants that were labeled as false positives.ResultsAfter training, the models identified 99.5% of the false positive heterozygous single nucleotide variants (SNVs) and heterozygous insertions/deletions variants (indels) while reducing confirmatory testing of true positive SNVs to 1.67% and indels to 20.29%. Employing the algorithm in clinical practice reduced orthogonal testing using dideoxynucleotide (Sanger) sequencing by 78.22%.ConclusionOur results indicate that a low false positive call rate can be maintained while significantly reducing the need for confirmatory testing. The framework that generated our models and results is publicly available at https://github.com/HudsonAlpha/STEVE.

Discovering Protein Drug Targets Using Knowledge Graph Embeddings

Motivation Computational approaches for predicting drug-target interactions (DTIs) can provide valuable insights into the drug mechanism of action. DTI predictions can help to quickly identify new promising (on-target) or unintended (off-target) effects of drugs. However, existing models face several challenges. Many can only process a limited number of drugs and/or have poor proteome coverage. The current approaches also often suffer from high false positive prediction rates. Results We propose a novel computational approach for predicting drug target proteins. The approach is based on formulating the problem as a link prediction in knowledge graphs (robust, machine-readable representations of networked knowledge). We use biomedical knowledge bases to create a knowledge graph of entities connected to both drugs and their potential targets. We propose a specific knowledge graph embedding model, TriModel, to learn vector representaions (i.e. embeddings) for all drugs and targets in the created knowledge graph. These representations are consequently used to infer candidate drug target interactions based on their scores computed by the trained TriModel model. We have experimentally evaluated our method using computer simulations and compared it to five existing models. This has shown that our approach outperforms all previous ones in terms of both area under ROC and precision-recall curves in standard benchmark tests. Availability The data, predictions, and models are available at: drugtargets.insight-centre.org

Use of CA-125 to Define Progression of Ovarian Cancer in Patients With Persistently Elevated Levels

PURPOSE: To determine an accurate definition for progression of ovarian cancer in patients with a persistently elevated serum CA-125. PATIENTS AND METHODS: A retrospective analysis was performed on 300 patients with epithelial ovarian carcinoma with at least one measurement of CA-125. The date of progression according to clinical or radiologic criteria was ascertained in the 88 patients with persistently elevated CA-125 levels (> 23 U/mL). This was compared with the date of progression according to CA-125, defined as the date on which the CA-125 level first increased to ≥ twice its nadir level, confirmed by a second sample also ≥ twice the nadir. RESULTS: Eighty of the 88 patients had evidence of progression by both standard and CA-125 criteria, giving a sensitivity of 94%. In six of these patients, no sample was taken to confirm CA-125 doubling. In 13 patients, CA-125 doubling occurred after the date of clinical progression. Only one patient had a false-positive prediction of progression according to CA-125; the patient died as a result of a myocardial infarct before evidence of clinical progression. CONCLUSION: In patients whose CA-125 level decreases to normal after chemotherapy, a doubling from the upper limit of normal has been shown to predict progression. In those with persistently elevated levels, doubling of CA-125 from its nadir level has now been shown to accurately define progression. If confirmed, these CA-125 criteria should be used as additional end points in clinical trials.