Machine learning methodology using a masked neural network for robust genetic risk score calculation from noisy and missing data.

purposeGenetic risk scores (GRSs) are summaries of genetic data that can improve prediction of disease risk and progression. GRSs are increasing available but rely on high-quality input data to produce good output results; with noisy or missing inputs the GRS may be inaccurate. We aimed to develop a method to produce a robust estimate of the GRS when input data are missing, noisy or both. APPROACH: We developed a neural network approach, named masked-multi-layer perceptron (MLP), for robust GRS calculation trained on a set of GRS scores calculated on clean data. The masked-MLP includes additional input data and has noise inserted during training, both which make the model more robust.

resultsA GRS for type 1 diabetes (T1D) calculated on input data with 10% of the data corrupted had a Spearman rank correlation to the clean GRS of 0.669 (0.665-0.674) while the equivalent for the masked-MLP was 0.951 (0.950-0.952). For the same data, the area under the receiver operating characteristic curve for separation of T1D from population samples fell from 0.919 (0.904-0.932) to 0.808 (0.787-0.827) for the GRS while the masked-MLP fell to 0.910 (0.895-0.924).

conclusionsThe masked-MLP was more robust to noise when calculating a GRS than using standard approaches. Our approach has the potential to enable GRS calculations which are more robust to noise.