https://doc.rero.ch/record/328505/files/zha_cnb.pdf

Computational network biology: Data, models, and applications

Somatic mutations in cancer cells can generate tumour-specific neoepitopes, which are recognized by autologous T cells in the host. As neoepitopes are not subject to central immune tolerance and are not expressed in healthy tissues, they are attractive targets for therapeutic cancer vaccines. Because the vast majority of cancer mutations are unique to the individual patient, harnessing the full potential of this rich source of targets requires individualized treatment approaches. Many computational algorithms and machine-learning tools have been developed to identify mutations in sequence data, to prioritize those that are more likely to be recognized by T cells and to design tailored vaccines for every patient. In this Review, we fill the gaps between the understanding of basic mechanisms of T cell recognition of neoantigens and the computational approaches for discovery of somatic mutations and neoantigen prediction for cancer immunotherapy. We present a new classification of neoantigens, distinguishing between guarding, restrained and ignored neoantigens, based on how they confer proficient antitumour immunity in a given clinical context. Such context-based differentiation will contribute to a framework that connects neoantigen biology to the clinical setting and medical peculiarities of cancer, and will enable future neoantigen-based therapies to provide greater clinical benefit. 

Identification of neoantigens for individualized therapeutic cancer vaccines

The presence of confounding effects (or biases) is one of the most critical challenges in using deep learning to advance discovery in medical imaging studies. Confounders affect the relationship between input data (e.g., brain MRIs) and output variables (e.g., diagnosis). Improper modeling of those relationships often results in spurious and biased associations. Traditional machine learning and statistical models minimize the impact of confounders by, for example, matching data sets, stratifying data, or residualizing imaging measurements. Alternative strategies are needed for state-of-the-art deep learning models that use end-to-end training to automatically extract informative features from large set of images. In this article, we introduce an end-to-end approach for deriving features invariant to confounding factors while accounting for intrinsic correlations between the confounder(s) and prediction outcome. The method does so by exploiting concepts from traditional statistical methods and recent fair machine learning schemes. We evaluate the method on predicting the diagnosis of HIV solely from Magnetic Resonance Images (MRIs), identifying morphological sex differences in adolescence from those of the National Consortium on Alcohol and Neurodevelopment in Adolescence (NCANDA), and determining the bone age from X-ray images of children. The results show that our method can accurately predict while reducing biases associated with confounders. The code is available at https://github.com/qingyuzhao/br-net .

/pdf/training-confounder-free-deep-learning-models-for-medical-5b0f0r6as6.pdf

Training confounder-free deep learning models for medical applications.

In the context of neuro-pathological disorders, neuroimaging has been widely accepted as a clinical tool for diagnosing patients with Alzheimer’s disease (AD) and mild cognitive impairment (MCI). T...

Automated MRI-Based Deep Learning Model for Detection of Alzheimer's Disease Process.

The repetitive nature and complexity of some medically relevant genes poses a challenge for their accurate analysis in a clinical setting. The Genome in a Bottle Consortium has provided variant benchmark sets, but these exclude nearly 400 medically relevant genes due to their repetitiveness or polymorphic complexity. Here, we characterize 273 of these 395 challenging autosomal genes using a haplotype-resolved whole-genome assembly. This curated benchmark reports over 17,000 single-nucleotide variations, 3,600 insertions and deletions and 200 structural variations each for human genome reference GRCh37 and GRCh38 across HG002. We show that false duplications in either GRCh37 or GRCh38 result in reference-specific, missed variants for short- and long-read technologies in medically relevant genes, including CBS, CRYAA and KCNE1. When masking these false duplications, variant recall can improve from 8% to 100%. Forming benchmarks from a haplotype-resolved whole-genome assembly may become a prototype for future benchmarks covering the whole genome. Variant detection in problematic genes is facilitated with a curated benchmark. 

Curated variation benchmarks for challenging medically relevant autosomal genes

Accurate detection of somatic mutations is still a challenge in cancer analysis. Here we present NeuSomatic, the first convolutional neural network approach for somatic mutation detection, which significantly outperforms previous methods on different sequencing platforms, sequencing strategies, and tumor purities. NeuSomatic summarizes sequence alignments into small matrices and incorporates more than a hundred features to capture mutation signals effectively. It can be used universally as a stand-alone somatic mutation detection method or with an ensemble of existing methods to achieve the highest accuracy.

/pdf/deep-convolutional-neural-networks-for-accurate-somatic-1w60abw20t.pdf

Deep convolutional neural networks for accurate somatic mutation detection.

Next generation sequencing provides an important opportunity for improved diagnosis in epilepsy. To date, the majority of diagnostic genetic testing is conducted in the paediatric arena, while the utility of such testing is less well understood in adults with epilepsy. We conducted whole exome sequencing (WES) and copy number variant analyses in an Irish cohort of 101 people with epilepsy and co-morbid intellectual disability to compare the diagnostic yield of genomic testing between adult and paediatric patients. Variant interpretation followed American College of Medical Genetics and Genomics (ACMG) guidelines. We demonstrate that WES, in combination with array-comparative genomic hybridisation, provides a diagnostic rate of 27% in unrelated adult epilepsy patients and 42% in unrelated paediatric patients. We observe a 2.7% rate of ACMG-defined incidental findings. Our findings indicate that WES has similar utility in both adult and paediatric cohorts and is appropriate for diagnostic testing in both epilepsy patient groups.

/pdf/a-comparison-of-genomic-diagnostics-in-adults-and-children-100qd0jjlz.pdf

Karl Podesta

Papers

Deep convolutional neural networks for accurate somatic mutation detection.

A comparison of genomic diagnostics in adults and children with epilepsy and comorbid intellectual disability