Research supports the potential use of microbiome as a predictor of some diseases. Motivated by the findings that microbiome data is complex in nature, and there is an inherent correlation due to hierarchical taxonomy of microbial Operational Taxonomic Units (OTUs), we propose a novel machine learning method incorporating a stratified approach to group OTUs into phylum clusters. Convolutional Neural Networks (CNNs) were used to train within each of the clusters individually. Further, through an ensemble learning approach, features obtained from each cluster were then concatenated to improve prediction accuracy. Our two-step approach comprising stratification prior to combining multiple CNNs, aided in capturing the relationships between OTUs sharing a phylum efficiently, as compared to using a single CNN ignoring OTU correlations. We used simulated datasets containing 168 OTUs in 200 cases and 200 controls for model testing. Thirty-two OTUs, potentially associated with risk of disease were randomly selected and interactions between three OTUs were used to introduce non-linearity. We also implemented this novel method in two human microbiome studies: (i) Cirrhosis with 118 cases, 114 controls; (ii) type 2 diabetes (T2D) with 170 cases, 174 controls; to demonstrate the model’s effectiveness. Extensive experimentation and comparison against conventional machine learning techniques yielded encouraging results. We obtained mean AUC values of 0.88, 0.92, 0.75, showing a consistent increment (5%, 3%, 7%) in simulations, Cirrhosis and T2D data, respectively, against the next best performing method, Random Forest. https://github.com/divya031090/TaxoNN_OTU. Supplementary data are available at Bioinformatics online.

People with Li–Fraumeni syndrome (LFS) harbor a germline pathogenic variant in the TP53 tumor suppressor gene, face a near 100% lifetime risk of cancer, and routinely undergo intensive surveillance protocols. Liquid biopsy has become an attractive tool for a range of clinical applications, including early cancer detection. Here, we provide a proof-of-principle for a multimodal liquid biopsy assay that integrates a targeted gene panel, shallow whole-genome, and cell-free methylated DNA immunoprecipitation sequencing for the early detection of cancer in a longitudinal cohort of 89 LFS patients. Multimodal analysis increased our detection rate in patients with an active cancer diagnosis over uni-modal analysis and was able to detect cancer-associated signal(s) in carriers prior to diagnosis with conventional screening (positive predictive value = 67.6%, negative predictive value = 96.5%). Although adoption of liquid biopsy into current surveillance will require further clinical validation, this study provides a framework for individuals with LFS. Significance: By utilizing an integrated cell-free DNA approach, liquid biopsy shows earlier detection of cancer in patients with LFS compared with current clinical surveillance methods such as imaging. Liquid biopsy provides improved accessibility and sensitivity, complementing current clinical surveillance methods to provide better care for these patients. See related commentary by Latham et al., p. 23. This article is featured in Selected Articles from This Issue, p. 5

BACKGROUND AND PURPOSE: Addressing the performance of an imaging-based parameter compared to a “gold standard” pathologic measurement is essential to achieve accurate clinical T-classification. Our aim was to determine the radiologic-pathologic tumor thickness correlation and its prognostic value in oral squamous cell carcinoma. MATERIALS AND METHODS: All pathologic T1–T3 (seventh edition of the Cancer Staging Manual of the American Joint Committee on Cancer) oral squamous cell carcinomas diagnosed between 2010 and 2015 were reviewed. Radiologic tumor thickness was measured on preoperative CT or MR imaging blinded to pathology. The radiologic-pathologic tumor thickness correlation was calculated. The impact of the imaging-to-surgery time interval and imaging technique on the correlation was explored. Intra-/interrater reliability on radiologic tumor thickness was calculated. The correlation of radiologic-versus-pathologic tumor thickness and its performance as the seventh edition T-category modifier was evaluated. Multivariable analysis assessed the prognostic value of the radiologic tumor thickness for overall survival adjusted for age, seventh edition T-category, and performance status. RESULTS: For 354 consecutive patients, the radiologic-pathologic tumor thickness correlation was similar for the image-to-surgery interval of ≤4.0 weeks (ρ = 0.76) versus 4–8 weeks (ρ = 0.80) but lower in those with more than an 8-week interval (ρ = 0.62). CT and MR imaging had similar correlations (0.76 and 0.80). Intrarater and interrater reliability was excellent (0.88 and 0.84). Excluding 19 cases with an imaging-to-surgery interval of >8 weeks, 335 patients were eligible for further analysis. The radiologic-pathologic tumor thickness correlation was 0.78. The accuracy for upstaging the T-classification based on radiologic tumor thickness was 83% for pathologic T1 and 74% for pathologic T2 tumors. Multivariable analysis confirmed the prognostic value of radiologic tumor thickness (hazard ratio = 1.5, P = .02) for overall survival. CONCLUSIONS: This study demonstrates a good radiologic-pathologic tumor thickness correlation. Intrarater and interrater reliability for radiologic tumor thickness was excellent. Radiologically thicker tumor was predictive of inferior survival.