A Highly Accurate Ensemble Classifier for the Molecular Diagnosis of ASD at Ages 1 to 4 Years

Importance: ASD diagnosis remains behavior-based and the median age of the first diagnosis remains unchanged at ~52 months, which is nearly 5 years after its first trimester origin. Long delays between ASD's prenatal onset and eventual diagnosis likely is a missed opportunity. However, accurate and clinically-translatable early-age diagnostic methods do not exist due to ASD genetic and clinical heterogeneity. There is a need for early-age diagnostic biomarkers of ASD that is robust against its heterogeneity. Objective: To develop a single blood-based molecular classifier that accurately diagnoses ASD at the age of first symptoms. Design, Setting, and Participants: N=264 ASD, typically developing (TD), and language delayed (LD) toddlers with their clinical, diagnostic, and leukocyte RNA data collected. Datasets included Discovery (n=175 ASD, TD subjects), Longitudinal (n=33 ASD, TD subjects), and Replication (n=89 ASD, TD, LD subjects). We developed an ensemble of ASD classifiers by testing 42,840 models composed of 3,570 feature selection sets and 12 classification methods. Models were trained on the Discovery dataset with 5-fold cross validation. Results were used to construct a Bayesian model averaging-based (BMA) ensemble classifier model that was tested in Discovery and Replication datasets. Data were collected from 2007 to 2012 and analyzed from August 2019 to April 2021. Main Outcomes and Measures: Primary outcomes were (1) comparisons of the performance of 42,840 classifier models in correctly identifying ASD vs TD and LD in Discovery and Replication datasets; and (2) performance of the ensemble model composed of 1,076 models and weighted by Bayesian model averaging technique. Results: Of 42,840 models trained in the Discovery dataset, 1,076 averaged AUC-ROC>0.8. These 1,076 models used 191 different feature routes and 2,764 gene features. Using weighted BMA of these features and routes, an ensemble classifier model was constructed which demonstrated excellent performance in Discovery and Replication datasets with ASD classification AUC-ROC scores of 84% to 88%. ASD classification accuracy was comparable against LD and TD subjects and in the Longitudinal dataset. ASD toddlers with ensemble scores above and below the ASD ensemble mean had similar diagnostic and psychometric scores, but those below the ASD ensemble mean had more prenatal risk events than TD toddlers. Ensemble features include genes with immune/inflammation, response to cytokines, transcriptional regulation, mitotic cell cycle, and PI3K-AKT, RAS, and Wnt signaling pathways. Conclusions and Relevance: An ensemble ASD molecular classifier has high and replicable accuracy across the spectrum of ASD clinical characteristics and across toddlers aged 1 to 4 years, which has potential for clinical translation.

Making External Validation Valid for Molecular Classifier Development

PURPOSE Accurate assessment of a molecular classifier that guides patient care is of paramount importance in precision oncology. Recent years have seen an increasing use of external validation for such assessment. However, little is known about how it is affected by ubiquitous unwanted variations in test data because of disparate experimental handling and by the use of data normalization for alleviating such variations. METHODS In this paper, we studied these issues using two microarray data sets for the same set of tumor samples and additional data simulated by resampling under various levels of signal-to-noise ratio and different designs for array-to-sample allocation. RESULTS We showed that (1) unwanted variations can lead to biased classifier assessment and (2) data normalization mitigates the bias to varying extents depending on the specific method used. In particular, frozen normalization methods for test data outperform their conventional forms in terms of both reducing the bias in accuracy estimation and increasing robustness to handling effects. We make available our benchmarking tool as an R package on GitHub for performing such evaluation on additional methods for normalization and classification. CONCLUSION Our findings thus highlight the importance of proper test-data normalization for valid assessment by external validation and call for caution on the choice of normalization method for molecular classifier development.

O08 Developing a DNA methylation signature for predicting rheumatoid arthritis using a machine learning pipeline

Background/Aims Early diagnosis and intervention improves outcomes of immune mediated rheumatic and musculoskeletal diseases (RMDs) but may be hampered by diagnostic uncertainty. The extent to which rationally selected molecular parameters add value to clinical characteristics for diagnostic prediction in undifferentiated disease states warrants investigation. B lymphocytes play an increasingly recognised role in rheumatoid arthritis (RA) pathogenesis, and cell-specific methylation patterns link environmental exposures to genetic risk. We derived and tested the practical utility of a B lymphocyte-derived DNA methylation signature for predicting RA in an early arthritis clinic cohort. Methods CD19+ B cell and peripheral blood mononuclear cell (PBMC) whole genome DNA methylation array data were available, respectively, from 109 inflammatory arthritis patients naïve to immunomodulatory drugs (Newcastle, UK; 38% confirmed to have a diagnosis of RA within 1 year) and 50 untreated undifferentiated arthritis (UA) patients (Leiden, The Netherlands; 68% classifiable RA within 1 year by 1987 ACR criteria versus alternate diagnoses). A bespoke machine learning pipeline employed a sequential model-based optimisation (SMBO) procedure for selecting, tuning and applying methods amongst ten feature-selection, six data-sampling and two classification algorithms in the Newcastle “training cohort.” The predictive performance of the resultant optimised molecular classifier was assessed in the independent Leiden “test cohort” alongside a previously described clinical prediction rule, using comparative area under receiver operating characteristic (AUROC) curves. A modification to the clinical prediction rule that incorporated a single parameter to reflect molecular classification was also assessed. The pipeline was implemented using the R machine learning package mlr. Results Using the SMBO approach, 27 CpGs maximally discriminatory for RA were selected from B lymphocyte DNA methylome training data, and a molecular classifier was derived using the random forest algorithm. Applied to the independent PBMC methylome in UA patients, the classifier and the validated Leiden prediction rule performed similarly in predicting RA (AUROC [95% CI] = 0.8 [0.66-0.94] versus 0.78 [0.64-0.92]). Interestingly, incorporating a molecular risk score based on the 27-CpG signature into the validated Leiden clinical prediction rule significantly improved its performance (AUROC [95% CI] = 0.89 [0.79-0.98] versus 0.78 [0.64-0.92]; p = 0.048). When applied to the sub-cohort of 25 patients in the Leiden cohort who were negative for anti-citrullinated peptide autoantibodies (ACPA), enhanced performance of the modified over the un-modified clinical prediction rule was maintained (AUROC [95% CI] = 0.82 [0.65-1] versus 0.70 [0.45-0.95], respectively), although the difference did not reach statistical significance in this smaller cohort. Conclusion We provide a proof of principle for the application of a B lymphocyte-derived epigenetic signature to enhance prediction of RA in UA patients using stored PBMCs. Further refinement of our pipeline represents a plausible means to expedite the diagnosis in undifferentiated RMDs and could offer pathophysiological insight. Disclosure N. Naamane: None. E. Niemantsverdriet: None. N. Thalayasingam: None. N. Nair: None. A.D. Clark: None. K. Murray: None. B. Hargreaves: None. L.N. Reynard: None. S. Eyre: None. A. Barton: None. A.H.M. van der Helm-van Mil: None. A.G. Pratt: None.

Preoperative detection of papillary and medullary thyroid cancer metastases in the lymph nodes of the neck lateral cellular tissue using a molecular classifier

Introduction. The main method of preoperative diagnosis of thyroid tumors and the identification of possible metastasis is a cytological examination of smears obtained by fine-needle aspiration biopsy. However, the cytological material of the lymph nodes may not be adequate, and the detection of metastases faces a number of difficulties. In our recent study, we described a variant of the molecular classifier that allows the detection and typing of malignant thyroid tumors by analyzing several molecular markers in cytological preparations.The study objective was to assess the applicability of the developed method for the preoperative detection of metastases of papillary and medullary thyroid cancer in the lymph nodes of the neck lateral cellular tissue.Materials and methods. A total of 86 cytological samples were used, obtained from individual lymph nodes of 62 patients who had a diagnosis – thyroid cancer. Samples were analyzed by real-time polymerase chain reaction regarding the preselected set of molecular markers: the BRAF V600E mutation, the normalized concentration of HMGA2, FN1 and SERPINA1 mRNA, 5 miRNAs and the mitochondrial/nuclear DNA ratio. The decision tree-based classifier was used to discriminate between benign and malignant samples.Results. The previously described classifier, based on the analysis of the BRAF V600E mutation, the content of HMGA2 mRNA, 3 miRNAs and the mitochondrial/nuclear DNA ratio, revealed metastases of thyroid cancer with good specificity (98 %) but less sensitivity (83 %). Therefore, a new classifier was built, including three markers – HMGA2 and FN1 mRNA, and miRNA-375, which, with regard to the detection of metastases, showed good sensitivity – 93 % with a slight decrease in specificity (up to 96 %).Conclusion. Thus, we demonstrated the possibility of preoperative detection of thyroid cancer metastases in the lymph nodes of the neck lateral cellular tissue by analyzing several molecular markers in cytological material.

Real-world, Prospective, and Multicenter Validation of a microRNA-based Thyroid Molecular Classifier

ABSTRACTBackgroundThe diagnosis of cancer in thyroid nodules with indeterminate cytology (Bethesda III/IV) is challenging as fine-needle aspiration (FNA), the gold standard method, has limitations, and these cases usually require diagnostic surgery. As approximately 77% of these nodules are not malignant, a diagnostic test accurately identifying benign thyroid nodules can reduce surgery rates. We have previously reported the development and validation of a microRNA-based thyroid molecular classifier for precision endocrinology (mir-THYpe) with high sensitivity and specificity, which could be performed directly from readily available cytological smear slides without the need for a new dedicated FNA. We sought to evaluate whether the use of this test in real-world clinical routine can reduce the rates of surgeries for Bethesda III/IV thyroid nodules and analyze the test performance.MethodsWe designed a real-world, prospective, multicenter cohort study. Molecular tests were performed in a real-world clinical routine with samples (FNA smear slides) prepared at 128 cytopathology laboratories. Patients were followed-up from March 2018 until surgery or until March 2020 (for those patients not recommended for surgery). The final diagnosis of thyroid tissue samples was retrieved from postsurgical anatomopathological reports.ResultsAfter applying the exclusion criteria, 435 patients (440 nodules) classified as Bethesda III/IV were followed-up. The rate of avoided surgeries was 52.5% for all surgeries and 74.6% for “potentially unnecessary” surgeries. After the statistical treatment of non-resected test-negative samples, the test achieved 89.3% sensitivity (95% CI 82–94.3), 81.65% specificity (95% CI 76.6–86), 66.2% positive predictive value (95% CI 60.3–71.7), and 95% negative predictive value (95% CI 91.7–97) at 28.7% (95% CI 24.3–33.5) cancer prevalence. The test influenced 92.3% of clinical decisions.ConclusionsThe reported data demonstrate that the use of the microRNA-based classifier in the real-world can reduce the rate of thyroid surgery with robust performance and significantly influence clinical decision-making.

KRAS-associated microRNAs in colorectal cancer

Colorectal cancer (CRC) is one of the leading causes of cancerrelated death worldwide. Despite progress in treatment of cancers, CRC with KRAS mutations are resistant towards anti-EGFR treatment. MicroRNAs have been discovered in an exponential manner within the last few years and have been known to exert either an onco-miRNA or tumor suppressive effect. Here, the various roles of microRNAs involved in the initiation and progression of KRAS-regulated CRC are summarized. A thorough understanding of the roles and functions of the plethora of microRNAs associated with KRAS in CRC will grant insights into the provision of other potential therapeutic targets as well as treatment. MicroRNAs may also serve as potential molecular classifier or early detection biomarkers for future treatment and diagnosis of CRC.