A non-coding hexanucleotide repeat expansion (HRE) in C9orf72 is a common cause of amyotrophic lateral sclerosis (ALS) and frontotemporal dementia (FTD) acting through a loss of function mechanism due to haploinsufficiency of C9orf72 or a gain of function mediated by aggregates of bidirectionally transcribed HRE-RNAs translated into di-peptide repeat (DPR) proteins. To fully understand regulation of C9orf72 expression we surveyed the C9orf72 locus using Cap Analysis of Gene Expression sequence data (CAGEseq). We observed C9orf72 was generally lowly expressed with the exception of a subset of myeloid cells, particularly CD14+ monocytes that showed up to seven fold higher expression as compared to central nervous system (CNS) and other tissues. The expression profile at the C9orf72 locus showed a complex architecture with differential expression of the transcription start sites (TSSs) for the annotated C9orf72 transcripts between myeloid and CNS tissues suggesting cell and/or tissue specific functions. We further detected novel TSSs in both the sense and antisense strand at the C9orf72 locus and confirmed their existence in brain tissues and CD14+ monocytes. Interestingly, our experiments showed a consistent decrease of C9orf72 coding transcripts not only in brain tissue and monocytes from C9orf72-HRE patients, but also in brains from MAPT and GRN mutation carriers together with an increase in antisense transcripts suggesting these could play a role in regulation of C9orf72. We found that the non-HRE related expression changes cannot be explained by promoter methylation but by the presence of the C9orf72-HRE risk haplotype and unknown functional interactions between C9orf72, MAPT and GRN.

Recent technological advances and international efforts, such as The Cancer Genome Atlas (TCGA), have made available several pan-cancer datasets encompassing multiple omics layers with detailed clinical information in large collection of samples. The need has thus arisen for the development of computational methods aimed at improving cancer subtyping and biomarker identification from multi-modal data. Here we apply the Integrative Network Fusion (INF) pipeline, which combines multiple omics layers exploiting Similarity Network Fusion (SNF) within a machine learning predictive framework. INF includes a feature ranking scheme (rSNF) on SNF-integrated features, used by a classifier over juxtaposed multi-omics features (juXT). In particular, we show instances of INF implementing Random Forest (RF) and linear Support Vector Machine (LSVM) as the classifier, and two baseline RF and LSVM models are also trained on juXT. A compact RF model, called rSNFi, trained on the intersection of top-ranked biomarkers from the two approaches juXT and rSNF is finally derived. All the classifiers are run in a 10x5-fold cross-validation schema to warrant reproducibility, following the guidelines for an unbiased Data Analysis Plan by the US FDA-led initiatives MAQC/SEQC. INF is demonstrated on four classification tasks on three multi-modal TCGA oncogenomics datasets. Gene expression, protein expression and copy number variants are used to predict estrogen receptor status (BRCA-ER, N = 381) and breast invasive carcinoma subtypes (BRCA-subtypes, N = 305), while gene expression, miRNA expression and methylation data is used as predictor layers for acute myeloid leukemia and renal clear cell carcinoma survival (AML-OS, N = 157; KIRC-OS, N = 181). In test, INF achieved similar Matthews Correlation Coefficient (MCC) values and 97% to 83% smaller feature sizes (FS), compared with juXT for BRCA-ER (MCC: 0.83 vs. 0.80; FS: 56 vs. 1801) and BRCA-subtypes (0.84 vs. 0.80; 302 vs. 1801), improving KIRC-OS performance (0.38 vs. 0.31; 111 vs. 2319). INF predictions are generally more accurate in test than one-dimensional omics models, with smaller signatures too, where transcriptomics consistently play the leading role. Overall, the INF framework effectively integrates multiple data levels in oncogenomics classification tasks, improving over the performance of single layers alone and naive juxtaposition, and provides compact signature sizes¹.

Artificial Intelligence is exponentially increasing its impact on healthcare. As deep learning is mastering computer vision tasks, its application to digital pathology is natural, with the promise of aiding in routine reporting and standardizing results across trials. Deep learning features inferred from digital pathology scans can improve validity and robustness of current clinico-pathological features, up to identifying novel histological patterns, e.g., from tumor infiltrating lymphocytes. In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. We introduce the DAPPER framework for validation based on a rigorous Data Analysis Plan derived from the FDA’s MAQC project, designed to analyze causes of variability in predictive biomarkers. We apply the framework on models that identify tissue of origin on 787 Whole Slide Images from the Genotype-Tissue Expression (GTEx) project. We test three different deep learning architectures (VGG, ResNet, Inception) as feature extractors and three classifiers (a fully connected multilayer, Support Vector Machine and Random Forests) and work with four datasets (5, 10, 20 or 30 classes), for a total of 53, 000 tiles at 512 × 512 resolution. We analyze accuracy and feature stability of the machine learning classifiers, also demonstrating the need for diagnostic tests (e.g., random labels) to identify selection bias and risks for reproducibility. Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1, 060 annotated tiles and validated on 265 unseen ones. The DAPPER software, including its deep learning pipeline and the Histological Imaging—Newsy Tiles (HINT) benchmark dataset derived from GTEx, is released as a basis for standardization and validation initiatives in AI for digital pathology. In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. It is indeed a top priority that reproducibility-by-design gets adopted as standard practice in building and validating AI methods in the healthcare domain. Here we introduce DAPPER, a first framework to evaluate deep features and classifiers in digital pathology, based on a rigorous data analysis plan originally developed in the FDA’s MAQC initiative for predictive biomarkers from massive omics data. We apply DAPPER on models trained to identify tissue of origin from the HINT benchmark dataset of 53, 000 tiles from 787 Whole Slide Images in the Genotype-Tissue Expression (GTEx) project, available at the web address https://gtexportal.org. We analyze accuracy and feature stability of different deep learning architectures (VGG, ResNet and Inception) as feature extractors and classifiers (a fully connected multilayer, Support Vector Machine and Random Forests) on up to 20 classes. Further, we use the deep features from the VGG model (trained on HINT) on the 1, 300 annotated tiles of the KIMIA24 dataset for identification of slide of origin (24 classes). The DAPPER software is available together with the scripts to generate the HINT benchmark dataset.

Hemoglobin (Hb) is the major protein in erythrocytes and carries oxygen (O₂) throughout the body. Recently, Hb has been found synthesized in atypical sites, including the brain. Hb is highly expressed in A9 dopaminergic (DA) neurons of the substantia nigra (SN), whose selective degeneration leads to Parkinson’s disease (PD). Here we show that Hb confers DA cells’ susceptibility to 1-methyl-4-phenylpyridinium (MPP⁺) and rotenone, neurochemical cellular models of PD. The toxic property of Hb does not depend on O₂ binding and is associated with insoluble aggregate formation in the nucleolus. Neurochemical stress induces epigenetic modifications, nucleolar alterations and autophagy inhibition that depend on Hb expression. When adeno-associated viruses carrying α- and β-chains of Hb are stereotaxically injected into mouse SN, Hb forms aggregates and causes motor learning impairment. These results position Hb as a potential player in DA cells’ homeostasis and dysfunction in PD.

High-throughput methodologies such as microarrays and next-generation sequencing are routinely used in cancer research, generating complex data at different omics layers. The effective integration of omics data could provide a broader insight into the mechanisms of cancer biology, helping researchers and clinicians to develop personalized therapies. In the context of CAMDA 2017 Neuroblastoma Data Integration challenge, we explore the use of Integrative Network Fusion (INF), a bioinformatics framework combining a similarity network fusion with machine learning for the integration of multiple omics data. We apply the INF framework for the prediction of neuroblastoma patient outcome, integrating RNA-Seq, microarray and array comparative genomic hybridization data. We additionally explore the use of autoencoders as a method to integrate microarray expression and copy number data. The INF method is effective for the integration of multiple data sources providing compact feature signatures for patient classification with performances comparable to other methods. Latent space representation of the integrated data provided by the autoencoder approach gives promising results, both by improving classification on survival endpoints and by providing means to discover two groups of patients characterized by distinct overall survival (OS) curves. This article was reviewed by Djork-Arné Clevert and Tieliu Shi.

Background: Drug-induced liver injury (DILI) is a major concern in drug development, as hepatotoxicity may not be apparent at early stages but can lead to life threatening consequences. The ability to predict DILI from in vitro data would be a crucial advantage. In 2018, the Critical Assessment Massive Data Analysis group proposed the CMap Drug Safety challenge focusing on DILI prediction. Methods and results: The challenge data included Affymetrix GeneChip expression profiles for the two cancer cell lines MCF7 and PC3 treated with 276 drug compounds and empty vehicles. Binary DILI labeling and a recommended train/test split for the development of predictive classification approaches were also provided. We devised three deep learning architectures for DILI prediction on the challenge data and compared them to random forest and multi-layer perceptron classifiers. On a subset of the data and for some of the models we additionally tested several strategies for balancing the two DILI classes and to identify alternative informative train/test splits. All the models were trained with the MAQC data analysis protocol (DAP), i.e., 10x5 cross-validation over the training set. In all the experiments, the classification performance in both cross-validation and external validation gave Matthews correlation coefficient (MCC) values below 0.2. We observed minimal differences between the two cell lines. Notably, deep learning approaches did not give an advantage on the classification performance. Discussion: We extensively tested multiple machine learning approaches for the DILI classification task obtaining poor to mediocre performance. The results suggest that the CMap expression data on the two cell lines MCF7 and PC3 are not sufficient for accurate DILI label prediction. Reviewers: This article was reviewed by Maciej Kandula and Paweł P. Labaj.