CSAX: Characterizing Systematic Anomalies in eXpression Data

A primer on the use of machine learning to distil knowledge from data in biological psychiatry

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

Personalized single-cell networks: a framework to predict the response of any gene to any drug for any patient

BACKGROUND

The last decade has seen a major increase in the availability of genomic data. This includes expert-curated databases that describe the biological activity of genes, as well as high-throughput assays that measure gene expression in bulk tissue and single cells. Integrating these heterogeneous data sources can generate new hypotheses about biological systems. Our primary objective is to combine population-level drug-response data with patient-level single-cell expression data to predict how any gene will respond to any drug for any patient.

METHODS

We take 2 approaches to benchmarking a "dual-channel" random walk with restart (RWR) for data integration. First, we evaluate how well RWR can predict known gene functions from single-cell gene co-expression networks. Second, we evaluate how well RWR can predict known drug responses from individual cell networks. We then present two exploratory applications. In the first application, we combine the Gene Ontology database with glioblastoma single cells from 5 individual patients to identify genes whose functions differ between cancers. In the second application, we combine the LINCS drug-response database with the same glioblastoma data to identify genes that may exhibit patient-specific drug responses.

CONCLUSIONS

Our manuscript introduces two innovations to the integration of heterogeneous biological data. First, we use a "dual-channel" method to predict up-regulation and down-regulation separately. Second, we use individualized single-cell gene co-expression networks to make personalized predictions. These innovations let us predict gene function and drug response for individual patients. Taken together, our work shows promise that single-cell co-expression data could be combined in heterogeneous information networks to facilitate precision medicine.

DECO: decompose heterogeneous population cohorts for patient stratification and discovery of sample biomarkers using omic data profiling

Motivation

Patient and sample diversity is one of the main challenges when dealing with clinical cohorts in biomedical genomics studies. During last decade, several methods have been developed to identify biomarkers assigned to specific individuals or subtypes of samples. However, current methods still fail to discover markers in complex scenarios where heterogeneity or hidden phenotypical factors are present. Here, we propose a method to analyze and understand heterogeneous data avoiding classical normalization approaches of reducing or removing variation.

Results

DEcomposing heterogeneous Cohorts using Omic data profiling (DECO) is a method to find significant association among biological features (biomarkers) and samples (individuals) analyzing large-scale omic data. The method identifies and categorizes biomarkers of specific phenotypic conditions based on a recurrent differential analysis integrated with a non-symmetrical correspondence analysis. DECO integrates both omic data dispersion and predictor–response relationship from non-symmetrical correspondence analysis in a unique statistic (called h-statistic), allowing the identification of closely related sample categories within complex cohorts. The performance is demonstrated using simulated data and five experimental transcriptomic datasets, and comparing to seven other methods. We show DECO greatly enhances the discovery and subtle identification of biomarkers, making it especially suited for deep and accurate patient stratification.

Availability and implementation

DECO is freely available as an R package (including a practical vignette) at Bioconductor repository (http://bioconductor.org/packages/deco/).

Supplementary information

Supplementary data are available at Bioinformatics online.

aTEMPO: Pathway-Specific Temporal Anomalies for Precision Therapeutics

Dynamic processes are inherently important in disease, and identifying disease-related disruptions of normal dynamic processes can provide information about individual patients. We have previously characterized individuals' disease states via pathway-based anomalies in expression data, and we have identified disease-correlated disruption of predictable dynamic patterns by modeling a virtual time series in static data. Here we combine the two approaches, using an anomaly detection model and virtual time series to identify anomalous temporal processes in specific disease states. We demonstrate that this approach can informatively characterize individual patients, suggesting personalized therapeutic approaches.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.

A cross-cancer metastasis signature in the microRNA-mRNA axis of paired tissue samples

In the progression of cancer, cells acquire genetic mutations that cause uncontrolled growth. Over time, the primary tumour may undergo additional mutations that allow for the cancerous cells to spread throughout the body as metastases. Since metastatic development typically results in markedly worse patient outcomes, research into the identity and function of metastasis-associated biomarkers could eventually translate into clinical diagnostics or novel therapeutics. Although the general processes underpinning metastatic progression are understood, no clear cross-cancer biomarker profile has emerged. However, the literature suggests that some microRNAs (miRNAs) may play an important role in the metastatic progression of several cancer types. Using a subset of The Cancer Genome Atlas (TCGA) data, we performed an integrated analysis of mRNA and miRNA expression with paired metastatic and primary tumour samples to interrogate how the miRNA-mRNA regulatory axis influences metastatic progression. From this, we successfully built mRNA- and miRNA-specific classifiers that can discriminate pairs of metastatic and primary samples across 11 cancer types. In addition, we identified a number of miRNAs whose metastasis-associated dysregulation could predict mRNA metastasis-associated dysregulation. Among the most predictive miRNAs, we found several previously implicated in cancer progression, including miR-301b, miR-1296, and miR-423. Taken together, our results suggest that metastatic samples have a common cross-cancer signature when compared with their primary tumour pair, and that these miRNA biomarkers can be used to predict metastatic status as well as mRNA expression.