With the rapid emergence of single-cell transcriptomics datasets, reproducible marker genes and functional annotation of cell type or state is becoming increasingly important. Conventional methods that rely on differential gene expression (DEG) analysis lack both consistency across datasets and functional annotations of selected markers. Here, we present scSCOPE, an R-based platform that utilizes stabilized LASSO (Least Absolute Shrinkage and Selection Operator) feature selection, bootstrapped co-expression networks, and pathway enrichments to identify reproducible and functionally relevant marker genes and associated pathways in scRNAseq datasets. Using 9 scRNAseq datasets from human and mouse immune cells generated by different sequencing technologies, we show that scSCOPE outperforms other conventional methods by automatically identifying cell type-specific marker genes and pathways with the highest consistency across all datasets. scSCOPE's gene co-expression and pathway analyses also provide in-depth molecular insights into the functionality of identified marker genes. We anticipate that scSCOPE will greatly improve cell type annotation and accelerate the design of experimental validation and functional investigations on cell heterogeneity.

Machine Learning models have been frequently used in transcriptome analyses. Particularly, Representation Learning (RL), e.g., autoencoders, are effective in learning critical representations in noisy data. However, learned representations, e.g., the "latent variables" in an autoencoder, are difficult to interpret, not to mention prioritizing essential genes for functional follow-up. In contrast, in traditional analyses, one may identify important genes such as Differentially Expressed (DiffEx), Differentially Co-Expressed (DiffCoEx), and Hub genes. Intuitively, the complex gene-gene interactions may be beyond the capture of marginal effects (DiffEx) or correlations (DiffCoEx and Hub), indicating the need of powerful RL models. However, the lack of interpretability and individual target genes is an obstacle for RL's broad use in practice. To facilitate interpretable analysis and gene-identification using RL, we propose "Critical genes", defined as genes that contribute highly to learned representations (e.g., latent variables in an autoencoder). As a proof-of-concept, supported by eXplainable Artificial Intelligence (XAI), we implemented eXplainable Autoencoder for Critical genes (XA4C) that quantifies each gene's contribution to latent variables, based on which Critical genes are prioritized. Applying XA4C to gene expression data in six cancers showed that Critical genes capture essential pathways underlying cancers. Remarkably, Critical genes has little overlap with Hub or DiffEx genes, however, has a higher enrichment in a comprehensive disease gene database (DisGeNET) and a cancer-specific database (COSMIC), evidencing its potential to disclose massive unknown biology. As an example, we discovered five Critical genes sitting in the center of Lysine degradation (hsa00310) pathway, displaying distinct interaction patterns in tumor and normal tissues. In conclusion, XA4C facilitates explainable analysis using RL and Critical genes discovered by explainable RL empowers the study of complex interactions.

Identifying gene-gene interaction is a hot topic in genome wide association studies. Two fundamental challenges are: (1) how to smartly identify combinations of variants that may be associated with the trait from astronomical number of all possible combinations; and (2) how to test epistatic interaction when all potential combinations are available. We developed AprioriGWAS, which brings two innovations. (1) Based on Apriori, a successful method in field of Frequent Itemset Mining (FIM) in which a pattern growth strategy is leveraged to effectively and accurately reduce search space, AprioriGWAS can efficiently identify genetically associated genotype patterns. (2) To test the hypotheses of epistasis, we adopt a new conditional permutation procedure to obtain reliable statistical inference of Pearson's chi-square test for the [Formula: see text] contingency table generated by associated variants. By applying AprioriGWAS to age-related macular degeneration (AMD) data, we found that: (1) angiopoietin 1 (ANGPT1) and four retinal genes interact with Complement Factor H (CFH). (2) GO term "glycosaminoglycan biosynthetic process" was enriched in AMD interacting genes. The epistatic interactions newly found by AprioriGWAS on AMD data are likely true interactions, since genes interacting with CFH are retinal genes, and GO term enrichment also verified that interaction between glycosaminoglycans (GAGs) and CFH plays an important role in disease pathology of AMD. By applying AprioriGWAS on Bipolar disorder in WTCCC data, we found variants without marginal effect show significant interactions. For example, multiple-SNP genotype patterns inside gene GABRB2 and GRIA1 (AMPA subunit 1 receptor gene). AMPARs are found in many parts of the brain and are the most commonly found receptor in the nervous system. The GABRB2 mediates the fastest inhibitory synaptic transmission in the central nervous system. GRIA1 and GABRB2 are relevant to mental disorders supported by multiple evidences.

SUMMARY: We present JAWAMix5, an out-of-core open-source toolkit for association mapping using high-throughput sequence data. Taking advantage of its HDF5-based implementation, JAWAMix5 stores genotype data on disk and accesses them as though stored in main memory. Therefore, it offers a scalable and fast analysis without concerns about memory usage, whatever the size of the dataset. We have implemented eight functions for association studies, including standard methods (linear models, linear mixed models, rare variants test, analysis in nested association mapping design and local variance component analysis), as well as a novel Bayesian local variance component analysis. Application to real data demonstrates that JAWAMix5 is reasonably fast compared with traditional solutions that load the complete dataset into memory, and that the memory usage is efficient regardless of the dataset size. AVAILABILITY: The source code, a 'batteries-included' executable and user manual can be freely downloaded from http://code.google.com/p/jawamix5/.

BACKGROUND: In addition to single-locus (main) effects of disease variants, there is a growing consensus that gene-gene and gene-environment interactions may play important roles in disease etiology. However, for the very large numbers of genetic markers currently in use, it has proven difficult to develop suitable and efficient approaches for detecting effects other than main effects due to single variants. RESULTS: We developed a method for jointly detecting disease-causing single-locus effects and gene-gene interactions. Our method is based on finding differences of genotype pattern frequencies between case and control individuals. Those single-nucleotide polymorphism markers with largest single-locus association test statistics are included in a pattern. For a logistic regression model comprising three disease variants exerting main and epistatic interaction effects, we demonstrate that our method is vastly superior to the traditional approach of looking for single-locus effects. In addition, our method is suitable for estimating the number of disease variants in a dataset. We successfully apply our approach to data on Parkinson Disease and heroin addiction. CONCLUSION: Our approach is suitable and powerful for detecting disease susceptibility variants with potentially small main effects and strong interaction effects. It can be applied to large numbers of genetic markers.