Recently, artificial intelligence and machine learning in general have demonstrated remarkable performances in many tasks, from image processing to natural language processing, especially with the advent of deep learning (DL). Along with research progress, they have encroached upon many different fields and disciplines. Some of them require high level of accountability and thus transparency, for example, the medical sector. Explanations for machine decisions and predictions are thus needed to justify their reliability. This requires greater interpretability, which often means we need to understand the mechanism underlying the algorithms. Unfortunately, the blackbox nature of the DL is still unresolved, and many machine decisions are still poorly understood. We provide a review on interpretabilities suggested by different research works and categorize them. The different categories show different dimensions in interpretability research, from approaches that provide “obviously” interpretable information to the studies of complex patterns. By applying the same categorization to interpretability in medical research, it is hoped that: 1) clinicians and practitioners can subsequently approach these methods with caution; 2) insight into interpretability will be born with more considerations for medical practices; and 3) initiatives to push forward data-based, mathematically grounded, and technically grounded medical education are encouraged.

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

MicroRNAs (miRNAs) are endogenous ∼23 nt RNAs that play important gene-regulatory roles in animals and plants by pairing to the mRNAs of protein-coding genes to direct their posttranscriptional repression. This review outlines the current understanding of miRNA target recognition in animals and discusses the widespread impact of miRNAs on both the expression and evolution of protein-coding genes.

MicroRNAs: Target Recognition and Regulatory Functions

Single-cell transcriptomics yields ever growing data sets containing RNA expression levels for thousands of genes from up to millions of cells. Common data analysis pipelines include a dimensionality reduction step for visualising the data in two dimensions, most frequently performed using t-distributed stochastic neighbour embedding (t-SNE). It excels at revealing local structure in high-dimensional data, but naive applications often suffer from severe shortcomings, e.g. the global structure of the data is not represented accurately. Here we describe how to circumvent such pitfalls, and develop a protocol for creating more faithful t-SNE visualisations. It includes PCA initialisation, a high learning rate, and multi-scale similarity kernels; for very large data sets, we additionally use exaggeration and downsampling-based initialisation. We use published single-cell RNA-seq data sets to demonstrate that this protocol yields superior results compared to the naive application of t-SNE. t-SNE is widely used for dimensionality reduction and visualization of high-dimensional single-cell data. Here, the authors introduce a protocol to help avoid common shortcomings of t-SNE, for example, enabling preservation of the global structure of the data.

/pdf/the-art-of-using-t-sne-for-single-cell-transcriptomics-pw74mkm2c4.pdf

The art of using t-SNE for single-cell transcriptomics.

Single-cell genomics has now made it possible to create a comprehensive atlas of human cells. At the same time, it has reopened definitions of a cell's identity and of the ways in which identity is regulated by the cell's molecular circuitry. Emerging computational analysis methods, especially in single-cell RNA sequencing (scRNA-seq), have already begun to reveal, in a data-driven way, the diverse simultaneous facets of a cell's identity, from discrete cell types to continuous dynamic transitions and spatial locations. These developments will eventually allow a cell to be represented as a superposition of 'basis vectors', each determining a different (but possibly dependent) aspect of cellular organization and function. However, computational methods must also overcome considerable challenges-from handling technical noise and data scale to forming new abstractions of biology. As the scale of single-cell experiments continues to increase, new computational approaches will be essential for constructing and characterizing a reference map of cell identities.

Revealing the vectors of cellular identity with single-cell genomics

Tobacco (Nicotiana tabacum) is an important plant model system that has played a key role in the early development of molecular plant biology. The tobacco genome is large and its characterisation challenging because it is an allotetraploid, likely arising from hybridisation between diploid N. sylvestris and N. tomentosiformis ancestors. A draft assembly was recently published for N. tabacum, but because of the aforementioned genome complexities it was of limited utility due to a high level of fragmentation. Here we report an improved tobacco genome assembly, which, aided by the application of optical mapping, achieves an N50 size of 2.17 Mb and enables anchoring of 64% of the genome to pseudomolecules; a significant increase from the previous value of 19%. We use this assembly to identify two homeologous genes that explain the differentiation of the burley tobacco market class, with potential for greater understanding of Nitrogen Utilization Efficiency and Nitrogen Use Efficiency in plants; an important trait for future sustainability of agricultural production. Development of an improved genome assembly for N. tabacum enables what we believe to be the first successful map-based gene discovery for the species, and demonstrates the value of an improved assembly for future research in this model and commercially-important species.

/pdf/a-reference-genome-for-nicotiana-tabacum-enables-map-based-18g1wfnu47.pdf

A reference genome for Nicotiana tabacum enables map-based cloning of homeologous loci implicated in nitrogen utilization efficiency.

Although high-throughput microarray based molecular diagnostic technologies show a great promise in cancer diagnosis, it is still far from a clinical application due to its low and instable sensitivities and specificities in cancer molecular pattern recognition. In fact, high-dimensional and heterogeneous tumor profiles challenge current machine learning methodologies for its small number of samples and large or even huge number of variables (genes). This naturally calls for the use of an effective feature selection in microarray data classification. We propose a novel feature selection method: multi-resolution independent component analysis (MICA) for large-scale gene expression data. This method overcomes the weak points of the widely used transform-based feature selection methods such as principal component analysis (PCA), independent component analysis (ICA), and nonnegative matrix factorization (NMF) by avoiding their global feature-selection mechanism. In addition to demonstrating the effectiveness of the multi-resolution independent component analysis in meaningful biomarker discovery, we present a multi-resolution independent component analysis based support vector machines (MICA-SVM) and linear discriminant analysis (MICA-LDA) to attain high-performance classifications in low-dimensional spaces. We have demonstrated the superiority and stability of our algorithms by performing comprehensive experimental comparisons with nine state-of-the-art algorithms on six high-dimensional heterogeneous profiles under cross validations. Our classification algorithms, especially, MICA-SVM, not only accomplish clinical or near-clinical level sensitivities and specificities, but also show strong performance stability over its peers in classification. Software that implements the major algorithm and data sets on which this paper focuses are freely available at https://sites.google.com/site/heyaumapbc2011/
 . This work suggests a new direction to accelerate microarray technologies into a clinical routine through building a high-performance classifier to attain clinical-level sensitivities and specificities by treating an input profile as a ‘profile-biomarker’. The multi-resolution data analysis based redundant global feature suppressing and effective local feature extraction also have a positive impact on large scale ‘omics’ data mining.

/pdf/multi-resolution-independent-component-analysis-for-high-5bxw29to5t.pdf

Multi-resolution independent component analysis for high-performance tumor classification and biomarker discovery.

The t-distributed stochastic neighbor embedding t-SNE is a new dimension reduction and visualization technique for high-dimensional data. t-SNE is rarely applied to human genetic data, even though it is commonly used in other data-intensive biological fields, such as single-cell genomics. We explore the applicability of t-SNE to human genetic data and make these observations: (i) similar to previously used dimension reduction techniques such as principal component analysis (PCA), t-SNE is able to separate samples from different continents; (ii) unlike PCA, t-SNE is more robust with respect to the presence of outliers; (iii) t-SNE is able to display both continental and sub-continental patterns in a single plot. We conclude that the ability for t-SNE to reveal population stratification at different scales could be useful for human genetic association studies.

/pdf/application-of-t-sne-to-human-genetic-data-10hahsk3xt.pdf

Application of t-SNE to human genetic data.

Background
As a novel cancer diagnostic paradigm, mass spectroscopic serum proteomic pattern diagnostics was reported superior to the conventional serologic cancer biomarkers. However, its clinical use is not fully validated yet. An important factor to prevent this young technology to become a mainstream cancer diagnostic paradigm is that robustly identifying cancer molecular patterns from high-dimensional protein expression data is still a challenge in machine learning and oncology research. As a well-established dimension reduction technique, PCA is widely integrated in pattern recognition analysis to discover cancer molecular patterns. However, its global feature selection mechanism prevents it from capturing local features. This may lead to difficulty in achieving high-performance proteomic pattern discovery, because only features interpreting global data behavior are used to train a learning machine.

/pdf/nonnegative-principal-component-analysis-for-mass-spectral-3m4khblmud.pdf

Nonnegative principal component analysis for mass spectral serum profiles and biomarker discovery.

MicroRNAs (miRNAs) are a class of important non-coding RNAs, which play important roles in tumorigenesis and development by targeting oncogenes or tumor suppressor genes. One miRNA can regulate multiple genes, and one gene can be regulated by multiple miRNAs. To promote the clinical application of miRNAs, two fundamental questions should be answered: what's the regulatory mechanism of a miRNA to a gene, and which miRNAs are important for a specific type of cancer. In this study, we propose a miRNA influence capturing (miRNAInf) to decipher regulation relations of miRNAs on target genes and identify critical miRNAs in cancers in a systematic approach. With the pair-wise miRNA/gene expression profiles data, we consider the assigning problem of a miRNA on target genes and determine the regulatory mechanisms by computing the Pearson correlation coefficient between the expression changes of a miRNA and that of its target gene. Furthermore, we compute the relative local influence strength of a miRNA on its target gene. Finally, integrate the local influence strength and target gene's importance to determine the critical miRNAs involved in specific cancer. Results on breast, liver and prostate cancers show that positive regulations are as common as negative regulations. The top-ranked miRNAs show great potential as therapeutic targets driving cancer to a normal state, and they are demonstrated to be closely related to cancers based on biological functional analysis, drug sensitivity/resistance analysis and survival analysis. This study will be helpful for the discovery of critical miRNAs and development of miRNAs-based clinical therapeutics.

/pdf/a-systematic-way-to-infer-the-regulation-relations-of-mirnas-4spi303tc1.pdf

A Systematic Way to Infer the Regulation Relations of miRNAs on Target Genes and Critical miRNAs in Cancers.

Background
As a promising way to transform medicine, mass spectrometry based proteomics technologies have seen a great progress in identifying disease biomarkers for clinical diagnosis and prognosis. However, there is a lack of effective feature selection methods that are able to capture essential data behaviors to achieve clinical level disease diagnosis. Moreover, it faces a challenge from data reproducibility, which means that no two independent studies have been found to produce same proteomic patterns. Such reproducibility issue causes the identified biomarker patterns to lose repeatability and prevents it from real clinical usage.

/pdf/derivative-component-analysis-for-mass-spectral-serum-32iporzp9y.pdf

Henry Han

Papers

Multi-resolution independent component analysis for high-performance tumor classification and biomarker discovery.

Application of t-SNE to human genetic data.

Nonnegative principal component analysis for mass spectral serum profiles and biomarker discovery.

A Systematic Way to Infer the Regulation Relations of miRNAs on Target Genes and Critical miRNAs in Cancers.

Derivative component analysis for mass spectral serum proteomic profiles.