Opening up the blackbox: an interpretable deep neural network-based classifier for cell-type specific enhancer predictions

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at unboxing how AI systems' black-box choices are made. This research field inspects the measures and models involved in decision-making and seeks solutions to explain them explicitly. Many of the machine learning algorithms cannot manifest how and why a decision has been cast. This is particularly true of the most popular deep neural network approaches currently in use. Consequently, our confidence in AI systems can be hindered by the lack of explainability in these black-box models. The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend in performance. The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are uncommon. In this study, we first surveyed the current progress of XAI and in particular its advances in healthcare applications. We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios. Comprehensive quantitative and qualitative analyses can prove the efficacy of our proposed XAI solutions, from which we can envisage successful applications in a broader range of clinical questions.

Machine Learning in Epigenomics: Insights into Cancer Biology and Medicine

The recent deluge of genome-wide technologies for the mapping of the epigenome and resulting data in cancer samples has provided the opportunity for gaining insights into and understanding the roles of epigenetic processes in cancer. However, the complexity, high-dimensionality, sparsity, and noise associated with these data pose challenges for extensive integrative analyses. Machine Learning (ML) algorithms are particularly suited for epigenomic data analyses due to their flexibility and ability to learn underlying hidden structures. We will discuss four overlapping but distinct major categories under ML: dimensionality reduction, unsupervised methods, supervised methods, and deep learning (DL). We review the preferred use cases of these algorithms in analyses of cancer epigenomics data with the hope to provide an overview of how ML approaches can be used to explore fundamental questions on the roles of epigenome in cancer biology and medicine.

Genome-wide prediction of DNA mutation effect on nucleosome positions for yeast synthetic genomics

Genetically modified genomes are often used today in many areas of fundamental and applied research. In many studies, coding or noncoding regions are modified in order to change protein sequences or gene expression levels. Modifying one or several nucleotides in a genome can also lead to unexpected changes in the epigenetic regulation of genes. When designing a synthetic genome with many mutations, it would thus be very informative to be able to predict the effect of these mutations on chromatin. We develop here a deep learning approach that quantifies the effect of every possible single mutation on nucleosome positions on the full Saccharomyces cerevisiae genome. This type of annotation track can be used when designing a modified S. cerevisiae genome. We further highlight how this track can provide new insights on the sequence-dependent mechanisms that drive nucleosomes' positions in vivo.

Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review

OBJECTIVE

To conduct a systematic scoping review of explainable artificial intelligence (XAI) models that use real-world electronic health record data, categorize these techniques according to different biomedical applications, identify gaps of current studies, and suggest future research directions.

MATERIALS AND METHODS

We searched MEDLINE, IEEE Xplore, and the Association for Computing Machinery (ACM) Digital Library to identify relevant papers published between January 1, 2009 and May 1, 2019. We summarized these studies based on the year of publication, prediction tasks, machine learning algorithm, dataset(s) used to build the models, the scope, category, and evaluation of the XAI methods. We further assessed the reproducibility of the studies in terms of the availability of data and code and discussed open issues and challenges.

RESULTS

Forty-two articles were included in this review. We reported the research trend and most-studied diseases. We grouped XAI methods into 5 categories: knowledge distillation and rule extraction (N = 13), intrinsically interpretable models (N = 9), data dimensionality reduction (N = 8), attention mechanism (N = 7), and feature interaction and importance (N = 5).

DISCUSSION

XAI evaluation is an open issue that requires a deeper focus in the case of medical applications. We also discuss the importance of reproducibility of research work in this field, as well as the challenges and opportunities of XAI from 2 medical professionals' point of view.

CONCLUSION

Based on our review, we found that XAI evaluation in medicine has not been adequately and formally practiced. Reproducibility remains a critical concern. Ample opportunities exist to advance XAI research in medicine.

AIKYATAN: mapping distal regulatory elements using convolutional learning on GPU

Background

The data deluge can leverage sophisticated ML techniques for functionally annotating the regulatory non-coding genome. The challenge lies in selecting the appropriate classifier for the specific functional annotation problem, within the bounds of the hardware constraints and the model’s complexity. In our system Aikyatan, we annotate distal epigenomic regulatory sites, e.g., enhancers. Specifically, we develop a binary classifier that classifies genome sequences as distal regulatory regions or not, given their histone modifications’ combinatorial signatures. This problem is challenging because the regulatory regions are distal to the genes, with diverse signatures across classes (e.g., enhancers and insulators) and even within each class (e.g., different enhancer sub-classes).

Results

We develop a suite of ML models, under the banner Aikyatan, including SVM models, random forest variants, and deep learning architectures, for distal regulatory element (DRE) detection. We demonstrate, with strong empirical evidence, deep learning approaches have a computational advantage. Plus, convolutional neural networks (CNN) provide the best-in-class accuracy, superior to the vanilla variant. With the human embryonic cell line H1, CNN achieves an accuracy of 97.9% and an order of magnitude lower runtime than the kernel SVM. Running on a GPU, the training time is sped up 21x and 30x (over CPU) for DNN and CNN, respectively. Finally, our CNN model enjoys superior prediction performance vis-‘a-vis the competition. Specifically, Aikyatan-CNN achieved 40% higher validation rate versus CSIANN and the same accuracy as RFECS.

Conclusions

Our exhaustive experiments using an array of ML tools validate the need for a model that is not only expressive but can scale with increasing data volumes and diversity. In addition, a subset of these datasets have image-like properties and benefit from spatial pooling of features. Our Aikyatan suite leverages diverse epigenomic datasets that can then be modeled using CNNs with optimized activation and pooling functions. The goal is to capture the salient features of the integrated epigenomic datasets for deciphering the distal (non-coding) regulatory elements, which have been found to be associated with functional variants. Our source code will be made publicly available at: https://bitbucket.org/cellsandmachines/aikyatan.

Electronic supplementary material

The online version of this article (10.1186/s12859-019-3049-1) contains supplementary material, which is available to authorized users.

Hybrid model for efficient prediction of poly(A) signals in human genomic DNA

Polyadenylation signals (PAS) are found in most protein-coding and some non-coding genes in eukaryotes. Their accurate recognition improves understanding gene regulation mechanisms and recognition of the 3'-end of transcribed gene regions where premature or alternate transcription ends may lead to various diseases. Although different methods and tools for in-silico prediction of genomic signals have been proposed, the correct identification of PAS in genomic DNA remains challenging due to a vast number of non-relevant hexamers identical to PAS hexamers. In this study, we developed a novel method for PAS recognition. The method is implemented in a hybrid PAS recognition model (HybPAS), which is based on deep neural networks (DNNs) and logistic regression models (LRMs). One of such models is developed for each of the 12 most frequent human PAS hexamers. DNN models appeared the best for eight PAS types (including the two most frequent PAS hexamers), while LRM appeared best for the remaining four PAS types. The new models use different combinations of signal processing-based, statistical, and sequence-based features as input. The results obtained on human genomic data show that HybPAS outperforms the well-tuned state-of-the-art Omni-PolyA models, reducing the classification error for different PAS hexamers by up to 57.35% for 10 out of 12 PAS types, with Omni-PolyA models being better for two PAS types. For the most frequent PAS types, 'AATAAA' and 'ATTAAA', HybPAS reduced the error rate by 35.14% and 34.48%, respectively. On average, HybPAS reduces the error by 30.29%. HybPAS is implemented partly in Python and in MATLAB available at https://github.com/EMANG-KAUST/PolyA_Prediction_LRM_DNN.

Artificial intelligence for aging and longevity research: Recent advances and perspectives

The applications of modern artificial intelligence (AI) algorithms within the field of aging research offer tremendous opportunities. Aging is an almost universal unifying feature possessed by all living organisms, tissues, and cells. Modern deep learning techniques used to develop age predictors offer new possibilities for formerly incompatible dynamic and static data types. AI biomarkers of aging enable a holistic view of biological processes and allow for novel methods for building causal models-extracting the most important features and identifying biological targets and mechanisms. Recent developments in generative adversarial networks (GANs) and reinforcement learning (RL) permit the generation of diverse synthetic molecular and patient data, identification of novel biological targets, and generation of novel molecular compounds with desired properties and geroprotectors. These novel techniques can be combined into a unified, seamless end-to-end biomarker development, target identification, drug discovery and real world evidence pipeline that may help accelerate and improve pharmaceutical research and development practices. Modern AI is therefore expected to contribute to the credibility and prominence of longevity biotechnology in the healthcare and pharmaceutical industry, and to the convergence of countless areas of research.

A Distributed Classifier for MicroRNA Target Prediction with Validation Through TCGA Expression Data

BACKGROUND

MicroRNAs (miRNAs) are approximately 22-nucleotide long regulatory RNA that mediate RNA interference by binding to cognate mRNA target regions. Here, we present a distributed kernel SVM-based binary classification scheme to predict miRNA targets. It captures the spatial profile of miRNA-mRNA interactions via smooth B-spline curves. This is accomplished separately for various input features, such as thermodynamic and sequence-based features. Further, we use a principled approach to uniformly model both canonical and non-canonical seed matches, using a novel seed enrichment metric. Finally, we verify our miRNA-mRNA pairings using an Elastic Net-based regression model on TCGA expression data for four cancer types to estimate the miRNAs that together regulate any given mRNA.

RESULTS

We present a suite of algorithms for miRNA target prediction, under the banner Avishkar, with superior prediction performance over the competition. Specifically, our final kernel SVM model, with an Apache Spark backend, achieves an average true positive rate (TPR) of more than 75 percent, when keeping the false positive rate of 20 percent, for non-canonical human miRNA target sites. This is an improvement of over 150 percent in the TPR for non-canonical sites, over the best-in-class algorithm. We are able to achieve such superior performance by representing the thermodynamic and sequence profiles of miRNA-mRNA interaction as curves, devising a novel seed enrichment metric, and learning an ensemble of miRNA family-specific kernel SVM classifiers. We provide an easy-to-use system for large-scale interactive analysis and prediction of miRNA targets. All operations in our system, namely candidate set generation, feature generation and transformation, training, prediction, and computing performance metrics are fully distributed and are scalable.

CONCLUSIONS

We have developed an efficient SVM-based model for miRNA target prediction using recent CLIP-seq data, demonstrating superior performance, evaluated using ROC curves for different species (human or mouse), or different target types (canonical or non-canonical). We analyzed the agreement between the target pairings using CLIP-seq data and using expression data from four cancer types. To the best of our knowledge, we provide the first distributed framework for miRNA target prediction based on Apache Hadoop and Spark.

AVAILABILITY

All source code and sample data are publicly available at https://bitbucket.org/cellsandmachines/avishkar. Our scalable implementation of kernel SVM using Apache Spark, which can be used to solve large-scale non-linear binary classification problems, is available at https://bitbucket.org/cellsandmachines/kernelsvmspark.

Adversarial Threshold Neural Computer for Molecular de Novo Design

In this article, we propose the deep neural network Adversarial Threshold Neural Computer (ATNC). The ATNC model is intended for the de novo design of novel small-molecule organic structures. The model is based on generative adversarial network architecture and reinforcement learning. ATNC uses a Differentiable Neural Computer as a generator and has a new specific block, called adversarial threshold (AT). AT acts as a filter between the agent (generator) and the environment (discriminator + objective reward functions). Furthermore, to generate more diverse molecules we introduce a new objective reward function named Internal Diversity Clustering (IDC). In this work, ATNC is tested and compared with the ORGANIC model. Both models were trained on the SMILES string representation of the molecules, using four objective functions (internal similarity, Muegge druglikeness filter, presence or absence of sp³-rich fragments, and IDC). The SMILES representations of 15K druglike molecules from the ChemDiv collection were used as a training data set. For the different functions, ATNC outperforms ORGANIC. Combined with the IDC, ATNC generates 72% of valid and 77% of unique SMILES strings, while ORGANIC generates only 7% of valid and 86% of unique SMILES strings. For each set of molecules generated by ATNC and ORGANIC, we analyzed distributions of four molecular descriptors (number of atoms, molecular weight, logP, and tpsa) and calculated five chemical statistical features (internal diversity, number of unique heterocycles, number of clusters, number of singletons, and number of compounds that have not been passed through medicinal chemistry filters). Analysis of key molecular descriptors and chemical statistical features demonstrated that the molecules generated by ATNC elicited better druglikeness properties. We also performed in vitro validation of the molecules generated by ATNC; results indicated that ATNC is an effective method for producing hit compounds.

CRISPR Genome Engineering for Human Pluripotent Stem Cell Research

The emergence of targeted and efficient genome editing technologies, such as repurposed bacterial programmable nucleases (e.g., CRISPR-Cas systems), has abetted the development of cell engineering approaches. Lessons learned from the development of RNA-interference (RNA-i) therapies can spur the translation of genome editing, such as those enabling the translation of human pluripotent stem cell engineering. In this review, we discuss the opportunities and the challenges of repurposing bacterial nucleases for genome editing, while appreciating their roles, primarily at the epigenomic granularity. First, we discuss the evolution of high-precision, genome editing technologies, highlighting CRISPR-Cas9. They exist in the form of programmable nucleases, engineered with sequence-specific localizing domains, and with the ability to revolutionize human stem cell technologies through precision targeting with greater on-target activities. Next, we highlight the major challenges that need to be met prior to bench-to-bedside translation, often learning from the path-to-clinic of complementary technologies, such as RNA-i. Finally, we suggest potential bioinformatics developments and CRISPR delivery vehicles that can be deployed to circumvent some of the challenges confronting genome editing technologies en route to the clinic.