A systematic review of biologically-informed deep learning models for cancer: fundamental trends for encoding and interpreting oncology data

Designing interpretable deep learning applications for functional genomics: a quantitative analysis

Deep learning applications have had a profound impact on many scientific fields, including functional genomics. Deep learning models can learn complex interactions between and within omics data; however, interpreting and explaining these models can be challenging. Interpretability is essential not only to help progress our understanding of the biological mechanisms underlying traits and diseases but also for establishing trust in these model's efficacy for healthcare applications. Recognizing this importance, recent years have seen the development of numerous diverse interpretability strategies, making it increasingly difficult to navigate the field. In this review, we present a quantitative analysis of the challenges arising when designing interpretable deep learning solutions in functional genomics. We explore design choices related to the characteristics of genomics data, the neural network architectures applied, and strategies for interpretation. By quantifying the current state of the field with a predefined set of criteria, we find the most frequent solutions, highlight exceptional examples, and identify unexplored opportunities for developing interpretable deep learning models in genomics.

BioM2: biologically informed multi-stage machine learning for phenotype prediction using omics data

Navigating the complex landscape of high-dimensional omics data with machine learning models presents a significant challenge. The integration of biological domain knowledge into these models has shown promise in creating more meaningful stratifications of predictor variables, leading to algorithms that are both more accurate and generalizable. However, the wider availability of machine learning tools capable of incorporating such biological knowledge remains limited. Addressing this gap, we introduce BioM2, a novel R package designed for biologically informed multistage machine learning. BioM2 uniquely leverages biological information to effectively stratify and aggregate high-dimensional biological data in the context of machine learning. Demonstrating its utility with genome-wide DNA methylation and transcriptome-wide gene expression data, BioM2 has shown to enhance predictive performance, surpassing traditional machine learning models that operate without the integration of biological knowledge. A key feature of BioM2 is its ability to rank predictor variables within biological categories, specifically Gene Ontology pathways. This functionality not only aids in the interpretability of the results but also enables a subsequent modular network analysis of these variables, shedding light on the intricate systems-level biology underpinning the predictive outcome. We have proposed a biologically informed multistage machine learning framework termed BioM2 for phenotype prediction based on omics data. BioM2 has been incorporated into the BioM2 CRAN package (https://cran.r-project.org/web/packages/BioM2/index.html).

MPAC: a computational framework for inferring cancer pathway activities from multi-omic data

Fully capturing cellular state requires examining genomic, epigenomic, transcriptomic, proteomic, and other assays for a biological sample and comprehensive computational modeling to reason with the complex and sometimes conflicting measurements. Modeling these so-called multi-omic data is especially beneficial in disease analysis, where observations across omic data types may reveal unexpected patient groupings and inform clinical outcomes and treatments. We present Multi-omic Pathway Analysis of Cancer (MPAC), a computational framework that interprets multi-omic data through prior knowledge from biological pathways. MPAC uses network relationships encoded in pathways using a factor graph to infer consensus activity levels for proteins and associated pathway entities from multi-omic data, runs permutation testing to eliminate spurious activity predictions, and groups biological samples by pathway activities to prioritize proteins with potential clinical relevance. Using DNA copy number alteration and RNA-seq data from head and neck squamous cell carcinoma patients from The Cancer Genome Atlas as an example, we demonstrate that MPAC predicts a patient subgroup related to immune responses not identified by analysis with either input omic data type alone. Key proteins identified via this subgroup have pathway activities related to clinical outcome as well as immune cell compositions. Our MPAC R package, available at https://bioconductor.org/packages/MPAC, enables similar multi-omic analyses on new datasets.

Ethics for AI in Plastic Surgery: Guidelines and Review

INTRODUCTION

Artificial intelligence (AI) holds the potential to revolutionize medicine, offering vast improvements for plastic surgery. While human physicians are limited to one lifetime of experience, AI is poised to soon surpass human capabilities, as it draws on limitless information and continuous learning abilities. Nevertheless, as AI becomes increasingly prevalent in this domain, it gives rise to critical ethical considerations that must be addressed by professionals.

MATERIALS AND METHODS

This work reviews the literature referring to the ethical challenges brought on by the ever-expanding use of AI in plastic surgery and offers guidelines for its application.

RESULTS

Ethical challenges include the disclosure of use of AI by caregivers, validation of decision-making, data privacy, informed consent and autonomy, potential biases in AI systems, the opaque nature of AI models, questions of liability, and the need for regulations.

CONCLUSIONS

There is a lack of consensus for the ethical use of AI in plastic surgery. Guidelines, such as those presented in this work, are needed within each discipline of medicine to respond to important ethical considerations for the safe use of AI.

LEVEL OF EVIDENCE V

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Inference of drug off-target effects on cellular signaling using interactome-based deep learning

Many diseases emerge from dysregulated cellular signaling, and drugs are often designed to target specific signaling proteins. Off-target effects are, however, common and may ultimately result in failed clinical trials. Here we develop a computer model of the cell's transcriptional response to drugs for improved understanding of their mechanisms of action. The model is based on ensembles of artificial neural networks and simultaneously infers drug-target interactions and their downstream effects on intracellular signaling. With this, it predicts transcription factors' activities, while recovering known drug-target interactions and inferring many new ones, which we validate with an independent dataset. As a case study, we analyze the effects of the drug Lestaurtinib on downstream signaling. Alongside its intended target, FLT3, the model predicts an inhibition of CDK2 that enhances the downregulation of the cell cycle-critical transcription factor FOXM1. Our approach can therefore enhance our understanding of drug signaling for therapeutic design.

AutoTransOP: translating omics signatures without orthologue requirements using deep learning

The development of therapeutics and vaccines for human diseases requires a systematic understanding of human biology. Although animal and in vitro culture models can elucidate some disease mechanisms, they typically fail to adequately recapitulate human biology as evidenced by the predominant likelihood of clinical trial failure. To address this problem, we developed AutoTransOP, a neural network autoencoder framework, to map omics profiles from designated species or cellular contexts into a global latent space, from which germane information for different contexts can be identified without the typically imposed requirement of matched orthologues. This approach was found in general to perform at least as well as current alternative methods in identifying animal/culture-specific molecular features predictive of other contexts-most importantly without requiring homology matching. For an especially challenging test case, we successfully applied our framework to a set of inter-species vaccine serology studies, where 1-to-1 mapping between human and non-human primate features does not exist.

Graph Neural Networks in Cancer and Oncology Research: Emerging and Future Trends

Next-generation cancer and oncology research needs to take full advantage of the multimodal structured, or graph, information, with the graph data types ranging from molecular structures to spatially resolved imaging and digital pathology, biological networks, and knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on large multimodal datasets. In this review article, we survey the landscape of recent (2020-present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. We then identify the most promising directions for future research. We compare GNNs with graphical models and "non-structured" deep learning, and devise guidelines for cancer and oncology researchers or physician-scientists, asking the question of whether they should adopt the GNN methodology in their research pipelines.

Reliable interpretability of biology-inspired deep neural networks

Deep neural networks display impressive performance but suffer from limited interpretability. Biology-inspired deep learning, where the architecture of the computational graph is based on biological knowledge, enables unique interpretability where real-world concepts are encoded in hidden nodes, which can be ranked by importance and thereby interpreted. In such models trained on single-cell transcriptomes, we previously demonstrated that node-level interpretations lack robustness upon repeated training and are influenced by biases in biological knowledge. Similar studies are missing for related models. Here, we test and extend our methodology for reliable interpretability in P-NET, a biology-inspired model trained on patient mutation data. We observe variability of interpretations and susceptibility to knowledge biases, and identify the network properties that drive interpretation biases. We further present an approach to control the robustness and biases of interpretations, which leads to more specific interpretations. In summary, our study reveals the broad importance of methods to ensure robust and bias-aware interpretability in biology-inspired deep learning.