Advances in molecular characterization have reshaped our understanding of low-grade glioma (LGG) subtypes, emphasizing the need for comprehensive classification beyond histology. Lever-aging this, we present a novel approach, network-based Subnetwork Enumeration, and Analysis (nSEA), to identify distinct LGG patient groups based on dysregulated molecular pathways. Using gene expression profiles from 516 patients and a protein-protein interaction network we generated 25 million sub-networks. Through our unsupervised bottom-up approach, we selected 92 subnetworks that categorized LGG patients into five groups. Notably, a new LGG patient group with a lack of mutations in EGFR, NF1, and PTEN emerged as a previously unidentified patient subgroup with unique clinical features and subnetwork states. Validation of the patient groups on an independent dataset demonstrated the robustness of our approach and revealed consistent survival traits across different patient populations. This study offers a comprehensive molecular classification of LGG, providing insights beyond traditional genetic markers. By integrating network analysis with patient clustering, we unveil a previously overlooked patient subgroup with potential implications for prognosis and treatment strategies. Our approach sheds light on the synergistic nature of driver genes and highlights the biological relevance of the identified subnetworks. With broad implications for glioma research, our findings pave the way for further investigations into the mechanistic underpinnings of LGG subtypes and their clinical relevance.Availability: Source code and supplementary data are available at https://github.com/bebeklab/nSEA.
Continuously decreasing cost, speed and efficiency of DNA and RNA sequencing, coupled with advances in real-world sensing, storage of electronic health records, publicly available databases, and new data processing techniques enable precision medicine at unprecedented scale. Machine learning and artificial intelligence emerge naturally as tools for analyzing and summarizing data, supporting clinical decisions with data-driven insights and further unlocking genetically driven mechanisms underlying individualized risk. While these computational tools allow modeling of complex relations in large datasets, they pose new challenges especially because a patient's health is at stake. Due to an often black-box nature and high reliance on the training data, these new tools are prone to biases and most commonly provide correlational rather than causal insights. Results of these analyses have been difficult to validate, interpret, and explain to practitioners, and most genetic studies have struggled to encompass the full spectrum of human diversity. In this work, we summarize recent research trends in addressing these issues with examples from submissions to the "Computational Challenges and Artificial Intelligence in Precision Medicine" session at Pacific Symposium on Biocomputing 2021. We observe growing research interest in identifying biases, deriving causal and interpretable relations, tuning parameters of models for production, and using artificial intelligence for quality control. We expect further upsurge in work on interpretability and low-risk applications of advanced computational tools.
Physicians’ beliefs and attitudes about COVID-19 are important to ascertain because of their central role in providing care to patients during the pandemic. Identifying topics and sentiments discussed by physicians and other healthcare workers can lead to identification of gaps relating to the COVID-19 pandemic response within the healthcare system. To better understand physicians’ perspectives on the COVID-19 response, we extracted Twitter data from a specific user group that allows physicians to stay anonymous while expressing their perspectives about the COVID-19 pandemic. All tweets were in English. We measured most frequent bigrams and trigrams, compared sentiment analysis methods, and compared our findings to a larger Twitter dataset containing general COVID-19 related discourse. We found significant differences between the two datasets for specific topical phrases. No statistically significant difference was found in sentiments between the two datasets, and both trended slightly more positive than negative. Upon comparison to manual sentiment analysis, it was determined that these sentiment analysis methods should be improved to accurately capture sentiments of anonymous physician data. Anonymous physician social media data is a unique source of information that provides important insights into COVID-19 perspectives.
An early biomarker would transform our ability to screen and treat patients with cancer. The large amount of multi-scale molecular data in public repositories from various cancers provide unprecedented opportunities to find such a biomarker. However, despite identification of numerous molecular biomarkers using these public data, fewer than 1% have proven robust enough to translate into clinical practice 1 . One of the most important factors affecting the successful translation to clinical practice is lack of real-world patient population heterogeneity in the discovery process. Almost all biomarker studies analyze only a single cohort of patients with the same cancer using a single modality. Recent studies in other diseases have demonstrated the advantage of leveraging biological and technical heterogeneity across multiple independent cohorts to identify robust disease biomarkers. Here we analyzed 17149 samples from patients with one of 23 cancers that were profiled using either DNA methylation, bulk and single-cell gene expression, or protein expression in tumor and serum. First, we analyzed DNA methylation profiles of 9855 samples across 23 cancers from The Cancer Genome Atlas (TCGA). We then examined the gene expression profile of the most significantly hypomethylated gene, KRT8 , in 6781 samples from 57 independent microarray datasets from NCBI GEO. KRT8 was significantly over-expressed across cancers except colon cancer (summary effect size=1.05; p < 0.0001). Further, single-cell RNAseq analysis of 7447 single cells from lung tumors showed that genes that significantly correlated with KRT8 (p < 0.05) were involved in p53-related pathways. Immunohistochemistry in tumor biopsies from 294 patients with lung cancer showed that high protein expression of KRT8 is a prognostic marker of poor survival (HR = 1.73, p = 0.01). Finally, detectable KRT8 in serum as measured by ELISA distinguished patients with pancreatic cancer from healthy controls with an AUROC=0.94. In summary, our analysis demonstrates that KRT8 is (1) differentially expressed in several cancers across all molecular modalities and (2) may be useful as a biomarker to identify patients that should be further tested for cancer.
Molecular mechanisms characterizing cancer development and progression are complex and process through thousands of interacting elements in the cell. Understanding the underlying structure of interactions requires the integration of cellular networks with extensive combinations of dysregulation patterns. Recent pan-cancer studies focused on identifying common dysregulation patterns in a confined set of pathways or targeting a manually curated set of genes. However, the complex nature of the disease presents a challenge for finding pathways that would constitute a basis for tumor progression and requires evaluation of subnetworks with functional interactions. Uncovering these relationships is critical for translational medicine and the identification of future therapeutics. We present a frequent subgraph mining algorithm to find functional dysregulation patterns across the cancer spectrum. We mined frequent subgraphs coupled with biased random walks utilizing genomic alterations, gene expression profiles, and protein-protein interaction networks. In this unsupervised approach, we have recovered expert-curated pathways previously reported for explaining the underlying biology of cancer progression in multiple cancer types. Furthermore, we have clustered the genes identified in the frequent subgraphs into highly connected networks using a greedy approach and evaluated biological significance through pathway enrichment analysis. Gene clusters further elaborated on the inherent heterogeneity of cancer samples by both suggesting specific mechanisms for cancer type and common dysregulation patterns across different cancer types. Survival analysis of sample level clusters also revealed significant differences among cancer types (p < 0.001). These results could extend the current understanding of disease etiology by identifying biologically relevant interactions.
Environmental exposure pathophysiology related to smoking can yield metabolic changes that are difficult to describe in a biologically informative fashion with manual proprietary software. Nuclear magnetic resonance (NMR) spectroscopy detects compounds found in biofluids yielding a metabolic snapshot. We applied our semi-automated NMR pipeline for a secondary analysis of a smoking study (MTBLS374 from the MetaboLights repository) (n = 112). This involved quality control (in the form of data preprocessing), automated metabolite quantification, and analysis. With our approach we putatively identified 79 metabolites that were previously unreported in the dataset. Quantified metabolites were used for metabolic pathway enrichment analysis that replicated 1 enriched pathway with the original study as well as 3 previously unreported pathways. Our pipeline generated a new random forest (RF) classifier between smoking classes that revealed several combinations of compounds. This study broadens our metabolomic understanding of smoking exposure by 1) notably increasing the number of quantified metabolites with our analytic pipeline, 2) suggesting smoking exposure may lead to heterogenous metabolic responses according to random forest modeling, and 3) modeling how newly quantified individual metabolites can determine smoking status. Our approach can be applied to other NMR studies to characterize environmental risk factors, allowing for the discovery of new biomarkers of disease and exposure status.
Epigenetics is a reversible molecular mechanism that plays a critical role in many developmental, adaptive, and disease processes. DNA methylation has been shown to regulate gene expression and the advent of high throughput technologies has made genome-wide DNA methylation analysis possible. We investigated the effect of DNA methylation on eQTL mapping (methylation-adjusted eQTLs), by incorporating DNA methylation as a SNP-based covariate in eQTL mapping in African American derived hepatocytes. We found that the addition of DNA methylation uncovered new eQTLs and eGenes. Previously discovered eQTLs were significantly altered by the addition of DNA methylation data suggesting that methylation may modulate the association of SNPs to gene expression. We found that methylation-adjusted eQTLs that were less significant compared to PC-adjusted eQTLs were enriched in lipoprotein measurements (FDR=0.0040), immune system disorders (FDR = 0.0042), and liver enzyme measurements (FDR=0.047), suggesting that DNA methylation modulates the genetic regulation of these phenotypes. Our methylation-adjusted eQTL analysis also uncovered novel SNP-gene pairs. For example, we found that the SNP, rs1332018, was associated to GSTM3. GSTM3 expression has been linked to Hepatitis B which African Americans suffer from disproportionately. Our methylation-adjusted method adds new understanding to the genetic basis of complex diseases that disproportionally affect African Americans.
Intimate partner violence (IPV) is an urgent, prevalent, and under-detected public health issue. We present machine learning models to assess patients for IPV and injury. We train the predictive algorithms on radiology reports with 1) IPV labels based on entry to a violence prevention program and 2) injury labels provided by emergency radiology fellowship-trained physicians. Our dataset includes 34,642 radiology reports and 1479 patients of IPV victims and control patients. Our best model predicts IPV a median of 3.08 years before violence prevention program entry with a sensitivity of 64% and a specificity of 95%. We conduct error analysis to determine for which patients our model has especially high or low performance and discuss next steps for a deployed clinical risk model.
Machine learning systems have received much attention recently for their ability to achieve expert-level performance on clinical tasks, particularly in medical imaging. Here, we examine the extent to which state-of-the-art deep learning classifiers trained to yield diagnostic labels from X-ray images are biased with respect to protected attributes. We train convolution neural networks to predict 14 diagnostic labels in 3 prominent public chest X-ray datasets: MIMIC-CXR, Chest-Xray8, CheXpert, as well as a multi-site aggregation of all those datasets. We evaluate the TPR disparity - the difference in true positive rates (TPR) - among different protected attributes such as patient sex, age, race, and insurance type as a proxy for socioeconomic status. We demonstrate that TPR disparities exist in the state-of-the-art classifiers in all datasets, for all clinical tasks, and all subgroups. A multi-source dataset corresponds to the smallest disparities, suggesting one way to reduce bias. We find that TPR disparities are not significantly correlated with a subgroup's proportional disease burden. As clinical models move from papers to products, we encourage clinical decision makers to carefully audit for algorithmic disparities prior to deployment. Our supplementary materials can be found at, http://www.marzyehghassemi.com/chexclusion-supp-3/.
User-Centered Design (UCD) focuses on deeply understanding the needs of users and ensuring these needs are met by tools and software. UCD methodology aims to make tools easier to use, reduce time spent in development and the need for user support, as well as make it easier to create and maintain documentation. The goal of UCD is to ultimately make a tool that meets user needs and is a pleasure to use. This workshop will give an overview of UCD and several examples of how UCD practices are already being used at several institutions. Attendees will leave with ideas of how to incorporate UCD into their tool development as well as general resources to get started.
Translational bioinformatics (TBI) is focused on the integration of biomedical data science and informatics. This combination is extremely powerful for scientific discovery as well as translation into clinical practice. Several topics where TBI research is at the leading edge are 1) the clinical utility of polygenic risk scores, 2) data integration, and 3) artificial intelligence and machine learning. This perspective discusses these three topics and points to the important elements for driving precision medicine into the future.
Several related viral shell disorder (disorder of shell proteins of viruses) models were built using a disorder predictor via AI. The parent model detected the presence of high levels of disorder at the outer shell in viruses, for which vaccines are not available. Another model found correlations between inner shell disorder and viral virulence. A third model was able to positively correlate the levels of respiratory transmission of coronaviruses (CoVs). These models are linked together by the fact that they have uncovered two novel immune evading strategies employed by the various viruses. The first involve the use of highly disordered "shape-shifting" outer shell to prevent antibodies from binding tightly to the virus thus leading to vaccine failure. The second usually involves a more disordered inner shell that provides for more efficient binding in the rapid replication of viral particles before any host immune response. This "Trojan horse" immune evasion often backfires on the virus, when the viral load becomes too great at a vital organ, which leads to death of the host. Just as such virulence entails the viral load to exceed at a vital organ, a minimal viral load in the saliva/mucus is necessary for respiratory transmission to be feasible. As for the SARS-CoV-2, no high levels of disorder can be detected at the outer shell membrane (M) protein, but some evidence of correlation between virulence and inner shell (nucleocapsid, N) disorder has been observed. This suggests that not only the development of vaccine for SARS-CoV-2, unlike HIV, HSV and HCV, is feasible but its attenuated vaccine strain can either be found in nature or generated by genetically modifying N.
Privacy and trust of biomedical solutions that capture and share data is an issue rising to the center of public attention and discourse. While large-scale academic, medical, and industrial research initiatives must collect increasing amounts of personal biomedical data from patient stakeholders, central to ensuring precision health becomes a reality, methods for providing sufficient privacy in biomedical databases and conveying a sense of trust to the user is equally crucial for the field of biocomputing to advance with the grace of those stakeholders. If the intended audience does not trust new precision health innovations, funding and support for these efforts will inevitably be limited. It is therefore crucial for the field to address these issues in a timely manner. Here we describe current research directions towards achieving trustworthy biomedical informatics solutions.
The environment plays an important role in mediating human health. In this session we consider research addressing ways to overcome the challenges associated with studying the multifaceted and ever-changing environment. Environmental health research has a need for technological and methodological advances which will further our knowledge of how exposures precipitate complex phenotypes and exacerbate disease.
Coral reefs are home to over two million species and provide habitat for roughly 25% of all marine animals, but they are being severely threatened by pollution and climate change. A large amount of genomic, transcriptomic, and other omics data is becoming increasingly available from different species of reef-building corals, the unicellular dinoflagellates, and the coral microbiome (bacteria, archaea, viruses, fungi, etc.). Such new data present an opportunity for bioinformatics researchers and computational biologists to contribute to a timely, compelling, and urgent investigation of critical factors that influence reef health and resilience.
The coronavirus pandemic has placed renewed focus on expanded access (EA) programs to provide compassionate use exceptions to the waves of patients seeking medical care in treating the novel disease. While commendable, justifiable, and compassionate, EA programs are not designed to collect the necessary vital clinical data that can be later used in the New Drug Application process before the U.S. Food and Drug Administration (FDA). In particular, they lack the necessary rigor of properly crafted and controlled randomized controlled trials (RCT) which ensure that each patient closely monitored for side effects and other potential dangers associated with the drug, that the data is documented, stable and are traceable and that the patient population is well defined with the defined target condition. Overall, while RCTs is deemed to be of the most reliable methodologies within evidence-based medicine, morally, however, they are problematic in EA programs. Nevertheless, actionable data ought to be collected from EA patients. To this end, we look to the growing incorporation of real-world data real-world evidence as increasingly useful substitutes for data collected via RCTs, including the ethical, legal and social implications thereof. Finally, we suggest the use of digital twins as an additional method to derive causal inferences from real-world trials involving expanded access patients.
The following sections are included:IntroductionUnderstanding Biology by Modeling Structure and Processes with Machine LearningData Integration with Applications to CancerDiscussionReferences.
Intimate partner violence (IPV) is an important social and public health problem, affecting millions of women worldwide. Violence in a relationship can occur in multiple ways, including physical violence, psychological aggression, and sexual violence. In this study, utilizing data from the National Intimate Partner and Sexual Violence Survey (NISVS), we comprehensively investigate the interplay between physical, psychological, and sexual violence, in terms of their co-occurrence patterns, their relation to trauma symptoms and overall health of victims. For this purpose, we perform network analysis and develop a visualization technique that enables in-depth navigation of the three-dimensional (physical, psychological, sexual) space of violence. Our findings show that physical violence tends to significantly co-occur with psychological abuse, and violence intensifies when both are present. We also find that sexual violence tends to overlap less with other types of violence, particularly with physical violence. Milder forms of psychological abuse are prominent in the population and seem to represent a separate type of abuse (micro-aggression) in terms of its occurrence patterns. Finally, we observe that trauma symptoms and health problems tend to be reported more by survivors at the presence of intense psychological aggression. Our findings can be useful in developing treatments that target different patterns of IPV.
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), a close relative of SARS-CoV-1, causes coronavirus disease 2019 (COVID-19), which, at the time of writing, has spread to over 19.9 million people worldwide. In this work, we aim to discover drugs capable of inhibiting SARS-CoV-2 through interaction modeling and statistical methods. Currently, many drug discovery approaches follow the typical protein structure-function paradigm, designing drugs to bind to fixed three-dimensional structures. However, in recent years such approaches have failed to address drug resistance and limit the set of possible drug targets and candidates. For these reasons we instead focus on targeting protein regions that lack a stable structure, known as intrinsically disordered regions (IDRs). Such regions are essential to numerous biological pathways that contribute to the virulence of various viruses. In this work, we discover eleven new SARS-CoV-2 drug candidates targeting IDRs and provide further evidence for the involvement of IDRs in viral processes such as enzymatic peptide cleavage while demonstrating the efficacy of our unique docking approach.
Women's health is an often-overlooked aspect of medicine. The National Institutes of Health has emphasized the importance of investigating 'sex as a biological variable' in all new research grants. This has placed emphasis once again on the need for more nuanced studies that explore the role of sex as a biological variable on study outcomes. This session sought to elicit participation from researchers with strong backgrounds in women's health and informatics to develop methods that harness big datasets and 'big data techniques' including machine learning and artificial intelligence and apply those tools to women's health questions. Some important questions discussed in this section include Intimate Partner Violence (IPV) and the importance of early identification along with C-section deliveries and the importance of emergency vs. elective procedures.
