Dissecting the cis-regulatory syntax of transcription initiation with deep learning.

Despite extensive characterization of mammalian Pol II transcription, the DNA sequence determinants of transcription initiation at a third of human promoters and most enhancers remain poorly understood. Hence, we trained and interpreted a neural network called ProCapNet that accurately models base-resolution initiation profiles from PRO-cap experiments using local DNA sequence. ProCapNet learns sequence motifs with distinct effects on initiation rates and TSS positioning and uncovers context-specific cryptic initiator elements intertwined within other TF motifs. ProCapNet annotates predictive motifs in nearly all actively transcribed regulatory elements across multiple cell-lines, revealing a shared cis-regulatory logic across promoters and enhancers mediated by a highly epistatic sequence syntax of cooperative and competitive motif interactions. ProCapNet models of RAMPAGE profiles measuring steady-state RNA abundance at TSSs distill initiation signals on par with models trained directly on PRO-cap profiles. ProCapNet learns a largely cell-type-agnostic cis-regulatory code of initiation complementing sequence drivers of cell-type-specific chromatin state critical for accurate prediction of cell-type-specific transcription initiation.

Health Justice and Systems of Care: A Required Longitudinal Course for MD Students.

Problem & Background: Medical education has acknowledged the impact of structural societal factors on health, prompting the need for curricula seeking to eliminate health inequities upstream while simultaneously caring for downstream effects of existing inequities. The Keck School of Medicine of USC (KSOM) implemented one such comprehensive curriculum, Health Justice and Systems of Care (HJSC), integrating health systems science, structural competency, and service-learning in a required course spanning the pre-clerkship and clerkship phases with an optional post clerkship elective. Approach: The HJSC course addresses topics including racism in medicine, health inequities, and health systems science. Using transformative learning theory, it fosters critical consciousness and structural competency. Assessments include case analyses, reflections, team-based learning sessions, and group projects related to social justice in healthcare. The program aims to instill cultural humility and practical application, fostering a holistic approach to medical education that implores physicians to become advocates for health justice. Outcomes of the Innovation: Feedback from students indicated generally positive perceptions of the curriculum. Students provided overall positive comments about discussions with guest speakers. However, students expressed a desire for more concrete examples of how health inequities can be remedied. Some found small-group activities less engaging. Other challenges included providing students of different readiness levels with tailored experiences and seamlessly integrating HJSC content within basic and clinical sciences courses. Critical Reflection: Next steps include continuing to integrate content into the science curriculum and clerkships, improving opportunities for meaningful student interactions, and enhancing faculty development to address health justice concerns in clinical settings.

Predicting chromatin conformation contact maps.

Over the past 15 years, a variety of next-generation sequencing assays have been developed for measuring the 3D conformation of DNA in the nucleus. Each of these assays gives, for a particular cell or tissue type, a distinct picture of 3D chromatin architecture. Accordingly, making sense of the relationship between genome structure and function requires teasing apart two closely related questions: how does chromatin 3D structure change from one cell type to the next, and how do different measurements of that structure differ from one another, even when the two assays are carried out in the same cell type? In this work, we assemble a collection of chromatin 3D datasets-each represented as a 2D contact map- spanning multiple assay types and cell types. We then build a machine learning model that predicts missing contact maps in this collection. We use the model to systematically explore how genome 3D architecture changes, at the level of compartments, domains, and loops, between cell type and between assay types.

Mental Health Disparities among Pre-Clinical Medical Students at Saint Louis University during the COVID-19 Pandemic.

The COVID-19 pandemic disproportionately affected racial and ethnic minorities. Medical students were also particularly impacted as they coped with increased stressors due to delayed medical training and a high prevalence of mental health conditions. This study investigates mental health disparities of underrepresented in medicine (URM) students at the Saint Louis University School of Medicine (SLUSOM). An anonymous online survey was distributed to first- and second-year medical students at SLUSOM in February 2021. The survey queried demographic information, lifestyle factors, and pandemic-related and institutional concerns. Mental health was assessed via the Generalized Anxiety Disorder-7 (GAD-7) and the Patient Health Questionnaire-9 (PHQ-9). Statistical tests were run with SPSS, version 27. A convenience sample of 87 students responded to the survey. Students who were categorized as URM were significantly more likely to be at risk of major depressive disorder during the pandemic. Concern about a lack of financial support was significantly greater among students categorized as URM. Concerns regarding a lack of financial support, mental health support, and decreased quality of medical training significantly predicted PHQ-9 scores. Our findings revealed several key factors that may exacerbate mental health disparities among URM students during the pandemic. Providing adequate financial and academic resources for URMs may improve mental health outcomes for similar adverse events in the future.

Transcription factor stoichiometry, motif affinity and syntax regulate single-cell chromatin dynamics during fibroblast reprogramming to pluripotency.

Ectopic expression of OCT4, SOX2, KLF4 and MYC (OSKM) transforms differentiated cells into induced pluripotent stem cells. To refine our mechanistic understanding of reprogramming, especially during the early stages, we profiled chromatin accessibility and gene expression at single-cell resolution across a densely sampled time course of human fibroblast reprogramming. Using neural networks that map DNA sequence to ATAC-seq profiles at base-resolution, we annotated cell-state-specific predictive transcription factor (TF) motif syntax in regulatory elements, inferred affinity- and concentration-dependent dynamics of Tn5-bias corrected TF footprints, linked peaks to putative target genes, and elucidated rewiring of TF-to-gene cis-regulatory networks. Our models reveal that early in reprogramming, OSK, at supraphysiological concentrations, rapidly open transient regulatory elements by occupying non-canonical low-affinity binding sites. As OSK concentration falls, the accessibility of these transient elements decays as a function of motif affinity. We find that these OSK-dependent transient elements sequester the somatic TF AP-1. This redistribution is strongly associated with the silencing of fibroblast-specific genes within individual nuclei. Together, our integrated single-cell resource and models reveal insights into the cis-regulatory code of reprogramming at unprecedented resolution, connect TF stoichiometry and motif syntax to diversification of cell fate trajectories, and provide new perspectives on the dynamics and role of transient regulatory elements in somatic silencing.

Cross-species imputation and comparison of single-cell transcriptomic profiles.

Cross-species comparison and prediction of gene expression profiles are important to understand regulatory changes during evolution and to transfer knowledge learned from model organisms to humans. Single-cell RNA-seq (scRNA-seq) profiles enable us to capture gene expression profiles with respect to variations among individual cells; however, cross-species comparison of scRNA-seq profiles is challenging because of data sparsity, batch effects, and the lack of one-to-one cell matching across species. Moreover, single-cell profiles are challenging to obtain in certain biological contexts, limiting the scope of hypothesis generation. Here we developed Icebear, a neural network framework that decomposes single-cell measurements into factors representing cell identity, species, and batch factors. Icebear enables accurate prediction of single-cell gene expression profiles across species, thereby providing high-resolution cell type and disease profiles in under-characterized contexts. Icebear also facilitates direct cross-species comparison of single-cell expression profiles for conserved genes that are located on the X chromosome in eutherian mammals but on autosomes in chicken. This comparison, for the first time, revealed evolutionary and diverse adaptations of X-chromosome upregulation in mammals.

Leveraging epigenomes and three-dimensional genome organization for interpreting regulatory variation.

Understanding the impact of regulatory variants on complex phenotypes is a significant challenge because the genes and pathways that are targeted by such variants and the cell type context in which regulatory variants operate are typically unknown. Cell-type-specific long-range regulatory interactions that occur between a distal regulatory sequence and a gene offer a powerful framework for examining the impact of regulatory variants on complex phenotypes. However, high-resolution maps of such long-range interactions are available only for a handful of cell types. Furthermore, identifying specific gene subnetworks or pathways that are targeted by a set of variants is a significant challenge. We have developed L-HiC-Reg, a Random Forests regression method to predict high-resolution contact counts in new cell types, and a network-based framework to identify candidate cell-type-specific gene networks targeted by a set of variants from a genome-wide association study (GWAS). We applied our approach to predict interactions in 55 Roadmap Epigenomics Mapping Consortium cell types, which we used to interpret regulatory single nucleotide polymorphisms (SNPs) in the NHGRI-EBI GWAS catalogue. Using our approach, we performed an in-depth characterization of fifteen different phenotypes including schizophrenia, coronary artery disease (CAD) and Crohn's disease. We found differentially wired subnetworks consisting of known as well as novel gene targets of regulatory SNPs. Taken together, our compendium of interactions and the associated network-based analysis pipeline leverages long-range regulatory interactions to examine the context-specific impact of regulatory variation in complex phenotypes.

The ENCODE Imputation Challenge: a critical assessment of methods for cross-cell type imputation of epigenomic profiles.

A promising alternative to comprehensively performing genomics experiments is to, instead, perform a subset of experiments and use computational methods to impute the remainder. However, identifying the best imputation methods and what measures meaningfully evaluate performance are open questions. We address these questions by comprehensively analyzing 23 methods from the ENCODE Imputation Challenge. We find that imputation evaluations are challenging and confounded by distributional shifts from differences in data collection and processing over time, the amount of available data, and redundancy among performance measures. Our analyses suggest simple steps for overcoming these issues and promising directions for more robust research.

GENCODE: reference annotation for the human and mouse genomes in 2023.

GENCODE produces high quality gene and transcript annotation for the human and mouse genomes. All GENCODE annotation is supported by experimental data and serves as a reference for genome biology and clinical genomics. The GENCODE consortium generates targeted experimental data, develops bioinformatic tools and carries out analyses that, along with externally produced data and methods, support the identification and annotation of transcript structures and the determination of their function. Here, we present an update on the annotation of human and mouse genes, including developments in the tools, data, analyses and major collaborations which underpin this progress. For example, we report the creation of a set of non-canonical ORFs identified in GENCODE transcripts, the LRGASP collaboration to assess the use of long transcriptomic data to build transcript models, the progress in collaborations with RefSeq and UniProt to increase convergence in the annotation of human and mouse protein-coding genes, the propagation of GENCODE across the human pan-genome and the development of new tools to support annotation of regulatory features by GENCODE. Our annotation is accessible via Ensembl, the UCSC Genome Browser and https://www.gencodegenes.org.

Proactive Coaching in General Surgery Internship: Incorporating Well-being Practices into Resident Professional Life.

OBJECTIVE: Coaching can provide learners with space to reflect on their performance while ensuring well-being and encouraging professional achievement and personal satisfaction outside of traditional mentorship and teaching models. We hypothesized that a proactive coaching program for general surgery interns coupled with individualized learning plans would help build foundational skills necessary for residency success and facilitate the incorporation of well-being practices into resident professional life. Here, we present the development, implementation, and outcomes of a novel well-being coaching program for surgical interns. DESIGN AND SETTING: A well-being coaching program was developed and implemented from July 2020 through June 2021 at a single university-based surgical residency program. To assess impact of the coaching program, we designed a mixed-methods study incorporating end-of-program survey results as well as participant narratives from commitment-to-act statements for thematic content. PARTICIPANTS: All 32 general surgery interns participated in aspects of the coaching program. RESULTS: The end-of-program survey was completed by 19/32 (59%) interns and commitment-to-act statements were completed by 22/32 (69%). The majority (89%) of survey respondents "agreed" or "strongly agreed" that the longitudinal intern coaching program helped them reach goals they had set for themselves this academic year; 15/19 (79%) noted that the coaching experience was effective in promoting well-being practices in their life. Well-being and professional goals were identified as major themes in the end-of-the-year commitment-to-act statements. Statements specifically mentioned resources highlighted and skills taught in our coaching program such as mindfulness techniques, gratitude journals, and self-compassion strategies. CONCLUSIONS: Our study illustrates the effectiveness of a coaching pilot program on promoting well-being practices in a university-based general surgery internship and can be a roadmap with proven efficacy and measurable outcomes.

Accelerating in silico saturation mutagenesis using compressed sensing.

MOTIVATION: In silico saturation mutagenesis (ISM) is a popular approach in computational genomics for calculating feature attributions on biological sequences that proceeds by systematically perturbing each position in a sequence and recording the difference in model output. However, this method can be slow because systematically perturbing each position requires performing a number of forward passes proportional to the length of the sequence being examined. RESULTS: In this work, we propose a modification of ISM that leverages the principles of compressed sensing to require only a constant number of forward passes, regardless of sequence length, when applied to models that contain operations with a limited receptive field, such as convolutions. Our method, named Yuzu, can reduce the time that ISM spends in convolution operations by several orders of magnitude and, consequently, Yuzu can speed up ISM on several commonly used architectures in genomics by over an order of magnitude. Notably, we found that Yuzu provides speedups that increase with the complexity of the convolution operation and the length of the sequence being analyzed, suggesting that Yuzu provides large benefits in realistic settings. AVAILABILITY AND IMPLEMENTATION: We have made this tool available at https://github.com/kundajelab/yuzu.

"Everybody in this room can understand": A qualitative exploration of peer support during residency training.

Objectives: Though peer support groups are often utilized during residency training, the dynamics, content, and impact of social support offered through peer support are poorly understood. We explored trainee perceptions of the benefits, drawbacks, and optimal membership and facilitation of peer support groups. Methods: After engaging in a peer support program at an emergency medicine residency program, 15 residents and 4 group facilitators participated in four focus groups in 2018. Interview questions explored the dynamics of group interactions, types of support offered, and psychological impacts of participation. The authors conducted a reflexive thematic analysis of data, performing iterative coding and organization of interview transcripts. Results: Discussions with experienced senior residents and alumni normalized residents' workplace struggles and provided them with insights into the trajectory of their residency experiences. Vulnerable group dialogue was enhanced by the use of "insider" participants; however, residents acknowledged the potential contributions of mental health professionals. Though groups occasionally utilized maladaptive coping strategies and lacked actual solutions, they also enhanced residents' sense of belonging, willingness to share personal struggles, and ability to "reset" in the clinical environment. Conclusions: Participants offered insights into the benefits and drawbacks of peer support as well as optimal peer group composition and facilitation. Support groups may be more effective if they engage a complementary model of alumni and pre-briefed psychologist facilitators, avoid fatalism, and aim to foster intimate connections among residents. These findings can inform the development of future initiatives aiming to create a safe space for trainees to discuss workplace stressors.

fastISM: performant in silico saturation mutagenesis for convolutional neural networks.

MOTIVATION: Deep-learning models, such as convolutional neural networks, are able to accurately map biological sequences to associated functional readouts and properties by learning predictive de novo representations. In silico saturation mutagenesis (ISM) is a popular feature attribution technique for inferring contributions of all characters in an input sequence to the model's predicted output. The main drawback of ISM is its runtime, as it involves multiple forward propagations of all possible mutations of each character in the input sequence through the trained model to predict the effects on the output. RESULTS: We present fastISM, an algorithm that speeds up ISM by a factor of over 10× for commonly used convolutional neural network architectures. fastISM is based on the observations that the majority of computation in ISM is spent in convolutional layers, and a single mutation only disrupts a limited region of intermediate layers, rendering most computation redundant. fastISM reduces the gap between backpropagation-based feature attribution methods and ISM. It far surpasses the runtime of backpropagation-based methods on multi-output architectures, making it feasible to run ISM on a large number of sequences. AVAILABILITY AND IMPLEMENTATION: An easy-to-use Keras/TensorFlow 2 implementation of fastISM is available at https://github.com/kundajelab/fastISM. fastISM can be installed using pip install fastism. A hands-on tutorial can be found at https://colab.research.google.com/github/kundajelab/fastISM/blob/master/notebooks/colab/DeepSEA.ipynb. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Navigating the pitfalls of applying machine learning in genomics.

The scale of genetic, epigenomic, transcriptomic, cheminformatic and proteomic data available today, coupled with easy-to-use machine learning (ML) toolkits, has propelled the application of supervised learning in genomics research. However, the assumptions behind the statistical models and performance evaluations in ML software frequently are not met in biological systems. In this Review, we illustrate the impact of several common pitfalls encountered when applying supervised ML in genomics. We explore how the structure of genomics data can bias performance evaluations and predictions. To address the challenges associated with applying cutting-edge ML methods to genomics, we describe solutions and appropriate use cases where ML modelling shows great potential.

Medical student anxiety and depression in the COVID-19 Era: Unique needs of underrepresented students.

Background: The COVID-19 pandemic has caused significant morbidity, mortality, and mental health consequences. Few studies have examined the mental toll of COVID-19 on United States (US) medical students, who experience greater rates of depression and anxiety than the general population. Students who identify as underrepresented in medicine (URM) may experience even greater mental health adversities than non-URM peers. This study examines COVID-19's impact on preclinical medical student anxiety and depression and unique challenges disproportionately affecting URM students during the initial phase of the pandemic. Methods: Medical students at four US institutions completed an anonymous survey including the Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) questionnaires for depression and anxiety. Participants provided information on demographics, past mental health difficulties, and concerns during the pandemic. Chi-square and Mann-Whitney U tests were performed using SPSS. Results: During the initial phase of the pandemic, URMs were 3.71 times more likely to be in the at-risk category on GAD-7 than non-URM peers. Before COVID-19, there was no significant difference between self-reported feelings or diagnoses of anxiety between groups. During the COVID-19 pandemic, there were significant differences in feelings of increased anxiety between URM (Mdn = 76) and non-URM (Mdn = 49) students, U = 702.5, P < 0.001, feelings of increased sadness between URM (Mdn = 49) and non-URM (Mdn = 34) students, U = 1036.5, P = 0.042, concern for new financial difficulty between URM (Mdn = 50) and non-URM students (Mdn = 7), U = 950.5, P = 0.012, and concern about lack of mental health support from their academic institution between URM (Mdn = 18) and non-URM students (Mdn = 9), U = 1083, P = 0.036 (one-tailed). Discussion: Large-scale crises such as COVID-19 may exacerbate mental health disparities between URM and non-URM students. Medical schools should consider increasing financial and mental health support for URM students in response to these significant adverse events.

Maladaptive Perfectionism, Impostor Phenomenon, and Suicidal Ideation Among Medical Students.

OBJECTIVE: Suicide is a leading cause of death for young adults, and medical students experience elevated rates of suicide and suicidal ideation. The present study uses mediation analysis to explore relationships between suicidal ideation and two dysfunctional mindsets common among medical students: maladaptive perfectionism, high standards accompanied by excessive self-criticism, and impostor phenomenon, pervasive feelings of inadequacy despite evidence of competence and success. METHODS: Two hundred and twenty-six medical students at a single institution completed an online survey which assessed maladaptive perfectionism, impostor phenomenon, and suicidal ideation. After calculating measures of association between all study variables, linear regression was conducted to establish the relationship between maladaptive perfectionism and suicidal ideation. To evaluate whether impostor phenomenon mediated the relationship between maladaptive perfectionism and suicidal ideation as hypothesized, a series of regression models were constructed and the regression coefficients were examined. The statistical significance of the indirect effect, representing the mediated relationship, was tested using bootstrapping. RESULTS: Significant positive associations between maladaptive perfectionism, impostor phenomenon, and suicidal ideation were observed. Impostor phenomenon score was found to mediate the relationship between maladaptive perfectionism and suicidal ideation. CONCLUSIONS: Medical students who exhibit maladaptive perfectionism are at increased risk for feelings of impostor phenomenon, which translates into increased risk for suicide. These results suggest that an intervention targeted at reducing feelings of impostor phenomenon among maladaptive perfectionists may be effective in reducing their higher risk for suicide. However, interventions promoting individual resilience are not sufficient; systemic change is needed to address medicine's "culture of perfection."

Machine learning for profile prediction in genomics.

A recent deluge of publicly available multi-omics data has fueled the development of machine learning methods aimed at investigating important questions in genomics. Although the motivations for these methods vary, a task that is commonly adopted is that of profile prediction, where predictions are made for one or more forms of biochemical activity along the genome, for example, histone modification, chromatin accessibility, or protein binding. In this review, we give an overview of the research works performing profile prediction, define two broad categories of profile prediction tasks, and discuss the types of scientific questions that can be answered in each.

Prioritizing transcriptomic and epigenomic experiments using an optimization strategy that leverages imputed data.

MOTIVATION: Successful science often involves not only performing experiments well, but also choosing well among many possible experiments. In a hypothesis generation setting, choosing an experiment well means choosing an experiment whose results are interesting or novel. In this work, we formalize this selection procedure in the context of genomics and epigenomics data generation. Specifically, we consider the task faced by a scientific consortium such as the National Institutes of Health ENCODE Consortium, whose goal is to characterize all of the functional elements in the human genome. Given a list of possible cell types or tissue types ('biosamples') and a list of possible high-throughput sequencing assays, where at least one experiment has been performed in each biosample and for each assay, we ask 'Which experiments should ENCODE perform next?' RESULTS: We demonstrate how to represent this task as a submodular optimization problem, where the goal is to choose a panel of experiments that maximize the facility location function. A key aspect of our approach is that we use imputed data, rather than experimental data, to directly answer the posed question. We find that, across several evaluations, our method chooses a panel of experiments that span a diversity of biochemical activity. Finally, we propose two modifications of the facility location function, including a novel submodular-supermodular function, that allow incorporation of domain knowledge or constraints into the optimization procedure. AVAILABILITY AND IMPLEMENTATION: Our method is available as a Python package at https://github.com/jmschrei/kiwano and can be installed using the command pip install kiwano. The source code used here and the similarity matrix can be found at http://doi.org/10.5281/zenodo.3708538. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.