DNA methylation in mammalian development and disease.

The DNA methylation field has matured from a phase of discovery and genomic characterization to one seeking deeper functional understanding of how this modification contributes to development, ageing and disease. In particular, the past decade has seen many exciting mechanistic discoveries that have substantially expanded our appreciation for how this generic, evolutionarily ancient modification can be incorporated into robust epigenetic codes. Here, we summarize the current understanding of the distinct DNA methylation landscapes that emerge over the mammalian lifespan and discuss how they interact with other regulatory layers to support diverse genomic functions. We then review the rising interest in alternative patterns found during senescence and the somatic transition to cancer. Alongside advancements in single-cell and long-read sequencing technologies, the collective insights made across these fields offer new opportunities to connect the biochemical and genetic features of DNA methylation to cell physiology, developmental potential and phenotype.

Integrative Analyses of Human Reprogramming Reveal Dynamic Nature of Induced Pluripotency.

Induced pluripotency is a promising avenue for disease modeling and therapy, but the molecular principles underlying this process, particularly in human cells, remain poorly understood due to donor-to-donor variability and intercellular heterogeneity. Here, we constructed and characterized a clonal, inducible human reprogramming system that provides a reliable source of cells at any stage of the process. This system enabled integrative transcriptional and epigenomic analysis across the human reprogramming timeline at high resolution. We observed distinct waves of gene network activation, including the ordered re-activation of broad developmental regulators followed by early embryonic patterning genes and culminating in the emergence of a signature reminiscent of pre-implantation stages. Moreover, complementary functional analyses allowed us to identify and validate novel regulators of the reprogramming process. Altogether, this study sheds light on the molecular underpinnings of induced pluripotency in human cells and provides a robust cell platform for further studies. PAPERCLIP.

Autonomous transposons tune their sequences to ensure somatic suppression.

Transposable elements (TEs) are a major constituent of human genes, occupying approximately half of the intronic space. During pre-messenger RNA synthesis, intronic TEs are transcribed along with their host genes but rarely contribute to the final mRNA product because they are spliced out together with the intron and rapidly degraded. Paradoxically, TEs are an abundant source of RNA-processing signals through which they can create new introns1, and also functional2 or non-functional chimeric transcripts3. The rarity of these events implies the existence of a resilient splicing code that is able to suppress TE exonization without compromising host pre-mRNA processing. Here we show that SAFB proteins protect genome integrity by preventing retrotransposition of L1 elements while maintaining splicing integrity, via prevention of the exonization of previously integrated TEs. This unique dual role is possible because of L1's conserved adenosine-rich coding sequences that are bound by SAFB proteins. The suppressive activity of SAFB extends to tissue-specific, giant protein-coding cassette exons, nested genes and Tigger DNA transposons. Moreover, SAFB also suppresses LTR/ERV elements in species in which they are still active, such as mice and flies. A significant subset of splicing events suppressed by SAFB in somatic cells are activated in the testis, coinciding with low SAFB expression in postmeiotic spermatids. Reminiscent of the division of labour between innate and adaptive immune systems that fight external pathogens, our results uncover SAFB proteins as an RNA-based, pattern-guided, non-adaptive defence system against TEs in the soma, complementing the RNA-based, adaptive Piwi-interacting RNA pathway of the germline.

Self-patterning of human stem cells into post-implantation lineages.

Investigating human development is a substantial scientific challenge due to the technical and ethical limitations of working with embryonic samples. In the face of these difficulties, stem cells have provided an alternative to experimentally model inaccessible stages of human development in vitro1-13. Here we show that human pluripotent stem cells can be triggered to self-organize into three-dimensional structures that recapitulate some key spatiotemporal events of early human post-implantation embryonic development. Our system reproducibly captures spontaneous differentiation and co-development of embryonic epiblast-like and extra-embryonic hypoblast-like lineages, establishes key signalling hubs with secreted modulators and undergoes symmetry breaking-like events. Single-cell transcriptomics confirms differentiation into diverse cell states of the perigastrulating human embryo14,15 without establishing placental cell types, including signatures of post-implantation epiblast, amniotic ectoderm, primitive streak, mesoderm, early extra-embryonic endoderm, as well as initial yolk sac induction. Collectively, our system captures key features of human embryonic development spanning from Carnegie stage16 4-7, offering a reproducible, tractable and scalable experimental platform to understand the basic cellular and molecular mechanisms that underlie human development, including new opportunities to dissect congenital pathologies with high throughput.

Molecular features of cellular reprogramming and development.

Differentiating somatic cells are progressively restricted to specialized functions during ontogeny, but they can be experimentally directed to form other cell types, including those with complete embryonic potential. Early nuclear reprogramming methods, such as somatic cell nuclear transfer (SCNT) and cell fusion, posed significant technical hurdles to precise dissection of the regulatory programmes governing cell identity. However, the discovery of reprogramming by ectopic expression of a defined set of transcription factors, known as direct reprogramming, provided a tractable platform to uncover molecular characteristics of cellular specification and differentiation, cell type stability and pluripotency. We discuss the control and maintenance of cellular identity during developmental transitions as they have been studied using direct reprogramming, with an emphasis on transcriptional and epigenetic regulation.

DOT1L promotes spermatid differentiation by regulating expression of genes required for histone-to-protamine replacement.

Unique chromatin remodeling factors orchestrate dramatic changes in nuclear morphology during differentiation of the mature sperm head. A crucial step in this process is histone-to-protamine exchange, which must be executed correctly to avoid sperm DNA damage, embryonic lethality and male sterility. Here, we define an essential role for the histone methyltransferase DOT1L in the histone-to-protamine transition. We show that DOT1L is abundantly expressed in mouse meiotic and postmeiotic germ cells, and that methylation of histone H3 lysine 79 (H3K79), the modification catalyzed by DOT1L, is enriched in developing spermatids in the initial stages of histone replacement. Elongating spermatids lacking DOT1L fail to fully replace histones and exhibit aberrant protamine recruitment, resulting in deformed sperm heads and male sterility. Loss of DOT1L results in transcriptional dysregulation coinciding with the onset of histone replacement and affecting genes required for histone-to-protamine exchange. DOT1L also deposits H3K79me2 and promotes accumulation of elongating RNA Polymerase II at the testis-specific bromodomain gene Brdt. Together, our results indicate that DOT1L is an important mediator of transcription during spermatid differentiation and an indispensable regulator of male fertility.

Reference Maps of human ES and iPS cell variation enable high-throughput characterization of pluripotent cell lines.

The developmental potential of human pluripotent stem cells suggests that they can produce disease-relevant cell types for biomedical research. However, substantial variation has been reported among pluripotent cell lines, which could affect their utility and clinical safety. Such cell-line-specific differences must be better understood before one can confidently use embryonic stem (ES) or induced pluripotent stem (iPS) cells in translational research. Toward this goal we have established genome-wide reference maps of DNA methylation and gene expression for 20 previously derived human ES lines and 12 human iPS cell lines, and we have measured the in vitro differentiation propensity of these cell lines. This resource enabled us to assess the epigenetic and transcriptional similarity of ES and iPS cells and to predict the differentiation efficiency of individual cell lines. The combination of assays yields a scorecard for quick and comprehensive characterization of pluripotent cell lines.

Epigenetic regulator function through mouse gastrulation.

During ontogeny, proliferating cells become restricted in their fate through the combined action of cell-type-specific transcription factors and ubiquitous epigenetic machinery, which recognizes universally available histone residues or nucleotides in a context-dependent manner1,2. The molecular functions of these regulators are generally well understood, but assigning direct developmental roles to them is hampered by complex mutant phenotypes that often emerge after gastrulation3,4. Single-cell RNA sequencing and analytical approaches have explored this highly conserved, dynamic period across numerous model organisms5-8, including mouse9-18. Here we advance these strategies using a combined zygotic perturbation and single-cell RNA-sequencing platform in which many mutant mouse embryos can be assayed simultaneously, recovering robust  morphological and transcriptional information across a panel of ten essential regulators. Deeper analysis of central Polycomb repressive complex (PRC) 1 and 2 components indicates substantial cooperativity, but distinguishes a dominant role for PRC2 in restricting the germline. Moreover, PRC mutant phenotypes emerge after gross epigenetic and transcriptional changes within the initial conceptus prior to gastrulation. Our experimental framework may eventually lead to a fully quantitative view of how cellular diversity emerges using an identical genetic template and from a single totipotent cell.

Indomethacin with or without prophylactic pancreatic stent placement to prevent pancreatitis after ERCP: a randomised non-inferiority trial.

BACKGROUND: The combination of rectally administered indomethacin and placement of a prophylactic pancreatic stent is recommended to prevent pancreatitis after endoscopic retrograde cholangiopancreatography (ERCP) in high-risk patients. Preliminary evidence suggests that the use of indomethacin might eliminate or substantially reduce the need for stent placement, a technically complex, costly, and potentially harmful intervention. METHODS: In this randomised, non-inferiority trial conducted at 20 referral centres in the USA and Canada, patients (aged ≥18 years) at high risk for post-ERCP pancreatitis were randomly assigned (1:1) to receive rectal indomethacin alone or the combination of indomethacin plus a prophylactic pancreatic stent. Patients, treating clinicians, and outcomes assessors were masked to study group assignment. The primary outcome was post-ERCP pancreatitis. To declare non-inferiority, the upper bound of the two-sided 95% CI for the difference in post-ERCP pancreatitis (indomethacin alone minus indomethacin plus stent) would have to be less than 5% (non-inferiority margin) in both the intention-to-treat and per-protocol populations. This trial is registered with ClinicalTrials.gov (NCT02476279), and is complete. FINDINGS: Between Sept 17, 2015, and Jan 25, 2023, a total of 1950 patients were randomly assigned. Post-ERCP pancreatitis occurred in 145 (14·9%) of 975 patients in the indomethacin alone group and in 110 (11·3%) of 975 in the indomethacin plus stent group (risk difference 3·6%; 95% CI 0·6-6·6; p=0·18 for non-inferiority). A post-hoc intention-to-treat analysis of the risk difference between groups showed that indomethacin alone was inferior to the combination of indomethacin plus prophylactic stent (p=0·011). The relative benefit of stent placement was generally consistent across study subgroups but appeared more prominent among patients at highest risk for pancreatitis. Safety outcomes (serious adverse events, intensive care unit admission, and hospital length of stay) did not differ between groups. INTERPRETATION: For preventing post-ERCP pancreatitis in high-risk patients, a strategy of indomethacin alone was not as effective as a strategy of indomethacin plus prophylactic pancreatic stent placement. These results support prophylactic pancreatic stent placement in addition to rectal indomethacin administration in high-risk patients, in accordance with clinical practice guidelines. FUNDING: US National Institutes of Health.

Enhanced Sampling with Machine Learning.

Molecular dynamics (MD) enables the study of physical systems with excellent spatiotemporal resolution but suffers from severe timescale limitations. To address this, enhanced sampling methods have been developed to improve the exploration of configurational space. However, implementing these methods is challenging and requires domain expertise. In recent years, integration of machine learning (ML) techniques into different domains has shown promise, prompting their adoption in enhanced sampling as well. Although ML is often employed in various fields primarily due to its data-driven nature, its integration with enhanced sampling is more natural with many common underlying synergies. This review explores the merging of ML and enhanced MD by presenting different shared viewpoints. It offers a comprehensive overview of this rapidly evolving field, which can be difficult to stay updated on. We highlight successful strategies such as dimensionality reduction, reinforcement learning, and flow-based methods. Finally, we discuss open problems at the exciting ML-enhanced MD interface.

DOT1L bridges transcription and heterochromatin formation at mammalian pericentromeres.

Repetitive DNA elements are packaged in heterochromatin, but many require bursts of transcription to initiate and maintain long-term silencing. The mechanisms by which these heterochromatic genome features are transcribed remain largely unknown. Here, we show that DOT1L, a conserved histone methyltransferase that modifies lysine 79 of histone H3 (H3K79), has a specialized role in transcription of major satellite repeats to maintain pericentromeric heterochromatin and genome stability. We find that H3K79me3 is selectively enriched relative to H3K79me2 at repetitive elements in mouse embryonic stem cells (mESCs), that DOT1L loss compromises pericentromeric satellite transcription, and that this activity involves possible coordination between DOT1L and the chromatin remodeler SMARCA5. Stimulation of transcript production from pericentromeric repeats by DOT1L participates in stabilization of heterochromatin structures in mESCs and cleavage-stage embryos and is required for preimplantation viability. Our findings uncover an important role for DOT1L as a bridge between transcriptional activation of repeat elements and heterochromatin stability, advancing our understanding of how genome integrity is maintained and how chromatin state is set up during early development.

Molecular recording of mammalian embryogenesis.

Ontogeny describes the emergence of complex multicellular organisms from single totipotent cells. This field is particularly challenging in mammals, owing to the indeterminate relationship between self-renewal and differentiation, variation in progenitor field sizes, and internal gestation in these animals. Here we present a flexible, high-information, multi-channel molecular recorder with a single-cell readout and apply it as an evolving lineage tracer to assemble mouse cell-fate maps from fertilization through gastrulation. By combining lineage information with single-cell RNA sequencing profiles, we recapitulate canonical developmental relationships between different tissue types and reveal the nearly complete transcriptional convergence of endodermal cells of extra-embryonic and embryonic origins. Finally, we apply our cell-fate maps to estimate the number of embryonic progenitor cells and their degree of asymmetric partitioning during specification. Our approach enables massively parallel, high-resolution recording of lineage and other information in mammalian systems, which will facilitate the construction of a quantitative framework for understanding developmental processes.

Penetrant-induced plasticization in microporous polymer membranes.

Penetrant-induced plasticization has prevented the industrial deployment of many polymers for membrane-based gas separations. With the advent of microporous polymers, new structural design features and unprecedented property sets are now accessible under controlled laboratory conditions, but property sets can often deteriorate due to plasticization. Therefore, a critical understanding of the origins of plasticization in microporous polymers and the development of strategies to mitigate this effect are needed to advance this area of research. Herein, an integrative discussion is provided on seminal plasticization theory and gas transport models, and these theories and models are compared to an exhaustive database of plasticization characteristics of microporous polymers. Correlations between specific polymer properties and plasticization behavior are presented, including analyses of plasticization pressures from pure-gas permeation tests and mixed-gas permeation tests for pure polymers and composite films. Finally, an evaluation of common and current state-of-the-art strategies to mitigate plasticization is provided along with suggestions for future directions of fundamental and applied research on the topic.

Transferrin Receptor Is Necessary for Proper Oligodendrocyte Iron Homeostasis and Development.

To test the hypothesis that the transferrin (Tf) cycle has unique importance for oligodendrocyte development and function, we disrupted the expression of the Tf receptor (Tfr) gene in oligodendrocyte progenitor cells (OPCs) on mice of either sex using the Cre/lox system. This ablation results in the elimination of iron incorporation via the Tf cycle but leaves other Tf functions intact. Mice lacking Tfr, specifically in NG2 or Sox10-positive OPCs, developed a hypomyelination phenotype. Both OPC differentiation and myelination were affected, and Tfr deletion resulted in impaired OPC iron absorption. Specifically, the brains of Tfr cKO animals presented a reduction in the quantity of myelinated axons, as well as fewer mature oligodendrocytes. In contrast, the ablation of Tfr in adult mice affected neither mature oligodendrocytes nor myelin synthesis. RNA-seq analysis performed in Tfr cKO OPCs revealed misregulated genes involved in OPC maturation, myelination, and mitochondrial activity. Tfr deletion in cortical OPCs also disrupted the activity of the mTORC1 signaling pathway, epigenetic mechanisms critical for gene transcription and the expression of structural mitochondrial genes. RNA-seq studies were additionally conducted in OPCs in which iron storage was disrupted by deleting the ferritin heavy chain. These OPCs display abnormal regulation of genes associated with iron transport, antioxidant activity, and mitochondrial activity. Thus, our results indicate that the Tf cycle is central for iron homeostasis in OPCs during postnatal development and suggest that both iron uptake via Tfr and iron storage in ferritin are critical for energy production, mitochondrial activity, and maturation of postnatal OPCs.SIGNIFICANCE STATEMENT By knocking-out transferrin receptor (Tfr) specifically in oligodendrocyte progenitor cells (OPCs), we have established that iron incorporation via the Tf cycle is key for OPC iron homeostasis and for the normal function of these cells during the postnatal development of the CNS. Moreover, RNA-seq analysis indicated that both Tfr iron uptake and ferritin iron storage are critical for proper OPC mitochondrial activity, energy production, and maturation.

Incidence, Predictors, and Outcomes of Clinically Significant Post-ERCP Bleeding: a Contemporary Multi-center Study.

BACKGROUND AIMS: Clinically significant post-endoscopic retrograde cholangiopancreatography (ERCP) bleeding (CSPEB) is common. Contemporary estimates of risk are lacking. We aimed to identify risk factors for and outcomes following CSPEB. METHODS: We analyzed multi-center prospective ERCP data between 2018-2023 with 30-day follow-up. The primary outcome was CSPEB, defined as hematemesis, melena, or hematochezia resulting in: hemoglobin drop ≥20 g/L or transfusion and/or endoscopy to evaluate suspected bleeding, and/or unplanned healthcare visitation and/or prolongation of existing admission. Firth logistic regression was employed. P-values <0.05 were significant, with odds ratios (ORs) and 95% confidence intervals reported. RESULTS: CSPEB occurred following 129 (1.5%) of 8,517 ERCPs (mean onset 3.2 days), with 110 of 4,849 events (2.3%) occurring following higher-risk interventions (sphincterotomy, sphincteroplasty, pre-cut sphincterotomy, and/or needle-knife access). CSPEB patients required endoscopy and transfusion in 86.0% and 53.5% of cases, respectively, with three cases (2.3%) being fatal. P2Y12 inhibitors were held for a median of 4 days (IQR 4) prior to higher-risk ERCP. Following higher-risk interventions, P2Y12 inhibitors (OR 3.33, 1.26-7.74), warfarin (OR 8.54, 3.32-19.81), dabigatran (OR 13.40, 2.06-59.96), rivaroxaban (OR 7.42, 3.43-15.24) and apixaban (OR 4.16, 1.99-8.20) were associated with CSPEB. Significant intraprocedural bleeding post sphincterotomy (OR 2.32, 1.06-4.60), but not post sphincteroplasty, was also associated. Concomitant cardiorespiratory events occurred more frequently within 30 days following CSPEB (OR 12.71, 4.75-32.54). CONCLUSIONS: Risks of antiplatelet-related CSPEB may be underestimated by endoscopists based on observations of suboptimal holding before higher-risk ERCP. Appropriate periprocedural antithrombotic management is essential and could represent novel quality initiative targets.

Technical Factors Associated With the Benefit of Prophylactic Pancreatic Stent Placement During High-Risk Endoscopic Retrograde Cholangiopancreatography: A Secondary Analysis of the SVI Trial Data Set.

INTRODUCTION: Prophylactic pancreatic stent placement (PSP) is effective for preventing pancreatitis after endoscopic retrograde cholangiopancreatography (ERCP) in high-risk cases, but the optimal technical approach to this intervention remains uncertain. METHODS: In this secondary analysis of 787 clinical trial patients who underwent successful stent placement, we studied the impact of (i) whether pancreatic wire access was achieved for the sole purpose of PSP or naturally during the conduct of the case, (ii) the amount of effort expended on PSP, (iii) stent length, (iv) stent diameter, and (v) guidewire caliber. We used logistic regression models to examine the adjusted association between each technical factor and post-ERCP pancreatitis (PEP). RESULTS: Ninety-one of the 787 patients experienced PEP. There was no clear association between PEP and whether pancreatic wire access was achieved for the sole purpose of PSP (vs occurring naturally; odds ratio [OR] 0.82, 95% confidence interval [CI] 0.37-1.84), whether substantial effort expended on stent placement (vs nonsubstantial effort; OR 1.58, 95% CI 0.73-3.45), stent length (>5 vs ≤5 cm; OR 1.01, 95% CI 0.63-1.61), stent diameter (≥5 vs <5 Fr; OR 1.13, 95% CI 0.65-1.96), or guidewire caliber (0.035 vs 0.025 in; 0.83, 95% CI 0.49-1.41). DISCUSSION: The 5 modifiable technical factors studied in this secondary analysis of large-scale randomized trial data did not appear to have a strong impact on the benefit of prophylactic PSP in preventing PEP after high-risk ERCP. Within the limitations of post hoc subgroup analysis, these findings may have important implications in procedural decision making and suggest that the benefit of PSP is robust to variations in technical approach.

The Impact of Difficult Biliary Cannulation on Post-ERCP Pancreatitis: A Secondary Analysis of the Stent versus Indomethacin Trial Dataset.

BACKGROUND AND AIMS: Difficult biliary cannulation (DBC) is a known risk factor for developing post-ERCP pancreatitis (PEP). To better understand how DBC increases PEP risk, we examined the interplay between technical aspects of DBC and known PEP risk factors. METHODS: This was a secondary analysis of a multicenter, randomized controlled trial comparing rectal indomethacin alone with the combination of rectal indomethacin and prophylactic pancreatic duct (PD) stent placement for PEP prophylaxis in high-risk patients. Participants were categorized into 3 groups: 1) DBC with high pre-procedure risk for PEP, 2) DBC without high pre-procedure risk, and 3) non-DBC at high pre-procedure risk. RESULTS: In all, 1601 (84.1%) participants experienced DBC, which required a mean of 12 (SD 10) cannulation attempts and mean duration of 14.7 minutes (SD 14.9). PEP rate was highest (20.7%) in DBC with high pre-procedure risk, followed by non-DBC with high pre-procedure risk (13.5%) and then DBC without high pre-procedure risk (8.8%). Increasing number of PD-wire passages (aOR:1.97, 95% CI:1.25-3.1) was associated with PEP in DBC, but PD injection, pancreatic sphincterotomy and number of cannulation attempts were not associated with PEP. Combining indomethacin with PD stenting lowered PEP risk (aOR:0.61, 95% CI:0.44-0.84) in DBCs. This protective effect was evident in up to at least 4 PD wire passages. CONCLUSIONS: DBC confers higher PEP risk in additive fashion to pre-procedural risk factors. PD wire passages appear to add the greatest PEP risk in DBCs, but combining indomethacin with PD stenting reduces this risk, even with increasing PD wire passages.

NCCN Guidelines® Insights: Kidney Cancer, Version 2.2024.

The NCCN Guidelines for Kidney Cancer provide multidisciplinary recommendations for diagnostic workup, staging, and treatment of patients with renal cell carcinoma (RCC). These NCCN Guidelines Insights focus on the systemic therapy options for patients with advanced RCC and summarize the new clinical data evaluated by the NCCN panel for the recommended therapies in Version 2.2024 of the NCCN Guidelines for Kidney Cancer.

Early Estimates of Updated 2023-2024 (Monovalent XBB.1.5) COVID-19 Vaccine Effectiveness Against Symptomatic SARS-CoV-2 Infection Attributable to Co-Circulating Omicron Variants Among Immunocompetent Adults - Increasing Community Access to Testing Program, United States, September 2023-January 2024.

On September 12, 2023, CDC's Advisory Committee on Immunization Practices recommended updated 2023-2024 (updated) COVID-19 vaccination with a monovalent XBB.1.5-derived vaccine for all persons aged ≥6 months to prevent COVID-19, including severe disease. During fall 2023, XBB lineages co-circulated with JN.1, an Omicron BA.2.86 lineage that emerged in September 2023. These variants have amino acid substitutions that might increase escape from neutralizing antibodies. XBB lineages predominated through December 2023, when JN.1 became predominant in the United States. Reduction or failure of spike gene (S-gene) amplification (i.e., S-gene target failure [SGTF]) in real-time reverse transcription-polymerase chain reaction testing is a time-dependent, proxy indicator of JN.1 infection. Data from the Increasing Community Access to Testing SARS-CoV-2 pharmacy testing program were analyzed to estimate updated COVID-19 vaccine effectiveness (VE) (i.e., receipt versus no receipt of updated vaccination) against symptomatic SARS-CoV-2 infection, including by SGTF result. Among 9,222 total eligible tests, overall VE among adults aged ≥18 years was 54% (95% CI = 46%-60%) at a median of 52 days after vaccination. Among 2,199 tests performed at a laboratory with SGTF testing, VE 60-119 days after vaccination was 49% (95% CI = 19%-68%) among tests exhibiting SGTF and 60% (95% CI = 35%-75%) among tests without SGTF. Updated COVID-19 vaccines provide protection against symptomatic infection, including against currently circulating lineages. CDC will continue monitoring VE, including for expected waning and against severe disease. All persons aged ≥6 months should receive an updated COVID-19 vaccine dose.

Graph Attention Site Prediction (GrASP): Identifying Druggable Binding Sites Using Graph Neural Networks with Attention.

Identifying and discovering druggable protein binding sites is an important early step in computer-aided drug discovery, but it remains a difficult task where most campaigns rely on a priori knowledge of binding sites from experiments. Here, we present a binding site prediction method called Graph Attention Site Prediction (GrASP) and re-evaluate assumptions in nearly every step in the site prediction workflow from data set preparation to model evaluation. GrASP is able to achieve state-of-the-art performance at recovering binding sites in PDB structures while maintaining a high degree of precision which will minimize wasted computation in downstream tasks such as docking and free energy perturbation.