Boltzmann Model Predicts Glycan Structures from Lectin Binding.

Glycans are complex oligosaccharides that are involved in many diseases and biological processes. Unfortunately, current methods for determining glycan composition and structure (glycan sequencing) are laborious and require a high level of expertise. Here, we assess the feasibility of sequencing glycans based on their lectin binding fingerprints. By training a Boltzmann model on lectin binding data, we predict the approximate structures of 88 ± 7% of N-glycans and 87 ± 13% of O-glycans in our test set. We show that our model generalizes well to the pharmaceutically relevant case of Chinese hamster ovary (CHO) cell glycans. We also analyze the motif specificity of a wide array of lectins and identify the most and least predictive lectins and glycan features. These results could help streamline glycoprotein research and be of use to anyone using lectins for glycobiology.

Consensus statements on the current landscape of artificial intelligence applications in endoscopy, addressing roadblocks, and advancing artificial intelligence in gastroenterology.

BACKGROUND AND AIMS: The American Society for Gastrointestinal Endoscopy (ASGE) AI Task Force along with experts in endoscopy, technology space, regulatory authorities, and other medical subspecialties initiated a consensus process that analyzed the current literature, highlighted potential areas, and outlined the necessary research in artificial intelligence (AI) to allow a clearer understanding of AI as it pertains to endoscopy currently. METHODS: A modified Delphi process was used to develop these consensus statements. RESULTS: Statement 1: Current advances in AI allow for the development of AI-based algorithms that can be applied to endoscopy to augment endoscopist performance in detection and characterization of endoscopic lesions. Statement 2: Computer vision-based algorithms provide opportunities to redefine quality metrics in endoscopy using AI, which can be standardized and can reduce subjectivity in reporting quality metrics. Natural language processing-based algorithms can help with the data abstraction needed for reporting current quality metrics in GI endoscopy effortlessly. Statement 3: AI technologies can support smart endoscopy suites, which may help optimize workflows in the endoscopy suite, including automated documentation. Statement 4: Using AI and machine learning helps in predictive modeling, diagnosis, and prognostication. High-quality data with multidimensionality are needed for risk prediction, prognostication of specific clinical conditions, and their outcomes when using machine learning methods. Statement 5: Big data and cloud-based tools can help advance clinical research in gastroenterology. Multimodal data are key to understanding the maximal extent of the disease state and unlocking treatment options. Statement 6: Understanding how to evaluate AI algorithms in the gastroenterology literature and clinical trials is important for gastroenterologists, trainees, and researchers, and hence education efforts by GI societies are needed. Statement 7: Several challenges regarding integrating AI solutions into the clinical practice of endoscopy exist, including understanding the role of human-AI interaction. Transparency, interpretability, and explainability of AI algorithms play a key role in their clinical adoption in GI endoscopy. Developing appropriate AI governance, data procurement, and tools needed for the AI lifecycle are critical for the successful implementation of AI into clinical practice. Statement 8: For payment of AI in endoscopy, a thorough evaluation of the potential value proposition for AI systems may help guide purchasing decisions in endoscopy. Reliable cost-effectiveness studies to guide reimbursement are needed. Statement 9: Relevant clinical outcomes and performance metrics for AI in gastroenterology are currently not well defined. To improve the quality and interpretability of research in the field, steps need to be taken to define these evidence standards. Statement 10: A balanced view of AI technologies and active collaboration between the medical technology industry, computer scientists, gastroenterologists, and researchers are critical for the meaningful advancement of AI in gastroenterology. CONCLUSIONS: The consensus process led by the ASGE AI Task Force and experts from various disciplines has shed light on the potential of AI in endoscopy and gastroenterology. AI-based algorithms have shown promise in augmenting endoscopist performance, redefining quality metrics, optimizing workflows, and aiding in predictive modeling and diagnosis. However, challenges remain in evaluating AI algorithms, ensuring transparency and interpretability, addressing governance and data procurement, determining payment models, defining relevant clinical outcomes, and fostering collaboration between stakeholders. Addressing these challenges while maintaining a balanced perspective is crucial for the meaningful advancement of AI in gastroenterology.

LeGenD: determining N-glycoprofiles using an explainable AI-leveraged model with lectin profiling.

Glycosylation affects many vital functions of organisms. Therefore, its surveillance is critical from basic science to biotechnology, including biopharmaceutical development and clinical diagnostics. However, conventional glycan structure analysis faces challenges with throughput and cost. Lectins offer an alternative approach for analyzing glycans, but they only provide glycan epitopes and not full glycan structure information. To overcome these limitations, we developed LeGenD, a lectin and AI-based approach to predict N-glycan structures and determine their relative abundance in purified proteins based on lectin-binding patterns. We trained the LeGenD model using 309 glycoprofiles from 10 recombinant proteins, produced in 30 glycoengineered CHO cell lines. Our approach accurately reconstructed experimentally-measured N-glycoprofiles of bovine Fetuin B and IgG from human sera. Explanatory AI analysis with SHapley Additive exPlanations (SHAP) helped identify the critical lectins for glycoprofile predictions. Our LeGenD approach thus presents an alternative approach for N-glycan analysis.

Safety, Efficacy and Clinical Utility of the 5.1mm EndoRotor Powered Debridement Catheter for Treatment of Walled-Off Pancreatic Necrosis.

BACKGROUND AND AIMS: Direct endoscopic necrosectomy (DEN) is a recommended strategy for treatment of walled-off-necrosis (WON). DEN uses a variety of devices including the EndoRotor (Interscope, Inc.) debridement catheter. Recently, a 5.1 mm EndoRotor with increased chamber size and rate of tissue removal was introduced. The aim of this study was to assess the efficacy and safety of this device. METHODS: A multi-center cohort study was conducted at eight institutions including patients who underwent DEN with the 5.1 mm EndoRotor. The primary outcome was the number of DEN sessions needed for WON resolution. Secondary outcomes included the average percent reduction in solid WON debris and decrease in WON area per session, total time spent performing EndoRotor therapy for WON resolution, and adverse events. RESULTS: 64 procedures in 41 patients were included. For patients in which the 5.1 mm EndoRotor catheter was the sole therapeutic modality, an average of 1.6 DEN sessions resulted in WON resolution with an average cumulative time of 85.5 minutes. Of the 21 procedures with data regarding percent of solid debris, the average reduction was 85% +/- 23% per session. Of the 19 procedures with data regarding WON area, the mean area significantly decreased from 97.6 +/- 72.0 cm2 to 27.1 +/- 35.5 cm2 (p<0.001) per session. Adverse events included two intra-procedural LAMS dislodgements managed endoscopically and three perforations none of which were related to EndoRotor. Bleeding was reported in seven cases, none required embolic or surgical therapy and two required blood transfusions. CONCLUSIONS: This is the first multi-center retrospective study to investigate the efficacy and safety of the 5.1 mm EndoRotor catheter for WON. Results from this study showed an average of 1.6 DEN sessions were needed to achieve WON resolution with an 85% single session reduction in solid debris and a 70% single session decrease in WON area with minimal adverse events.

LipidSIM: Inferring mechanistic lipid biosynthesis perturbations from lipidomics with a flexible, low-parameter, Markov modeling framework.

Lipid metabolism is a complex and dynamic system involving numerous enzymes at the junction of multiple metabolic pathways. Disruption of these pathways leads to systematic dyslipidemia, a hallmark of many pathological developments, such as nonalcoholic steatohepatitis and diabetes. Recent advances in computational tools can provide insights into the dysregulation of lipid biosynthesis, but limitations remain due to the complexity of lipidomic data, limited knowledge of interactions among involved enzymes, and technical challenges in standardizing across different lipid types. Here, we present a low-parameter, biologically interpretable framework named Lipid Synthesis Investigative Markov model (LipidSIM), which models and predicts the source of perturbations in lipid biosynthesis from lipidomic data. LipidSIM achieves this by accounting for the interdependency between the lipid species via the lipid biosynthesis network and generates testable hypotheses regarding changes in lipid biosynthetic reactions. This feature allows the integration of lipidomics with other omics types, such as transcriptomics, to elucidate the direct driving mechanisms of altered lipidomes due to treatments or disease progression. To demonstrate the value of LipidSIM, we first applied it to hepatic lipidomics following Keap1 knockdown and found that changes in mRNA expression of the lipid pathways were consistent with the LipidSIM-predicted fluxes. Second, we used it to study lipidomic changes following intraperitoneal injection of CCl4 to induce fast NAFLD/NASH development and the progression of fibrosis and hepatic cancer. Finally, to show the power of LipidSIM for classifying samples with dyslipidemia, we used a Dgat2-knockdown study dataset. Thus, we show that as it demands no a priori knowledge of enzyme kinetics, LipidSIM is a valuable and intuitive framework for extracting biological insights from complex lipidomic data.

Mechanotransduction-induced interplay between phospholamban and yes-activated protein induces smooth muscle cell hypertrophy.

The gastrointestinal system is a hollow organ affected by fibrostenotic diseases that cause volumetric compromise of the lumen via smooth muscle hypertrophy and fibrosis. Many of the driving mechanisms remain unclear. Yes-associated protein-1 (YAP) is a critical mechanosensory transcriptional regulator that mediates cell hypertrophy in response to elevated extracellular rigidity. In the type 2 inflammatory disorder, eosinophilic esophagitis (EoE), phospholamban (PLN) can induce smooth muscle cell hypertrophy. We used EoE as a disease model for understanding a mechanistic pathway in which PLN and YAP interact in response to rigid extracellular substrate to induce smooth muscle cell hypertrophy. PLN-induced YAP nuclear sequestration in a feed-forward loop caused increased cell size in response to a rigid substrate. This mechanism of rigidity sensing may have previously unappreciated clinical implications for PLN-expressing hollow systems such as the esophagus and heart.

Colonic-enteric lumen-apposing metal stents: a promising and safe alternative for endoscopic management of small-bowel obstruction.

BACKGROUND AND AIMS: Lumen-apposing metal stents (LAMSs) have revolutionized the treatment of various gastroenterologic conditions that previously required surgery. The use of LAMSs for the management of small-bowel obstruction (SBO) involves EUS-guided coloenterostomy (EUS-CE) between the colon and a dilated loop of the small intestine proximal to the point of obstruction. This procedure is potentially beneficial for patients with malignant SBO who are poor surgical candidates. METHODS: A retrospective cohort study was conducted at 2 tertiary care hospitals. Patients who underwent EUS-CE for SBO were identified, and data regarding patient demographics, indication for the procedure, location of the obstruction, procedural details, and adverse events were collected. The primary outcome was technical success of the procedure. Secondary outcomes were clinical success, resolution of symptoms, ability to tolerate enteral nutrition, and adverse events. RESULTS: Twenty-six patients who underwent the EUS-CE procedure were included. Technical success was achieved in all 26 patients, clinical success (resolution of obstructive symptoms) was achieved in 92.3% of patients (24/26), and the ability to resume enteral nutrition in 84.6% (22/26). Adverse events occurred in 4 patients (15.4%) and included bleeding (1/26), diarrhea (2/26), and postprocedure sepsis (1/26). Patients were followed for a mean of 54.8 days (range, 2-190). CONCLUSIONS: This study highlights that EUS-CE with LAMSs can be performed with high technical and clinical success for the management of SBO, particularly in patients with malignant obstructions who are not suitable candidates for surgical interventions. Further research with larger sample sizes will be essential to substantiate its efficacy and safety.

A Boltzmann model predicts glycan structures from lectin binding.

Glycans are complex oligosaccharides involved in many diseases and biological processes. Unfortunately, current methods for determining glycan composition and structure (glycan sequencing) are laborious and require a high level of expertise. Here, we assess the feasibility of sequencing glycans based on their lectin binding fingerprints. By training a Boltzmann model on lectin binding data, we predict the approximate structures of 88 ± 7% of N-glycans and 87 ± 13% of O-glycans in our test set. We show that our model generalizes well to the pharmaceutically relevant case of Chinese Hamster Ovary (CHO) cell glycans. We also analyze the motif specificity of a wide array of lectins and identify the most and least predictive lectins and glycan features. These results could help streamline glycoprotein research and be of use to anyone using lectins for glycobiology.

Randomized trial of gastric and colorectal endoscopic submucosal dissection defect closure comparing a novel through-the-scope suturing system with an over-the-scope suturing system (with video).

BACKGROUND AND AIMS: Mucosal closure adds time but reduces adverse events associated with endoscopic submucosal dissection (ESD). We aimed to assess the closure time (CT), technical success, and cost-effectiveness between a novel through-the-scope helix tack suture system (TTSS) and the over-the-scope suturing system (OTSS). METHODS: In this single-center, prospective, randomized trial, all patients undergoing ESD with anticipated closure were randomized 1:1 to TTSS (study group) or OTSS (control group). Primary outcomes were CT and overall CT (OCT; CT + setup time). Secondary outcomes were rates of technical success, adverse events, and cost-effectiveness. RESULTS: Forty patients were randomized to OTSS (n = 20) or TTSS (n = 20). OTSS and TTSS groups were similar with respect to age, gender, proportion of colorectal polyps, proximal colon polyps, and mean size of the resected specimen (40.9 mm vs 40.4 mm). The mean CT was 18.4 minutes for OTSS and 23.3 minutes for TTSS (P = .36). The mean OCT was 32 minutes for OTSS and 39.5 minutes for TTSS (P = .36). Closure with a primary device was successful in 17 cases (85%) with OTSS and 18 cases (90%) with TTSS (P = .63). No closure-related intraprocedural adverse events or delayed perforations were noted. Mean cost of closure was significantly lower in the TTSS group for lesions <35 mm (P = .008). CONCLUSIONS: TTSS was not found to be superior to OTSS with respect to CT and technical and clinical success for closure of gastric and colorectal ESD defects. TTSS is more cost-effective for closure of lesions <35 mm. (Clinical trial registration number: NCT04925271.).

Identification of sentinel lymph nodes in esophageal cancer patients using contrast-enhanced EUS with peritumoral injections.

Objectives: The objective of this pilot study was to compare the performance of contrast-enhanced EUS (CE-EUS)-guided fine-needle aspiration (FNA) with EUS-FNA for lymph node (LN) staging in esophageal cancer. Methods: Thirty-seven subjects with esophageal cancer undergoing EUS staging were enrolled, and 30 completed this institutional review board-approved study. A Prosound F75 US system (Hitachi Medical Systems, Tokyo, Japan) with harmonic contrast imaging software and GF-UCT180 curvilinear endoscope (Olympus, Tokyo, Japan) was utilized. All LNs identified by standard EUS were first noted. Sonazoid (dose: 1 mL; GE Healthcare, Oslo, Norway) was administered peritumorally, and all enhanced LNs were recorded. Fine-needle aspiration was performed on LNs considered suspicious by EUS alone, as well as LNs enhanced on CE-EUS. Performance of each modality was compared using FNA cytology as reference standard. Results: A total of 132 LNs were detected with EUS, of which 59 showed enhancement on CE-EUS. Fifty-three LNs underwent FNA, and 22 LNs were determined to be malignant. Among the latter, 10 were considered suspicious by EUS, whereas the other 12 LNs underwent FNA only because of CE-EUS enhancement. Contrast-enhanced EUS showed enhancement in 19 of the 22 malignant LNs. The rate of metastatic node identification from EUS was 45% (10/22), and it was 86% (19/22; P = 0.008) for CE-EUS. Eight subjects (8/30 [27% of study total]) had nodal status upgraded by the addition of CE-EUS, which influenced LN staging and clinical management. Conclusions: Fine-needle aspiration of LNs identified by CE-EUS may increase metastasis positive rate by ruling out LNs not associated with the tumor drainage pattern. In addition, CE-EUS seems to identify more metastatic LNs that would not be biopsied under the standard EUS criteria.

EUS-guided Gastroenterostomy: A Multicenter International Study Comparing Benign and Malignant Diseases.

BACKGROUND: Endoscopic ultrasound (EUS)-guided gastroenterostomy (EUS-GE) is a minimally invasive therapy for patients with gastric outlet obstruction without the risks of surgical bypass and the limited long-term efficacy of enteral self-expanding metal stent placement. However, due to its novelty, there is a lack of significant data comparing long-term outcomes of patients with EUS-GE, based on the underlying disease. In this study, we compare outcomes of EUS-GE on benign versus malignant indications. METHODS: Consecutive patients from 12 international, tertiary care centers who underwent EUS-GE over 3 years were extracted in a retrospective registry. Demographic characteristics, procedure-related information and follow-up data was collected. Primary outcome was the rate of adverse events associated with EUS-GE and the comparison of the rate of adverse events in benign versus malignant diseases. Secondary outcomes included technical and clinical success as well as hospitalization admission. RESULTS: A total of 103 patients were included: 72 malignant and 31 benign. The characteristics of the patients undergoing EUS-GE is shown in Table 1. The mean age of the cohort was 68 years and 58 years for malignant and benign etiology. Gender distribution was 57% and 39% being females in malignant and benign etiology group, respectively. Clinical success, technical success, average procedure time, and hospital length of stay were similar in both groups. Patients with benign underlying etiology had significantly higher number of surgically altered midgut anatomy (P=0.0379). CONCLUSION: EUS-GE is equally efficient regardless of the underlying etiology (malignant vs. benign), and the adverse events both groups were comparable.

GlycoMME, a Markov modeling platform for studying N-glycosylation biosynthesis from glycomics data.

Variations in N-glycosylation, which is crucial to glycoprotein functions, impact many diseases and the safety and efficacy of biotherapeutic drugs. Here, we present a protocol for using GlycoMME (Glycosylation Markov Model Evaluator) to study N-glycosylation biosynthesis from glycomics data. We describe steps for annotating glycomics data and quantifying perturbations to N-glycan biosynthesis with interpretable models. We then detail procedures to predict the impact of mutations in disease or potential glycoengineering strategies in drug development. For complete details on the use and execution of this protocol, please refer to Liang et al. (2020).1.

Preparing glycomics data for robust statistical analysis with GlyCompareCT.

GlyCompareCT is a portable command-line tool to facilitate downstream glycomic data analyses, by addressing data inherent sparsity and non-independence. Inputting glycan abundances, users can run GlyCompareCT with one line of code to obtain the abundances of a minimal substructure set, named glycomotif, thereby quantifying hidden biosynthetic relationships between measured glycans. Optional parameters tuning and annotation are supported for personal preference. For complete details on the use and execution of this protocol, please refer to Bao et al. (2021).1.

CHOGlycoNET: Comprehensive glycosylation reaction network for CHO cells.

Chinese hamster ovary (CHO) cells are extensively used for the production of glycoprotein therapeutics proteins, for which N-linked glycans are a critical quality attribute due to their influence on activity and immunogenicity. Manipulation of protein glycosylation is commonly achieved through cell or process engineering, which are often guided by mathematical models. However, each study considers a unique glycosylation reaction network that is tailored around the cell line and product at hand. Herein, we use 200 glycan datasets for both recombinantly produced and native proteins from different CHO cell lines to reconstruct a comprehensive reaction network, CHOGlycoNET, based on the individual minimal reaction networks describing each dataset. CHOGlycoNET is used to investigate the distribution of mannosidase and glycosyltransferase enzymes in the Golgi apparatus and identify key network reactions using machine learning and dimensionality reduction techniques. CHOGlycoNET can be used for accelerating glycomodel development and predicting the effect of glycoengineering strategies. Finally, CHOGlycoNET is wrapped in a SBML file to be used as a standalone model or in combination with CHO cell genome scale models.

A predictive ensemble classifier for the gene expression diagnosis of ASD at ages 1 to 4 years.

Autism Spectrum Disorder (ASD) diagnosis remains behavior-based and the median age of diagnosis is ~52 months, nearly 5 years after its first-trimester origin. Accurate and clinically-translatable early-age diagnostics do not exist due to ASD genetic and clinical heterogeneity. Here we collected clinical, diagnostic, and leukocyte RNA data from 240 ASD and typically developing (TD) toddlers (175 toddlers for training and 65 for test). To identify gene expression ASD diagnostic classifiers, we developed 42,840 models composed of 3570 gene expression feature selection sets and 12 classification methods. We found that 742 models had AUC-ROC ≥ 0.8 on both Training and Test sets. Weighted Bayesian model averaging of these 742 models yielded an ensemble classifier model with accurate performance in Training and Test gene expression datasets with ASD diagnostic classification AUC-ROC scores of 85-89% and AUC-PR scores of 84-92%. ASD toddlers with ensemble scores above and below the overall ASD ensemble mean of 0.723 (on a scale of 0 to 1) had similar diagnostic and psychometric scores, but those below this ASD ensemble mean had more prenatal risk events than TD toddlers. Ensemble model feature genes were involved in cell cycle, inflammation/immune response, transcriptional gene regulation, cytokine response, and PI3K-AKT, RAS and Wnt signaling pathways. We additionally collected targeted DNA sequencing smMIPs data on a subset of ASD risk genes from 217 of the 240 ASD and TD toddlers. This DNA sequencing found about the same percentage of SFARI Level 1 and 2 ASD risk gene mutations in TD (12 of 105) as in ASD (13 of 112) toddlers, and classification based only on the presence of mutation in these risk genes performed at a chance level of 49%. By contrast, the leukocyte ensemble gene expression classifier correctly diagnostically classified 88% of TD and ASD toddlers with ASD risk gene mutations. Our ensemble ASD gene expression classifier is diagnostically predictive and replicable across different toddler ages, races, and ethnicities; out-performs a risk gene mutation classifier; and has potential for clinical translation.

Non-protective immune imprint underlies failure of Staphylococcus aureus IsdB vaccine.

Humans frequently encounter Staphylococcus aureus (SA) throughout life. Animal studies have yielded SA candidate vaccines, yet all human SA vaccine trials have failed. One notable vaccine "failure" targeted IsdB, critical for host iron acquisition. We explored a fundamental difference between humans and laboratory animals-natural SA exposure. Recapitulating the failed phase III IsdB vaccine trial, mice previously infected with SA do not mount protective antibody responses to vaccination, unlike naive animals. Non-protective antibodies exhibit increased α2,3 sialylation that blunts opsonophagocytosis and preferentially targets a non-protective IsdB domain. IsdB vaccination of SA-infected mice recalls non-neutralizing humoral responses, further reducing vaccine efficacy through direct antibody competition. IsdB vaccine interference was overcome by immunization against the IsdB heme-binding domain. Purified human IsdB-specific antibodies also blunt IsdB passive immunization, and additional SA vaccines are susceptible to SA pre-exposure. Thus, failed anti-SA immunization trials could be explained by non-protective imprint from prior host-SA interaction.

Metastatic Anal Squamous Cell Carcinoma Presenting as an Indeterminate Biliary Stricture Diagnosed By Cholangioscopy.

Anal squamous cell carcinoma (SCC) rarely metastasizes outside the pelvis. Although liver involvement has been described, biliary strictures from metastatic disease are exceedingly rare. We report a case of a patient with metastatic anal SCC presenting as a biliary stricture, which was identified on endoscopic retrograde cholangiopancreatography with single-operator cholangioscopy. Direct visualization of the stricture with single-operator cholangioscopy may prove critical in obtaining a timely diagnosis. Therapeutic options for metastatic anal SCC are limited, but chemotherapy can be considered, and surgical resection is an option for limited disease.

Artificial intelligence in the analysis of glycosylation data.

Glycans are complex, yet ubiquitous across biological systems. They are involved in diverse essential organismal functions. Aberrant glycosylation may lead to disease development, such as cancer, autoimmune diseases, and inflammatory diseases. Glycans, both normal and aberrant, are synthesized using extensive glycosylation machinery, and understanding this machinery can provide invaluable insights for diagnosis, prognosis, and treatment of various diseases. Increasing amounts of glycomics data are being generated thanks to advances in glycoanalytics technologies, but to maximize the value of such data, innovations are needed for analyzing and interpreting large-scale glycomics data. Artificial intelligence (AI) provides a powerful analysis toolbox in many scientific fields, and here we review state-of-the-art AI approaches on glycosylation analysis. We further discuss how models can be analyzed to gain mechanistic insights into glycosylation machinery and how the machinery shapes glycans under different scenarios. Finally, we propose how to leverage the gained knowledge for developing predictive AI-based models of glycosylation. Thus, guiding future research of AI-based glycosylation model development will provide valuable insights into glycosylation and glycan machinery.