Faculty Bibliography

BACKGROUND:Postpartum hemorrhage remains one of the largest causes of maternal morbidity and mortality in the United States. OBJECTIVE:The aim of this paper is to use machine learning techniques to identify patients at risk for postpartum hemorrhage at obstetric delivery. METHODS:Women aged 18 to 55 years delivering at a major academic center from July 2013 to October 2018 were included for analysis (N=30,867). A total of 497 variables were collected from the electronic medical record including the following: demographic information; obstetric, medical, surgical, and family history; vital signs; laboratory results; labor medication exposures; and delivery outcomes. Postpartum hemorrhage was defined as a blood loss of ≥1000 mL at the time of delivery, regardless of delivery method, with 2179 (7.1%) positive cases observed. Supervised learning with regression-, tree-, and kernel-based machine learning methods was used to create classification models based upon training (21,606/30,867, 70%) and validation (4630/30,867, 15%) cohorts. Models were tuned using feature selection algorithms and domain knowledge. An independent test cohort (4631/30,867, 15%) determined final performance by assessing for accuracy, area under the receiver operating curve (AUROC), and sensitivity for proper classification of postpartum hemorrhage. Separate models were created using all collected data versus models limited to data available prior to the second stage of labor or at the time of decision to proceed with cesarean delivery. Additional models examined patients by mode of delivery. RESULTS:Gradient boosted decision trees achieved the best discrimination in the overall model. The model including all data mildly outperformed the second stage model (AUROC 0.979, 95% CI 0.971-0.986 vs AUROC 0.955, 95% CI 0.939-0.970). Optimal model accuracy was 98.1% with a sensitivity of 0.763 for positive prediction of postpartum hemorrhage. The second stage model achieved an accuracy of 98.0% with a sensitivity of 0.737. Other selected algorithms returned models that performed with decreased discrimination. Models stratified by mode of delivery achieved good to excellent discrimination but lacked the sensitivity necessary for clinical applicability. CONCLUSIONS:Machine learning methods can be used to identify women at risk for postpartum hemorrhage who may benefit from individualized preventative measures. Models limited to data available prior to delivery perform nearly as well as those with more complete data sets, supporting their potential utility in the clinical setting. Further work is necessary to create successful models based upon mode of delivery and to validate the findings of this study. An unbiased approach to hemorrhage risk prediction may be superior to human risk assessment and represents an area for future research.

A recent study by Saldanha et al. demonstrates that blockchain-based models outcompeted local models and performed similarly with merged models to predict molecular features from cancer histopathology images. The results reveal the capability of decentralized models in molecular diagnosis of cancer.

Image-based analysis as a method for mutation detection can be advantageous in settings when tumor tissue is limited or unavailable for direct testing. Here, we utilize two distinct and complementary machine learning methods of analyzing whole slide images (WSI) for predicting mutated BRAF. In the first method, WSI of melanomas from 256 patients were used to train a deep convolutional neural network (CNN) in order to develop a fully automated model that first selects for tumor-rich areas (Area Under the Curve AUC=0.96) then predicts for mutated BRAF (AUC=0.71). Saliency mapping was performed and revealed that pixels corresponding to nuclei were the most relevant to network learning. In the second method, WSI were analyzed using a pathomics pipeline that first annotates nuclei and then quantifies nuclear features, demonstrating that mutated BRAF nuclei were significantly larger and rounder nuclei compared to BRAF WT nuclei. Lastly, we developed a model that combines clinical information, deep learning, and pathomics that improves the predictive performance for mutated BRAF to AUC=0.89. Not only does this provide additional insights on how BRAF mutations affect tumor structural characteristics, machine learning-based analysis of WSI has the potential to be integrated into higher order models for understanding tumor biology.

The deubiquitinase USP1 is a critical regulator of genome integrity through the deubiquitylation of Fanconi Anemia proteins and the DNA replication processivity factor, proliferating cell nuclear antigen (PCNA). Uniquely, following UV irradiation, USP1 self-inactivates through autocleavage, which enables its own degradation and in turn, upregulates PCNA monoubiquitylation. However, the functional role for this autocleavage event during physiological conditions remains elusive. Herein, we discover that cells harboring an autocleavage-defective USP1 mutant, while still able to robustly deubiquitylate PCNA, experience more replication fork-stalling and premature fork termination events. Using super-resolution microscopy and live-cell single-molecule tracking, we show that these defects are related to the inability of this USP1 mutant to be properly recycled from sites of active DNA synthesis, resulting in replication-associated lesions. Furthermore, we find that the removal of USP1 molecules from DNA is facilitated by the DNA-dependent metalloprotease Spartan to counteract the cytotoxicity caused by "USP1-trapping". We propose a utility of USP1 inhibitors in cancer therapy based on their ability to induce USP1-trapping lesions and consequent replication stress and genomic instability in cancer cells, similar to how non-covalent DNA-protein crosslinks cause cytotoxicity by imposing steric hindrances upon proteins involved in DNA transactions.

Retrotransposons are genomic DNA sequences that copy themselves to new genomic locations via RNA intermediates; LINE-1 is the only active and autonomous retrotransposon in the human genome. The mobility of LINE-1 is largely repressed in somatic tissues but is derepressed in many cancers, where LINE-1 retrotransposition is correlated with p53 mutation and copy number alteration (CNA). In cell lines, inducing LINE-1 expression can cause double-strand breaks (DSBs) and replication stress. Reanalyzing multiomic data from breast, ovarian, endometrial, and colon cancers, we confirmed correlations between LINE-1 expression, p53 mutation status, and CNA. We observed a consistent correlation between LINE-1 expression and the abundance of DNA replication complex components, indicating that LINE-1 may also induce replication stress in human tumors. In endometrial cancer, high-quality phosphoproteomic data allowed us to identify the DSB-induced ATM-MRN-SMC S phase checkpoint pathway as the primary DNA damage response (DDR) pathway associated with LINE-1 expression. Induction of LINE-1 expression in an in vitro model led to increased phosphorylation of MRN complex member RAD50, suggesting that LINE-1 directly activates this pathway.

The emergence of SARS-CoV-2 variants threatens current vaccines and therapeutic antibodies and urgently demands powerful new therapeutics that can resist viral escape. We therefore generated a large nanobody repertoire to saturate the distinct and highly conserved available epitope space of SARS-CoV-2 spike, including the S1 receptor binding domain, N-terminal domain, and the S2 subunit, to identify new nanobody binding sites that may reflect novel mechanisms of viral neutralization. Structural mapping and functional assays show that indeed these highly stable monovalent nanobodies potently inhibit SARS-CoV-2 infection, display numerous neutralization mechanisms, are effective against emerging variants of concern, and are resistant to mutational escape. Rational combinations of these nanobodies that bind to distinct sites within and between spike subunits exhibit extraordinary synergy and suggest multiple tailored therapeutic and prophylactic strategies.

The determination of endometrial carcinoma histological subtypes, molecular subtypes, and mutation status is critical for the diagnostic process, and directly affects patients' prognosis and treatment. Sequencing, albeit slower and more expensive, can provide additional information on molecular subtypes and mutations that can be used to better select treatments. Here, we implement a customized multi-resolution deep convolutional neural network, Panoptes, that predicts not only the histological subtypes but also the molecular subtypes and 18 common gene mutations based on digitized H&E-stained pathological images. The model achieves high accuracy and generalizes well on independent datasets. Our results suggest that Panoptes, with further refinement, has the potential for clinical application to help pathologists determine molecular subtypes and mutations of endometrial carcinoma without sequencing.

Pancreatic ductal adenocarcinoma (PDAC) is a highly aggressive cancer with poor patient survival. Toward understanding the underlying molecular alterations that drive PDAC oncogenesis, we conducted comprehensive proteogenomic analysis of 140 pancreatic cancers, 67 normal adjacent tissues, and 9 normal pancreatic ductal tissues. Proteomic, phosphoproteomic, and glycoproteomic analyses were used to characterize proteins and their modifications. In addition, whole-genome sequencing, whole-exome sequencing, methylation, RNA sequencing (RNA-seq), and microRNA sequencing (miRNA-seq) were performed on the same tissues to facilitate an integrated proteogenomic analysis and determine the impact of genomic alterations on protein expression, signaling pathways, and post-translational modifications. To ensure robust downstream analyses, tumor neoplastic cellularity was assessed via multiple orthogonal strategies using molecular features and verified via pathological estimation of tumor cellularity based on histological review. This integrated proteogenomic characterization of PDAC will serve as a valuable resource for the community, paving the way for early detection and identification of novel therapeutic targets.

Adenosine signaling plays a critical role in the maintenance of articular cartilage and may serve as a novel therapeutic for osteoarthritis (OA), a highly prevalent and morbid disease without effective therapeutics in the current market. Mice lacking adenosine A2A receptors (A2AR) develop spontaneous OA by 16 weeks of age, a finding relevant to human OA since loss of adenosine signaling due to diminished adenosine production (NT5E deficiency) also leads to development of OA in mice and humans. To better understand the mechanism by which A2AR and adenosine generation protect from OA development, we examined differential gene expression in neonatal chondrocytes from WT and A2AR null mice. Analysis of differentially expressed genes was analyzed by KEGG pathway analysis, and oPOSSUM and the flatiron database were used to identify transcription factor binding enrichment, and tissue-specific network analyses and patterns were compared to gene expression patterns in chondrocytes from patients with OA. There was a differential expression of 2211 genes (padj<0.05). Pathway enrichment analysis revealed that pro-inflammatory changes, increased metalloprotease, reduced matrix organization, and homeostasis are upregulated in A2AR null chondrocytes. Moreover, stress responses, including autophagy and HIF-1 signaling, seem to be important drivers of OA and bear marked resemblance to the human OA transcriptome. Although A2AR null mice are born with grossly intact articular cartilage, we identify here the molecular foundations for early-onset OA in these mice, further establishing their role as models for human disease and the potential use of adenosine as a treatment for human disease.

Lung squamous cell carcinoma (LSCC) remains a leading cause of cancer death with few therapeutic options. We characterized the proteogenomic landscape of LSCC, providing a deeper exposition of LSCC biology with potential therapeutic implications. We identify NSD3 as an alternative driver in FGFR1-amplified tumors and low-p63 tumors overexpressing the therapeutic target survivin. SOX2 is considered undruggable, but our analyses provide rationale for exploring chromatin modifiers such as LSD1 and EZH2 to target SOX2-overexpressing tumors. Our data support complex regulation of metabolic pathways by crosstalk between post-translational modifications including ubiquitylation. Numerous immune-related proteogenomic observations suggest directions for further investigation. Proteogenomic dissection of CDKN2A mutations argue for more nuanced assessment of RB1 protein expression and phosphorylation before declaring CDK4/6 inhibition unsuccessful. Finally, triangulation between LSCC, LUAD, and HNSCC identified both unique and common therapeutic vulnerabilities. These observations and proteogenomics data resources may guide research into the biology and treatment of LSCC.