MrIML: Multi-response interpretable machine learning to model genomic landscapes

Interpretable machine learning models for predicting in-hospital and 30 days adverse events in acute coronary syndrome patients in Kuwait

The relationships between acute coronary syndromes (ACS) adverse events and the associated risk factors are typically complicated and nonlinear, which poses significant challenges to clinicians' attempts at risk stratification. Here, we aim to explore the implementation of modern risk stratification tools to untangle how these complex factors shape the risk of adverse events in patients with ACS. We used an interpretable multi-algorithm machine learning (ML) approach and clinical features to fit predictive models to 1,976 patients with ACS in Kuwait. We demonstrated that random forest (RF) and extreme gradient boosting (XGB) algorithms, remarkably outperform traditional logistic regression model (AUCs = 0.84 & 0.79 for RF and XGB, respectively). Our in-hospital adverse events model identified left ventricular ejection fraction as the most important predictor with the highest interaction strength with other factors. However, using the 30-days adverse events model, we found that performing an urgent coronary artery bypass graft was the most important predictor, with creatinine levels having the strongest overall interaction with other related factors. Our ML models not only untangled the non-linear relationships that shape the clinical epidemiology of ACS adverse events but also elucidated their risk in individual patients based on their unique features.

The spectral underpinnings of pathogen spread on animal networks

Predicting what factors promote or protect populations from infectious disease is a fundamental epidemiological challenge. Social networks, where nodes represent hosts and edges represent direct or indirect contacts between them, are important in quantifying these aspects of infectious disease dynamics. However, how network structure and epidemic parameters interact in empirical networks to promote or protect animal populations from infectious disease remains a challenge. Here we draw on advances in spectral graph theory and machine learning to build predictive models of pathogen spread on a large collection of empirical networks from across the animal kingdom. We show that the spectral features of an animal network are powerful predictors of pathogen spread for a variety of hosts and pathogens and can be a valuable proxy for the vulnerability of animal networks to pathogen spread. We validate our findings using interpretable machine learning techniques and provide a flexible web application for animal health practitioners to assess the vulnerability of a particular network to pathogen spread.

Automated Analysis of PD1 and PDL1 Expression in Lymph Nodes and the Microenvironment of Transmissible Tumors in Tasmanian Devils

The wild Tasmanian devil (Sarcophilus harrisii) population has suffered a devastating decline due to two clonal transmissible cancers. The first devil facial tumor 1 (DFT1) was observed in 1996, followed by a second genetically distinct transmissible tumor, the devil facial tumor 2 (DFT2), in 2014. DFT1/2 frequently metastasize, with lymph nodes being common metastatic sites. MHC-I downregulation by DFT1 cells is a primary means of evading allograft immunity aimed at polymorphic MHC-I proteins. DFT2 cells constitutively express MHC-I, and MHC-I is upregulated on DFT1/2 cells by interferon gamma, suggesting other immune evasion mechanisms may contribute to overcoming allograft and anti-tumor immunity. Human clinical trials have demonstrated PD1/PDL1 blockade effectively treats patients showing increased expression of PD1 in tumor draining lymph nodes, and PDL1 on peritumoral immune cells and tumor cells. The effects of DFT1/2 on systemic immunity remain largely uncharacterized. This study applied the open-access software QuPath to develop a semiautomated pipeline for whole slide analysis of stained tissue sections to quantify PD1/PDL1 expression in devil lymph nodes. The QuPath protocol provided strong correlations to manual counting. PD-1 expression was approximately 10-fold higher than PD-L1 expression in lymph nodes and was primarily expressed in germinal centers, whereas PD-L1 expression was more widely distributed throughout the lymph nodes. The density of PD1 positive cells was increased in lymph nodes containing DFT2 metastases, compared to DFT1. This suggests PD1/PDL1 exploitation may contribute to the poorly immunogenic nature of transmissible tumors in some devils and could be targeted in therapeutic or prophylactic treatments.Abbreviations: PD1: programmed cell death protein 1; PDL1: programmed death ligand 1; DFT1: devil facial tumor 1; DFT2: devil facial tumor 2; DFTD: devil facial tumor disease; MCC: Matthew's correlation coefficient; DAB: diaminobenzidine; ROI: region of interest.

Habitat connectivity and host relatedness influence virus spread across an urbanising landscape in a fragmentation-sensitive carnivore

Spatially heterogeneous landscape factors such as urbanisation can have substantial effects on the severity and spread of wildlife diseases. However, research linking patterns of pathogen transmission to landscape features remains rare. Using a combination of phylogeographic and machine learning approaches, we tested the influence of landscape and host factors on feline immunodeficiency virus (FIV_Lru) genetic variation and spread among bobcats (Lynx rufus) sampled from coastal southern California. We found evidence for increased rates of FIV_Lru lineage spread through areas of higher vegetation density. Furthermore, single-nucleotide polymorphism (SNP) variation among FIV_Lru sequences was associated with host genetic distances and geographic location, with FIV_Lru genetic discontinuities precisely correlating with known urban barriers to host dispersal. An effect of forest land cover on FIV_Lru SNP variation was likely attributable to host population structure and differences in forest land cover between different populations. Taken together, these results suggest that the spread of FIV_Lru is constrained by large-scale urban barriers to host movement. Although urbanisation at fine spatial scales did not appear to directly influence virus transmission or spread, we found evidence that viruses transmit and spread more quickly through areas containing higher proportions of natural habitat. These multiple lines of evidence demonstrate how urbanisation can change patterns of contact-dependent pathogen transmission and provide insights into how continued urban development may influence the incidence and management of wildlife disease.

Neoadjuvant tislelizumab and tegafur/gimeracil/octeracil (S-1) plus oxaliplatin in patients with locally advanced gastric or gastroesophageal junction cancer: Early results of a phase 2, single-arm trial

Background

Recently, the combination of immunotherapy with chemotherapy has been recommended as first-line treatment of metastatic gastric/gastroesophageal junction (G/GEJ) in the clinical guidelines of many countries; the therapeutic potential of this application needs to be further investigated for neoadjuvant therapy of advanced G/GEJ cancer patients.

Methods

We performed a prospective, single-arm, open-label, phase 2 trial of the PD-1 inhibitor tislelizumab combined with S-1 plus oxaliplatin (SOX) in patients with advanced LAG/GEJ cancer. All patients underwent the three-cycle (21 days/cycle) treatment except for one patient who underwent two cycles. The primary endpoints were tumor major pathology response (MPR) and other events of tumor response assessed by the RECIST 1.1 and Becker criteria. Moreover, we constructed a few-shot learning model to predict the probability of MPR, which could screen those patients who might benefit from the neoadjuvant immunotherapy–chemotherapy scheme. This study was registered at https://clinicaltrials.gov/ct2/show/NCT0-4890392.

Results

Thirty-two patients were enrolled; 17 patients (53.1%) achieved MPR (≤10% viable tumor cells) after treatment, and among them, 8 (25.0%) had a pathological complete response (pCR). The 1-year overall survival (OS) rate was 91.4% and the 1-year recurrence-free survival (RFS) rate was 90.0%. Adverse events occurred in 24 patients (65.6%) and grade III–IV adverse events were observed in 4 patients (12.5%) during the neoadjuvant period. Furthermore, we found commonly used preoperative assessment tools such as CT and EUS, which presented limited accuracy of tumor therapeutic response in this study; thus, we developed a therapeutic response predictive model that consisted of TNFα, IFNγ, IL-10, CD4, and age of patient, and the AUC of this FSL model was 0.856 (95% CI: 0.823–0.884).

Discussion

Our study showed that the neoadjuvant PD-1 inhibitor tislelizumab combined with SOX had promising application potential and presented no increasing treatment-related adverse events in patients with advanced G/GEJ cancer. Moreover, the predictive model could help therapists to evaluate the therapeutic response of this scheme accurately.

Clinical Trial Registration

https://clinicaltrials.gov/ct2/show/NCT0-4890392, identifier [NCT04890392].

Interpretable machine learning applied to on-farm biosecurity and porcine reproductive and respiratory syndrome virus

Effective biosecurity practices in swine production are key in preventing the introduction and dissemination of infectious pathogens. Ideally, on-farm biosecurity practices should be chosen by their impact on bio-containment and bio-exclusion; however, quantitative supporting evidence is often unavailable. Therefore, the development of methodologies capable of quantifying and ranking biosecurity practices according to their efficacy in reducing disease risk has the potential to facilitate better-informed choices of biosecurity practices. Using survey data on biosecurity practices, farm demographics, and previous outbreaks from 139 herds, a set of machine learning algorithms were trained to classify farms by porcine reproductive and respiratory syndrome virus status, depending on their biosecurity practices and farm demographics, to produce a predicted outbreak risk. A novel interpretable machine learning toolkit, MrIML-biosecurity, was developed to benchmark farms and production systems by predicted risk and quantify the impact of biosecurity practices on disease risk at individual farms. By quantifying the variable impact on predicted risk, 50% of 42 variables were associated with fomite spread while 31% were associated with local transmission. Results from machine learning interpretations identified similar results, finding substantial contribution to predicted outbreak risk from biosecurity practices relating to the turnover and number of employees, the surrounding density of swine premises and pigs, the sharing of haul trailers, distance from the public road and farm production type. In addition, the development of individualized biosecurity assessments provides the opportunity to better guide biosecurity implementation on a case-by-case basis. Finally, the flexibility of the MrIML-biosecurity toolkit gives it the potential to be applied to wider areas of biosecurity benchmarking, to address biosecurity weaknesses in other livestock systems and industry-relevant diseases.