Improving Anticancer Drug Selection and Prioritization via Neural Learning to Rank

Personalized cancer treatment requires a thorough understanding of complex interactions between drugs and cancer cell lines in varying genetic and molecular contexts. To address this, high-throughput screening has been used to generate large-scale drug response data, facilitating data-driven computational models. Such models can capture complex drug-cell line interactions across various contexts in a fully data-driven manner. However, accurately prioritizing the most effective drugs for each cell line still remains a significant challenge. To address this, we developed multiple neural ranking approaches that leverage large-scale drug response data across multiple cell lines from diverse cancer types. Unlike existing approaches that primarily utilize regression and classification techniques for drug response prediction, we formulated the objective of drug selection and prioritization as a drug ranking problem. In this work, we proposed multiple pairwise and listwise neural ranking methods that learn latent representations of drugs and cell lines and then use those representations to score drugs in each cell line via a learnable scoring function. Specifically, we developed neural pairwise and listwise ranking methods, Pair-PushC and List-One on top of the existing methods, pLETORg and ListNet, respectively. Additionally, we proposed a novel listwise ranking method, List-All, that focuses on all the effective drugs instead of the top effective drug, unlike List-One. We also provide an exhaustive empirical evaluation with state-of-the-art regression and ranking baselines on large-scale data sets across multiple experimental settings. Our results demonstrate that our proposed ranking methods mostly outperform the best baselines with significant improvements of as much as 25.6% in terms of selecting truly effective drugs within the top 20 predicted drugs (i.e., hit@20) across 50% test cell lines. Furthermore, our analyses suggest that the learned latent spaces from our proposed methods demonstrate informative clustering structures and capture relevant underlying biological features. Moreover, our comprehensive evaluation provides a thorough and objective comparison of the performance of different methods (including our proposed ones).

The relationship between histopathological features, immunosuppression and outcome in patients undergoing native kidney biopsies

AIMS

To assess retrospectively the association between histopathological lesions on renal biopsy and subsequent impairment of renal function across the spectrum of kidney diseases and to explore the influence of immunosuppressive therapy within the first 6 months after biopsy on this association.

METHODS AND RESULTS

Clinical data from 488 adult patients having a renal biopsy reported at a single centre from 2017 to 2019 were obtained during a median follow-up period of 786 days. Seventeen semi-quantitative histology parameters were recorded at the time of biopsy, 14 of which were suitable for assessment of association with loss of eGFR by multivariable Cox regression analysis, measurement of eGFR slope and measurement of eGFR 12 months after biopsy. A widely used histopathological chronicity score was also assessed. Clinical baseline variables including prescription of immunosuppression were recorded. Seven of 14 histology parameters: mesangial matrix expansion, global glomerulosclerosis, tubular atrophy, interstitial fibrosis, arteriolosclerosis, mesangial hypercellularity and acute tubular injury; and the chronicity score, predicted loss of kidney function by all three measures. Prescription of immunosuppression was more likely in patients with active inflammatory pathology and less likely in patients with chronic fibrotic pathology, and was associated with reduced risk of loss of eGFR.

CONCLUSIONS

This retrospective study demonstrates the prognostic significance and complex relationship with immunosuppression of routinely reported histopathological variables in patients having native kidney biopsies, across the spectrum of kidney diseases. It provides useful information for renal biopsy prognostication and design of retrospective studies, including machine learning models.

Outcomes in ANCA-Associated Vasculitis in Scotland: Validation of the Renal Risk Score in a Complete National Cohort

Introduction

Antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis (AAV) causes autoimmune-mediated inflammation of small blood vessels in multiple organs, including the kidneys. The ability to accurately predict kidney outcomes would enable a more personalized therapeutic approach.

Methods

We used our national renal biopsy registry to validate the ability of ANCA Renal Risk Score (ARRS) to predict end-stage kidney disease (ESKD) for individual patients. This score uses histopathological and biochemical data to stratify patients as high, medium, or low risk for developing ESKD.

Results

A total of 288 patients were eligible for inclusion in the study (low risk n = 144, medium risk n = 122, high risk n = 12). Using adjusted Cox proportional hazard models with the low-risk group as reference, we show that outcome differs between the categories: high-risk hazard ratio (HR) 16.69 (2.91-95.81, P = 0.002); medium risk HR 4.14 (1.07-16.01, P = 0.039). Incremental multivariable-adjusted Cox proportional hazards models demonstrated that adding ARRS to a model adjusted for multiple clinical parameters enhanced predictive discrimination (basic model C-statistic 0.864 [95% CI 0.813-0.914], basic model plus ARRS C-statistic 0.877 [95% CI 0.823-0.931]; P <0.01).

Conclusion

The ARRS better discriminates risk of ESKD in AAV and offers clinicians more prognostic information than the use of standard biochemical and clinical measures alone. This is the first time the ARRS has been validated in a national cohort. The proportion of patients with high-risk scores is lower in our cohort compared to others and should be noted as a limitation of this study.

Understanding comorbidities and health disparities related to COVID-19: a comprehensive study of 776 936 cases and 1 362 545 controls in the state of Indiana, USA

Objective

To characterize COVID-19 patients in Indiana, United States, and to evaluate their demographics and comorbidities as risk factors to COVID-19 severity.

Materials and Methods

EHR data of 776 936 COVID-19 cases and 1 362 545 controls were collected from the COVID-19 Research Data Commons (CoRDaCo) in Indiana. Data regarding county population and per capita income were obtained from the US Census Bureau. Statistical analysis was conducted to determine the association of demographic and clinical variables with COVID-19 severity. Predictive analysis was conducted to evaluate the predictive power of CoRDaCo EHR data in determining COVID-19 severity.

Results

Chronic obstructive pulmonary disease, cardiovascular disease, and type 2 diabetes were found in 3.49%, 2.59%, and 4.76% of the COVID-19 patients, respectively. Such COVID-19 patients have significantly higher ICU admission rates of 10.23%, 14.33%, and 11.11%, respectively, compared to the entire COVID-19 patient population (1.94%). Furthermore, patients with these comorbidities have significantly higher mortality rates compared to the entire COVID-19 patient population. Health disparity analysis suggests potential health disparities among counties in Indiana. Predictive analysis achieved F1-scores of 0.8011 and 0.7072 for classifying COVID-19 cases versus controls and ICU versus non-ICU cases, respectively.

Discussion

Black population in Indiana was more adversely affected by COVID-19 than the White population. This is consistent to findings from existing studies. Our findings also indicate other health disparities in terms of demographic and economic factors.

Conclusion

This study characterizes the relationship between comorbidities and COVID-19 outcomes with respect to ICU admission across a large COVID-19 patient population in Indiana.

Neutrophil-to-lymphocyte and platelet-to-lymphocyte ratios: associations with mortality in a haemodialysis cohort

Background

Lymphocyte ratios reflect inflammation and have been associated with adverse outcomes in a range of diseases. We sought to determine any association between neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) and mortality in a haemodialysis cohort, including a coronavirus disease 2019 (COVID-19) infection subpopulation.

Methods

A retrospective analysis was performed of adults commencing hospital haemodialysis in the West of Scotland during 2010-21. NLR and PLR were calculated from routine samples around haemodialysis initiation. Kaplan-Meier and Cox proportional hazards analyses were used to assess mortality associations.

Results

In 1720 haemodialysis patients over a median of 21.9 (interquartile range 9.1-42.9) months, there were 840 all-cause deaths. NLR but not PLR was associated with all-cause mortality after multivariable adjustment [adjusted hazard ratio (aHR) for in participants with baseline NLR in quartile 4 (NLR ≥8.23) versus quartile 1 (NLR <3.12) 1.63, 95% confidence interval (CI) 1.32-2.00]. The association was stronger for cardiovascular death (NLR quartile 4 versus 1 aHR 3.06, 95% CI 1.53-6.09) than for non-cardiovascular death (NLR quartile 4 versus 1 aHR 1.85, 95% CI 1.34-2.56). In the COVID-19 subpopulation, both NLR and PLR at haemodialysis initiation were associated with risk of COVID-19-related death after adjustment for age and sex (NLR: aHR 4.69, 95% CI 1.48-14.92 and PLR: aHR 3.40, 95% CI 1.02-11.36; for highest vs lowest quartiles).

Conclusions

NLR is strongly associated with mortality in haemodialysis patients while the association between PLR and adverse outcomes is weaker. NLR is an inexpensive, readily available biomarker with potential utility in risk stratification of haemodialysis patients.

Improving Compound Activity Classification via Deep Transfer and Representation Learning

Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure-activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks.

A Pipeline to Understand Emerging Illness Via Social Media Data Analysis: Case Study on Breast Implant Illness

Background

A new illness can come to public attention through social media before it is medically defined, formally documented, or systematically studied. One example is a condition known as breast implant illness (BII), which has been extensively discussed on social media, although it is vaguely defined in the medical literature.

Objective

The objective of this study is to construct a data analysis pipeline to understand emerging illnesses using social media data and to apply the pipeline to understand the key attributes of BII.

Methods

We constructed a pipeline of social media data analysis using natural language processing and topic modeling. Mentions related to signs, symptoms, diseases, disorders, and medical procedures were extracted from social media data using the clinical Text Analysis and Knowledge Extraction System. We mapped the mentions to standard medical concepts and then summarized these mapped concepts as topics using latent Dirichlet allocation. Finally, we applied this pipeline to understand BII from several BII-dedicated social media sites.

Results

Our pipeline identified topics related to toxicity, cancer, and mental health issues that were highly associated with BII. Our pipeline also showed that cancers, autoimmune disorders, and mental health problems were emerging concerns associated with breast implants, based on social media discussions. Furthermore, the pipeline identified mentions such as rupture, infection, pain, and fatigue as common self-reported issues among the public, as well as concerns about toxicity from silicone implants.

Conclusions

Our study could inspire future studies on the suggested symptoms and factors of BII. Our study provides the first analysis and derived knowledge of BII from social media using natural language processing techniques and demonstrates the potential of using social media information to better understand similar emerging illnesses.

ANCA-associated renal vasculitis is associated with rurality but not seasonality or deprivation in a complete national cohort study

Background

Small studies suggest an association between ANCA-associated vasculitis (AAV) incidence and rurality, seasonality and socioeconomic deprivation. We examined the incidence of kidney biopsy-proven AAV and its relationship with these factors in the adult Scottish population.

Methods

Using the Scottish Renal Biopsy Registry, all adult native kidney biopsies performed between 2014 and 2018 with a diagnosis of granulomatosis with polyangiitis (GPA) or microscopic polyangiitis (MPA) were identified. The Scottish Government Urban Rural Classification was used for rurality analysis. Seasons were defined as autumn (September–November), winter (December–February), spring (March–May) and summer (June–August). Patients were separated into quintiles of socioeconomic deprivation using the validated Scottish Index of Multiple Deprivation and incidence standardised to age. Estimated glomerular filtration rate and urine protein:creatinine ratio at time of biopsy were used to assess disease severity.

Results

339 cases of renal AAV were identified, of which 62% had MPA and 38% had GPA diagnosis. AAV incidence was 15.1 per million population per year (pmp/year). Mean age was 66 years and 54% were female. Incidence of GPA (but not MPA) was positively associated with rurality (5.2, 8.4 and 9.1 pmp/year in ‘urban’, ‘accessible remote’ and ‘rural remote’ areas, respectively; p=0.04). The age-standardised incidence ratio was similar across all quintiles of deprivation (p=ns).

Conclusions

Seasonality and disease severity did not vary across AAV study groups. In this complete national cohort study, we observed a positive association between kidney biopsy-proven GPA and rurality.

A National Registry Study of Patient and Renal Survival in Adult Nephrotic Syndrome

Introduction

We aimed to determine the mortality rate, cause of death, and rate of end-stage kidney disease (ESKD) in adults with nephrotic syndrome (NS).

Methods

We conducted a national registry–based study, including all 522 adults who had a kidney biopsy for NS in Scotland in 2014–2017. We linked the Scottish Renal Registry to death certificate data. We performed survival and Cox proportional hazards analyses, accounting for competing risks of death and ESKD. We compared mortality rates with those in the age- and sex-matched general population.

Results

A total of 372 patients had primary NS; 150 had secondary NS. Over a median follow-up of 866 days, 110 patients (21%) died. In patients with primary NS, observed versus population 3-year mortality was 2.1% (95% CI 0.0%–4.6%) versus 0.9% (0.8%–1.0%) in patients aged <60 years and 24.9% (18.4%–30.8%) versus 9.4% (8.3%–10.5%) in those aged ≥60 years. In secondary NS, this discrepancy was 17.1% (5.6%–27.2%) versus 1.1% (0.9%–1.2%) in <60-year-olds and 49.4% (36.6%–59.7%) versus 8.1% (6.6%–9.6%) in ≥60-year-olds. In primary NS, cardiovascular causes accounted for 28% of deaths, compared with 18% in the general population. Eighty patients (15%) progressed to ESKD. Incidence of ESKD by 3 years was 8.4% (95% CI 4.9%–11.7%) in primary and 35.1% (24.3%–44.5%) in secondary NS. Early remission of proteinuria and the absence of early acute kidney injury (AKI) were associated with lower rates of death and ESKD.

Conclusions

Adults with NS have high rates of death and ESKD. Cardiovascular causes account for excess mortality in primary NS.

Symptomatic fracture risk in the renal replacement therapy population

Background

Bone fractures are an important cause of morbidity and mortality in patients on renal replacement therapy (RRT). The aim of this multicentre observational study was to quantify the incidence of radiologically proven bone fracture by anatomical site in prevalent RRT groups and study its relationship to potential risk factors.

Methods

We performed a retrospective analysis of electronic records of all 2096 adults prevalent on RRT in the West of Scotland on 7 July 2010 across all hospitals (except one where inception was 1 August 2011) to identify all subsequent radiologically proven fractures during a median 3-year follow-up.

Results

There were 340 fractures, with an incidence of 62.8 per 1000 patient-years. The incidences were 37.6, 99.2 and 57.6 per 1000 patient-years in the transplant, haemodialysis (HD) and peritoneal dialysis (PD) groups, respectively (P < 0.05). In the multivariable model, age and HD (relative to transplant or PD) were independently associated with increased risk of fractures, while primary glomerular disease, increasing serum albumin and taking alfacalcidol or lanthanum were associated with decreased risk. In a multivariable model of only HD patients, age was independently associated with an increased risk of fractures, while glomerular disease, high serum albumin and being on alfacalcidol and lanthanum were associated with decreased risk. In a multivariable model in transplant patients, there were no significant independent predictors of fracture.

Conclusions

The risk of symptomatic bone fracture is high in RRT patients and is ∼2.5 times higher in HD than in renal transplant patients, with the increased risk being independent of baseline factors. Fracture risk increases with age and lower serum albumin and is reduced if the primary renal diagnosis is glomerular disease. The possible protective role of alfacalcidol and lanthanum in HD patients deserves further exploration.

Telehealth: Acceptability, clinical interventions and quality of life in peritoneal dialysis

Introduction:

Telehealth technologies are being widely adopted across the globe for management of long-term conditions. There are limited data on its use, effectiveness and patient experience in end-stage renal disease. The aim of this pilot project was to explore patient acceptability of technology and evaluate its effect on clinical interventions and quality of life in patients undergoing peritoneal dialysis.

Methods:

Peritoneal dialysis patients were provided with computer tablets (PODs). PODs contained a knowledge database with treatment- and symptom-based questionnaires that generated alerts for the clinical team. Alerts were reviewed daily and followed up by a telephone call or clinic visit. Interventions were at the discretion of clinicians. Data were recorded prospectively and quality of life and Quebec User Evaluation of Satisfaction with assistive Technology questionnaires evaluated at the start and end of the programme.

Results:

In all, 22 patients have participated over 15 months. The mean age was 61.6 years and PODs were utilised for an average of 341.9 days with 59.1% choosing to continue beyond the study period. We received a total of 1195 alerts with an average of 2.6 alerts per day. A total of 36 admissions were avoided and patients supported to self-manage on 154 occasions. Quebec User Evaluation of Satisfaction with assistive Technology scores remained high throughout the programme although no improvement in quality of life was seen.

Discussion:

Telehealth is useful to monitor patients with renal failure on peritoneal dialysis. It is acceptable across age groups and provides an additional resource for patients to self-manage. Satisfaction scores and retention rates suggest a high level of acceptability.

Thrice-Weekly Nocturnal In-Centre Haemodiafiltration: A 2-Year Experience

Background

Adequate control of plasma phosphate without phosphate binders is difficult to achieve on a thrice-weekly haemodialysis schedule. The use of quotidian nocturnal dialysis is effective but not practical in the in-centre setting. This quality improvement project was set up as an exercise allowing the evaluation of small-solute clearance by combining convection with extended-hour dialysis in a thrice-weekly hospital setting.

Methods

A single-centred, prospective analysis of patients' electronic records was performed from August 2012 to July 2014. The duration of haemodiafiltration was increased from a median of 4.5 to 8 h. Dialysis adequacy, biochemical parameters and medications were reviewed on a monthly basis. A reduction in plasma phosphate was anticipated, so all phosphate binders were stopped.

Results

Since inception, 14 patients have participated with over 2,000 sessions of dialysis. The pre-dialysis phosphate level fell from a mean of 1.52 ± 0.4 to 1.06 ± 0.1 mmol/l (p < 0.05). The average binder intake of 3.26 ± 2.6 tablets was eliminated. A normal plasma phosphate range has been maintained with increased dietary phosphate intake and no requirement for intradialytic phosphate supplementation.

Conclusion

Phosphate control can be achieved without the need for binders or supplementation on a thrice-weekly in-centre haemodiafiltration program.