Computational methods using genome-wide association studies to predict radiotherapy complications and to identify correlative molecular processes

Lipid metabolism and neuromuscular junction as common pathways underlying the genetic basis of erectile dysfunction and obstructive sleep apnea

Erectile dysfunction (ED) incidence is higher in patients with obstructive sleep apnea (OSA). Studies have suggested that ED and OSA may activate similar pathways; however, few have investigated the links between their underlying genotypic profiles. Therefore, we conducted an in-silico analysis to test whether ED and OSA share genetic variants of risk and to identify any molecular, cellular and biological interactions between them. Two gene lists were manually curated through a literature review based on a PUBMED search, which resulted in one gene list associated with ED (total of 205 genes) and the other with OSA (total of 2622 genes). Between those gene sets, 35 were common for both lists (Fisher exact test, p-value = 0.027). The Protein-protein interaction (PPI) analysis using the intersect list as input showed that 3 of them had direct interactions (LPL, DGKB and PLCB1). In addition, the biological function of the genes contained in the intersect list suggested that pathways related to lipid metabolism and the neuromuscular junction were commonly found in the genetic basis of ED and OSA. From the shared genes between both conditions, the biological pathways highlighted in this study may serve as preliminary findings for future functional investigations on OSA and ED association.

Genome-wide association study as a powerful tool for dissecting competitive traits in legumes

Legumes are extremely valuable because of their high protein content and several other nutritional components. The major challenge lies in maintaining the quantity and quality of protein and other nutritional compounds in view of climate change conditions. The global need for plant-based proteins has increased the demand for seeds with a high protein content that includes essential amino acids. Genome-wide association studies (GWAS) have evolved as a standard approach in agricultural genetics for examining such intricate characters. Recent development in machine learning methods shows promising applications for dimensionality reduction, which is a major challenge in GWAS. With the advancement in biotechnology, sequencing, and bioinformatics tools, estimation of linkage disequilibrium (LD) based associations between a genome-wide collection of single-nucleotide polymorphisms (SNPs) and desired phenotypic traits has become accessible. The markers from GWAS could be utilized for genomic selection (GS) to predict superior lines by calculating genomic estimated breeding values (GEBVs). For prediction accuracy, an assortment of statistical models could be utilized, such as ridge regression best linear unbiased prediction (rrBLUP), genomic best linear unbiased predictor (gBLUP), Bayesian, and random forest (RF). Both naturally diverse germplasm panels and family-based breeding populations can be used for association mapping based on the nature of the breeding system (inbred or outbred) in the plant species. MAGIC, MCILs, RIAILs, NAM, and ROAM are being used for association mapping in several crops. Several modifications of NAM, such as doubled haploid NAM (DH-NAM), backcross NAM (BC-NAM), and advanced backcross NAM (AB-NAM), have also been used in crops like rice, wheat, maize, barley mustard, etc. for reliable marker-trait associations (MTAs), phenotyping accuracy is equally important as genotyping. Highthroughput genotyping, phenomics, and computational techniques have advanced during the past few years, making it possible to explore such enormous datasets. Each population has unique virtues and flaws at the genomics and phenomics levels, which will be covered in more detail in this review study. The current investigation includes utilizing elite breeding lines as association mapping population, optimizing the choice of GWAS selection, population size, and hurdles in phenotyping, and statistical methods which will analyze competitive traits in legume breeding.

Predicting the germline dependence of hematuria risk in prostate cancer radiotherapy patients

BACKGROUND AND PURPOSE

Late radiation-induced hematuria can develop in prostate cancer patients undergoing radiotherapy and can negatively impact the quality-of-life of survivors. If a genetic component of risk could be modeled, this could potentially be the basis for modifying treatment for high-risk patients. We therefore investigated whether a previously developed machine learning-based modeling method using genome-wide common single nucleotide polymorphisms (SNPs) can stratify patients in terms of the risk of radiation-induced hematuria.

MATERIALS AND METHODS

We applied a two-step machine learning algorithm that we previously developed for genome-wide association studies called pre-conditioned random forest regression (PRFR). PRFR includes a pre-conditioning step, producing adjusted outcomes, followed by random forest regression modeling. Data was from germline genome-wide SNPs for 668 prostate cancer patients treated with radiotherapy. The cohort was stratified only once, at the outset of the modeling process, into two groups: a training set (2/3 of samples) for modeling and a validation set (1/3 of samples). Post-modeling bioinformatics analysis was conducted to identify biological correlates plausibly associated with the risk of hematuria.

RESULTS

The PRFR method achieved significantly better predictive performance compared to other alternative methods (all p < 0.05). The odds ratio between the high and low risk groups, each of which consisted of 1/3 of samples in the validation set, was 2.87 (p = 0.029), implying a clinically useful level of discrimination. Bioinformatics analysis identified six key proteins encoded by CTNND2, GSK3B, KCNQ2, NEDD4L, PRKAA1, and TXNL1 genes as well as four statistically significant biological process networks previously shown to be associated with the bladder and urinary tract.

CONCLUSION

The risk of hematuria is significantly dependent on common genetic variants. The PRFR algorithm resulted in a stratification of prostate cancer patients at differential risk levels of post-radiotherapy hematuria. Bioinformatics analysis identified important biological processes involved in radiation-induced hematuria.

Normal Tissue Toxicity Prediction: Clinical Translation on the Horizon

Improvements in radiotherapy delivery have enabled higher therapeutic doses and improved efficacy, contributing to the growing number of long-term cancer survivors. These survivors are at risk of developing late toxicity from radiotherapy, and the inability to predict who is most susceptible results in substantial impact on quality of life and limits further curative dose escalation. A predictive assay or algorithm for normal tissue radiosensitivity would allow more personalized treatment planning, reducing the burden of late toxicity, and improving the therapeutic index. Progress over the last 10 years has shown that the etiology of late clinical radiotoxicity is multifactorial and informs development of predictive models that combine information on treatment (eg, dose, adjuvant treatment), demographic and health behaviors (eg, smoking, age), co-morbidities (eg, diabetes, collagen vascular disease), and biology (eg, genetics, ex vivo functional assays). AI has emerged as a useful tool and is facilitating extraction of signal from large datasets and development of high-level multivariable models. Some models are progressing to evaluation in clinical trials, and we anticipate adoption of these into the clinical workflow in the coming years. Information on predicted risk of toxicity could prompt modification of radiotherapy delivery (eg, use of protons, altered dose and/or fractionation, reduced volume) or, in rare instances of very high predicted risk, avoidance of radiotherapy. Risk information can also be used to assist treatment decision-making for cancers where efficacy of radiotherapy is equivalent to other treatments (eg, low-risk prostate cancer) and can be used to guide follow-up screening in instances where radiotherapy is still the best choice to maximize tumor control probability. Here, we review promising predictive assays for clinical radiotoxicity and highlight studies that are progressing to develop an evidence base for clinical utility.

Bloemen- van Gurp E, Dekker A, Fijten RRR. Development and external validation of multivariate prediction models for erectile dysfunction in men with localized prostate cancer

While the 10-year survival rate for localized prostate cancer patients is very good (>98%), side effects of treatment may limit quality of life significantly. Erectile dysfunction (ED) is a common burden associated with increasing age as well as prostate cancer treatment. Although many studies have investigated the factors affecting erectile dysfunction (ED) after prostate cancer treatment, only limited studies have investigated whether ED can be predicted before the start of treatment. The advent of machine learning (ML) based prediction tools in oncology offers a promising approach to improve the accuracy of prediction and quality of care. Predicting ED may help aid shared decision-making by making the advantages and disadvantages of certain treatments clear, so that a tailored treatment for an individual patient can be chosen. This study aimed to predict ED at 1-year and 2-year post-diagnosis based on patient demographics, clinical data and patient-reported outcomes (PROMs) measured at diagnosis. We used a subset of the ProZIB dataset collected by the Netherlands Comprehensive Cancer Organization (Integraal Kankercentrum Nederland; IKNL) that contained information on 964 localized prostate cancer cases from 69 Dutch hospitals for model training and external validation. Two models were generated using a logistic regression algorithm coupled with Recursive Feature Elimination (RFE). The first predicted ED 1 year post-diagnosis and required 10 pre-treatment variables; the second predicted ED 2 years post-diagnosis with 9 pre-treatment variables. The validation AUCs were 0.84 and 0.81 for 1 year and 2 years post-diagnosis respectively. To immediately allow patients and clinicians to use these models in the clinical decision-making process, nomograms were generated. In conclusion, we successfully developed and validated two models that predicted ED in patients with localized prostate cancer. These models will allow physicians and patients alike to make informed evidence-based decisions about the most suitable treatment with quality of life in mind.

Artificial intelligence in radiotherapy

Radiotherapy is a discipline closely integrated with computer science. Artificial intelligence (AI) has developed rapidly over the past few years. With the explosive growth of medical big data, AI promises to revolutionize the field of radiotherapy through highly automated workflow, enhanced quality assurance, improved regional balances of expert experiences, and individualized treatment guided by multi-omics. In addition to independent researchers, the increasing number of large databases, biobanks, and open challenges significantly facilitated AI studies on radiation oncology. This article reviews the latest research, clinical applications, and challenges of AI in each part of radiotherapy including image processing, contouring, planning, quality assurance, motion management, and outcome prediction. By summarizing cutting-edge findings and challenges, we aim to inspire researchers to explore more future possibilities and accelerate the arrival of AI radiotherapy.

Identification of Novel Regulators of Radiosensitivity Using High-Throughput Genetic Screening

The biological impact of ionizing radiation (IR) on humans depends not only on the physical properties and absorbed dose of radiation but also on the unique susceptibility of the exposed individual. A critical target of IR is DNA, and the DNA damage response is a safeguard mechanism for maintaining genomic integrity in response to the induced cellular stress. Unrepaired DNA lesions lead to various mutations, contributing to adverse health effects. Cellular sensitivity to IR is highly correlated with the ability of cells to repair DNA lesions, in particular coding sequences of genes that affect that process and of others that contribute to preserving genomic integrity. However, accurate profiling of the molecular events underlying individual sensitivity requires techniques with sensitive readouts. Here we summarize recent studies that have used whole-genome analysis and identified genes that impact individual radiosensitivity. Whereas microarray and RNA-seq provide a snapshot of the transcriptome, RNA interference (RNAi) and CRISPR-Cas9 techniques are powerful tools that enable modulation of gene expression and characterizing the function of specific genes involved in radiosensitivity or radioresistance. Notably, CRISPR-Cas9 has altered the landscape of genome-editing technology with its increased readiness, precision, and sensitivity. Identifying critical regulators of cellular radiosensitivity would help tailor regimens that enhance the efficacy of therapeutic treatments and fast-track prediction of clinical outcomes. It would also contribute to occupational protection based on average individual sensitivity, as well as the formulation of countermeasures to the harmful effects of radiation.

Applications of artificial intelligence in the diagnosis and prediction of erectile dysfunction: a narrative review

Despite the high prevalence of erectile dysfunction, patients are reluctant to seek medical advice, which leads to low diagnostic rates in clinical practice. Artificial intelligence has been widely applied in the diagnosis of many diseases and may alleviate the situation. However, the applications of artificial intelligence in erectile dysfunction have not been reviewed to date. Therefore, the assistance from artificial intelligence needs to be summarized. In this review, 418 publications before January 10, 2021, regarding artificial intelligence applications in diagnosing and predicting erectile dysfunction, were retrieved from five databases, including PubMed, EMBASE, the Cochrane Library, and two Chinese databases (WANFANG and CNKI). In addition, the reference lists of the included studies or relevant reviews were checked to avoid bias. Finally, 30 articles were reviewed to summarize the current status, merits, and limitations of applying artificial intelligence in diagnosing and predicting erectile dysfunction. The results showed that artificial intelligence contributed to developing novel diagnostic questionnaires, equipment, expert systems, classifiers by images and predictive models. However, most of the included studies were not subjected to external validations, resulting in doubt on the generalizability. In the future, more rigorously designed studies with high-quality datasets for erectile dysfunction are required.

Development of a method for generating SNP interaction-aware polygenic risk scores for radiotherapy toxicity

AIM

To identify the effect of single nucleotide polymorphism (SNP) interactions on the risk of toxicity following radiotherapy (RT) for prostate cancer (PCa) and propose a new method for polygenic risk score incorporating SNP-SNP interactions (PRSi).

MATERIALS AND METHODS

Analysis included the REQUITE PCa cohort that received external beam RT and was followed for 2 years. Late toxicity endpoints were: rectal bleeding, urinary frequency, haematuria, nocturia, decreased urinary stream. Among 43 literature-identified SNPs, the 30% most strongly associated with each toxicity were tested. SNP-SNP combinations (named SNP-allele sets) seen in ≥10% of the cohort were condensed into risk (RS) and protection (PS) scores, respectively indicating increased or decreased toxicity risk. Performance of RS and PS was evaluated by logistic regression. RS and PS were then combined into a single PRSi evaluated by area under the receiver operating characteristic curve (AUC).

RESULTS

Among 1,387 analysed patients, toxicity rates were 11.7% (rectal bleeding), 4.0% (urinary frequency), 5.5% (haematuria), 7.8% (nocturia) and 17.1% (decreased urinary stream). RS and PS combined 8 to 15 different SNP-allele sets, depending on the toxicity endpoint. Distributions of PRSi differed significantly in patients with/without toxicity with AUCs ranging from 0.61 to 0.78. PRSi was better than the classical summed PRS, particularly for the urinary frequency, haematuria and decreased urinary stream endpoints.

CONCLUSIONS

Our method incorporates SNP-SNP interactions when calculating PRS for radiotherapy toxicity. Our approach is better than classical summation in discriminating patients with toxicity and should enable incorporating genetic information to improve normal tissue complication probability models.

National Cancer Institute Workshop on Artificial Intelligence in Radiation Oncology: Training the Next Generation

PURPOSE

Artificial intelligence (AI) is about to touch every aspect of radiation therapy, from consultation to treatment planning, quality assurance, therapy delivery, and outcomes modeling. There is an urgent need to train radiation oncologists and medical physicists in data science to help shepherd AI solutions into clinical practice. Poorly trained personnel may do more harm than good when attempting to apply rapidly developing and complex technologies. As the amount of AI research expands in our field, the radiation oncology community needs to discuss how to educate future generations in this area.

METHODS AND MATERIALS

The National Cancer Institute (NCI) Workshop on AI in Radiation Oncology (Shady Grove, MD, April 4-5, 2019) was the first of 2 data science workshops in radiation oncology hosted by the NCI in 2019. During this workshop, the Training and Education Working Group was formed by volunteers among the invited attendees. Its members represent radiation oncology, medical physics, radiology, computer science, industry, and the NCI.

RESULTS

In this perspective article written by members of the Training and Education Working Group, we provide and discuss action points relevant for future trainees interested in radiation oncology AI: (1) creating AI awareness and responsible conduct; (2) implementing a practical didactic curriculum; (3) creating a publicly available database of training resources; and (4) accelerating learning and funding opportunities.

CONCLUSION

Together, these action points can facilitate the translation of AI into clinical practice.

Identification of biological correlates associated with respiratory failure in COVID-19

Background

Coronavirus disease 2019 (COVID-19) is a global public health concern. Recently, a genome-wide association study (GWAS) was performed with participants recruited from Italy and Spain by an international consortium group.

Methods

Summary GWAS statistics for 1610 patients with COVID-19 respiratory failure and 2205 controls were downloaded. In the current study, we analyzed the summary statistics with the information of loci and p-values for 8,582,968 single-nucleotide polymorphisms (SNPs), using gene ontology analysis to determine the top biological processes implicated in respiratory failure in COVID-19 patients.

Results

We considered the top 708 SNPs, using a p-value cutoff of 5 × 10^− 5, which were mapped to the nearest genes, leading to 144 unique genes. The list of genes was input into a curated database to conduct gene ontology and protein-protein interaction (PPI) analyses. The top ranked biological processes were wound healing, epithelial structure maintenance, muscle system processes, and cardiac-relevant biological processes with a false discovery rate < 0.05. In the PPI analysis, the largest connected network consisted of 8 genes. Through a literature search, 7 out of the 8 gene products were found to be implicated in both pulmonary and cardiac diseases.

Conclusion

Gene ontology and PPI analyses identified cardio-pulmonary processes that may partially explain the risk of respiratory failure in COVID-19 patients.

Harnessing genome-wide association studies to minimize adverse radiation-induced side effects

Radiotherapy is used as definitive treatment in approximately two-thirds of all cancers. However, like any treatment, radiation has significant acute and long-term side effects including secondary malignancies. Even when similar radiation parameters are used, 5%–10% of patients will experience adverse radiation side effects. Genomic susceptibility is thought to be responsible for approximately 40% of the clinical variability observed. In the era of precision medicine, the link between genetic susceptibility and radiation-induced side effects is further strengthening. Genome-wide association studies (GWAS) have begun to identify single-nucleotide polymorphisms (SNPs) attributed to overall and tissue-specific toxicity following radiation for treatment of breast cancer, prostate cancer, and other cancers. Here, we review the use of GWAS in identifying polymorphisms that are predictive of acute and long-term radiation-induced side effects with a focus on chest, pelvic, and head-and-neck irradiation. Integration of GWAS with “omic” data, patient characteristics, and clinical correlates into predictive models could decrease radiation-induced side effects while increasing therapeutic efficacy.

A Deep Learning Approach Validates Genetic Risk Factors for Late Toxicity After Prostate Cancer Radiotherapy in a REQUITE Multi-National Cohort

Background: REQUITE (validating pREdictive models and biomarkers of radiotherapy toxicity to reduce side effects and improve QUalITy of lifE in cancer survivors) is an international prospective cohort study. The purpose of this project was to analyse a cohort of patients recruited into REQUITE using a deep learning algorithm to identify patient-specific features associated with the development of toxicity, and test the approach by attempting to validate previously published genetic risk factors. Methods: The study involved REQUITE prostate cancer patients treated with external beam radiotherapy who had complete 2-year follow-up. We used five separate late toxicity endpoints: ≥grade 1 late rectal bleeding, ≥grade 2 urinary frequency, ≥grade 1 haematuria, ≥ grade 2 nocturia, ≥ grade 1 decreased urinary stream. Forty-three single nucleotide polymorphisms (SNPs) already reported in the literature to be associated with the toxicity endpoints were included in the analysis. No SNP had been studied before in the REQUITE cohort. Deep Sparse AutoEncoders (DSAE) were trained to recognize features (SNPs) identifying patients with no toxicity and tested on a different independent mixed population including patients without and with toxicity. Results: One thousand, four hundred and one patients were included, and toxicity rates were: rectal bleeding 11.7%, urinary frequency 4%, haematuria 5.5%, nocturia 7.8%, decreased urinary stream 17.1%. Twenty-four of the 43 SNPs that were associated with the toxicity endpoints were validated as identifying patients with toxicity. Twenty of the 24 SNPs were associated with the same toxicity endpoint as reported in the literature: 9 SNPs for urinary symptoms and 11 SNPs for overall toxicity. The other 4 SNPs were associated with a different endpoint. Conclusion: Deep learning algorithms can validate SNPs associated with toxicity after radiotherapy for prostate cancer. The method should be studied further to identify polygenic SNP risk signatures for radiotherapy toxicity. The signatures could then be included in integrated normal tissue complication probability models and tested for their ability to personalize radiotherapy treatment planning.

Prediction of Breast Cancer Treatment-Induced Fatigue by Machine Learning Using Genome-Wide Association Data

BACKGROUND

We aimed at predicting fatigue after breast cancer treatment using machine learning on clinical covariates and germline genome-wide data.

METHODS

We accessed germline genome-wide data of 2799 early-stage breast cancer patients from the Cancer Toxicity study (NCT01993498). The primary endpoint was defined as scoring zero at diagnosis and higher than quartile 3 at 1 year after primary treatment completion on European Organization for Research and Treatment of Cancer quality-of-life questionnaires for Overall Fatigue and on the multidimensional questionnaire for Physical, Emotional, and Cognitive fatigue. First, we tested univariate associations of each endpoint with clinical variables and genome-wide variants. Then, using preselected clinical (false discovery rate < 0.05) and genomic (P < .001) variables, a multivariable preconditioned random-forest regression model was built and validated on a hold-out subset to predict fatigue. Gene set enrichment analysis identified key biological correlates (MetaCore). All statistical tests were 2-sided.

RESULTS

Statistically significant clinical associations were found only with Emotional and Cognitive Fatigue, including receipt of chemotherapy, anxiety, and pain. Some single nucleotide polymorphisms had some degree of association (P < .001) with the different fatigue endpoints, although there were no genome-wide statistically significant (P < 5.00 × 10^-8) associations. Only for Cognitive Fatigue, the predictive ability of the genomic multivariable model was statistically significantly better than random (area under the curve = 0.59, P = .01) and marginally improved with clinical variables (area under the curve = 0.60, P = .005). Single nucleotide polymorphisms found to be associated (P < .001) with Cognitive Fatigue belonged to genes linked to inflammation (false discovery rate adjusted P = .03), cognitive disorders (P = 1.51 × 10^-12), and synaptic transmission (P = 6.28 × 10^-8).

CONCLUSIONS

Genomic analyses in this large cohort of breast cancer survivors suggest a possible genetic role for severe Cognitive Fatigue that warrants further exploration.

Prediction of Breast Cancer Treatment-Induced Fatigue by Machine Learning Using Genome-Wide Association Data

BACKGROUND

We aimed at predicting fatigue after breast cancer treatment using machine learning on clinical covariates and germline genome-wide data.

METHODS

We accessed germline genome-wide data of 2799 early-stage breast cancer patients from the Cancer Toxicity study (NCT01993498). The primary endpoint was defined as scoring zero at diagnosis and higher than quartile 3 at 1 year after primary treatment completion on European Organization for Research and Treatment of Cancer quality-of-life questionnaires for Overall Fatigue and on the multidimensional questionnaire for Physical, Emotional, and Cognitive fatigue. First, we tested univariate associations of each endpoint with clinical variables and genome-wide variants. Then, using preselected clinical (false discovery rate < 0.05) and genomic (P < .001) variables, a multivariable preconditioned random-forest regression model was built and validated on a hold-out subset to predict fatigue. Gene set enrichment analysis identified key biological correlates (MetaCore). All statistical tests were 2-sided.

RESULTS

Statistically significant clinical associations were found only with Emotional and Cognitive Fatigue, including receipt of chemotherapy, anxiety, and pain. Some single nucleotide polymorphisms had some degree of association (P < .001) with the different fatigue endpoints, although there were no genome-wide statistically significant (P < 5.00 × 10-8) associations. Only for Cognitive Fatigue, the predictive ability of the genomic multivariable model was statistically significantly better than random (area under the curve = 0.59, P = .01) and marginally improved with clinical variables (area under the curve = 0.60, P = .005). Single nucleotide polymorphisms found to be associated (P < .001) with Cognitive Fatigue belonged to genes linked to inflammation (false discovery rate adjusted P = .03), cognitive disorders (P = 1.51 × 10-12), and synaptic transmission (P = 6.28 × 10-8).

CONCLUSIONS

Genomic analyses in this large cohort of breast cancer survivors suggest a possible genetic role for severe Cognitive Fatigue that warrants further exploration.

The Application of Artificial Intelligence in Prostate Cancer Management—What Improvements Can Be Expected? A Systematic Review

Artificial Intelligence (AI) is progressively remodeling our daily life. A large amount of information from “big data” now enables machines to perform predictions and improve our healthcare system. AI has the potential to reshape prostate cancer (PCa) management thanks to growing applications in the field. The purpose of this review is to provide a global overview of AI in PCa for urologists, pathologists, radiotherapists, and oncologists to consider future changes in their daily practice. A systematic review was performed, based on PubMed MEDLINE, Google Scholar, and DBLP databases for original studies published in English from January 2009 to January 2019 relevant to PCa, AI, Machine Learning, Artificial Neural Networks, Convolutional Neural Networks, and Natural-Language Processing. Only articles with full text accessible were considered. A total of 1008 articles were reviewed, and 48 articles were included. AI has potential applications in all fields of PCa management: analysis of genetic predispositions, diagnosis in imaging, and pathology to detect PCa or to differentiate between significant and non-significant PCa. AI also applies to PCa treatment, whether surgical intervention or radiotherapy, skills training, or assessment, to improve treatment modalities and outcome prediction. AI in PCa management has the potential to provide a useful role by predicting PCa more accurately, using a multiomic approach and risk-stratifying patients to provide personalized medicine.

Machine Learning-Based Models for Prediction of Toxicity Outcomes in Radiotherapy

In order to limit radiotherapy (RT)-related side effects, effective toxicity prediction and assessment schemes are essential. In recent years, the growing interest toward artificial intelligence and machine learning (ML) within the science community has led to the implementation of innovative tools in RT. Several researchers have demonstrated the high performance of ML-based models in predicting toxicity, but the application of these approaches in clinics is still lagging, partly due to their low interpretability. Therefore, an overview of contemporary research is needed in order to familiarize practitioners with common methods and strategies. Here, we present a review of ML-based models for predicting and classifying RT-induced complications from both a methodological and a clinical standpoint, focusing on the type of features considered, the ML methods used, and the main results achieved. Our work overviews published research in multiple cancer sites, including brain, breast, esophagus, gynecological, head and neck, liver, lung, and prostate cancers. The aim is to define the current state of the art and main achievements within the field for both researchers and clinicians.

Genomics models in radiotherapy: From mechanistic to machine learning

Machine learning (ML) provides a broad framework for addressing high-dimensional prediction problems in classification and regression. While ML is often applied for imaging problems in medical physics, there are many efforts to apply these principles to biological data toward questions of radiation biology. Here, we provide a review of radiogenomics modeling frameworks and efforts toward genomically guided radiotherapy. We first discuss medical oncology efforts to develop precision biomarkers. We next discuss similar efforts to create clinical assays for normal tissue or tumor radiosensitivity. We then discuss modeling frameworks for radiosensitivity and the evolution of ML to create predictive models for radiogenomics.

Reaching the End-Game for GWAS: Machine Learning Approaches for the Prioritization of Complex Disease Loci

Genome-wide association studies (GWAS) have revealed thousands of genetic loci that underpin the complex biology of many human traits. However, the strength of GWAS - the ability to detect genetic association by linkage disequilibrium (LD) - is also its limitation. Whilst the ever-increasing study size and improved design have augmented the power of GWAS to detect effects, differentiation of causal variants or genes from other highly correlated genes associated by LD remains the real challenge. This has severely hindered the biological insights and clinical translation of GWAS findings. Although thousands of disease susceptibility loci have been reported, causal genes at these loci remain elusive. Machine learning (ML) techniques offer an opportunity to dissect the heterogeneity of variant and gene signals in the post-GWAS analysis phase. ML models for GWAS prioritization vary greatly in their complexity, ranging from relatively simple logistic regression approaches to more complex ensemble models such as random forests and gradient boosting, as well as deep learning models, i.e., neural networks. Paired with functional validation, these methods show important promise for clinical translation, providing a strong evidence-based approach to direct post-GWAS research. However, as ML approaches continue to evolve to meet the challenge of causal gene identification, a critical assessment of the underlying methodologies and their applicability to the GWAS prioritization problem is needed. This review investigates the landscape of ML applications in three parts: selected models, input features, and output model performance, with a focus on prioritizations of complex disease associated loci. Overall, we explore the contributions ML has made towards reaching the GWAS end-game with consequent wide-ranging translational impact.

Machine learning on genome-wide association studies to predict the risk of radiation-associated contralateral breast cancer in the WECARE Study

The purpose of this study was to identify germline single nucleotide polymorphisms (SNPs) that optimally predict radiation-associated contralateral breast cancer (RCBC) and to provide new biological insights into the carcinogenic process. Fifty-two women with contralateral breast cancer and 153 women with unilateral breast cancer were identified within the Women’s Environmental Cancer and Radiation Epidemiology (WECARE) Study who were at increased risk of RCBC because they were ≤ 40 years of age at first diagnosis of breast cancer and received a scatter radiation dose > 1 Gy to the contralateral breast. A previously reported algorithm, preconditioned random forest regression, was applied to predict the risk of developing RCBC. The resulting model produced an area under the curve (AUC) of 0.62 (p = 0.04) on hold-out validation data. The biological analysis identified the cyclic AMP-mediated signaling and Ephrin-A as significant biological correlates, which were previously shown to influence cell survival after radiation in an ATM-dependent manner. The key connected genes and proteins that are identified in this analysis were previously identified as relevant to breast cancer, radiation response, or both. In summary, machine learning/bioinformatics methods applied to genome-wide genotyping data have great potential to reveal plausible biological correlates associated with the risk of RCBC.

Long-term Consequences of Pelvic Irradiation: Toxicities, Challenges, and Therapeutic Opportunities with Pharmacologic Mitigators

A percentage of long-term cancer survivors who receive pelvic irradiation will develop treatment-related late effects, collectively termed pelvic radiation disease. Thus, there is a need to prevent or ameliorate treatment-related late effects in these patients. Modern radiotherapy methods can preferentially protect normal tissues from radiation toxicities to permit higher doses to targets. However, concerns about chronic small bowel toxicity, for example, still constrain the prescription dose. This provides strong rationale for considering adding pharmacologic mitigators. Implementation of modern targeted radiotherapy methods enables delivery of focused radiation to target volumes, while minimizing dose to normal tissues. In prostate cancer, these technical advances enabled safe radiation dose escalation and better local tumor control without increasing normal tissue complications. In other pelvic diseases, these new radiotherapy methods have not resulted in the low probability of normal tissue damage achieved with prostate radiotherapy. The persistence of toxicity provides rationale for pharmacologic mitigators. Several new agents could be readily tested in clinical trials because they are being or have been studied in human patients already. Although there are promising preclinical data supporting mitigators, no clinically proven options to treat or prevent pelvic radiation disease currently exist. This review highlights therapeutic options for prevention and/or treatment of pelvic radiation disease, using pharmacologic mitigators. Successful development of mitigators would reduce the number of survivors who suffer from these devastating consequences of pelvic radiotherapy. It is important to note that pharmacologic mitigators to ameliorate pelvic radiation disease may be applicable to other irradiated sites in which chronic toxicity impairs quality of life.

Germinal immunogenetics as a predictive factor for immunotherapy

Clinical response to checkpoint inhibitors-based (CPIs) therapies can vary among tumor types and between patients. This led to a significant amount of pre-clinical and clinical research into biomarker identification. Biomarkers have been found to cover both the tumor itself and the tumor microenvironment. Entering host-related parameters into the equation should provide a valuable strategy for identifying not only factors predictive of treatment efficacy but also of treatment-related toxicity. It is clear that germline variants can offer efficient and easily-assessable indicators (blood DNA) to enlarge the spectrum of predictive markers for CPI-based treatment. A major issue concerns the real functional significance of the reported single-nucleotide polymorphisms (SNPs) linked to CPI-treatment outcome. Powered calculations should lead to an optimal trade-off between sample size and allele frequency. New molecular technologies and new analytical methods should provide opportunities to bridge the knowledge gap between SNP-CPI treatment associations and the functional impact of these SNPs.

Machine Learning and Radiogenomics: Lessons Learned and Future Directions

Due to the rapid increase in the availability of patient data, there is significant interest in precision medicine that could facilitate the development of a personalized treatment plan for each patient on an individual basis. Radiation oncology is particularly suited for predictive machine learning (ML) models due to the enormous amount of diagnostic data used as input and therapeutic data generated as output. An emerging field in precision radiation oncology that can take advantage of ML approaches is radiogenomics, which is the study of the impact of genomic variations on the sensitivity of normal and tumor tissue to radiation. Currently, patients undergoing radiotherapy are treated using uniform dose constraints specific to the tumor and surrounding normal tissues. This is suboptimal in many ways. First, the dose that can be delivered to the target volume may be insufficient for control but is constrained by the surrounding normal tissue, as dose escalation can lead to significant morbidity and rare. Second, two patients with nearly identical dose distributions can have substantially different acute and late toxicities, resulting in lengthy treatment breaks and suboptimal control, or chronic morbidities leading to poor quality of life. Despite significant advances in radiogenomics, the magnitude of the genetic contribution to radiation response far exceeds our current understanding of individual risk variants. In the field of genomics, ML methods are being used to extract harder-to-detect knowledge, but these methods have yet to fully penetrate radiogenomics. Hence, the goal of this publication is to provide an overview of ML as it applies to radiogenomics. We begin with a brief history of radiogenomics and its relationship to precision medicine. We then introduce ML and compare it to statistical hypothesis testing to reflect on shared lessons and to avoid common pitfalls. Current ML approaches to genome-wide association studies are examined. The application of ML specifically to radiogenomics is next presented. We end with important lessons for the proper integration of ML into radiogenomics.

Machine Learning on a Genome-wide Association Study to Predict Late Genitourinary Toxicity After Prostate Radiation Therapy

PURPOSE

Late genitourinary (GU) toxicity after radiation therapy limits the quality of life of prostate cancer survivors; however, efforts to explain GU toxicity using patient and dose information have remained unsuccessful. We identified patients with a greater congenital GU toxicity risk by identifying and integrating patterns in genome-wide single nucleotide polymorphisms (SNPs).

METHODS AND MATERIALS

We applied a preconditioned random forest regression method for predicting risk from the genome-wide data to combine the effects of multiple SNPs and overcome the statistical power limitations of single-SNP analysis. We studied a cohort of 324 prostate cancer patients who were self-assessed for 4 urinary symptoms at 2 years after radiation therapy using the International Prostate Symptom Score.

RESULTS

The predictive accuracy of the method varied across the symptoms. Only for the weak stream endpoint did it achieve a significant area under the curve of 0.70 (95% confidence interval 0.54-0.86; P = .01) on hold-out validation data that outperformed competing methods. Gene ontology analysis highlighted key biological processes, such as neurogenesis and ion transport, from the genes known to be important for urinary tract functions.

CONCLUSIONS

We applied machine learning methods and bioinformatics tools to genome-wide data to predict and explain GU toxicity. Our approach enabled the design of a more powerful predictive model and the determination of plausible biomarkers and biological processes associated with GU toxicity.