Robust SNP-based prediction of rheumatoid arthritis through machine-learning-optimized polygenic risk score.

BACKGROUND: The popular statistics-based Genome-wide association studies (GWAS) have provided deep insights into the field of complex disorder genetics. However, its clinical applicability to predict disease/trait outcomes remains unclear as statistical models are not designed to make predictions. This study employs statistics-free machine-learning (ML)-optimized polygenic risk score (PRS) to complement existing GWAS and bring the prediction of disease/trait outcomes closer to clinical application. Rheumatoid Arthritis (RA) was selected as a model disease to demonstrate the robustness of ML in disease prediction as RA is a prevalent chronic inflammatory joint disease with high mortality rates, affecting adults at the economic prime. Early identification of at-risk individuals may facilitate measures to mitigate the effects of the disease. METHODS: This study employs a robust ML feature selection algorithm to identify single nucleotide polymorphisms (SNPs) that can predict RA from a set of training data comprising RA patients and population control samples. Thereafter, selected SNPs were evaluated for their predictive performances across 3 independent, unseen test datasets. The selected SNPs were subsequently used to generate PRS which was also evaluated for its predictive capacity as a sole feature. RESULTS: Through robust ML feature selection, 9 SNPs were found to be the minimum number of features for excellent predictive performance (AUC > 0.9) in 3 independent, unseen test datasets. PRS based on these 9 SNPs was significantly associated with (P < 1 × 10-16) and predictive (AUC > 0.9) of RA in the 3 unseen datasets. A RA ML-PRS calculator of these 9 SNPs was developed ( https://xistance.shinyapps.io/prs-ra/ ) to facilitate individualized clinical applicability. The majority of the predictive SNPs are protective, reside in non-coding regions, and are either predicted to be potentially functional SNPs (pfSNPs) or in high linkage disequilibrium (r2 > 0.8) with un-interrogated pfSNPs. CONCLUSIONS: These findings highlight the promise of this ML strategy to identify useful genetic features that can robustly predict disease and amenable to translation for clinical application.

Machine learning using genetic and clinical data identifies a signature that robustly predicts methotrexate response in rheumatoid arthritis.

OBJECTIVE: To develop a hypothesis-free model that best predicts response to MTX drug in RA patients utilizing biologically meaningful genetic feature selection of potentially functional single nucleotide polymorphisms (pfSNPs) through robust machine learning (ML) feature selection methods. METHODS: MTX-treated RA patients with known response were divided in a 4:1 ratio into training and test sets. From the patients' exomes, potential features for classifier prediction were identified from pfSNPs and non-genetic factors through ML using recursive feature elimination with cross-validation incorporating the random forest classifier. Feature selection was repeated on random subsets of the training cohort, and consensus features were assembled into the final feature set. This feature set was evaluated for predictive potential using six ML classifiers, first by cross-validation within the training set, and finally by analysing its performance with the unseen test set. RESULTS: The final feature set contains 56 pfSNPs and five non-genetic factors. The majority of these pfSNPs are located in pathways related to RA pathogenesis or MTX action and are predicted to modulate gene expression. When used for training in six ML classifiers, performance was good in both the training set (area under the curve: 0.855-0.916; sensitivity: 0.715-0.892; and specificity: 0.733-0.862) and the unseen test set (area under the curve: 0.751-0.826; sensitivity: 0.581-0.839; and specificity: 0.641-0.923). CONCLUSION: Sensitive and specific predictors of MTX response in RA patients were identified in this study through a novel strategy combining biologically meaningful and machine learning feature selection and training. These predictors may facilitate better treatment decision-making in RA management.

Machine Learning Identifies a Signature of Nine Exosomal RNAs That Predicts Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related death worldwide. Although alpha fetoprotein (AFP) remains a commonly used serological marker of HCC, the sensitivity and specificity of AFP in detecting HCC is often limited. Exosomal RNA has emerged as a promising diagnostic tool for various cancers, but its use in HCC detection has yet to be fully explored. Here, we employed Machine Learning on 114,602 exosomal RNAs to identify a signature that can predict HCC. The exosomal expression data of 118 HCC patients and 112 healthy individuals were stratified split into Training, Validation and Unseen Test datasets. Feature selection was then performed on the initial training dataset using permutation importance, and the predictive performance of the selected features were tested on the validation dataset using Support Vector Machine (SVM) Classifier. A minimum of nine features were identified to be predictive of HCC and these nine features were then evaluated across six different models in an unseen test set. These features, mainly in the immune, platelet/neutrophil and cytoskeletal pathways, exhibited good predictive performance with ROC-AUC from 0.79-0.88 in the unseen test set. Hence, these nine exosomal RNAs have potential to be clinically useful minimally invasive biomarkers for HCC.

Functional coding haplotypes and machine-learning feature elimination identifies predictors of Methotrexate Response in Rheumatoid Arthritis patients.

BACKGROUND: Major challenges in large scale genetic association studies include not only the identification of causative single nucleotide polymorphisms (SNPs), but also accounting for SNP-SNP interactions. This study thus proposes a novel feature engineering approach integrating potentially functional coding haplotypes (pfcHap) with machine-learning (ML) feature selection to identify biologically meaningful, possibly causative genetic factors, that take into consideration potential SNP-SNP interactions within the pfcHap, to best predict for methotrexate (MTX) response in rheumatoid arthritis (RA) patients. METHODS: Exome sequencing from 349 RA patients were analysed, of which they were split into training and unseen test set. Inferred pfcHaps were combined with 30 non-genetic features to undergo ML recursive feature elimination with cross-validation using the training set. Predictive capacity and robustness of the selected features were assessed using six popular machine learning models through a train set cross-validation and evaluated in an unseen test set. FINDINGS: Significantly, 100 features (95 pfcHaps, 5 non-genetic factors) were identified to have good predictive performance (AUC: 0.776-0.828; Sensitivity: 0.656-0.813; Specificity: 0.684-0.868) across all six ML models in an unseen test dataset for the prediction of MTX response in RA patients. INTERPRETATION: Majority of the predictive pfcHap SNPs were predicted to be potentially functional and some of the genes in which the pfcHap resides in were identified to be associated with previously reported MTX/RA pathways. FUNDING: Singapore Ministry of Health's National Medical Research Council (NMRC) [NMRC/CBRG/0095/2015; CG12Aug17; CGAug16M012; NMRC/CG/017/2013]; National Cancer Center Research Fund and block funding Duke-NUS Medical School.; Singapore Ministry of Education Academic Research Fund Tier 2 grant MOE2019-T2-1-138.

Sentiments Regarding COVID-19 Vaccination among Graduate Students in Singapore.

As the COVID-19 pandemic rages unabated, and with more infectious variants, vaccination may offer a way to transit out of strict restrictions on physical human interactions to curb the virus spread and prevent overwhelming the healthcare system. However, vaccine hesitancy threatens to significantly impact our progress towards achieving this. It is thus important to understand the sentiments regarding vaccination for different segments of the population to facilitate the development of effective strategies to persuade these groups. Here, we surveyed the COVID-19 vaccination sentiments among a highly educated group of graduate students from the National University of Singapore (NUS). Graduate students who are citizens of 54 different countries, mainly from Asia, pursue studies in diverse fields, with 32% expressing vaccine hesitancy. Citizenship, religion, country of undergraduate/postgraduate studies, exposure risk and field of study are significantly associated with vaccine sentiments. Students who are Chinese citizens or studied in Chinese Universities prior to joining NUS are more hesitant, while students of Indian descent or studied in India are less hesitant about vaccination. Side effects, safety issues and vaccine choice are the major concerns of the hesitant group. Hence, this study would facilitate the development of strategies that focus on these determinants to enhance vaccine acceptance.

Highly deregulated lncRNA LOC is associated with overall worse prognosis in Hepatocellular Carcinoma patients.

Although numerous long non-coding RNAs (lncRNAs) were reported to be deregulated in Hepatocellular Carcinoma (HCC), experimentally characterized, and/or associated with patient's clinical characteristics, there is, thus far, minimal concerted research strategy to identify deregulated lncRNAs that modulate prognosis of HCC patients. Here, we present a novel strategy where we identify lncRNAs, which are not only de-regulated in HCC patients, but are also associated with pertinent clinical characteristics, potentially contributing to the prognosis of HCC patients. LOC101926913 (LOC) was further characterized because it is the most highly differentially expressed amongst those that are associated with the most number of clinical features (tumor-stage, vascular and tumor invasion and poorer overall survival). Experimental gain- and loss-of-function manipulation of LOC in liver cell-lines highlight LOC as a potential onco-lncRNA promoting cell proliferation, anchorage independent growth and invasion. LOC expression in cells up-regulated genes involved in GTPase-activities and downregulated genes associated with cellular detoxification, oxygen- and drug-transport. Hence, LOC may represent a novel therapeutic target, modulating prognosis of HCC patients through up-regulating GTPase-activities and down-regulating detoxification, oxygen- and drug-transport. This strategy may thus be useful for the identification of clinically relevant lncRNAs as potential biomarkers/targets that modulate prognosis in other cancers as well.

Network of clinically-relevant lncRNAs-mRNAs associated with prognosis of hepatocellular carcinoma patients.

Long non-coding RNAs (lncRNAs) are often aberrantly expressed in Hepatocellular Carcinoma (HCC). We hypothesize that lncRNAs modulate HCC prognoses through differential deregulation of key lncRNAs affecting important gene network in key cancer pathways associated with pertinent clinical phenotype. Here, we present a novel approach integrating lncRNA-mRNA expression profiles with clinical characteristics to identify lncRNA signatures in clinically-relevant co-expression lncRNA-mRNA networks residing in pertinent cancer pathways. Notably one network, associated with poorer prognosis, comprises five up-regulated lncRNAs significantly correlated (|Pearson Correlation Coefficient|≥ 0.9) with 91 up-regulated genes in the cell-cycle and Rho-GTPase pathways. All 5 lncRNAs and 85/91 (93.4%) of the correlated genes were significantly associated with higher tumor-grade while 3/5 lncRNAs were also associated with no tumor capsule. Interestingly, 2/5 lncRNAs that are correlated with numerous genes in this oncogenic network were experimentally shown to up-regulate genes involved in cell-cycle and transcriptional regulation. Another network comprising 4 down-regulated lncRNAs and 8 down-regulated metallothionein-family genes are significantly associated with tumor invasion. The identification of these key lncRNAs signatures that deregulate important network of genes in key cancer pathways associated with pertinent clinical phenotype may facilitate the design of novel therapeutic strategies targeting these 'master' regulators for better patient outcome.

Roles and Regulation of Long Noncoding RNAs in Hepatocellular Carcinoma.

Next-generation sequencing has uncovered thousands of long noncoding RNAs (lncRNA). Many are reported to be aberrantly expressed in various cancers, including hepatocellular carcinoma (HCC), and play key roles in tumorigenesis. This review provides an in-depth discussion of the oncogenic mechanisms reported to be associated with deregulated HCC-associated lncRNAs. Transcriptional expression of lncRNAs in HCC is modulated through transcription factors, or epigenetically by aberrant histone acetylation or DNA methylation, and posttranscriptionally by lncRNA transcript stability modulated by miRNAs and RNA-binding proteins. Seventy-four deregulated lncRNAs have been identified in HCC, of which, 52 are upregulated. This review maps the oncogenic roles of these deregulated lncRNAs by integrating diverse datasets including clinicopathologic features, affected cancer phenotypes, associated miRNA and/or protein-interacting partners as well as modulated gene/protein expression. Notably, 63 deregulated lncRNAs are significantly associated with clinicopathologic features of HCC. Twenty-three deregulated lncRNAs associated with both tumor and metastatic clinical features were also tumorigenic and prometastatic in experimental models of HCC, and eight of these mapped to known cancer pathways. Fifty-two upregulated lncRNAs exhibit oncogenic properties and are associated with prominent hallmarks of cancer, whereas 22 downregulated lncRNAs have tumor-suppressive properties. Aberrantly expressed lncRNAs in HCC exert pleiotropic effects on miRNAs, mRNAs, and proteins. They affect multiple cancer phenotypes by altering miRNA and mRNA expression and stability, as well as through effects on protein expression, degradation, structure, or interactions with transcriptional regulators. Hence, these insights reveal novel lncRNAs as potential biomarkers and may enable the design of precision therapy for HCC.