Genome-wide interaction analysis of folate for colorectal cancer risk.

BACKGROUND: Epidemiological and experimental evidence suggests that higher folate intake is associated with decreased colorectal cancer (CRC) risk; however, the mechanisms underlying this relationship are not fully understood. Genetic variation that may have a direct or indirect impact on folate metabolism can provide insights into folate's role in CRC. OBJECTIVES: Our aim was to perform a genome-wide interaction analysis to identify genetic variants that may modify the association of folate on CRC risk. METHODS: We applied traditional case-control logistic regression, joint 3-degree of freedom, and a 2-step weighted hypothesis approach to test the interactions of common variants (allele frequency >1%) across the genome and dietary folate, folic acid supplement use, and total folate in relation to risk of CRC in 30,550 cases and 42,336 controls from 51 studies from 3 genetic consortia (CCFR, CORECT, GECCO). RESULTS: Inverse associations of dietary, total folate, and folic acid supplement with CRC were found (odds ratio [OR]: 0.93; 95% confidence interval [CI]: 0.90, 0.96; and 0.91; 95% CI: 0.89, 0.94 per quartile higher intake, and 0.82 (95% CI: 0.78, 0.88) for users compared with nonusers, respectively). Interactions (P-interaction < 5×10-8) of folic acid supplement and variants in the 3p25.2 locus (in the region of Synapsin II [SYN2]/tissue inhibitor of metalloproteinase 4 [TIMP4]) were found using traditional interaction analysis, with variant rs150924902 (located upstream to SYN2) showing the strongest interaction. In stratified analyses by rs150924902 genotypes, folate supplementation was associated with decreased CRC risk among those carrying the TT genotype (OR: 0.82; 95% CI: 0.79, 0.86) but increased CRC risk among those carrying the TA genotype (OR: 1.63; 95% CI: 1.29, 2.05), suggesting a qualitative interaction (P-interaction = 1.4×10-8). No interactions were observed for dietary and total folate. CONCLUSIONS: Variation in 3p25.2 locus may modify the association of folate supplement with CRC risk. Experimental studies and studies incorporating other relevant omics data are warranted to validate this finding.

Probing the diabetes and colorectal cancer relationship using gene - environment interaction analyses.

BACKGROUND: Diabetes is an established risk factor for colorectal cancer. However, the mechanisms underlying this relationship still require investigation and it is not known if the association is modified by genetic variants. To address these questions, we undertook a genome-wide gene-environment interaction analysis. METHODS: We used data from 3 genetic consortia (CCFR, CORECT, GECCO; 31,318 colorectal cancer cases/41,499 controls) and undertook genome-wide gene-environment interaction analyses with colorectal cancer risk, including interaction tests of genetics(G)xdiabetes (1-degree of freedom; d.f.) and joint testing of Gxdiabetes, G-colorectal cancer association (2-d.f. joint test) and G-diabetes correlation (3-d.f. joint test). RESULTS: Based on the joint tests, we found that the association of diabetes with colorectal cancer risk is modified by loci on chromosomes 8q24.11 (rs3802177, SLC30A8 - ORAA: 1.62, 95% CI: 1.34-1.96; ORAG: 1.41, 95% CI: 1.30-1.54; ORGG: 1.22, 95% CI: 1.13-1.31; p-value3-d.f.: 5.46 × 10-11) and 13q14.13 (rs9526201, LRCH1 - ORGG: 2.11, 95% CI: 1.56-2.83; ORGA: 1.52, 95% CI: 1.38-1.68; ORAA: 1.13, 95% CI: 1.06-1.21; p-value2-d.f.: 7.84 × 10-09). DISCUSSION: These results suggest that variation in genes related to insulin signaling (SLC30A8) and immune function (LRCH1) may modify the association of diabetes with colorectal cancer risk and provide novel insights into the biology underlying the diabetes and colorectal cancer relationship.

A Genetic Locus within the FMN1/GREM1 Gene Region Interacts with Body Mass Index in Colorectal Cancer Risk.

Colorectal cancer risk can be impacted by genetic, environmental, and lifestyle factors, including diet and obesity. Gene-environment interactions (G × E) can provide biological insights into the effects of obesity on colorectal cancer risk. Here, we assessed potential genome-wide G × E interactions between body mass index (BMI) and common SNPs for colorectal cancer risk using data from 36,415 colorectal cancer cases and 48,451 controls from three international colorectal cancer consortia (CCFR, CORECT, and GECCO). The G × E tests included the conventional logistic regression using multiplicative terms (one degree of freedom, 1DF test), the two-step EDGE method, and the joint 3DF test, each of which is powerful for detecting G × E interactions under specific conditions. BMI was associated with higher colorectal cancer risk. The two-step approach revealed a statistically significant G×BMI interaction located within the Formin 1/Gremlin 1 (FMN1/GREM1) gene region (rs58349661). This SNP was also identified by the 3DF test, with a suggestive statistical significance in the 1DF test. Among participants with the CC genotype of rs58349661, overweight and obesity categories were associated with higher colorectal cancer risk, whereas null associations were observed across BMI categories in those with the TT genotype. Using data from three large international consortia, this study discovered a locus in the FMN1/GREM1 gene region that interacts with BMI on the association with colorectal cancer risk. Further studies should examine the potential mechanisms through which this locus modifies the etiologic link between obesity and colorectal cancer. SIGNIFICANCE: This gene-environment interaction analysis revealed a genetic locus in FMN1/GREM1 that interacts with body mass index in colorectal cancer risk, suggesting potential implications for precision prevention strategies.

A systematic literature review of machine learning application in COVID-19 medical image classification.

Detecting COVID-19 as early as possible and quickly is one way to stop the spread of COVID-19. Machine learning development can help to diagnose COVID-19 more quickly and accurately. This report aims to find out how far research has progressed and what lessons can be learned for future research in this sector. By filtering titles, abstracts, and content in the Google Scholar database, this literature review was able to find 19 related papers to answer two research questions, i.e. what medical images are commonly used for COVID-19 classification and what are the methods for COVID-19 classification. According to the findings, chest X-ray were the most commonly used data to categorize COVID-19 and transfer learning techniques were the method used in this study. Researchers also concluded that lung segmentation and use of multimodal data could improve performance.

Counting people inside a region-of-interest in CCTV footage with deep learning.

In recent years, the performance of people-counting models has been dramatically increased that they can be implemented in practical cases. However, the current models can only count all of the people captured in the inputted closed circuit television (CCTV) footage. Oftentimes, we only want to count people in a specific Region-of-Interest (RoI) in the footage. Unfortunately, simple approaches such as covering the area outside of the RoI are not applicable without degrading the performance of the models. Therefore, we developed a novel learning strategy that enables a deep-learning-based people counting model to count people only in a certain RoI. In the proposed method, the people counting model has two heads that are attached on top of a crowd counting backbone network. These two heads respectively learn to count people inside the RoI and negate the people count outside the RoI. We named this proposed method Gap Regularizer and tested it on ResNet-50, ResNet-101, CSRNet, and SFCN. The experiment results showed that Gap Regularizer can reduce the mean absolute error (MAE), root mean square error (RMSE), and grid average mean error (GAME) of ResNet-50, which is the smallest CNN model, with the highest reduction of 45.2%, 41.25%, and 46.43%, respectively. On shallow models such as the CSRNet, the regularizer can also drastically increase the SSIM by up to 248.65% in addition to reducing the MAE, RMSE, and GAME. The Gap Regularizer can also improve the performance of SFCN which is a deep CNN model with back-end features by up to 17.22% and 10.54% compared to its standard version. Moreover, the impacts of the Gap Regularizer on these two models are also generally statistically significant (P-value < 0.05) on the MOT17-09, MOT20-02, and RHC datasets. However, it has a limitation in which it is unable to make significant impacts on deep models without back-end features such as the ResNet-101.

Deep polygenic neural network for predicting and identifying yield-associated genes in Indonesian rice accessions.

As the fourth most populous country in the world, Indonesia must increase the annual rice production rate to achieve national food security by 2050. One possible solution comes from the nanoscopic level: a genetic variant called Single Nucleotide Polymorphism (SNP), which can express significant yield-associated genes. The prior benchmark of this study utilized a statistical genetics model where no SNP position information and attention mechanism were involved. Hence, we developed a novel deep polygenic neural network, named the NucleoNet model, to address these obstacles. The NucleoNets were constructed with the combination of prominent components that include positional SNP encoding, the context vector, wide models, Elastic Net, and Shannon's entropy loss. This polygenic modeling obtained up to 2.779 of Mean Squared Error (MSE) with 47.156% of Symmetric Mean Absolute Percentage Error (SMAPE), while revealing 15 new important SNPs. Furthermore, the NucleoNets reduced the MSE score up to 32.28% compared to the Ordinary Least Squares (OLS) model. Through the ablation study, we learned that the combination of Xavier distribution for weights initialization and Normal distribution for biases initialization sparked more various important SNPs throughout 12 chromosomes. Our findings confirmed that the NucleoNet model was successfully outperformed the OLS model and identified important SNPs to Indonesian rice yields.

Beyond GWAS of Colorectal Cancer: Evidence of Interaction with Alcohol Consumption and Putative Causal Variant for the 10q24.2 Region.

BACKGROUND: Currently known associations between common genetic variants and colorectal cancer explain less than half of its heritability of 25%. As alcohol consumption has a J-shape association with colorectal cancer risk, nondrinking and heavy drinking are both risk factors for colorectal cancer. METHODS: Individual-level data was pooled from the Colon Cancer Family Registry, Colorectal Transdisciplinary Study, and Genetics and Epidemiology of Colorectal Cancer Consortium to compare nondrinkers (≤1 g/day) and heavy drinkers (>28 g/day) with light-to-moderate drinkers (1-28 g/day) in GxE analyses. To improve power, we implemented joint 2df and 3df tests and a novel two-step method that modifies the weighted hypothesis testing framework. We prioritized putative causal variants by predicting allelic effects using support vector machine models. RESULTS: For nondrinking as compared with light-to-moderate drinking, the hybrid two-step approach identified 13 significant SNPs with pairwise r2 > 0.9 in the 10q24.2/COX15 region. When stratified by alcohol intake, the A allele of lead SNP rs2300985 has a dose-response increase in risk of colorectal cancer as compared with the G allele in light-to-moderate drinkers [OR for GA genotype = 1.11; 95% confidence interval (CI), 1.06-1.17; OR for AA genotype = 1.22; 95% CI, 1.14-1.31], but not in nondrinkers or heavy drinkers. Among the correlated candidate SNPs in the 10q24.2/COX15 region, rs1318920 was predicted to disrupt an HNF4 transcription factor binding motif. CONCLUSIONS: Our study suggests that the association with colorectal cancer in 10q24.2/COX15 observed in genome-wide association study is strongest in nondrinkers. We also identified rs1318920 as the putative causal regulatory variant for the region. IMPACT: The study identifies multifaceted evidence of a possible functional effect for rs1318920.

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction.

BACKGROUND: Conventional in vivo methods for post-translational modification site prediction such as spectrophotometry, Western blotting, and chromatin immune precipitation can be very expensive and time-consuming. Neural networks (NN) are one of the computational approaches that can predict effectively the post-translational modification site. We developed a neural network model, namely the Sequential and Spatial Methylation Fusion Network (SSMFN), to predict possible methylation sites on protein sequences. METHOD: We designed our model to be able to extract spatial and sequential information from amino acid sequences. Convolutional neural networks (CNN) is applied to harness spatial information, while long short-term memory (LSTM) is applied for sequential data. The latent representation of the CNN and LSTM branch are then fused. Afterwards, we compared the performance of our proposed model to the state-of-the-art methylation site prediction models on the balanced and imbalanced dataset. RESULTS: Our model appeared to be better in almost all measurement when trained on the balanced training dataset. On the imbalanced training dataset, all of the models gave better performance since they are trained on more data. In several metrics, our model also surpasses the PRMePred model, which requires a laborious effort for feature extraction and selection. CONCLUSION: Our models achieved the best performance across different environments in almost all measurements. Also, our result suggests that the NN model trained on a balanced training dataset and tested on an imbalanced dataset will offer high specificity and low sensitivity. Thus, the NN model for methylation site prediction should be trained on an imbalanced dataset. Since in the actual application, there are far more negative samples than positive samples.