Identification of epistatic SNP combinations in rheumatoid arthritis using LAMPLINK and Japanese cohorts.

Genome-wide association studies have enabled the identification of important genetic factors in many trait studies. However, only a fraction of the heritability can be explained by known genetic factors, even in the most common diseases. Genetic loci combinations, or epistatic contributions expressed by combinations of single nucleotide polymorphisms (SNPs), have been argued to be one of the critical factors explaining some of the missing heritability, especially in oligogenic/polygenic diseases. Rheumatoid arthritis (RA) is a complex disease with more than 100 reported SNP associations, as well as various HLA haplotypes and amino acids; however, many associations between RA and inter-chromosomal SNP combinations are unknown. To discover novel associations of epistatic interactions with high odds ratios in RA, we applied the LAMPLINK method, a systematic enumerative procedure for identifying high-order SNP combinations, to a Japanese RA cohort (discovery cohort; 4024 patients with RA and 7731 controls). We validated the identified associations in a different Japanese cohort (validation cohort; 810 RA patients and 6303 controls). In this study, we identified 90 significant genetic associations in the discovery cohort. Among these, 74 (82.2%) associations were replicated in the validation cohort, and eight combinations were inter-chromosomal, all of which comprised rs7765379 or rs35265698 located in the HLA region. These two SNPs exhibited strong correlations with valine at amino acid position 11 in HLA-DRB1 (HLA-DRB1-11-Val). Finally, we discovered that rs9624 showed an association with RA through an epistatic interaction with HLA-DRB1-11-Val. Overall, LAMPLINK showed high reliability for identifying epistatic genetic contributions hidden in complex traits.

Seasonal pigment fluctuation in diploid and polyploid Arabidopsis revealed by machine learning-based phenotyping method PlantServation.

Long-term field monitoring of leaf pigment content is informative for understanding plant responses to environments distinct from regulated chambers but is impractical by conventional destructive measurements. We developed PlantServation, a method incorporating robust image-acquisition hardware and deep learning-based software that extracts leaf color by detecting plant individuals automatically. As a case study, we applied PlantServation to examine environmental and genotypic effects on the pigment anthocyanin content estimated from leaf color. We processed >4 million images of small individuals of four Arabidopsis species in the field, where the plant shape, color, and background vary over months. Past radiation, coldness, and precipitation significantly affected the anthocyanin content. The synthetic allopolyploid A. kamchatica recapitulated the fluctuations of natural polyploids by integrating diploid responses. The data support a long-standing hypothesis stating that allopolyploids can inherit and combine the traits of progenitors. PlantServation facilitates the study of plant responses to complex environments termed "in natura".

A low-coverage 3' RNA-seq to detect homeolog expression in polyploid wheat.

Although allopolyploid species are common among natural and crop species, it is not easy to distinguish duplicated genes, known as homeologs, during their genomic analysis. Yet, cost-efficient RNA sequencing (RNA-seq) is to be developed for large-scale transcriptomic studies such as time-series analysis and genome-wide association studies in allopolyploids. In this study, we employed a 3' RNA-seq utilizing 3' untranslated regions (UTRs) containing frequent mutations among homeologous genes, compared to coding sequence. Among the 3' RNA-seq protocols, we examined a low-cost method Lasy-Seq using an allohexaploid bread wheat, Triticum aestivum. HISAT2 showed the best performance for 3' RNA-seq with the least mapping errors and quick computational time. The number of detected homeologs was further improved by extending 1 kb of the 3' UTR annotation. Differentially expressed genes in response to mild cold treatment detected by the 3' RNA-seq were verified with high-coverage conventional RNA-seq, although the latter detected more differentially expressed genes. Finally, downsampling showed that even a 2 million sequencing depth can still detect more than half of expressed homeologs identifiable by the conventional 32 million reads. These data demonstrate that this low-cost 3' RNA-seq facilitates large-scale transcriptomic studies of allohexaploid wheat and indicate the potential application to other allopolyploid species.

Wearable Sensor and Mobile App-Based mHealth Approach for Investigating Substance Use and Related Factors in Daily Life: Protocol for an Ecological Momentary Assessment Study.

BACKGROUND: Digital health technologies using mobile apps and wearable devices are a promising approach to the investigation of substance use in the real world and for the analysis of predictive factors or harms from substance use. Moreover, consecutive repeated data collection enables the development of predictive algorithms for substance use by machine learning methods. OBJECTIVE: We developed a new self-monitoring mobile app to record daily substance use, triggers, and cravings. Additionally, a wearable activity tracker (Fitbit) was used to collect objective biological and behavioral data before, during, and after substance use. This study aims to describe a model using machine learning methods to determine substance use. METHODS: This study is an ongoing observational study using a Fitbit and a self-monitoring app. Participants of this study were people with health risks due to alcohol or methamphetamine use. They were required to record their daily substance use and related factors on the self-monitoring app and to always wear a Fitbit for 8 weeks, which collected the following data: (1) heart rate per minute, (2) sleep duration per day, (3) sleep stages per day, (4) the number of steps per day, and (5) the amount of physical activity per day. Fitbit data will first be visualized for data analysis to confirm typical Fitbit data patterns for individual users. Next, machine learning and statistical analysis methods will be performed to create a detection model for substance use based on the combined Fitbit and self-monitoring data. The model will be tested based on 5-fold cross-validation, and further preprocessing and machine learning methods will be conducted based on the preliminary results. The usability and feasibility of this approach will also be evaluated. RESULTS: Enrollment for the trial began in September 2020, and the data collection finished in April 2021. In total, 13 people with methamphetamine use disorder and 36 with alcohol problems participated in this study. The severity of methamphetamine or alcohol use disorder assessed by the Drug Abuse Screening Test-10 or the Alcohol Use Disorders Identification Test-10 was moderate to severe. The anticipated results of this study include understanding the physiological and behavioral data before, during, and after alcohol or methamphetamine use and identifying individual patterns of behavior. CONCLUSIONS: Real-time data on daily life among people with substance use problems were collected in this study. This new approach to data collection might be helpful because of its high confidentiality and convenience. The findings of this study will provide data to support the development of interventions to reduce alcohol and methamphetamine use and associated negative consequences. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/44275.

Prediction of the cell-type-specific transcription of non-coding RNAs from genome sequences via machine learning.

Gene transcription is regulated through complex mechanisms involving non-coding RNAs (ncRNAs). As the transcription of ncRNAs, especially of enhancer RNAs, is often low and cell type specific, how the levels of RNA transcription depend on genotype remains largely unexplored. Here we report the development and utility of a machine-learning model (MENTR) that reliably links genome sequence and ncRNA expression at the cell type level. Effects on ncRNA transcription predicted by the model were concordant with estimates from published studies in a cell-type-dependent manner, regardless of allele frequency and genetic linkage. Among 41,223 variants from genome-wide association studies, the model identified 7,775 enhancer RNAs and 3,548 long ncRNAs causally associated with complex traits across 348 major human primary cells and tissues, such as rare variants plausibly altering the transcription of enhancer RNAs to influence the risks of Crohn's disease and asthma. The model may aid the discovery of causal variants and the generation of testable hypotheses for biological mechanisms driving complex traits.

Volumetric Analysis of Glioblastoma for Determining Which CpG Sites Should Be Tested by Pyrosequencing to Predict Temozolomide Efficacy.

The aim of the present study was to determine which individual or combined CpG sites among O6-methylguanine DNA methyltransferase CpG 74-89 in glioblastoma mainly affects the response to temozolomide resulting from CpG methylation using statistical analyses focused on the tumor volume ratio (TVR). We retrospectively examined 44 patients who had postoperative volumetrically measurable residual tumor tissue and received adjuvant temozolomide therapy for at least 6 months after initial chemoradiotherapy. TVR was defined as the tumor volume 6 months after the initial chemoradiotherapy divided by that before the start of chemoradiotherapy. Predictive values for TVR as a response to adjuvant therapy were compared among the averaged methylation percentages of individual or combined CpGs using the receiver operating characteristic curve. Our data revealed that combined CpG 78 and 79 showed a high area under the curve (AUC) and a positive likelihood ratio and that combined CpG 76-79 showed the highest AUC among all combinations. AUCs of consecutive CpG combinations tended to be higher for CpG 74-82 in exon 1 than for CpG 83-89 in intron 1. In conclusion, the methylation status at CpG sites in exon 1 was strongly associated with TVR reduction in glioblastoma.

Estimating Physical/Mental Health Condition Using Heart Rate Data from a Wearable Device.

We propose an estimation method of subjects' physical/mental health condition from their heart rate (HR) and evaluate it on the newly collected data including 25 million points over 97 participants. The accurate health condition estimation is important for an employee's mental health care and an objective understanding of our condition. For the estimation, the heart rate variability (HRV) has been widely used, but there are some technical difficulties with measuring the HRV, such as maintaining a good quality of data for a long period of time. Here, we predict the subjects' physical/mental health only from the HR measured by Fitbit instead of the HRV. We first measured more than 25 million points of HR and steps data from 97 participants over 3 months using the Fitbit Inspire HRTM. We also conducted questionnaires to check their physical conditions each day. We then predict their condition by focusing on the inactive period of HR and applying the support vector machine to the preprocessed data. The best balanced accuracy of our method achieved 0.582, which was higher than the state-of-the-art method with HRV whose accuracy is 0.565.

Preliminary study for developing a navigation system for gastric cancer surgery using artificial intelligence.

PURPOSE: We are attempting to develop a navigation system for safe and effective peripancreatic lymphadenectomy in gastric cancer surgery. As a preliminary study, we examined whether or not the peripancreatic dissection line could be learned by a machine learning model (MLM). METHODS: Among the 41 patients with gastric cancer who underwent radical gastrectomy between April 2019 and January 2020, we selected 6 in whom the pancreatic contour was relatively easy to trace. The pancreatic contour was annotated by a trainer surgeon in 1242 images captured from the video recordings. The MLM was trained using the annotated images from five of the six patients. The pancreatic contour was then segmented by the trained MLM using images from the remaining patient. The same procedure was repeated for all six combinations. RESULTS: The median maximum intersection over union of each image was 0.708, which was higher than the threshold (0.5). However, the pancreatic contour was misidentified in parts where fatty tissue or thin vessels overlaid the pancreas in some cases. CONCLUSION: The contour of the pancreas could be traced relatively well using the trained MLM. Further investigations and training of the system are needed to develop a practical navigation system.

The genome of Shorea leprosula (Dipterocarpaceae) highlights the ecological relevance of drought in aseasonal tropical rainforests.

Hyperdiverse tropical rainforests, such as the aseasonal forests in Southeast Asia, are supported by high annual rainfall. Its canopy is dominated by the species-rich tree family of Dipterocarpaceae (Asian dipterocarps), which has both ecological (e.g., supports flora and fauna) and economical (e.g., timber production) importance. Recent ecological studies suggested that rare irregular drought events may be an environmental stress and signal for the tropical trees. We assembled the genome of a widespread but near threatened dipterocarp, Shorea leprosula, and analyzed the transcriptome sequences of ten dipterocarp species representing seven genera. Comparative genomic and molecular dating analyses suggested a whole-genome duplication close to the Cretaceous-Paleogene extinction event followed by the diversification of major dipterocarp lineages (i.e. Dipterocarpoideae). Interestingly, the retained duplicated genes were enriched for genes upregulated by no-irrigation treatment. These findings provide molecular support for the relevance of drought for tropical trees despite the lack of an annual dry season.

ARPEGGIO: Automated Reproducible Polyploid EpiGenetic GuIdance workflOw.

BACKGROUND: Whole genome duplication (WGD) events are common in the evolutionary history of many living organisms. For decades, researchers have been trying to understand the genetic and epigenetic impact of WGD and its underlying molecular mechanisms. Particular attention was given to allopolyploid study systems, species resulting from an hybridization event accompanied by WGD. Investigating the mechanisms behind the survival of a newly formed allopolyploid highlighted the key role of DNA methylation. With the improvement of high-throughput methods, such as whole genome bisulfite sequencing (WGBS), an opportunity opened to further understand the role of DNA methylation at a larger scale and higher resolution. However, only a few studies have applied WGBS to allopolyploids, which might be due to lack of genomic resources combined with a burdensome data analysis process. To overcome these problems, we developed the Automated Reproducible Polyploid EpiGenetic GuIdance workflOw (ARPEGGIO): the first workflow for the analysis of epigenetic data in polyploids. This workflow analyzes WGBS data from allopolyploid species via the genome assemblies of the allopolyploid's parent species. ARPEGGIO utilizes an updated read classification algorithm (EAGLE-RC), to tackle the challenge of sequence similarity amongst parental genomes. ARPEGGIO offers automation, but more importantly, a complete set of analyses including spot checks starting from raw WGBS data: quality checks, trimming, alignment, methylation extraction, statistical analyses and downstream analyses. A full run of ARPEGGIO outputs a list of genes showing differential methylation. ARPEGGIO was made simple to set up, run and interpret, and its implementation ensures reproducibility by including both package management and containerization. RESULTS: We evaluated ARPEGGIO in two ways. First, we tested EAGLE-RC's performance with publicly available datasets given a ground truth, and we show that EAGLE-RC decreases the error rate by 3 to 4 times compared to standard approaches. Second, using the same initial dataset, we show agreement between ARPEGGIO's output and published results. Compared to other similar workflows, ARPEGGIO is the only one supporting polyploid data. CONCLUSIONS: The goal of ARPEGGIO is to promote, support and improve polyploid research with a reproducible and automated set of analyses in a convenient implementation. ARPEGGIO is available at https://github.com/supermaxiste/ARPEGGIO .

Assessing Versatile Machine Learning Models for Glioma Radiogenomic Studies across Hospitals.

Radiogenomics use non-invasively obtained imaging data, such as magnetic resonance imaging (MRI), to predict critical biomarkers of patients. Developing an accurate machine learning (ML) technique for MRI requires data from hundreds of patients, which cannot be gathered from any single local hospital. Hence, a model universally applicable to multiple cohorts/hospitals is required. We applied various ML and image pre-processing procedures on a glioma dataset from The Cancer Image Archive (TCIA, n = 159). The models that showed a high level of accuracy in predicting glioblastoma or WHO Grade II and III glioma using the TCIA dataset, were then tested for the data from the National Cancer Center Hospital, Japan (NCC, n = 166) whether they could maintain similar levels of high accuracy. Results: we confirmed that our ML procedure achieved a level of accuracy (AUROC = 0.904) comparable to that shown previously by the deep-learning methods using TCIA. However, when we directly applied the model to the NCC dataset, its AUROC dropped to 0.383. Introduction of standardization and dimension reduction procedures before classification without re-training improved the prediction accuracy obtained using NCC (0.804) without a loss in prediction accuracy for the TCIA dataset. Furthermore, we confirmed the same tendency in a model for IDH1/2 mutation prediction with standardization and application of dimension reduction that was also applicable to multiple hospitals. Our results demonstrated that overfitting may occur when an ML method providing the highest accuracy in a small training dataset is used for different heterogeneous data sets, and suggested a promising process for developing an ML method applicable to multiple cohorts.

Evaluation of repair activity by quantification of ribonucleotides in the genome.

Ribonucleotides incorporated in the genome are a source of endogenous DNA damage and also serve as signals for repair. Although recent advances of ribonucleotide detection by sequencing, the balance between incorporation and repair of ribonucleotides has not been elucidated. Here, we describe a competitive sequencing method, Ribonucleotide Scanning Quantification sequencing (RiSQ-seq), which enables absolute quantification of misincorporated ribonucleotides throughout the genome by background normalization and standard adjustment within a single sample. RiSQ-seq analysis of cells harboring wild-type DNA polymerases revealed that ribonucleotides were incorporated nonuniformly in the genome with a 3'-shifted distribution and preference for GC sequences. Although ribonucleotide profiles in wild-type and repair-deficient mutant strains showed a similar pattern, direct comparison of distinct ribonucleotide levels in the strains by RiSQ-seq enabled evaluation of ribonucleotide excision repair activity at base resolution and revealed the strand bias of repair. The distinct preferences of ribonucleotide incorporation and repair create vulnerable regions associated with indel hotspots, suggesting that repair at sites of ribonucleotide misincorporation serves to maintain genome integrity and that RiSQ-seq can provide an estimate of indel risk.

Fine-Tuning Approach for Segmentation of Gliomas in Brain Magnetic Resonance Images with a Machine Learning Method to Normalize Image Differences among Facilities.

Machine learning models for automated magnetic resonance image segmentation may be useful in aiding glioma detection. However, the image differences among facilities cause performance degradation and impede detection. This study proposes a method to solve this issue. We used the data from the Multimodal Brain Tumor Image Segmentation Benchmark (BraTS) and the Japanese cohort (JC) datasets. Three models for tumor segmentation are developed. In our methodology, the BraTS and JC models are trained on the BraTS and JC datasets, respectively, whereas the fine-tuning models are developed from the BraTS model and fine-tuned using the JC dataset. Our results show that the Dice coefficient score of the JC model for the test portion of the JC dataset was 0.779 ± 0.137, whereas that of the BraTS model was lower (0.717 ± 0.207). The mean Dice coefficient score of the fine-tuning model was 0.769 ± 0.138. There was a significant difference between the BraTS and JC models (p < 0.0001) and the BraTS and fine-tuning models (p = 0.002); however, no significant difference between the JC and fine-tuning models (p = 0.673). As our fine-tuning method requires fewer than 20 cases, this method is useful even in a facility where the number of glioma cases is small.

Fine-scale empirical data on niche divergence and homeolog expression patterns in an allopolyploid and its diploid progenitor species.

Polyploidization is pervasive in plants, but little is known about the niche divergence of wild allopolyploids (species that harbor polyploid genomes originating from different diploid species) relative to their diploid progenitor species and the gene expression patterns that may underlie such ecological divergence. We conducted a fine-scale empirical study on habitat and gene expression of an allopolyploid and its diploid progenitors. We quantified soil properties and light availability of habitats of an allotetraploid Cardamine flexuosa and its diploid progenitors Cardamine amara and Cardamine hirsuta in two seasons. We analyzed expression patterns of genes and homeologs (homeologous gene copies in allopolyploids) using RNA sequencing. We detected niche divergence between the allopolyploid and its diploid progenitors along water availability gradient at a fine scale: the diploids in opposite extremes and the allopolyploid in a broader range between diploids, with limited overlap with diploids at both ends. Most of the genes whose homeolog expression ratio changed among habitats in C. flexuosa varied spatially and temporally. These findings provide empirical evidence for niche divergence between an allopolyploid and its diploid progenitor species at a fine scale and suggest that divergent expression patterns of homeologs in an allopolyploid may underlie its persistence in diverse habitats.

De Novo Genome Assembly of the Japanese Wheat Cultivar Norin 61 Highlights Functional Variation in Flowering Time and Fusarium-Resistant Genes in East Asian Genotypes.

Bread wheat is a major crop that has long been the focus of basic and breeding research. Assembly of its genome has been difficult because of its large size and allohexaploid nature (AABBDD genome). Following the first reported assembly of the genome of the experimental strain Chinese Spring (CS), the 10+ Wheat Genomes Project was launched to produce multiple assemblies of worldwide modern cultivars. The only Asian cultivar in the project is Norin 61, a representative Japanese cultivar adapted to grow across a broad latitudinal range, mostly characterized by a wet climate and a short growing season. Here, we characterize the key aspects of its chromosome-scale genome assembly spanning 15 Gb with a raw scaffold N50 of 22 Mb. Analysis of the repetitive elements identified chromosomal regions unique to Norin 61 that encompass a tandem array of the pathogenesis-related 13 family. We report novel copy-number variations in the B homeolog of the florigen gene FT1/VRN3, pseudogenization of its D homeolog and the association of its A homeologous alleles with the spring/winter growth habit. Furthermore, the Norin 61 genome carries typical East Asian functional variants different from CS, ranging from a single nucleotide to multi-Mb scale. Examples of such variation are the Fhb1 locus, which confers Fusarium head-blight resistance, Ppd-D1a, which confers early flowering, Glu-D1f for Asian noodle quality and Rht-D1b, which introduced semi-dwarfism during the green revolution. The adoption of Norin 61 as a reference assembly for functional and evolutionary studies will enable comprehensive characterization of the underexploited Asian bread wheat diversity.

Application of Artificial Intelligence Technology in Oncology: Towards the Establishment of Precision Medicine.

In recent years, advances in artificial intelligence (AI) technology have led to the rapid clinical implementation of devices with AI technology in the medical field. More than 60 AI-equipped medical devices have already been approved by the Food and Drug Administration (FDA) in the United States, and the active introduction of AI technology is considered to be an inevitable trend in the future of medicine. In the field of oncology, clinical applications of medical devices using AI technology are already underway, mainly in radiology, and AI technology is expected to be positioned as an important core technology. In particular, "precision medicine," a medical treatment that selects the most appropriate treatment for each patient based on a vast amount of medical data such as genome information, has become a worldwide trend; AI technology is expected to be utilized in the process of extracting truly useful information from a large amount of medical data and applying it to diagnosis and treatment. In this review, we would like to introduce the history of AI technology and the current state of medical AI, especially in the oncology field, as well as discuss the possibilities and challenges of AI technology in the medical field.

A Recently Formed Triploid Cardamine insueta Inherits Leaf Vivipary and Submergence Tolerance Traits of Parents.

Contemporary speciation provides a unique opportunity to directly observe the traits and environmental responses of a new species. Cardamine insueta is an allotriploid species that appeared within the past 150 years in a Swiss village, Urnerboden. In contrast to its two progenitor species, Cardamine amara and Cardamine rivularis that live in wet and open habitats, respectively, C. insueta is found in-between their habitats with temporal water level fluctuation. This triploid species propagates clonally and serves as a triploid bridge to form higher ploidy species. Although niche separation is observed in field studies, the mechanisms underlying the environmental robustness of C. insueta are not clear. To characterize responses to a fluctuating environment, we performed a time-course analysis of homeolog gene expression in C. insueta in response to submergence treatment. For this purpose, the two parental (C. amara and C. rivularis) genome sequences were assembled with a reference-guided approach, and homeolog-specific gene expression was quantified using HomeoRoq software. We found that C. insueta and C. rivularis initiated vegetative propagation by forming ectopic meristems on leaves, while C. amara did not. We examined homeolog-specific gene expression of three species at nine time points during the treatment. The genome-wide expression ratio of homeolog pairs was 2:1 over the time-course, consistent with the ploidy number. By searching the genes with high coefficient of variation of expression over time-course transcriptome data, we found many known key transcriptional factors related to meristem development and formation upregulated in both C. rivularis and rivularis-homeolog of C. insueta, but not in C. amara. Moreover, some amara-homeologs of these genes were also upregulated in the triploid, suggesting trans-regulation. In turn, Gene Ontology analysis suggested that the expression pattern of submergence tolerant genes in the triploid was inherited from C. amara. These results suggest that the triploid C. insueta combined advantageous patterns of parental transcriptomes to contribute to its establishment in a new niche along a water-usage gradient.

Predicting Deep Learning Based Multi-Omics Parallel Integration Survival Subtypes in Lung Cancer Using Reverse Phase Protein Array Data.

Mortality attributed to lung cancer accounts for a large fraction of cancer deaths worldwide. With increasing mortality figures, the accurate prediction of prognosis has become essential. In recent years, multi-omics analysis has emerged as a useful survival prediction tool. However, the methodology relevant to multi-omics analysis has not yet been fully established and further improvements are required for clinical applications. In this study, we developed a novel method to accurately predict the survival of patients with lung cancer using multi-omics data. With unsupervised learning techniques, survival-associated subtypes in non-small cell lung cancer were first detected using the multi-omics datasets from six categories in The Cancer Genome Atlas (TCGA). The new subtypes, referred to as integration survival subtypes, clearly divided patients into longer and shorter-surviving groups (log-rank test: p = 0.003) and we confirmed that this is independent of histopathological classification (Chi-square test of independence: p = 0.94). Next, an attempt was made to detect the integration survival subtypes using only one categorical dataset. Our machine learning model that was only trained on the reverse phase protein array (RPPA) could accurately predict the integration survival subtypes (AUC = 0.99). The predicted subtypes could also distinguish between high and low risk patients (log-rank test: p = 0.012). Overall, this study explores novel potentials of multi-omics analysis to accurately predict the prognosis of patients with lung cancer.

Uncovering Prognosis-Related Genes and Pathways by Multi-Omics Analysis in Lung Cancer.

Lung cancer is one of the leading causes of death worldwide. Therefore, understanding the factors linked to patient survival is essential. Recently, multi-omics analysis has emerged, allowing for patient groups to be classified according to prognosis and at a more individual level, to support the use of precision medicine. Here, we combined RNA expression and miRNA expression with clinical information, to conduct a multi-omics analysis, using publicly available datasets (the cancer genome atlas (TCGA) focusing on lung adenocarcinoma (LUAD)). We were able to successfully subclass patients according to survival. The classifiers we developed, using inferred labels obtained from patient subtypes showed that a support vector machine (SVM), gave the best classification results, with an accuracy of 0.82 with the test dataset. Using these subtypes, we ranked genes based on RNA expression levels. The top 25 genes were investigated, to elucidate the mechanisms that underlie patient prognosis. Bioinformatics analyses showed that the expression levels of six out of 25 genes (ERO1B, DPY19L1, NCAM1, RET, MARCH1, and SLC7A8) were associated with LUAD patient survival (p < 0.05), and pathway analyses indicated that major cancer signaling was altered in the subtypes.