Evaluation of data discretization methods to derive platform independent isoform expression signatures for multi-class tumor subtyping

Augusta: From RNA-Seq to gene regulatory networks and Boolean models

Computational models of gene regulations help to understand regulatory mechanisms and are extensively used in a wide range of areas, e.g., biotechnology or medicine, with significant benefits. Unfortunately, there are only a few computational gene regulatory models of whole genomes allowing static and dynamic analysis due to the lack of sophisticated tools for their reconstruction. Here, we describe Augusta, an open-source Python package for Gene Regulatory Network (GRN) and Boolean Network (BN) inference from the high-throughput gene expression data. Augusta can reconstruct genome-wide models suitable for static and dynamic analyses. Augusta uses a unique approach where the first estimation of a GRN inferred from expression data is further refined by predicting transcription factor binding motifs in promoters of regulated genes and by incorporating verified interactions obtained from databases. Moreover, a refined GRN is transformed into a draft BN by searching in the curated model database and setting logical rules to incoming edges of target genes, which can be further manually edited as the model is provided in the SBML file format. The approach is applicable even if information about the organism under study is not available in the databases, which is typically the case for non-model organisms including most microbes. Augusta can be operated from the command line and, thus, is easy to use for automated prediction of models for various genomes. The Augusta package is freely available at github.com/JanaMus/Augusta. Documentation and tutorials are available at augusta.readthedocs.io.

SLC22A3 that encodes organic cation transporter-3 is associated with prognosis and immunogenicity of human lung squamous cell carcinoma

Background

SLC22A3, the gene which encodes organic cation transporter (OCT)-3, has been linked to the prognosis of several types of cancer. However, its role in lung squamous cell carcinoma (LSCC) has not been addressed elsewhere.

Methods

We analyzed gene expression, DNA methylation, and clinicopathological data from The Cancer Genome Atlas - Lung Squamous Cell Carcinoma (TCGA-LUSC) (n=501), a publicly available database exclusively consisting of LSCC patients. Using a 5 FPKM (fragments per kilobase of exon per million mapped fragments) cut-off, we divided LSCC patients into two groups: patients with tumors possessing high and low SLC22A3 expression (SLC22A3-high and SLC22A3-low, respectively). Prognostic significance was determined through Cox analyses and Kaplan-Meier curves for overall survival (OS) and disease-free survival (DFS). Differential methylation position (DMP), differentially gene expression, and pathway analyses were performed. Validation was carried out in GSE74777 (n=107), GSE37745 (n=66), GSE162520 (n=45) and GSE161537 (n=17).

Results

SLC22A3-high LSCC patients had lower OS and DFS rates than SLC22A3-low LSCC patients. The different expression levels of SLC22A3 in LSCC were correlated with the methylation status of the SLC22A3 gene. Pathway analysis indicated that SLC22A3 expression levels were positively correlated with immune-related pathways such as inflammatory response and abundance of infiltrating immune cells in the tumor microenvironment (TME). Notably, in the SLC22A3-high group, many genes encoding immunological checkpoint inhibitory molecules were upregulated. In addition, SLC22A3 expression positively correlated with the Hot Oral Tumor (HOT) score, indicating high tumor immunogenicity.

Conclusions

These findings suggest that high expression of SLC22A3 is associated with poor prognosis and high immunogenicity in LSCC tumors.

Prediction of prostate cancer biochemical recurrence by using discretization supports the critical contribution of the extra-cellular matrix genes

Due to its complexity, much effort has been devoted to the development of biomarkers for prostate cancer that have acquired the utmost clinical relevance for diagnosis and grading. However, all of these advances are limited due to the relatively large percentage of biochemical recurrence (BCR) and the limited strategies for follow up. This work proposes a methodology that uses discretization to predict prostate cancer BCR while optimizing the necessary variables. We used discretization of RNA-seq data to increase the prediction of biochemical recurrence and retrieve a subset of ten genes functionally known to be related to the tissue structure. Equal width and equal frequency data discretization methods were compared to isolate the contribution of the genes and their interval of action, simultaneously. Adding a robust clinical biomarker such as prostate specific antigen (PSA) improved the prediction of BCR. Discretization allowed classifying the cancer patients with an accuracy of 82% on testing datasets, and 75% on a validation dataset when a five-bin discretization by equal width was used. After data pre-processing, feature selection and classification, our predictions had a precision of 71% (testing dataset: MSKCC and GSE54460) and 69% (Validation dataset: GSE70769) should the patients present BCR up to 24 months after their final treatment. These results emphasize the use of equal width discretization as a pre-processing step to improve classification for a limited number of genes in the signature. Functionally, many of these genes have a direct or expected role in tissue structure and extracellular matrix organization. The processing steps presented in this study are also applicable to other cancer types to increase the speed and accuracy of the models in diverse datasets.

GReNaDIne: A Data-Driven Python Library to Infer Gene Regulatory Networks from Gene Expression Data

Context: Inferring gene regulatory networks (GRN) from high-throughput gene expression data is a challenging task for which different strategies have been developed. Nevertheless, no ever-winning method exists, and each method has its advantages, intrinsic biases, and application domains. Thus, in order to analyze a dataset, users should be able to test different techniques and choose the most appropriate one. This step can be particularly difficult and time consuming, since most methods' implementations are made available independently, possibly in different programming languages. The implementation of an open-source library containing different inference methods within a common framework is expected to be a valuable toolkit for the systems biology community. Results: In this work, we introduce GReNaDIne (Gene Regulatory Network Data-driven Inference), a Python package that implements 18 machine learning data-driven gene regulatory network inference methods. It also includes eight generalist preprocessing techniques, suitable for both RNA-seq and microarray dataset analysis, as well as four normalization techniques dedicated to RNA-seq. In addition, this package implements the possibility to combine the results of different inference tools to form robust and efficient ensembles. This package has been successfully assessed under the DREAM5 challenge benchmark dataset. The open-source GReNaDIne Python package is made freely available in a dedicated GitLab repository, as well as in the official third-party software repository PyPI Python Package Index. The latest documentation on the GReNaDIne library is also available at Read the Docs, an open-source software documentation hosting platform. Contribution: The GReNaDIne tool represents a technological contribution to the field of systems biology. This package can be used to infer gene regulatory networks from high-throughput gene expression data using different algorithms within the same framework. In order to analyze their datasets, users can apply a battery of preprocessing and postprocessing tools and choose the most adapted inference method from the GReNaDIne library and even combine the output of different methods to obtain more robust results. The results format provided by GReNaDIne is compatible with well-known complementary refinement tools such as PYSCENIC.

Aristotle: stratified causal discovery for omics data

BACKGROUND

There has been a simultaneous increase in demand and accessibility across genomics, transcriptomics, proteomics and metabolomics data, known as omics data. This has encouraged widespread application of omics data in life sciences, from personalized medicine to the discovery of underlying pathophysiology of diseases. Causal analysis of omics data may provide important insight into the underlying biological mechanisms. Existing causal analysis methods yield promising results when identifying potential general causes of an observed outcome based on omics data. However, they may fail to discover the causes specific to a particular stratum of individuals and missing from others.

METHODS

To fill this gap, we introduce the problem of stratified causal discovery and propose a method, Aristotle, for solving it. Aristotle addresses the two challenges intrinsic to omics data: high dimensionality and hidden stratification. It employs existing biological knowledge and a state-of-the-art patient stratification method to tackle the above challenges and applies a quasi-experimental design method to each stratum to find stratum-specific potential causes.

RESULTS

Evaluation based on synthetic data shows better performance for Aristotle in discovering true causes under different conditions compared to existing causal discovery methods. Experiments on a real dataset on Anthracycline Cardiotoxicity indicate that Aristotle's predictions are consistent with the existing literature. Moreover, Aristotle makes additional predictions that suggest further investigations.

An Ensemble Model for Tumor Type Identification and Cancer Origins Classification

Tissue biopsy can be wildly used in cancer diagnosis. However, manually classifying the cancerous status of biopsies and tissue origin of tumors for cancerous ones requires skilled specialists and sophisticated equipment. As a result, a data-based model is urgently needed. In this paper, we propose a data-based ensemble model for tumor type identification and cancer origins classification. Our model is an ensemble model that combines different models based on mRNA groups which serve distinct functions. The experiment on the TCGA dataset exhibits a promising result on both tasks - 98% on tumor type identification and 96.1% on cancer origin classification. We also test our model on external validation datasets, which prove the robustness of our model.

How Well Does a Sequential Minimal Optimization Model Perform in Predicting Medicine Prices for Procurement System?

The lack of an efficient approach in managing pharmaceutical prices in the procurement system led to a substantial burden on government budgets. In Thailand, although the reference price policy was implemented to contain the drug expenditure, there have been some challenges with the price dispersion of medicines and pricing information transparency. This phenomenon calls for the development of a potential algorithm to estimate appropriate prices for medical products. To serve this purpose, in this paper, we first developed the model by the sequential minimal optimization (SMO) algorithm for predicting the range of the prices for each medicine, using the Waikato environment for knowledge analysis software, and applying feature selection techniques also to examine improving predictive accuracy. We used the dataset comprised of 2424 records listed on the procurement system in Thailand from January to March 2019 in the application and used a 10-fold cross-validation test to validate the model. The results demonstrated that the model derived by the SMO algorithm with the gain ratio selection method provided good performance at an accuracy of approximately 92.62%, with high sensitivity and precision. Additionally, we found that the model can distinguish the differences in the prices of medicines in the pharmaceutical market by using eight major features—the segmented buyers, the generic product groups, trade product names, procurement methods, dosage forms, pack sizes, manufacturers, and total purchase budgets—that provided the highest predictive accuracy. Our findings are useful to health policymakers who could employ our proposed model in monitoring the situation of medicine prices and providing feedback directly to suggest the best possible price for hospital purchasing managers based on the feature inputs in their procurement system.

Artificial Intelligence in Bulk and Single-Cell RNA-Sequencing Data to Foster Precision Oncology

Artificial intelligence, or the discipline of developing computational algorithms able to perform tasks that requires human intelligence, offers the opportunity to improve our idea and delivery of precision medicine. Here, we provide an overview of artificial intelligence approaches for the analysis of large-scale RNA-sequencing datasets in cancer. We present the major solutions to disentangle inter- and intra-tumor heterogeneity of transcriptome profiles for an effective improvement of patient management. We outline the contributions of learning algorithms to the needs of cancer genomics, from identifying rare cancer subtypes to personalizing therapeutic treatments.

Country-level pandemic risk and preparedness classification based on COVID-19 data: A machine learning approach

In this work we present a three-stage Machine Learning strategy to country-level risk classification based on countries that are reporting COVID-19 information. A K% binning discretisation (K = 25) is used to create four risk groups of countries based on the risk of transmission (coronavirus cases per million population), risk of mortality (coronavirus deaths per million population), and risk of inability to test (coronavirus tests per million population). The four risk groups produced by K% binning are labelled as 'low', 'medium-low', 'medium-high', and 'high'. Coronavirus-related data are then removed and the attributes for prediction of the three types of risk are given as the geopolitical and demographic data describing each country. Thus, the calculation of class label is based on coronavirus data but the input attributes are country-level information regardless of coronavirus data. The three four-class classification problems are then explored and benchmarked through leave-one-country-out cross validation to find the strongest model, producing a Stack of Gradient Boosting and Decision Tree algorithms for risk of transmission, a Stack of Support Vector Machine and Extra Trees for risk of mortality, and a Gradient Boosting algorithm for the risk of inability to test. It is noted that high risk for inability to test is often coupled with low risks for transmission and mortality, therefore the risk of inability to test should be interpreted first, before consideration is given to the predicted transmission and mortality risks. Finally, the approach is applied to more recent risk levels to data from September 2020 and weaker results are noted due to the growth of international collaboration detracting useful knowledge from country-level attributes which suggests that similar machine learning approaches are more useful prior to situations later unfolding.

Platform-Independent Classification System to Predict Molecular Subtypes of High-Grade Serous Ovarian Carcinoma

PURPOSE

Molecular cancer subtyping is an important tool in predicting prognosis and developing novel precision medicine approaches. We developed a novel platform-independent gene expression-based classification system for molecular subtyping of patients with high-grade serous ovarian carcinoma (HGSOC).

METHODS

Unprocessed exon array (569 tumor and nine normal) and RNA sequencing (RNA-seq; 376 tumor) HGSOC data sets, with clinical annotations, were downloaded from the Genomic Data Commons portal. Sample clustering was performed by non-negative matrix factorization by using isoform-level expression estimates. The association between the subtypes and overall survival was evaluated by Cox proportional hazards regression model after adjusting for the covariates. A novel classification system was developed for HGSOC molecular subtyping. Robustness and generalizability of the gene signatures were validated using independent microarray and RNA-seq data sets.

RESULTS

Sample clustering recaptured the four known The Cancer Genome Atlas molecular subtypes but switched the subtype for 22% of the cases, which resulted in significant (P = .006) survival differences among the refined subgroups. After adjusting for covariate effects, the mesenchymal subgroup was found to be at an increased hazard for death compared with the immunoreactive subgroup. Both gene- and isoform-level signatures achieved more than 92% prediction accuracy when tested on independent samples profiled on the exon array platform. When the classifier was applied to RNA-seq data, the subtyping calls agreed with the predictions made from exon array data for 95% of the 279 samples profiled by both platforms.

CONCLUSION

Isoform-level expression analysis successfully stratifies patients with HGSOC into groups with differing prognosis and has led to the development of robust, platform-independent gene signatures for HGSOC molecular subtyping. The association of the refined The Cancer Genome Atlas HGSOC subtypes with overall survival, independent of covariates, enhances the clinical annotation of the HGSOC cohort.

SUBSTRA: Supervised Bayesian Patient Stratification

Motivation

Patient stratification methods are key to the vision of precision medicine. Here, we consider transcriptional data to segment the patient population into subsets relevant to a given phenotype. Whereas most existing patient stratification methods focus either on predictive performance or interpretable features, we developed a method striking a balance between these two important goals.

Results

We introduce a Bayesian method called SUBSTRA that uses regularized biclustering to identify patient subtypes and interpretable subtype-specific transcript clusters. The method iteratively re-weights feature importance to optimize phenotype prediction performance by producing more phenotype-relevant patient subtypes. We investigate the performance of SUBSTRA in finding relevant features using simulated data and successfully benchmark it against state-of-the-art unsupervised stratification methods and supervised alternatives. Moreover, SUBSTRA achieves predictive performance competitive with the supervised benchmark methods and provides interpretable transcriptional features in diverse biological settings, such as drug response prediction, cancer diagnosis, or kidney transplant rejection.

Availability and implementation

The R code of SUBSTRA is available at https://github.com/sahandk/SUBSTRA.

Supplementary information

Supplementary data are available at Bioinformatics online.