A greedy feature selection algorithm for Big Data of high dimensionality

piscesCSM: prediction of anticancer synergistic drug combinations

While drug combination therapies are of great importance, particularly in cancer treatment, identifying novel synergistic drug combinations has been a challenging venture. Computational methods have emerged in this context as a promising tool for prioritizing drug combinations for further evaluation, though they have presented limited performance, utility, and interpretability. Here, we propose a novel predictive tool, piscesCSM, that leverages graph-based representations to model small molecule chemical structures to accurately predict drug combinations with favourable anticancer synergistic effects against one or multiple cancer cell lines. Leveraging these insights, we developed a general supervised machine learning model to guide the prediction of anticancer synergistic drug combinations in over 30 cell lines. It achieved an area under the receiver operating characteristic curve (AUROC) of up to 0.89 on independent non-redundant blind tests, outperforming state-of-the-art approaches on both large-scale oncology screening data and an independent test set generated by AstraZeneca (with more than a 16% improvement in predictive accuracy). Moreover, by exploring the interpretability of our approach, we found that simple physicochemical properties and graph-based signatures are predictive of chemotherapy synergism. To provide a simple and integrated platform to rapidly screen potential candidate pairs with favourable synergistic anticancer effects, we made piscesCSM freely available online at https://biosig.lab.uq.edu.au/piscescsm/ as a web server and API. We believe that our predictive tool will provide a valuable resource for optimizing and augmenting combinatorial screening libraries to identify effective and safe synergistic anticancer drug combinations. SCIENTIFIC CONTRIBUTION: This work proposes piscesCSM, a machine-learning-based framework that relies on well-established graph-based representations of small molecules to identify and provide better predictive accuracy of syngenetic drug combinations. Our model, piscesCSM, shows that combining physiochemical properties with graph-based signatures can outperform current architectures on classification prediction tasks. Furthermore, implementing our tool as a web server offers a user-friendly platform for researchers to screen for potential synergistic drug combinations with favorable anticancer effects against one or multiple cancer cell lines.

Emerging applications of machine learning in genomic medicine and healthcare

The integration of artificial intelligence technologies has propelled the progress of clinical and genomic medicine in recent years. The significant increase in computing power has facilitated the ability of artificial intelligence models to analyze and extract features from extensive medical data and images, thereby contributing to the advancement of intelligent diagnostic tools. Artificial intelligence (AI) models have been utilized in the field of personalized medicine to integrate clinical data and genomic information of patients. This integration allows for the identification of customized treatment recommendations, ultimately leading to enhanced patient outcomes. Notwithstanding the notable advancements, the application of artificial intelligence (AI) in the field of medicine is impeded by various obstacles such as the limited availability of clinical and genomic data, the diversity of datasets, ethical implications, and the inconclusive interpretation of AI models' results. In this review, a comprehensive evaluation of multiple machine learning algorithms utilized in the fields of clinical and genomic medicine is conducted. Furthermore, we present an overview of the implementation of artificial intelligence (AI) in the fields of clinical medicine, drug discovery, and genomic medicine. Finally, a number of constraints pertaining to the implementation of artificial intelligence within the healthcare industry are examined.

Automated machine learning for genome wide association studies

MOTIVATION

Genome-wide association studies (GWAS) present several computational and statistical challenges for their data analysis, including knowledge discovery, interpretability, and translation to clinical practice.

RESULTS

We develop, apply, and comparatively evaluate an automated machine learning (AutoML) approach, customized for genomic data that delivers reliable predictive and diagnostic models, the set of genetic variants that are important for predictions (called a biosignature), and an estimate of the out-of-sample predictive power. This AutoML approach discovers variants with higher predictive performance compared to standard GWAS methods, computes an individual risk prediction score, generalizes to new, unseen data, is shown to better differentiate causal variants from other highly correlated variants, and enhances knowledge discovery and interpretability by reporting multiple equivalent biosignatures.

AVAILABILITY AND IMPLEMENTATION

Code for this study is available at: https://github.com/mensxmachina/autoML-GWAS. JADBio offers a free version at: https://jadbio.com/sign-up/. SNP data can be downloaded from the EGA repository (https://ega-archive.org/). PRS data are found at: https://www.aicrowd.com/challenges/opensnp-height-prediction. Simulation data to study population structure can be found at: https://easygwas.ethz.ch/data/public/dataset/view/1/.

embryoTox: Using Graph-Based Signatures to Predict the Teratogenicity of Small Molecules

Teratogenic drugs can lead to extreme fetal malformation and consequently critically influence the fetus's health, yet the teratogenic risks associated with most approved drugs are unknown. Here, we propose a novel predictive tool, embryoTox, which utilizes a graph-based signature representation of the chemical structure of a small molecule to predict and classify molecules likely to be safe during pregnancy. embryoTox was trained and validated using in vitro bioactivity data of over 700 small molecules with characterized teratogenicity effects. Our final model achieved an area under the receiver operating characteristic curve (AUC) of up to 0.96 on 10-fold cross-validation and 0.82 on nonredundant blind tests, outperforming alternative approaches. We believe that our predictive tool will provide a practical resource for optimizing screening libraries to determine effective and safe molecules to use during pregnancy. To provide a simple and integrated platform to rapidly screen for potential safe molecules and their risk factors, we made embryoTox freely available online at https://biosig.lab.uq.edu.au/embryotox/.

A Steering-Matrix-Based Multiobjective Evolutionary Algorithm for High-Dimensional Feature Selection

In recent years, multiobjective evolutionary algorithms (MOEAs) have been demonstrated to show promising performance in feature selection (FS) tasks. However, designing an MOEA for high-dimensional FS is more challenging due to the curse of dimensionality. To address this problem, in this article, a steering-matrix-based multiobjective evolutionary algorithm, called SM-MOEA, is proposed. In SM-MOEA, a steering matrix is suggested and harnessed to guide the evolution of the population, which not only improves the search efficiency greatly but also obtains the feature subsets with high quality. Specifically, each element SM (i, j) in the steering matrix SM reflects the probability of the j th feature that is selected in the i th individual (feature subset), which is generated by considering the importance of both the feature j and the individual i . Based on the suggested steering matrix, two important operators referred to as dimensionality reduction and individual repairing operators are developed to effectively steer the population evolution in each generation. In addition, an effective initialization and update strategy for the steering matrix is also designed to further improve the performance of SM-MOEA. The experimental results on 12 high-dimensional datasets with the number of features ranging from 3000 to 13 000 demonstrate the superiority of the proposed algorithm over several state-of-the-art algorithms (including single-objective and MOEAs for high-dimensional FS) in terms of both the number and quality of the selected features.

Computational Recognition of a Regulatory T-cell-specific Signature With Potential Implications in Prognosis, Immunotherapy, and Therapeutic Resistance of Prostate Cancer

Prostate cancer, recognized as a "cold" tumor, has an immunosuppressive microenvironment in which regulatory T cells (Tregs) usually play a major role. Therefore, identifying a prognostic signature of Tregs has promising benefits of improving survival of prostate cancer patients. However, the traditional methods of Treg quantification usually suffer from bias and variability. Transcriptional characteristics have recently been found to have a predictive power for the infiltration of Tregs. Thus, a novel machine learning-based computational framework has been presented using Tregs and 19 other immune cell types using 42 purified immune cell datasets from GEO to identify Treg-specific mRNAs, and a prognostic signature of Tregs (named "TILTregSig") consisting of five mRNAs (SOCS2, EGR1, RRM2, TPP1, and C11orf54) was developed and validated to monitor the prognosis of prostate cancer using the TCGA and ICGC datasets. The TILTregSig showed a stronger predictive power for tumor immunity compared with tumor mutation burden and glycolytic activity, which have been reported as immune predictors. Further analyses indicate that the TILTregSig might influence tumor immunity mainly by mediating tumor-infiltrating Tregs and could be a powerful predictor for Tregs in prostate cancer. Moreover, the TILTregSig showed a promising potential for predicting cancer immunotherapy (CIT) response in five CIT response datasets and therapeutic resistance in the GSCALite dataset in multiple cancers. Our TILTregSig derived from PBMCs makes it possible to achieve a straightforward, noninvasive, and inexpensive detection assay for prostate cancer compared with the current histopathological examination that requires invasive tissue puncture, which lays the foundation for the future development of a panel of different molecules in peripheral blood comprising a biomarker of prostate cancer.

Understanding and predicting the functional consequences of missense mutations in BRCA1 and BRCA2

BRCA1 and BRCA2 are tumour suppressor genes that play a critical role in maintaining genomic stability via the DNA repair mechanism. DNA repair defects caused by BRCA1 and BRCA2 missense variants increase the risk of developing breast and ovarian cancers. Accurate identification of these variants becomes clinically relevant, as means to guide personalized patient management and early detection. Next-generation sequencing efforts have significantly increased data availability but also the discovery of variants of uncertain significance that need interpretation. Experimental approaches used to measure the molecular consequences of these variants, however, are usually costly and time-consuming. Therefore, computational tools have emerged as faster alternatives for assisting in the interpretation of the clinical significance of newly discovered variants. To better understand and predict variant pathogenicity in BRCA1 and BRCA2, various machine learning algorithms have been proposed, however presented limited performance. Here we present BRCA1 and BRCA2 gene-specific models and a generic model for quantifying the functional impacts of single-point missense variants in these genes. Across tenfold cross-validation, our final models achieved a Matthew's Correlation Coefficient (MCC) of up to 0.98 and comparable performance of up to 0.89 across independent, non-redundant blind tests, outperforming alternative approaches. We believe our predictive tool will be a valuable resource for providing insights into understanding and interpreting the functional consequences of missense variants in these genes and as a tool for guiding the interpretation of newly discovered variants and prioritizing mutations for experimental validation.

Accelerating Causal Inference and Feature Selection Methods through G-Test Computation Reuse

This article presents a novel and remarkably efficient method of computing the statistical G-test made possible by exploiting a connection with the fundamental elements of information theory: by writing the G statistic as a sum of joint entropy terms, its computation is decomposed into easily reusable partial results with no change in the resulting value. This method greatly improves the efficiency of applications that perform a series of G-tests on permutations of the same features, such as feature selection and causal inference applications because this decomposition allows for an intensive reuse of these partial results. The efficiency of this method is demonstrated by implementing it as part of an experiment involving IPC–MB, an efficient Markov blanket discovery algorithm, applicable both as a feature selection algorithm and as a causal inference method. The results show outstanding efficiency gains for IPC–MB when the G-test is computed with the proposed method, compared to the unoptimized G-test, but also when compared to IPC–MB++, a variant of IPC–MB which is enhanced with an AD–tree, both static and dynamic. Even if this proposed method of computing the G-test is presented here in the context of IPC–MB, it is in fact bound neither to IPC–MB in particular, nor to feature selection or causal inference applications in general, because this method targets the information-theoretic concept that underlies the G-test, namely conditional mutual information. This aspect grants it wide applicability in data sciences.

Extending greedy feature selection algorithms to multiple solutions

Most feature selection methods identify only a single solution. This is acceptable for predictive purposes, but is not sufficient for knowledge discovery if multiple solutions exist. We propose a strategy to extend a class of greedy methods to efficiently identify multiple solutions, and show under which conditions it identifies all solutions. We also introduce a taxonomy of features that takes the existence of multiple solutions into account. Furthermore, we explore different definitions of statistical equivalence of solutions, as well as methods for testing equivalence. A novel algorithm for compactly representing and visualizing multiple solutions is also introduced. In experiments we show that (a) the proposed algorithm is significantly more computationally efficient than the TIE* algorithm, the only alternative approach with similar theoretical guarantees, while identifying similar solutions to it, and (b) that the identified solutions have similar predictive performance.

Core Competitiveness Evaluation of Clean Energy Incubators Based on Matter-Element Extension Combined with TOPSIS and KPCA-NSGA-II-LSSVM

Scientific and accurate core competitiveness evaluation of clean energy incubators is of great significance for improving their burgeoning development. Hence, this paper proposes a hybrid model on the basis of matter-element extension integrated with TOPSIS and KPCA-NSGA-II-LSSVM. The core competitiveness evaluation index system of clean energy incubators is established from five aspects, namely strategic positioning ability, seed selection ability, intelligent transplantation ability, growth catalytic ability and service value-added ability. Then matter-element extension and TOPSIS based on entropy weight is applied to index weighting and comprehensive evaluation. For the purpose of feature dimension reduction, kernel principal component analysis (KPCA) is used to extract momentous information among variables as the input. The evaluation results can be obtained by least squares support vector machine (LSSVM) optimized by NSGA-II. The experiment study validates the precision and applicability of this novel approach, which is conducive to comprehensive evaluation of the core competitiveness for clean energy incubators and decision-making for more reasonable operation.

Genetic Variants Detection Based on Weighted Sparse Group Lasso

Identification of genetic variants associated with complex traits is a critical step for improving plant resistance and breeding. Although the majority of existing methods for variants detection have good predictive performance in the average case, they can not precisely identify the variants present in a small number of target genes. In this paper, we propose a weighted sparse group lasso (WSGL) method to select both common and low-frequency variants in groups. Under the biologically realistic assumption that complex traits are influenced by a few single loci in a small number of genes, our method involves a sparse group lasso approach to simultaneously select associated groups along with the loci within each group. To increase the probability of selecting out low-frequency variants, biological prior information is introduced in the model by re-weighting lasso regularization based on weights calculated from input data. Experimental results from both simulation and real data of single nucleotide polymorphisms (SNPs) associated with Arabidopsis flowering traits demonstrate the superiority of WSGL over other competitive approaches for genetic variants detection.