ECMarker: interpretable machine learning model identifies gene expression biomarkers predicting clinical outcomes and reveals molecular mechanisms of human disease in early stages

Specific feature recognition on group specific networks (SFR-GSN): a biomarker identification model for cancer stages

Background and Objective

Accurate identification of cancer stages is challenging due to the complexity and heterogeneity of the disease. Current clinical diagnosis methods primarily rely on phenotypic observations, which may not capture early molecular-level changes accurately.

Methods

In this study, a novel biomarker recognition method was proposed tailored for cancer stages by considering the change of gene expression relationships. Utilizing the sample-specific information and protein-protein interaction networks, the group specific networks were constructed to address the limited specificity of potential biomarkers. Then, a specific feature recognition method was proposed based on these group specific networks, which employed the random forest algorithm for initial screening followed by a recursive feature elimination process to identify the optimal biomarker subset. During exploring optimal results, a strategy termed the Cost-Benefit Ratio, was devised to facilitate the identification of stage-specific biomarkers.

Results

Comparative experiments were conducted on lung adenocarcinoma and breast cancer datasets to validate the method's efficacy and generalizability. The results showed that the identified biomarkers were highly stage-specific, and the F1 scores for predicting cancer stages were significantly improved. For the lung adenocarcinoma dataset, the F1 score reached 97.68%, and for the breast cancer dataset, it achieved 96.87%. These results significantly surpassed those of three conventional methods in terms of F1 scores. Moreover, from the perspective of biological functions, the biomarkers were proved playing an important role in cancer stage-evolution.

Conclusion

The proposed method demonstrated its effectiveness in identifying stage-related biomarkers. By using these biomarkers as features, accurate prediction of cancer stages was achieved. Furthermore, the method exhibited potential for biomarker identification in subtype analyses, offering novel perspectives for cancer prognosis.

AITeQ: a machine learning framework for Alzheimer's prediction using a distinctive five-gene signature

Neurodegenerative diseases, such as Alzheimer's disease, pose a significant global health challenge with their complex etiology and elusive biomarkers. In this study, we developed the Alzheimer's Identification Tool (AITeQ) using ribonucleic acid-sequencing (RNA-seq), a machine learning (ML) model based on an optimized ensemble algorithm for the identification of Alzheimer's from RNA-seq data. Analysis of RNA-seq data from several studies identified 87 differentially expressed genes. This was followed by a ML protocol involving feature selection, model training, performance evaluation, and hyperparameter tuning. The feature selection process undertaken in this study, employing a combination of four different methodologies, culminated in the identification of a compact yet impactful set of five genes. Twelve diverse ML models were trained and tested using these five genes (CNKSR1, EPHA2, CLSPN, OLFML3, and TARBP1). Performance metrics, including precision, recall, F1 score, accuracy, Matthew's correlation coefficient, and receiver operating characteristic area under the curve were assessed for the finally selected model. Overall, the ensemble model consisting of logistic regression, naive Bayes classifier, and support vector machine with optimized hyperparameters was identified as the best and was used to develop AITeQ. AITeQ is available at: https://github.com/ishtiaque-ahammad/AITeQ.

PheSeq, a Bayesian deep learning model to enhance and interpret the gene-disease association studies

Despite the abundance of genotype-phenotype association studies, the resulting association outcomes often lack robustness and interpretations. To address these challenges, we introduce PheSeq, a Bayesian deep learning model that enhances and interprets association studies through the integration and perception of phenotype descriptions. By implementing the PheSeq model in three case studies on Alzheimer's disease, breast cancer, and lung cancer, we identify 1024 priority genes for Alzheimer's disease and 818 and 566 genes for breast cancer and lung cancer, respectively. Benefiting from data fusion, these findings represent moderate positive rates, high recall rates, and interpretation in gene-disease association studies.

Interpretable machine learning for dementia: A systematic review

INTRODUCTION

Machine learning research into automated dementia diagnosis is becoming increasingly popular but so far has had limited clinical impact. A key challenge is building robust and generalizable models that generate decisions that can be reliably explained. Some models are designed to be inherently "interpretable," whereas post hoc "explainability" methods can be used for other models.

METHODS

Here we sought to summarize the state-of-the-art of interpretable machine learning for dementia.

RESULTS

We identified 92 studies using PubMed, Web of Science, and Scopus. Studies demonstrate promising classification performance but vary in their validation procedures and reporting standards and rely heavily on popular data sets.

DISCUSSION

Future work should incorporate clinicians to validate explanation methods and make conclusive inferences about dementia-related disease pathology. Critically analyzing model explanations also requires an understanding of the interpretability methods itself. Patient-specific explanations are also required to demonstrate the benefit of interpretable machine learning in clinical practice.

LncRNA NCK1-AS1-mediated regulatory functions in human diseases

Disease development requires the activation of complex multi-factor processes involving numerous long noncoding RNAs (lncRNAs), which describe non-protein-coding RNAs longer than 200 nucleotides. Emerging evidence indicates that lncRNAs act as essential regulators that perform pivotal roles in the pathogenesis and progression of human diseases. The mechanisms underlying lncRNA involvement in diverse diseases have been extensively explored, and lncRNAs are considered powerful biomarkers for clinical practice. The lncRNA noncatalytic region of tyrosine kinase adaptor protein 1 (NCK1) antisense 1 (NCK1-AS1), also known as NCK1 divergent transcript (NCK1-DT), is encoded on human chromosome 3q22.3 and produces a 27,274-base-long transcript. NCK1-AS1 has increasingly been characterized as a causative agent for multiple diseases. The abnormal expression and involvement of NCK1-AS1 in various biological processes have been associated with several diseases. Further exploration of the mechanisms through which NCK1-AS1 contributes to disease development and progression will provide a foundation for potential clinical applications of NCK1-AS1 in the diagnosis and treatment of various diseases. This review summarizes the current understanding of the various functions and mechanisms through which NCK1-AS1 contributes to various diseases and the clinical application prospects for NCK1-AS1.

High-impact opportunities to address ischemia: a focus on heart and circulatory research

Myocardial ischemic injury and its resolution are the key determinants of morbidity or mortality in heart failure. The cause and duration of ischemia in patients vary. Numerous experimental models and methods have been developed to define genetic, metabolic, molecular, cellular, and pathophysiological mechanisms, in addition to defining structural and functional deterioration of cardiovascular performance. The rapid rise of big data, such as single-cell analysis techniques with bioinformatics, machine learning, and neural networking, brings a new level of sophistication to our understanding of myocardial ischemia. This mini-review explores the multifaceted nature of ischemic injury in the myocardium. We highlight recent state-of-the-art findings and strategies to show new directions of high-impact approach to understanding myocardial tissue remodeling. This next age of heart and circulatory physiology research will be more comprehensive and collaborative to uncover the origin, progression, and manifestation of heart failure while strengthening novel treatment strategies.

Identification and validation of a novel prognostic model based on platinum Resistance-related genes in bladder cancer

BACKGROUND

The depth of response to platinum in urothelial neoplasm tissues varies greatly. Biomarkers that have practical value in prognosis stratification are increasingly needed. Our study aimed to select a set of BC (bladder cancer)-related genes involved in both platinum resistance and survival, then use these genes to establish the prognostic model.

MATERIALS AND METHODS

Platinum resistance-related DEGs (differentially expressed genes) and tumorigenesis-related DEGs were identified. Ten most predictive co-DEGs were acquired followed by building a risk score model. Survival analysis and ROC (receiver operating characteristic) plot were used to evaluate the predictive accuracy. Combined with age and tumor stages, a nomogram was generated to create a graphical representation of survival rates at 1-, 3-, 5-, and 8-year in BC patients. The prognostic performance was validated in three independent BC datasets with platinum-based chemotherapy. The potential mechanism was explored by enrichment analysis.

RESULTS

PPP2R2B, TSPAN7, ATAD3C, SYT15, SAPCD1, AKR1B1, TCHH, AKAP12, AGLN3, and IGF2 were selected for our prognostic model. Patients in high- and low-risk groups exhibited a significant survival difference with HR (hazard ratio) = 2.7 (p < 0.0001). The prognostic nomogram of predicting 3-year OS (overall survival) for BC patients could yield an AUC (area under the curve) of 0.819. In the external validation dataset, the risk score also has a robust predictive ability.

CONCLUSION

A prognostic model derived from platinum resistance-related genes was constructed, we confirmed its value in predicting platinum-based chemotherapy benefits and overall survival for BC patients. The model might assist in therapeutic decisions for bladder malignancy.

Dynamic cancer drivers: a causal approach for cancer driver discovery based on bio-pathological trajectories

The traditional way for discovering genes which drive cancer (namely cancer drivers) neglects the dynamic information of cancer development, even though it is well known that cancer progresses dynamically. To enhance cancer driver discovery, we expand cancer driver concept to dynamic cancer driver as a gene driving one or more bio-pathological transitions during cancer progression. Our method refers to the fact that cancer should not be considered as a single process but a compendium of altered biological processes causing the disease to develop over time. Reciprocally, different drivers of cancer can potentially be discovered by analysing different bio-pathological pathways. We propose a novel approach for causal inference of genes driving one or more core processes during cancer development (i.e. dynamic cancer driver). We use the concept of pseudotime for inferring the latent progression of samples along a biological transition during cancer and identifying a critical event when such a process is significantly deviated from normal to carcinogenic. We infer driver genes by assessing the causal effect they have on the process after such a critical event. We have applied our method to single-cell and bulk sequencing datasets of breast cancer. The evaluation results show that our method outperforms well-recognized cancer driver inference methods. These results suggest that including information of the underlying dynamics of cancer improves the inference process (in comparison with using static data), and allows us to discover different sets of driver genes from different processes in cancer. R scripts and datasets can be found at https://github.com/AndresMCB/DynamicCancerDriver.

Ensemble machine learning model identifies patients with HFpEF from matrix-related plasma biomarkers

Arterial hypertension can lead to structural changes within the heart including left ventricular hypertrophy (LVH) and eventually heart failure with preserved ejection fraction (HFpEF). The initial diagnosis of HFpEF is costly and generally based on later stage remodeling; thus, improved predictive diagnostic tools offer potential clinical benefit. Recent work has shown predictive value of multibiomarker plasma panels for the classification of patients with LVH and HFpEF. We hypothesized that machine learning algorithms could substantially improve the predictive value of circulating plasma biomarkers by leveraging more sophisticated statistical approaches. In this work, we developed an ensemble classification algorithm for the diagnosis of HFpEF within a population of 480 individuals including patients with HFpEF, patients with LVH, and referent control patients. Algorithms showed strong diagnostic performance with receiver-operating-characteristic curve (ROC) areas of 0.92 for identifying patients with LVH and 0.90 for identifying patients with HFpEF using demographic information, plasma biomarkers related to extracellular matrix remodeling, and echocardiogram data. More impressively, the ensemble algorithm produced an ROC area of 0.88 for HFpEF diagnosis using only demographic and plasma panel data. Our findings demonstrate that machine learning-based classification algorithms show promise as a noninvasive diagnostic tool for HFpEF, while also suggesting priority biomarkers for future mechanistic studies to elucidate more specific regulatory roles.NEW & NOTEWORTHY Machine learning algorithms correctly classified patients with heart failure with preserved ejection fraction with over 90% area under receiver-operating-characteristic curves. Classifications using multidomain features (demographics and circulating biomarkers and echo-based ventricle metrics) proved more accurate than previous studies using single-domain features alone. Excitingly, HFpEF diagnoses were generally accurate even without echo-based measurements, demonstrating that such algorithms could provide an early screening tool using blood-based measurements before sophisticated imaging.

SEPA: Signalling entropy-based algorithm to evaluate personalized pathway activation for survival analysis on pan-cancer data

MOTIVATION

Biomarkers with prognostic ability and biological interpretability can be used to support decision-making in the survival analysis. Genes usually form functional modules to play synergistic roles, such as pathways. Predicting significant features from the functional level can effectively reduce the adverse effects of heterogeneity and obtain more reproducible and interpretable biomarkers. Personalized pathway activation inference can quantify the dysregulation of essential pathways involved in the initiation and progression of cancers, and can contribute to the development of personalized medical treatments.

RESULTS

In this study, we propose a novel method to evaluate personalized pathway activation based on signalling entropy for survival analysis (SEPA), which is a new attempt to introduce the information-theoretic entropy in generating pathway representation for each patient. SEPA effectively integrates pathway-level information into gene expression data, converting the high-dimensional gene expression data into the low-dimensional biological pathway activation scores. SEPA shows its classification power on the prognostic pan-cancer genomic data, and the potential pathway markers identified based on SEPA have statistical significance in the discrimination of high-risk and low-risk cohorts and are likely to be associated with the initiation and progress of cancers. The results show that SEPA scores can be used as an indicator to precisely distinguish cancer patients with different clinical outcomes, and identify important pathway features with strong discriminative power and biological interpretability.

AVAILABILITY

The MATLAB-package for SEPA is freely available from https://github.com/xingyili/SEPA.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

A Review on Recent Progress in Machine Learning and Deep Learning Methods for Cancer Classification on Gene Expression Data

Data-driven model with predictive ability are important to be used in medical and healthcare. However, the most challenging task in predictive modeling is to construct a prediction model, which can be addressed using machine learning (ML) methods. The methods are used to learn and trained the model using a gene expression dataset without being programmed explicitly. Due to the vast amount of gene expression data, this task becomes complex and time consuming. This paper provides a recent review on recent progress in ML and deep learning (DL) for cancer classification, which has received increasing attention in bioinformatics and computational biology. The development of cancer classification methods based on ML and DL is mostly focused on this review. Although many methods have been applied to the cancer classification problem, recent progress shows that most of the successful techniques are those based on supervised and DL methods. In addition, the sources of the healthcare dataset are also described. The development of many machine learning methods for insight analysis in cancer classification has brought a lot of improvement in healthcare. Currently, it seems that there is highly demanded further development of efficient classification methods to address the expansion of healthcare applications.

Machine learning in the prediction of cancer therapy

Resistance to therapy remains a major cause of cancer treatment failures, resulting in many cancer-related deaths. Resistance can occur at any time during the treatment, even at the beginning. The current treatment plan is dependent mainly on cancer subtypes and the presence of genetic mutations. Evidently, the presence of a genetic mutation does not always predict the therapeutic response and can vary for different cancer subtypes. Therefore, there is an unmet need for predictive models to match a cancer patient with a specific drug or drug combination. Recent advancements in predictive models using artificial intelligence have shown great promise in preclinical settings. However, despite massive improvements in computational power, building clinically useable models remains challenging due to a lack of clinically meaningful pharmacogenomic data. In this review, we provide an overview of recent advancements in therapeutic response prediction using machine learning, which is the most widely used branch of artificial intelligence. We describe the basics of machine learning algorithms, illustrate their use, and highlight the current challenges in therapy response prediction for clinical practice.

Machine learning approaches to predicting amyloid status using data from an online research and recruitment registry: The Brain Health Registry

INTRODUCTION

This study investigated the extent to which subjective and objective data from an online registry can be analyzed using machine learning methodologies to predict the current brain amyloid beta (Aβ) status of registry participants.

METHODS

We developed and optimized machine learning models using data from up to 664 registry participants. Models were assessed on their ability to predict Aβ positivity using the results of positron emission tomography as ground truth.

RESULTS

Study partner-assessed Everyday Cognition score was preferentially selected for inclusion in the models by a feature selection algorithm during optimization.

DISCUSSION

Our results suggest that inclusion of study partner assessments would increase the ability of machine learning models to predict Aβ positivity.

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.