A guide to machine learning for biologists

Unsupervised machine learning highlights the challenges of subtyping disorders of gut-brain interaction

BACKGROUND

Unsupervised machine learning describes a collection of powerful techniques that seek to identify hidden patterns in unlabeled data. These techniques can be broadly categorized into dimension reduction, which transforms and combines the original set of measurements to simplify data, and cluster analysis, which seeks to group subjects based on some measure of similarity. Unsupervised machine learning can be used to explore alternative subtyping of disorders of gut-brain interaction (DGBI) compared to the existing gastrointestinal symptom-based definitions of Rome IV.

PURPOSE

This present review aims to familiarize the reader with fundamental concepts of unsupervised machine learning using accessible definitions and provide a critical summary of their application to the evaluation of DGBI subtyping. By considering the overlap between Rome IV clinical definitions and identified clusters, along with clinical and physiological insights, this paper speculates on the possible implications for DGBI. Also considered are algorithmic developments in the unsupervised machine learning community that may help leverage increasingly available omics data to explore biologically informed definitions. Unsupervised machine learning challenges the modern subtyping of DGBI and, with the necessary clinical validation, has the potential to enhance future iterations of the Rome criteria to identify more homogeneous, diagnosable, and treatable patient populations.

Multi-transcriptomics analysis of microvascular invasion-related malignant cells and development of a machine learning-based prognostic model in hepatocellular carcinoma

Background

Microvascular invasion (MVI) stands as a pivotal pathological hallmark of hepatocellular carcinoma (HCC), closely linked to unfavorable prognosis, early recurrence, and metastatic progression. However, the precise mechanistic underpinnings governing its onset and advancement remain elusive.

Methods

In this research, we downloaded bulk RNA-seq data from the TCGA and HCCDB repositories, single-cell RNA-seq data from the GEO database, and spatial transcriptomics data from the CNCB database. Leveraging the Scissor algorithm, we delineated prognosis-related cell subpopulations and discerned a distinct MVI-related malignant cell subtype. A comprehensive exploration of these malignant cell subpopulations was undertaken through pseudotime analysis and cell-cell communication scrutiny. Furthermore, we engineered a prognostic model grounded in MVI-related genes, employing 101 algorithm combinations integrated by 10 machine-learning algorithms on the TCGA training set. Rigorous evaluation ensued on internal testing sets and external validation sets, employing C-index, calibration curves, and decision curve analysis (DCA).

Results

Pseudotime analysis indicated that malignant cells, showing a positive correlation with MVI, were primarily concentrated in the early to middle stages of differentiation, correlating with an unfavorable prognosis. Importantly, these cells showed significant enrichment in the MYC pathway and were involved in extensive interactions with diverse cell types via the MIF signaling pathway. The association of malignant cells with the MVI phenotype was corroborated through validation in spatial transcriptomics data. The prognostic model we devised demonstrated exceptional sensitivity and specificity, surpassing the performance of most previously published models. Calibration curves and DCA underscored the clinical utility of this model.

Conclusions

Through integrated multi-transcriptomics analysis, we delineated MVI-related malignant cells and elucidated their biological functions. This study provided novel insights for managing HCC, with the constructed prognostic model offering valuable support for clinical decision-making.

AI hybrid survival assessment for advanced heart failure patients with renal dysfunction

Renal dysfunction (RD) often characterizes the worse course of patients with advanced heart failure (AHF). Many prognosis assessments are hindered by researcher biases, redundant predictors, and lack of clinical applicability. In this study, we enroll 1736 AHF/RD patients, including data from Henan Province Clinical Research Center for Cardiovascular Diseases (which encompasses 11 hospital subcenters), and Beth Israel Deaconess Medical Center. We developed an AI hybrid modeling framework, assembling 12 learners with different feature selection paradigms to expand modeling schemes. The optimized strategy is identified from 132 potential schemes to establish an explainable survival assessment system: AIHFLevel. The conditional inference survival tree determines a probability threshold for prognostic stratification. The evaluation confirmed the system's robustness in discrimination, calibration, generalization, and clinical implications. AIHFLevel outperforms existing models, clinical features, and biomarkers. We also launch an open and user-friendly website www.hf-ai-survival.com , empowering healthcare professionals with enhanced tools for continuous risk monitoring and precise risk profiling.

Artificial intelligence in plant breeding

Harnessing cutting-edge technologies to enhance crop productivity is a pivotal goal in modern plant breeding. Artificial intelligence (AI) is renowned for its prowess in big data analysis and pattern recognition, and is revolutionizing numerous scientific domains including plant breeding. We explore the wider potential of AI tools in various facets of breeding, including data collection, unlocking genetic diversity within genebanks, and bridging the genotype-phenotype gap to facilitate crop breeding. This will enable the development of crop cultivars tailored to the projected future environments. Moreover, AI tools also hold promise for refining crop traits by improving the precision of gene-editing systems and predicting the potential effects of gene variants on plant phenotypes. Leveraging AI-enabled precision breeding can augment the efficiency of breeding programs and holds promise for optimizing cropping systems at the grassroots level. This entails identifying optimal inter-cropping and crop-rotation models to enhance agricultural sustainability and productivity in the field.

Artificial intelligence-assisted metastasis and prognosis model for patients with nodular melanoma

OBJECTIVE

The objective of this study was to identify the risk factors that influence metastasis and prognosis in patients with nodular melanoma (NM), as well as to develop and validate a prognostic model using artificial intelligence (AI) algorithms.

METHODS

The Surveillance, Epidemiology, and End Results (SEER) database was queried for 4,727 patients with NM based on the inclusion/exclusion criteria. Their clinicopathological characteristics were retrospectively reviewed, and logistic regression analysis was utilized to identify risk factors for metastasis. This was followed by employing Multilayer Perceptron (MLP), Adaptive Boosting (AB), Bagging (BAG), logistic regression (LR), Gradient Boosting Machine (GBM), and eXtreme Gradient Boosting (XGB) algorithms to develop metastasis models. The performance of the six models was evaluated and compared, leading to the selection and visualization of the optimal model. Through integrating the prognostic factors of Cox regression analysis with the optimal models, the prognostic prediction model was constructed, validated, and assessed.

RESULTS

Logistic regression analyses identified that marital status, gender, primary site, surgery, radiation, chemotherapy, system management, and N stage were all independent risk factors for NM metastasis. MLP emerged as the optimal model among the six models (AUC = 0.932, F1 = 0.855, Accuracy = 0.856, Sensitivity = 0.878), and the corresponding network calculator (https://shimunana-nm-distant-m-nm-m-distant-8z8k54.streamlit.app/) was developed. The following were examined as independent prognostic factors: MLP, age, marital status, sequence number, laterality, surgery, radiation, chemotherapy, system management, T stage, and N stage. System management and surgery emerged as protective factors (HR < 1). To predict 1-, 3-, and 5-year overall survival (OS), a nomogram was created. The validation results demonstrated that the model exhibited good discrimination and consistency, as well as high clinical usefulness.

CONCLUSION

The developed prediction model more effectively reflects the prognosis of patients with NM and differentiates between the risk level of patients, serving as a useful supplement to the classical American Joint Committee on Cancer (AJCC) staging system and offering a reference for clinically stratified individualized treatment and prognosis prediction. Furthermore, the model enables clinicians to quantify the risk of metastasis in NM patients, assess patient survival, and administer precise treatments.

Advancing plant biology through deep learning-powered natural language processing

The application of deep learning methods, specifically the utilization of Large Language Models (LLMs), in the field of plant biology holds significant promise for generating novel knowledge on plant cell systems. The LLM framework exhibits exceptional potential, particularly with the development of Protein Language Models (PLMs), allowing for in-depth analyses of nucleic acid and protein sequences. This analytical capacity facilitates the discernment of intricate patterns and relationships within biological data, encompassing multi-scale information within DNA or protein sequences. The contribution of PLMs extends beyond mere sequence patterns and structure--function recognition; it also supports advancements in genetic improvements for agriculture. The integration of deep learning approaches into the domain of plant sciences offers opportunities for major breakthroughs in basic research across multi-scale plant traits. Consequently, the strategic application of deep learning methodologies, particularly leveraging the potential of LLMs, will undoubtedly play a pivotal role in advancing plant sciences, plant production, plant uses and propelling the trajectory toward sustainable agroecological and agro-food transitions.

Enhancing Withanolide Production in the Withania Species: Advances in In Vitro Culture and Synthetic Biology Approaches

Withanolides are naturally occurring steroidal lactones found in certain species of the Withania genus, especially Withania somnifera (commonly known as Ashwagandha). These compounds have gained considerable attention due to their wide range of therapeutic properties and potential applications in modern medicine. To meet the rapidly growing demand for withanolides, innovative approaches such as in vitro culture techniques and synthetic biology offer promising solutions. In recent years, synthetic biology has enabled the production of engineered withanolides using heterologous systems, such as yeast and bacteria. Additionally, in vitro methods like cell suspension culture and hairy root culture have been employed to enhance withanolide production. Nevertheless, one of the primary obstacles to increasing the production of withanolides using these techniques has been the intricacy of the biosynthetic pathways for withanolides. The present article examines new developments in withanolide production through in vitro culture. A comprehensive summary of viable traditional methods for producing withanolide is also provided. The development of withanolide production in heterologous systems is examined and emphasized. The use of machine learning as a potent tool to model and improve the bioprocesses involved in the generation of withanolide is then discussed. In addition, the control and modification of the withanolide biosynthesis pathway by metabolic engineering mediated by CRISPR are discussed.

Machine-learning-based models assist the prediction of pulmonary embolism in autoimmune diseases: A retrospective, multicenter study

BACKGROUND

Pulmonary embolism (PE) is a severe and acute cardiovascular syndrome with high mortality among patients with autoimmune inflammatory rheumatic diseases (AIIRDs). Accurate prediction and timely intervention play a pivotal role in enhancing survival rates. However, there is a notable scarcity of practical early prediction and risk assessment systems of PE in patients with AIIRD.

METHODS

In the training cohort, 60 AIIRD with PE cases and 180 age-, gender-, and disease-matched AIIRD non-PE cases were identified from 7254 AIIRD cases in Tongji Hospital from 2014 to 2022. Univariable logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) were used to select the clinical features for further training with machine learning (ML) methods, including random forest (RF), support vector machines (SVM), neural network (NN), logistic regression (LR), gradient boosted decision tree (GBDT), classification and regression trees (CART), and C5.0 models. The performances of these models were subsequently validated using a multicenter validation cohort.

RESULTS

In the training cohort, 24 and 13 clinical features were selected by univariable LR and LASSO strategies, respectively. The five ML models (RF, SVM, NN, LR, and GBDT) showed promising performances, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.962-1.000 in the training cohort and 0.969-0.999 in the validation cohort. CART and C5.0 models achieved AUCs of 0.850 and 0.932, respectively, in the training cohort. Using D-dimer as a pre-screening index, the refined C5.0 model achieved an AUC exceeding 0.948 in the training cohort and an AUC above 0.925 in the validation cohort. These results markedly outperformed the use of D-dimer levels alone.

CONCLUSION

ML-based models are proven to be precise for predicting the onset of PE in patients with AIIRD exhibiting clinical suspicion of PE.

TRIAL REGISTRATION

Chictr.org.cn : ChiCTR2200059599.

A methodological approach to age estimation of the intra-puparial period of the forensically relevant blow fly Calliphora vicina via Fourier transform infrared spectroscopy

Estimating the age of immature blow flies is of great importance for forensic entomology. However, no gold-standard technique for an accurate determination of the intra-puparial age has yet been established. Fourier transform infrared (FTIR) spectroscopy is a method to (bio-)chemically characterise material based on the absorbance of electromagnetic energy by functional groups of molecules. In recent years, it also has become a powerful tool in forensic and life sciences, as it is a fast and cost-effective way to characterise all kinds of material and biological traces. This study is the first to collect developmental reference data on the changes in absorption spectra during the intra-puparial period of the forensically important blow fly Calliphora vicina Robineau-Desvoidy (Diptera: Calliphoridae). Calliphora vicina was reared at constant 20°C and 25°C and specimens were killed every other day throughout their intra-puparial development. In order to investigate which part yields the highest detectable differences in absorption spectra throughout the intra-puparial development, each specimen was divided into two different subsamples: the pupal body and the former cuticle of the third instar, that is, the puparium. Absorption spectra were collected with a FTIR spectrometer coupled to an attenuated total reflection (ATR) unit. Classification accuracies of different wavenumber regions with two machine learning models, i.e., random forests (RF) and support vector machines (SVMs), were tested. The best age predictions for both temperature settings and machine learning models were obtained by using the full spectral range from 3700 to 600 cm-1. While SVMs resulted in better accuracies for C. vicina reared at 20°C, RFs performed almost as good as SVMs for data obtained from 25°C. In terms of sample type, the pupal body gave smoother spectra and usually better classification accuracies than the puparia. This study shows that FTIR spectroscopy is a promising technique in forensic entomology to support the estimation of the minimum post-mortem interval (PMImin), by estimating the age of a given insect specimen.

Screening antimicrobial peptides and probiotics using multiple deep learning and directed evolution strategies

Owing to their limited accuracy and narrow applicability, current antimicrobial peptide (AMP) prediction models face obstacles in industrial application. To address these limitations, we developed and improved an AMP prediction model using Comparing and Optimizing Multiple DEep Learning (COMDEL) algorithms, coupled with high-throughput AMP screening method, finally reaching an accuracy of 94.8% in test and 88% in experiment verification, surpassing other state-of-the-art models. In conjunction with COMDEL, we employed the phage-assisted evolution method to screen Sortase in vivo and developed a cell-free AMP synthesis system in vitro, ultimately increasing AMPs yields to a range of 0.5-2.1 g/L within hours. Moreover, by multi-omics analysis using COMDEL, we identified Lactobacillus plantarum as the most promising candidate for AMP generation among 35 edible probiotics. Following this, we developed a microdroplet sorting approach and successfully screened three L. plantarum mutants, each showing a twofold increase in antimicrobial ability, underscoring their substantial industrial application values.

A machine learning enhanced EMS mutagenesis probability map for efficient identification of causal mutations in Caenorhabditis elegans

Chemical mutagenesis-driven forward genetic screens are pivotal in unveiling gene functions, yet identifying causal mutations behind phenotypes remains laborious, hindering their high-throughput application. Here, we reveal a non-uniform mutation rate caused by Ethyl Methane Sulfonate (EMS) mutagenesis in the C. elegans genome, indicating that mutation frequency is influenced by proximate sequence context and chromatin status. Leveraging these factors, we developed a machine learning enhanced pipeline to create a comprehensive EMS mutagenesis probability map for the C. elegans genome. This map operates on the principle that causative mutations are enriched in genetic screens targeting specific phenotypes among random mutations. Applying this map to Whole Genome Sequencing (WGS) data of genetic suppressors that rescue a C. elegans ciliary kinesin mutant, we successfully pinpointed causal mutations without generating recombinant inbred lines. This method can be adapted in other species, offering a scalable approach for identifying causal genes and revitalizing the effectiveness of forward genetic screens.

Machine learning approaches for influenza A virus risk assessment identifies predictive correlates using ferret model in vivo data

In vivo assessments of influenza A virus (IAV) pathogenicity and transmissibility in ferrets represent a crucial component of many pandemic risk assessment rubrics, but few systematic efforts to identify which data from in vivo experimentation are most useful for predicting pathogenesis and transmission outcomes have been conducted. To this aim, we aggregated viral and molecular data from 125 contemporary IAV (H1, H2, H3, H5, H7, and H9 subtypes) evaluated in ferrets under a consistent protocol. Three overarching predictive classification outcomes (lethality, morbidity, transmissibility) were constructed using machine learning (ML) techniques, employing datasets emphasizing virological and clinical parameters from inoculated ferrets, limited to viral sequence-based information, or combining both data types. Among 11 different ML algorithms tested and assessed, gradient boosting machines and random forest algorithms yielded the highest performance, with models for lethality and transmission consistently better performing than models predicting morbidity. Comparisons of feature selection among models was performed, and highest performing models were validated with results from external risk assessment studies. Our findings show that ML algorithms can be used to summarize complex in vivo experimental work into succinct summaries that inform and enhance risk assessment criteria for pandemic preparedness that take in vivo data into account.

Deep learning enhancing guide RNA design for CRISPR/Cas12a-based diagnostics

Rapid and accurate diagnostic tests are fundamental for improving patient outcomes and combating infectious diseases. The Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) Cas12a-based detection system has emerged as a promising solution for on-site nucleic acid testing. Nonetheless, the effective design of CRISPR RNA (crRNA) for Cas12a-based detection remains challenging and time-consuming. In this study, we propose an enhanced crRNA design system with deep learning for Cas12a-mediated diagnostics, referred to as EasyDesign. This system employs an optimized convolutional neural network (CNN) prediction model, trained on a comprehensive data set comprising 11,496 experimentally validated Cas12a-based detection cases, encompassing a wide spectrum of prevalent pathogens, achieving Spearman's ρ = 0.812. We further assessed the model performance in crRNA design for four pathogens not included in the training data: Monkeypox Virus, Enterovirus 71, Coxsackievirus A16, and Listeria monocytogenes. The results demonstrated superior prediction performance compared to the traditional experiment screening. Furthermore, we have developed an interactive web server (https://crispr.zhejianglab.com/) that integrates EasyDesign with recombinase polymerase amplification (RPA) primer design, enhancing user accessibility. Through this web-based platform, we successfully designed optimal Cas12a crRNAs for six human papillomavirus (HPV) subtypes. Remarkably, all the top five predicted crRNAs for each HPV subtype exhibited robust fluorescent signals in CRISPR assays, thereby suggesting that the platform could effectively facilitate clinical sample testing. In conclusion, EasyDesign offers a rapid and reliable solution for crRNA design in Cas12a-based detection, which could serve as a valuable tool for clinical diagnostics and research applications.

An rs-fMRI based neuroimaging marker for adult absence epilepsy

OBJECTIVE

Approximately 20-30 % of epilepsy patients exhibit negative findings on routine magnetic resonance imaging, and this condition is known as nonlesional epilepsy. Absence epilepsy (AE) is a prevalent form of nonlesional epilepsy. This study aimed to investigate the clinical diagnostic utility of regional homogeneity (ReHo) assessed through the support vector machine (SVM) approach for identifying AE.

METHODS

This research involved 102 healthy individuals and 93 AE patients. Resting-state functional magnetic resonance imaging was employed for data acquisition in all participants. ReHo analysis, coupled with SVM methodology, was utilized for data processing.

RESULTS

Compared to healthy control individuals, AE patients demonstrated significantly elevated ReHo values in the bilateral putamen, accompanied by decreased ReHo in the bilateral thalamus. SVM was used to differentiate patients with AE from healthy control individuals based on rs-fMRI data. A composite assessment of altered ReHo in the left putamen and left thalamus yielded the highest accuracy at 81.64 %, with a sensitivity of 95.41 % and a specificity of 69.23 %.

SIGNIFICANCE

According to the results, altered ReHo values in the bilateral putamen and thalamus could serve as neuroimaging markers for AE, offering objective guidance for its diagnosis.

A hyper-distance-based method for hypernetwork comparison

Hypernetwork is a useful way to depict multiple connections between nodes, making it an ideal tool for representing complex relationships in network science. In recent years, there has been a marked increase in studies on hypernetworks; however, the comparison of the difference between two hypernetworks has received less attention. This paper proposes a hyper-distance (HD)-based method for comparing hypernetworks. The method is based on higher-order information, i.e, the higher-order distance between nodes and Jensen-Shannon divergence. Experiments carried out on synthetic hypernetworks have shown that HD is capable of distinguishing between hypernetworks generated with different parameters, and it is successful in the classification of hypernetworks. Furthermore, HD outperforms current state-of-the-art baselines to distinguish empirical hypernetworks when hyperedges are randomly perturbed.

Strategies in engineering sustainable biochemical synthesis through microbial systems

Growing environmental concerns and the urgency to address climate change have increased demand for the development of sustainable alternatives to fossil-derived fuels and chemicals. Microbial systems, possessing inherent biosynthetic capabilities, present a promising approach for achieving this goal. This review discusses the coupling of systems and synthetic biology to enable the elucidation and manipulation of microbial phenotypes for the production of chemicals that can substitute for petroleum-derived counterparts and contribute to advancing green biotechnology. The integration of artificial intelligence with metabolic engineering to facilitate precise and data-driven design of biosynthetic pathways is also discussed, along with the identification of current limitations and proposition of strategies for optimizing biosystems, thereby propelling the field of chemical biology towards sustainable chemical production.

Prognostic model incorporating immune checkpoint genes to predict the immunotherapy efficacy for lung adenocarcinoma: a cohort study integrating machine learning algorithms

This study aimed to develop and validate a nomogram based on immune checkpoint genes (ICGs) for predicting prognosis and immune checkpoint blockade (ICB) efficacy in lung adenocarcinoma (LUAD) patients. A total of 385 LUAD patients from the TCGA database and 269 LUAD patients in the combined dataset (GSE41272 + GSE50081) were divided into training and validation cohorts, respectively. Three different machine learning algorithms including random forest (RF), least absolute shrinkage and selection operator (LASSO) logistic regression analysis, and support vector machine (SVM) were employed to select the predictive markers from 82 ICGs to construct the prognostic nomogram. The X-tile software was used to stratify patients into high- and low-risk subgroups based on the nomogram-derived risk scores. Differences in functional enrichment and immune infiltration between the two subgroups were assessed using gene set variation analysis (GSVA) and various algorithms. Additionally, three lung cancer cohorts receiving ICB therapy were utilized to evaluate the ability of the model to predict ICB efficacy in the real world. Five ICGs were identified as predictive markers across all three machine learning algorithms, leading to the construction of a nomogram with strong potential for prognosis prediction in both the training and validation cohorts (all AUC values close to 0.800). The patients were divided into high- (risk score ≥ 185.0) and low-risk subgroups (risk score < 185.0). Compared to the high-risk subgroup, the low-risk subgroup exhibited enrichment in immune activation pathways and increased infiltration of activated immune cells, such as CD8 + T cells and M1 macrophages (P < 0.05). Furthermore, the low-risk subgroup had a greater likelihood of benefiting from ICB therapy and longer progression-free survival (PFS) than did the high-risk subgroup (P < 0.05) in the two cohorts receiving ICB therapy. A nomogram based on ICGs was constructed and validated to aid in predicting prognosis and ICB treatment efficacy in LUAD patients.

Identification of genetic susceptibility for Chinese migraine with depression using machine learning

Background

Migraine is a common primary headache that has a significant impact on patients' quality of life. The co-occurrence of migraine and depression is frequent, resulting in more complex symptoms and a poorer prognosis. The evidence suggests that depression and migraine comorbidity share a polygenic genetic background.

Objective

The aim of this study is to identify related genetic variants that contribute to genetic susceptibility to migraine with and without depression in a Chinese cohort.

Methods

In this case-control study, 263 individuals with migraines and 223 race-matched controls were included. Eight genetic polymorphism loci selected from the GWAS were genotyped using Sequenom's MALDI-TOF iPLEX platform.

Results

In univariate analysis, ANKDD1B rs904743 showed significant differences in genotype and allele distribution between migraineurs and controls. Furthermore, a machine learning approach was used to perform multivariate analysis. The results of the Random Forest algorithm indicated that ANKDD1B rs904743 was a significant risk factor for migraine susceptibility in China. Additionally, subgroup analysis by the Boruta algorithm showed a significant association between this SNP and migraine comorbid depression. Migraineurs with depression have been observed to have worse scores on the Beck Anxiety Inventory (BAI) and the Migraine Disability Assessment Scale (MIDAS).

Conclusion

The study indicates that there is an association between ANKDD1B rs904743 and susceptibility to migraine with and without depression in Chinese patients.

Machine learning-based screening and validation of liver metastasis-specific genes in colorectal cancer

Colorectal liver metastasis (CRLM) is challenging in the clinical treatment of colorectal cancer. Limited research has been conducted on how CRLM develops. RNA sequencing data were obtained from the Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA). Four machine learning algorithms were used to screen the hub CRLM-specific genes, including Least Absolute Shrinkage and Selection Operator (Lasso), Random forest, SVM-RFE, and XGboost. The model for identifying CRLM was developed using stepwise logistic regression and was validated using internal and independent datasets. The prognostic value of hub CRLM-specific genes was assessed using the Lasso-Cox method. The in vitro experiments were performed using SW620 cells. The CRLM identification model was developed based on four CRLM-specific genes (SPP1, ZG16, P2RY14, and PRKAR2B), and the model efficacy was validated using GSE41258 and three external cohorts. Five CRLM-specific prognostic hub genes, SPP1, ZG16, P2RY14, CYP2E1, and C5, were identified using the Lasso-Cox algorithm, and a risk score was constructed. The risk score was validated using the GSE39582 cohort. Three genes have both efficacy in identifying CRLM and prognostic value: ZG16, P2RY14, and SPP1. Immune infiltration and enrichment analyses demonstrated that SPP1 was associated with M2 macrophage polarization and extracellular matrix remodeling. In vitro experiments indicated that SPP1 may act as a cancer-promoting factor. The hub CRLM-specific gene SPP1 can help determine the diagnosis, prognosis, and immune infiltration of patients with CRLM.

AI-Assisted Rational Design and Activity Prediction of Biological Elements for Optimizing Transcription-Factor-Based Biosensors

The rational design, activity prediction, and adaptive application of biological elements (bio-elements) are crucial research fields in synthetic biology. Currently, a major challenge in the field is efficiently designing desired bio-elements and accurately predicting their activity using vast datasets. The advancement of artificial intelligence (AI) technology has enabled machine learning and deep learning algorithms to excel in uncovering patterns in bio-element data and predicting their performance. This review explores the application of AI algorithms in the rational design of bio-elements, activity prediction, and the regulation of transcription-factor-based biosensor response performance using AI-designed elements. We discuss the advantages, adaptability, and biological challenges addressed by the AI algorithms in various applications, highlighting their powerful potential in analyzing biological data. Furthermore, we propose innovative solutions to the challenges faced by AI algorithms in the field and suggest future research directions. By consolidating current research and demonstrating the practical applications and future potential of AI in synthetic biology, this review provides valuable insights for advancing both academic research and practical applications in biotechnology.

Harnessing Machine Learning to Uncover Hidden Patterns in Azole-Resistant CYP51/ERG11 Proteins

Fungal resistance is a public health concern due to the limited availability of antifungal resources and the complexities associated with treating persistent fungal infections. Azoles are thus far the primary line of defense against fungi. Specifically, azoles inhibit the conversion of lanosterol to ergosterol, producing defective sterols and impairing fluidity in fungal plasmatic membranes. Studies on azole resistance have emphasized specific point mutations in CYP51/ERG11 proteins linked to resistance. Although very insightful, the traditional approach to studying azole resistance is time-consuming and prone to errors during meticulous alignment evaluation. It relies on a reference-based method using a specific protein sequence obtained from a wild-type (WT) phenotype. Therefore, this study introduces a machine learning (ML)-based approach utilizing molecular descriptors representing the physiochemical attributes of CYP51/ERG11 protein isoforms. This approach aims to unravel hidden patterns associated with azole resistance. The results highlight that descriptors related to amino acid composition and their combination of hydrophobicity and hydrophilicity effectively explain the slight differences between the resistant non-wild-type (NWT) and WT (nonresistant) protein sequences. This study underscores the potential of ML to unravel nuanced patterns in CYP51/ERG11 sequences, providing valuable molecular signatures that could inform future endeavors in drug development and computational screening of resistant and nonresistant fungal lineages.

BioM2: biologically informed multi-stage machine learning for phenotype prediction using omics data

Navigating the complex landscape of high-dimensional omics data with machine learning models presents a significant challenge. The integration of biological domain knowledge into these models has shown promise in creating more meaningful stratifications of predictor variables, leading to algorithms that are both more accurate and generalizable. However, the wider availability of machine learning tools capable of incorporating such biological knowledge remains limited. Addressing this gap, we introduce BioM2, a novel R package designed for biologically informed multistage machine learning. BioM2 uniquely leverages biological information to effectively stratify and aggregate high-dimensional biological data in the context of machine learning. Demonstrating its utility with genome-wide DNA methylation and transcriptome-wide gene expression data, BioM2 has shown to enhance predictive performance, surpassing traditional machine learning models that operate without the integration of biological knowledge. A key feature of BioM2 is its ability to rank predictor variables within biological categories, specifically Gene Ontology pathways. This functionality not only aids in the interpretability of the results but also enables a subsequent modular network analysis of these variables, shedding light on the intricate systems-level biology underpinning the predictive outcome. We have proposed a biologically informed multistage machine learning framework termed BioM2 for phenotype prediction based on omics data. BioM2 has been incorporated into the BioM2 CRAN package (https://cran.r-project.org/web/packages/BioM2/index.html).

Integrated multi-omics with machine learning to uncover the intricacies of kidney disease

The development of omics technologies has driven a profound expansion in the scale of biological data and the increased complexity in internal dimensions, prompting the utilization of machine learning (ML) as a powerful toolkit for extracting knowledge and understanding underlying biological patterns. Kidney disease represents one of the major growing global health threats with intricate pathogenic mechanisms and a lack of precise molecular pathology-based therapeutic modalities. Accordingly, there is a need for advanced high-throughput approaches to capture implicit molecular features and complement current experiments and statistics. This review aims to delineate strategies for integrating multi-omics data with appropriate ML methods, highlighting key clinical translational scenarios, including predicting disease progression risks to improve medical decision-making, comprehensively understanding disease molecular mechanisms, and practical applications of image recognition in renal digital pathology. Examining the benefits and challenges of current integration efforts is expected to shed light on the complexity of kidney disease and advance clinical practice.

Machine learning and bioinformatics analysis of diagnostic biomarkers associated with the occurrence and development of lung adenocarcinoma

Objective

Lung adenocarcinoma poses a major global health challenge and is a leading cause of cancer-related deaths worldwide. This study is a review of three molecular biomarkers screened by machine learning that are not only important in the occurrence and progression of lung adenocarcinoma but also have the potential to serve as biomarkers for clinical diagnosis, prognosis evaluation and treatment guidance.

Methods

Differentially expressed genes (DEGs) were identified using comprehensive GSE1987 and GSE18842 gene expression databases. A comprehensive bioinformatics analysis of these DEGs was conducted to explore enriched functions and pathways, relative expression levels, and interaction networks. Random Forest and LASSO regression analysis techniques were used to identify the three most significant target genes. The TCGA database and quantitative polymerase chain reaction (qPCR) experiments were used to verify the expression levels and receiver operating characteristic (ROC) curves of these three target genes. Furthermore, immune invasiveness, pan-cancer, and mRNA-miRNA interaction network analyses were performed.

Results

Eighty-nine genes showed increased expression and 190 genes showed decreased expression. Notably, the upregulated DEGs were predominantly associated with organelle fission and nuclear division, whereas the downregulated DEGs were mainly associated with genitourinary system development and cell-substrate adhesion. The construction of the DEG protein-protein interaction network revealed 32 and 19 hub genes with the highest moderate values among the upregulated and downregulated genes, respectively. Using random forest and LASSO regression analyses, the hub genes were employed to identify three most significant target genes.TCGA database and qPCR experiments were used to verify the expression levels and ROC curves of these three target genes, and immunoinvasive analysis, pan-cancer analysis and mRNA-miRNA interaction network analysis were performed.

Conclusion

Three target genes identified by machine learning: BUB1B, CENPF, and PLK1 play key roles in LUAD development of lung adenocarcinoma.

A comprehensive survey on deep learning-based identification and predicting the interaction mechanism of long non-coding RNAs

Long noncoding RNAs (lncRNAs) have been discovered to be extensively involved in eukaryotic epigenetic, transcriptional, and post-transcriptional regulatory processes with the advancements in sequencing technology and genomics research. Therefore, they play crucial roles in the body's normal physiology and various disease outcomes. Presently, numerous unknown lncRNA sequencing data require exploration. Establishing deep learning-based prediction models for lncRNAs provides valuable insights for researchers, substantially reducing time and costs associated with trial and error and facilitating the disease-relevant lncRNA identification for prognosis analysis and targeted drug development as the era of artificial intelligence progresses. However, most lncRNA-related researchers lack awareness of the latest advancements in deep learning models and model selection and application in functional research on lncRNAs. Thus, we elucidate the concept of deep learning models, explore several prevalent deep learning algorithms and their data preferences, conduct a comprehensive review of recent literature studies with exemplary predictive performance over the past 5 years in conjunction with diverse prediction functions, critically analyze and discuss the merits and limitations of current deep learning models and solutions, while also proposing prospects based on cutting-edge advancements in lncRNA research.

Evaluation of transfer ensemble learning-based convolutional neural network models for the identification of chronic gingivitis from oral photographs

BACKGROUND

To evaluate the performances of several advanced deep convolutional neural network models (AlexNet, VGG, GoogLeNet, ResNet) based on ensemble learning for recognizing chronic gingivitis from screening oral images.

METHODS

A total of 683 intraoral clinical images acquired from 134 volunteers were used to construct the database and evaluate the models. Four deep ConvNet models were developed using ensemble learning and outperformed a single model. The performances of the different models were evaluated by comparing the accuracy and sensitivity for recognizing the existence of gingivitis from intraoral images.

RESULTS

The ResNet model achieved an area under the curve (AUC) value of 97%, while the AUC values for the GoogLeNet, AlexNet, and VGG models were 94%, 92%, and 89%, respectively. Although the ResNet and GoogLeNet models performed best in classifying gingivitis from images, the sensitivity outcomes were not significantly different among the ResNet, GoogLeNet, and Alexnet models (p>0.05). However, the sensitivity of the VGGNet model differed significantly from those of the other models (p < 0.001).

CONCLUSION

The ResNet and GoogLeNet models show promise for identifying chronic gingivitis from images. These models can help doctors diagnose periodontal diseases efficiently or based on self-examination of the oral cavity by patients.

Novel AT2 Cell Subpopulations and Diagnostic Biomarkers in IPF: Integrating Machine Learning with Single-Cell Analysis

Idiopathic pulmonary fibrosis (IPF) is a long-term condition with an unidentified cause, and currently there are no specific treatment options available. Alveolar epithelial type II cells (AT2) constitute a heterogeneous population crucial for secreting and regenerative functions in the alveolus, essential for maintaining lung homeostasis. However, a comprehensive investigation into their cellular diversity, molecular features, and clinical implications is currently lacking. In this study, we conducted a comprehensive examination of single-cell RNA sequencing data from both normal and fibrotic lung tissues. We analyzed alterations in cellular composition between IPF and normal tissue and investigated differentially expressed genes across each cell population. This analysis revealed the presence of two distinct subpopulations of IPF-related alveolar epithelial type II cells (IR_AT2). Subsequently, three unique gene co-expression modules associated with the IR_AT2 subtype were identified through the use of hdWGCNA. Furthermore, we refined and identified IPF-related AT2-related gene (IARG) signatures using various machine learning algorithms. Our analysis demonstrated a significant association between high IARG scores in IPF patients and shorter survival times (p-value < 0.01). Additionally, we observed a negative correlation between the percent predicted diffusing capacity for lung carbon monoxide (% DLCO) and increased IARG scores (cor = -0.44, p-value < 0.05). The cross-validation findings demonstrated a high level of accuracy (AUC > 0.85, p-value < 0.01) in the prognostication of patients with IPF utilizing the identified IARG signatures. Our study has identified distinct molecular and biological features among AT2 subpopulations, specifically highlighting the unique characteristics of IPF-related AT2 cells. Importantly, our findings underscore the prognostic relevance of specific genes associated with IPF-related AT2 cells, offering valuable insights into the advancement of IPF.

Biosimilars in the Era of Artificial Intelligence-International Regulations and the Use in Oncological Treatments

This research is based on three fundamental aspects of successful biosimilar development in the challenging biopharmaceutical market. First, biosimilar regulations in eight selected countries: Japan, South Korea, the United States, Canada, Brazil, Argentina, Australia, and South Africa, represent the four continents. The regulatory aspects of the countries studied are analyzed, highlighting the challenges facing biosimilars, including their complex approval processes and the need for standardized regulatory guidelines. There is an inconsistency depending on whether the biosimilar is used in a developed or developing country. In the countries observed, biosimilars are considered excellent alternatives to patent-protected biological products for the treatment of chronic diseases. In the second aspect addressed, various analytical AI modeling methods (such as machine learning tools, reinforcement learning, supervised, unsupervised, and deep learning tools) were analyzed to observe patterns that lead to the prevalence of biosimilars used in cancer to model the behaviors of the most prominent active compounds with spectroscopy. Finally, an analysis of the use of active compounds of biosimilars used in cancer and approved by the FDA and EMA was proposed.

Artificial intelligence in andrology - fact or fiction: essential takeaway for busy clinicians

ABSTRACT

Artificial intelligence (AI) is revolutionizing the current approach to medicine. AI uses machine learning algorithms to predict the success of therapeutic procedures or assist the clinician in the decision-making process. To date, machine learning studies in the andrological field have mainly focused on prostate cancer imaging and management. However, an increasing number of studies are documenting the use of AI to assist clinicians in decision-making and patient management in andrological diseases such as varicocele or sexual dysfunction. Additionally, machine learning applications are being employed to enhance success rates in assisted reproductive techniques (ARTs). This article offers the clinicians as well as the researchers with a brief overview of the current use of AI in andrology, highlighting the current state-of-the-art scientific evidence, the direction in which the research is going, and the strengths and limitations of this approach.

An novel effective and safe model for the diagnosis of nonalcoholic fatty liver disease in China: gene excavations, clinical validations, and mechanism elucidation

BACKGROUND

Non-alcoholic fatty liver disease (NAFLD) is one of the most common chronic liver diseases. NAFLD leads to liver fibrosis and hepatocellular carcinoma, and it also has systemic effects associated with metabolic diseases, cardiovascular diseases, chronic kidney disease, and malignant tumors. Therefore, it is important to diagnose NAFLD early to prevent these adverse effects.

METHODS

The GSE89632 dataset was downloaded from the Gene Expression Omnibus database, and then the optimal genes were screened from the data cohort using lasso and Support Vector Machine Recursive Feature Elimination (SVM-RFE). The ROC values of the optimal genes for the diagnosis of NAFLD were calculated. The relationship between optimal genes and immune cells was determined using the DECONVOLUTION algorithm CIBERSORT. Finally, the specificity and sensitivity of the diagnostic genes were verified by detecting the expression of the diagnostic genes in blood samples from 320 NAFLD patients and liver samples from 12 mice.

RESULTS

Through machine learning we identified FOSB, GPAT3, RGCC and RNF43 were the key diagnostic genes for NAFLD, and they were further demonstrated by a receiver operating characteristic curve analysis. We found that the combined diagnosis of the four genes identified NAFLD samples well from normal samples (AUC = 0.997). FOSB, GPAT3, RGCC and RNF43 were strongly associated with immune cell infiltration. We also experimentally examined the expression of these genes in NAFLD patients and NAFLD mice, and the results showed that these genes are highly specific and sensitive.

CONCLUSIONS

Data from both clinical and animal studies demonstrate the high sensitivity, specificity and safety of FOSB, GPAT3, RGCC and RNF43 for the diagnosis of NAFLD. The relationship between diagnostic key genes and immune cell infiltration may help to understand the development of NAFLD. The study was reviewed and approved by Ethics Committee of Tianjin Second People's Hospital in 2021 (ChiCTR1900024415).

Constructing diagnostic signature of serum microRNAs using machine learning for early pan-cancer detection

BACKGROUND

Cancer is a major public health concern and the second leading cause of death worldwide. Various studies have reported the use of serum microRNAs (miRNAs) as non-invasive biomarkers for cancer detection. However, large-scale pan-cancer studies based on serum miRNAs have been relatively scarce.

METHODS

An optimized machine learning workflow, combining least absolute shrinkage and selection operator (LASSO) analyses, recursive feature elimination (RFE), and fourteen kinds of machine learning algorithms, was use to screen out candidate miRNAs from 2540 serum miRNAs and constructed a potent diagnostic signature (Cancer-related Serum miRNA Signatures) for pan-cancer detection, based on a serum miRNA expression dataset of 38,223 samples.

RESULT

Cancer-related Serum miRNA Signatures performed well in pan-cancer detection with an area under curve (AUC) of 0.999, 94.51% sensitivity, and 99.49% specificity in the external validation cohort, and represented an acceptable diagnostic performance for identifying early-stage tumors. Furthermore, the ability of multi-classification of tumors by serum miRNAs in pancreatic, colorectal, and biliary tract cancers was lower than that in other cancers, which showed accuracies of 59%, 58.5%, and 28.9%, respectively, indicating that the difference in serum miRNA expression profiles among a small number of tumor subtypes was not as significant as that between cancer samples and non-cancer controls.

CONCLUSION

We have developed a serum miRNA signature using machine learning that may be a cost-effective risk tool for pan-cancer detection. Our findings will benefit not only the predictive diagnosis of cancer but also a preventive and more personalized screening plan.

Artificial intelligence empowering public health education: prospects and challenges

Artificial Intelligence (AI) is revolutionizing public health education through its capacity for intricate analysis of large-scale health datasets and the tailored dissemination of health-related information and interventions. This article conducts a profound exploration into the integration of AI within public health, accentuating its scientific foundations, prospective progress, and practical application scenarios. It underscores the transformative potential of AI in crafting individualized educational programs, developing sophisticated behavioral models, and informing the creation of health policies. The manuscript strives to thoroughly evaluate the extant landscape of AI applications in public health, scrutinizing critical challenges such as the propensity for data bias and the imperative of safeguarding privacy. By dissecting these issues, the article contributes to the conversation on how AI can be harnessed responsibly and effectively, ensuring that its application in public health education is both ethically grounded and equitable. The paper's significance is multifold: it aims to provide a blueprint for policy formulation, offer actionable insights for public health authorities, and catalyze the progression of health interventions toward increasingly sophisticated and precise approaches. Ultimately, this research anticipates fostering an environment where AI not only augments public health education but also does so with a steadfast commitment to the principles of justice and inclusivity, thereby elevating the standard and reach of health education initiatives globally.

Application of machine learning for high-throughput tumor marker screening

High-throughput sequencing and multiomics technologies have allowed increasing numbers of biomarkers to be mined and used for disease diagnosis, risk stratification, efficacy assessment, and prognosis prediction. However, the large number and complexity of tumor markers make screening them a substantial challenge. Machine learning (ML) offers new and effective ways to solve the screening problem. ML goes beyond mere data processing and is instrumental in recognizing intricate patterns within data. ML also has a crucial role in modeling dynamic changes associated with diseases. Used together, ML techniques have been included in automatic pipelines for tumor marker screening, thereby enhancing the efficiency and accuracy of the screening process. In this review, we discuss the general processes and common ML algorithms, and highlight recent applications of ML in tumor marker screening of genomic, transcriptomic, proteomic, and metabolomic data of patients with various types of cancers. Finally, the challenges and future prospects of the application of ML in tumor therapy are discussed.

Machine learning for the identification of neoantigen-reactive CD8 + T cells in gastrointestinal cancer using single-cell sequencing

BACKGROUND

It appears that tumour-infiltrating neoantigen-reactive CD8 + T (Neo T) cells are the primary driver of immune responses to gastrointestinal cancer in patients. However, the conventional method is very time-consuming and complex for identifying Neo T cells and their corresponding T cell receptors (TCRs).

METHODS

By mapping neoantigen-reactive T cells from the single-cell transcriptomes of thousands of tumour-infiltrating lymphocytes, we developed a 26-gene machine learning model for the identification of neoantigen-reactive T cells.

RESULTS

In both training and validation sets, the model performed admirably. We discovered that the majority of Neo T cells exhibited notable differences in the biological processes of amide-related signal pathways. The analysis of potential cell-to-cell interactions, in conjunction with spatial transcriptomic and multiplex immunohistochemistry data, has revealed that Neo T cells possess potent signalling molecules, including LTA, which can potentially engage with tumour cells within the tumour microenvironment, thereby exerting anti-tumour effects. By sequencing CD8 + T cells in tumour samples of patients undergoing neoadjuvant immunotherapy, we determined that the fraction of Neo T cells was significantly and positively linked with the clinical benefit and overall survival rate of patients.

CONCLUSION

This method expedites the identification of neoantigen-reactive TCRs and the engineering of neoantigen-reactive T cells for therapy.

Analysis of gene expression in microglial apoptotic cell clearance following spinal cord injury based on machine learning algorithms

Spinal cord injury (SCI) is a severe neurological complication following spinal fracture, which has long posed a challenge for clinicians. Microglia play a dual role in the pathophysiological process after SCI, both beneficial and detrimental. The underlying mechanisms of microglial actions following SCI require further exploration. The present study combined three different machine learning algorithms, namely weighted gene co-expression network analysis, random forest analysis and least absolute shrinkage and selection operator analysis, to screen for differentially expressed genes in the GSE96055 microglia dataset after SCI. It then used protein-protein interaction networks and gene set enrichment analysis with single genes to investigate the key genes and signaling pathways involved in microglial function following SCI. The results indicated that microglia not only participate in neuroinflammation but also serve a significant role in the clearance mechanism of apoptotic cells following SCI. Notably, bioinformatics analysis and lipopolysaccharide + UNC569 (a MerTK-specific inhibitor) stimulation of BV2 cell experiments showed that the expression levels of Anxa2, Myo1e and Spp1 in microglia were significantly upregulated following SCI, thus potentially involved in regulating the clearance mechanism of apoptotic cells. The present study suggested that Anxa2, Myo1e and Spp1 may serve as potential targets for the future treatment of SCI and provided a theoretical basis for the development of new methods and drugs for treating SCI.

Machine Learning: A Potential Therapeutic Tool to Facilitate Neonatal Therapeutic Decision Making

Bacterial infection is one of the major causes of neonatal morbidity and mortality worldwide. Finding rapid and reliable methods for early recognition and diagnosis of bacterial infections and early individualization of antibacterial drug administration are essential to eradicate these infections and prevent serious complications. However, this is often difficult to perform due to non-specific clinical presentations, low accuracy of current diagnostic methods, and limited knowledge of neonatal pharmacokinetics. Although neonatal medicine has been relatively late to embrace the benefits of machine learning (ML), there have been some initial applications of ML for the early prediction of neonatal sepsis and individualization of antibiotics. This article provides a brief introduction to ML and discusses the current state of the art in diagnosing and treating neonatal bacterial infections, gaps, potential uses of ML, and future directions to address the limitations of current studies. Neonatal bacterial infections involve a combination of physiologic development, disease expression, and treatment response outcomes. To address this complex relationship, future models could consider appropriate ML algorithms to capture time series features while integrating influences from the host, microbes, and drugs to optimize antimicrobial drug use in neonates. All models require prospective clinical trials to validate their clinical utility before clinical use.

Development of a machine learning model for predicting pneumothorax risk in coaxial core needle biopsy (≤3 cm)

PURPOSE

The aim is to devise a machine learning algorithm exploiting preoperative clinical data to forecast the hazard of pneumothorax post-coaxial needle lung biopsy (CCNB), thereby informing clinical decision-making and enhancing perioperative care.

METHOD

This retrospective analysis aggregated clinical and imaging data from patients with lung nodules (≤3 cm) biopsies. Variable selection was done using univariate analysis and LASSO regression, with the dataset subsequently divided into training (80 %) and validation (20 %) subsets. Various machine learning (ML) classifiers were employed in a consolidated approach to ascertain the paramount model, which was followed by individualized risk profiling showcased through Shapley Additive eXplanations (SHAP).

RESULTS

Out of the 325 patients included in the study, 19.6% (64/325) experienced postoperative pneumothorax. High-risk factors determined were Cancer, Lesion_type, GOLD, Size, and Depth. The Gaussian Naive Bayes (GNB) classifier demonstrated superior prediction with an Area Under the Curve (AUC) of 0.82 (95% CI 0.71-0.94), complemented by an accuracy rate of 0.8, sensitivity of 0.71, specificity of 0.84, and an F1 score of 0.61 in the test cohort.

CONCLUSION

The formulated prognostic algorithm exhibited commendable efficacy in preoperatively prognosticating CCNB-induced pneumothorax, harboring the potential to refine personalized risk appraisals, steer clinical judgment, and ameliorate perioperative patient stewardship.

Best practices for machine learning in antibody discovery and development

In the past 40 years, therapeutic antibody discovery and development have advanced considerably, with machine learning (ML) offering a promising way to speed up the process by reducing costs and the number of experiments required. Recent progress in ML-guided antibody design and development (D&D) has been hindered by the diversity of data sets and evaluation methods, which makes it difficult to conduct comparisons and assess utility. Establishing standards and guidelines will be crucial for the wider adoption of ML and the advancement of the field. This perspective critically reviews current practices, highlights common pitfalls and proposes method development and evaluation guidelines for various ML-based techniques in therapeutic antibody D&D. Addressing challenges across the ML process, best practices are recommended for each stage to enhance reproducibility and progress.

Health Star Rating of Nonalcoholic, Packaged, and Ready-to-Drink Beverages in Türkiye: A Decision Tree Model Study

This study aimed to compare the nutritional quality of beverages sold in Türkiye according to their labeling profiles. A total of 304 nonalcoholic beverages sold in supermarkets and online markets with the highest market capacity in Türkiye were included. Milk and dairy products, sports drinks, and beverages for children were excluded. The health star rating (HSR) was used to assess the nutritional quality of beverages. The nutritional quality of beverages was evaluated using a decision tree model according to the HSR score based on the variables presented on the beverage label. Moreover, confusion matrix tests were used to test the model's accuracy. The mean HSR score of beverages was 2.6±1.9, of which 30.2% were in the healthy category (HSR≥3.5). Fermented and 100% fruit juice beverages had the highest mean HSR scores. According to the decision tree model of the training set, the predictors of HSR quality score, in order of importance, were as follows: added sugar (46%), sweetener (28%), additives (19%), fructose-glucose syrup (4%), and caffeine (3%). In the test set, the accuracy rate and F1 score were 0.90 and 0.82, respectively, suggesting that the prediction performance of our model had the perfect fit. According to the HSR classification, most beverages were found to be unhealthy. Thus, they increase the risk of the development of obesity and other diseases because of their easy consumption. The decision tree learning algorithm could guide the population to choose healthy beverages based on their labeling information.

Machine learning-enabled colorimetric sensors for foodborne pathogen detection

In the past decade, there have been various advancements to colorimetric sensors to improve their potential applications in food and agriculture. One application of growing interest is sensing foodborne pathogens. There are unique considerations for sensing in the food industry, including food sample destruction, specificity amidst a complex food matrix, and high sensitivity requirements. Incorporating novel technology, such as nanotechnology, microfluidics, and smartphone app development, into colorimetric sensing methodology can enhance sensor performance. Nonetheless, there remain challenges to integrating sensors with existing food safety infrastructure. Recently, increasingly advanced machine learning techniques have been employed to facilitate nondestructive, multiplex detection for feasible assimilation of sensors into the food industry. With its ability to analyze and make predictions from highly complex data, machine learning holds potential for advanced yet practical colorimetric sensing of foodborne pathogens. This article summarizes recent developments and hurdles of machine learning-enabled colorimetric foodborne pathogen sensing. These advancements underscore the potential of interdisciplinary, cutting-edge technology in providing safer and more efficient food systems.

Progress in the Computer-Aided Analysis in Multiple Aspects of Nanocatalysis Research

Making the utmost of the differences and advantages of multiple disciplines, interdisciplinary integration breaks the science boundaries and accelerates the progress in mutual quests. As an organic connection of material science, enzymology, and biomedicine, nanozyme-related research is further supported by computer technology, which injects in new vitality, and contributes to in-depth understanding, unprecedented insights, and broadened application possibilities. Utilizing computer-aided first-principles method, high-speed and high-throughput mathematic, physic, and chemic models are introduced to perform atomic-level kinetic analysis for nanocatalytic reaction process, and theoretically illustrate the underlying nanozymetic mechanism and structure-function relationship. On this basis, nanozymes with desirable properties can be designed and demand-oriented synthesized without repeated trial-and-error experiments. Besides that, computational analysis and device also play an indispensable role in nanozyme-based detecting methods to realize automatic readouts with improved accuracy and reproducibility. Here, this work focuses on the crossing of nanocatalysis research and computational technology, to inspire the research in computer-aided analysis in nanozyme field to a greater extent.

Integrated multi-omics analysis and machine learning to refine molecular subtypes, prognosis, and immunotherapy in lung adenocarcinoma

Lung adenocarcinoma (LUAD) has a malignant characteristic that is highly aggressive and prone to metastasis. There is still a lack of suitable biomarkers to facilitate the refinement of precision-based therapeutic regimens. We used a combination of 10 known clustering algorithms and the omics data from 4 dimensions to identify high-resolution molecular subtypes of LUAD. Subsequently, consensus machine learning-related prognostic signature (CMRS) was developed based on subtypes related genes and an integrated program framework containing 10 machine learning algorithms. The efficiency of CMRS was analyzed from the perspectives of tumor microenvironment, genomic landscape, immunotherapy, drug sensitivity, and single-cell analysis. In terms of results, through multi-omics clustering, we identified 2 comprehensive omics subtypes (CSs) in which CS1 patients had worse survival outcomes, higher aggressiveness, mRNAsi and mutation frequency. Subsequently, we developed CMRS based on 13 key genes up-regulated in CS1. The prognostic predictive efficiency of CMRS was superior to most established LUAD prognostic signatures. CMRS demonstrated a strong correlation with tumor microenvironmental feature variants and genomic instability generation. Regarding clinical performance, patients in the high CMRS group were more likely to benefit from immunotherapy, whereas low CMRS were more likely to benefit from chemotherapy and targeted drug therapy. In addition, we evaluated that drugs such as neratinib, oligomycin A, and others may be candidates for patients in the high CMRS group. Single-cell analysis revealed that CMRS-related genes were mainly expressed in epithelial cells. The novel molecular subtypes identified in this study based on multi-omics data could provide new insights into the stratified treatment of LUAD, while the development of CMRS could serve as a candidate indicator of the degree of benefit of precision therapy and immunotherapy for LUAD.

Identification of diagnostic biomarkers and potential therapeutic targets for biliary atresia via WGCNA and machine learning methods

Biliary atresia (BA) is a severe and progressive biliary obstructive disease in infants that requires early diagnosis and new therapeutic targets. This study employed bioinformatics methods to identify diagnostic biomarkers and potential therapeutic targets for BA. Our analysis of mRNA expression from Gene Expression Omnibus datasets revealed 3,273 differentially expressed genes between patients with BA and those without BA (nBA). Weighted gene coexpression network analysis determined that the turquoise gene coexpression module, consisting of 298 genes, is predominantly associated with BA. The machine learning method then filtered out the top 2 important genes, CXCL8 and TMSB10, from the turquoise module. The area under receiver operating characteristic curves for TMSB10 and CXCL8 were 0.961 and 0.927 in the training group and 0.819 and 0.791 in the testing group, which indicated a high diagnostic value. Besides, combining TMSB10 and CXCL8, a nomogram with better diagnostic performance was built for clinical translation. Several studies have highlighted the potential of CXCL8 as a therapeutic target for BA, while TMSB10 has been shown to regulate cell polarity, which was related to BA progression. Our analysis with qRT PCR and immunohistochemistry also confirmed the upregulation of TMSB10 at mRNA and protein levels in BA liver samples. These findings highlight the sensitivity of CXCL8 and TMSB10 as diagnostic biomarkers and their potential as therapeutic targets for BA.

Integrated machine learning and multimodal data fusion for patho-phenotypic feature recognition in iPSC models of dilated cardiomyopathy

Integration of multiple data sources presents a challenge for accurate prediction of molecular patho-phenotypic features in automated analysis of data from human model systems. Here, we applied a machine learning-based data integration to distinguish patho-phenotypic features at the subcellular level for dilated cardiomyopathy (DCM). We employed a human induced pluripotent stem cell-derived cardiomyocyte (iPSC-CM) model of a DCM mutation in the sarcomere protein troponin T (TnT), TnT-R141W, compared to isogenic healthy (WT) control iPSC-CMs. We established a multimodal data fusion (MDF)-based analysis to integrate source datasets for Ca2+ transients, force measurements, and contractility recordings. Data were acquired for three additional layer types, single cells, cell monolayers, and 3D spheroid iPSC-CM models. For data analysis, numerical conversion as well as fusion of data from Ca2+ transients, force measurements, and contractility recordings, a non-negative blind deconvolution (NNBD)-based method was applied. Using an XGBoost algorithm, we found a high prediction accuracy for fused single cell, monolayer, and 3D spheroid iPSC-CM models (≥92 ± 0.08 %), as well as for fused Ca2+ transient, beating force, and contractility models (>96 ± 0.04 %). Integrating MDF and XGBoost provides a highly effective analysis tool for prediction of patho-phenotypic features in complex human disease models such as DCM iPSC-CMs.

Deep learning models for predicting the survival of patients with medulloblastoma based on a surveillance, epidemiology, and end results analysis

Medulloblastoma is a malignant neuroepithelial tumor of the central nervous system. Accurate prediction of prognosis is essential for therapeutic decisions in medulloblastoma patients. We analyzed data from 2,322 medulloblastoma patients using the SEER database and randomly divided the dataset into training and testing datasets in a 7:3 ratio. We chose three models to build, one based on neural networks (DeepSurv), one based on ensemble learning that Random Survival Forest (RSF), and a typical Cox Proportional-hazards (CoxPH) model. The DeepSurv model outperformed the RSF and classic CoxPH models with C-indexes of 0.751 and 0.763 for the training and test datasets. Additionally, the DeepSurv model showed better accuracy in predicting 1-, 3-, and 5-year survival rates (AUC: 0.767-0.793). Therefore, our prediction model based on deep learning algorithms can more accurately predict the survival rate and survival period of medulloblastoma compared to other models.

PredCoffee: A binary classification approach specifically for coffee odor

Compared to traditional methods, using machine learning to assess or predict the odor of molecules can save costs in various aspects. Our research aims to collect molecules with coffee odor and summarize the regularity of these molecules, ultimately creating a binary classifier that can determine whether a molecule has a coffee odor. In this study, a total of 371 coffee-odor molecules and 9,700 non-coffee-odor molecules were collected. The Knowledge-guided Pre-training of Graph Transformer (KPGT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP), and message-passing neural networks (MPNN) were used to train the data. The model with the best performance was selected as the basis of the predictor. The prediction accuracy value of the KPGT model exceeded 0.84 and the predictor has been deployed as a webserver PredCoffee.

Mechanism-based and data-driven modeling in cell-free synthetic biology

Cell-free systems have emerged as a versatile platform in synthetic biology, finding applications in various areas such as prototyping synthetic circuits, biosensor development, and biomanufacturing. To streamline the prototyping process, cell-free systems often incorporate a modeling step that predicts the outcomes of various experimental scenarios, providing a deeper insight into the underlying mechanisms and functions. There are two recognized approaches for modeling these systems: mechanism-based modeling, which models the underlying reaction mechanisms; and data-driven modeling, which makes predictions based on data without preconceived interactions between system components. In this highlight, we focus on the latest advancements in both modeling approaches for cell-free systems, exploring their potential for the design and optimization of synthetic genetic circuits.

FPR1, as a Potential Biomarker of Diagnosis and Infliximab Therapy Responses for Crohn's Disease, is Related to Disease Activity, Inflammation and Macrophage Polarization

Purpose

Crohn's disease (CD) represents a multifaceted inflammatory gastrointestinal condition, with a profound significance placed on unraveling its molecular pathways to enhance both diagnostic capabilities and therapeutic interventions. This study focused on identifying a robust macrophage-related signatures (MacroSig) for diagnosing CD, emphasizing the role of FPR1 in macrophage polarization and its implications in CD.

Patients and Methods

Expression profiles from intestinal biopsies and macrophages of 1804 CD patients were retrieved from the Gene Expression Omnibus (GEO). Utilizing CIBERSORTx, differential expression analysis, and weighted correlation network analysis to to identify macrophage-related genes (MRGs). By unsupervised clustering, distinct clusters of CD were identified. Potential biomarkers were identified via using four machine learning algorithms, leading to the establishment of MacroSig which combines insights from 12 machine learning algorithms. Furthermore, the expression of FPR1 was verified in intestinal biopsies of CD patients and two murine experimental colitis models. Finally, we further explored the role of FPR1 in macrophage polarization through single-cell analysis as well as through the study of RAW264.7 cells and peritoneal macrophages.

Results

Two distinct clusters with differential levels of macrophage infiltration and inflammation were identified. The MacroSig, which included FPR1 and LILRB2, exhibited high diagnostic accuracy and outperformed existing biomarkers and signatures. Clinical analysis demonstrated a strong correlation of FPR1 with disease activity, endoscopic inflammation status, and response to infliximab treatment. The expression levels of FPR1 were validated in our CD cohort by immunohistochemistry and confirmed in two colitis mouse models. Single-cell analysis indicated that FPR1 is predominantly expressed in macrophages and monocytes. In vitro studies demonstrated that FPR1 was upregulated in M1 macrophages, and its activation promoted M1 polarization.

Conclusion

We developed a promising diagnostic signature for CD, and targeting FPR1 to modulate macrophage polarization may represent a novel therapeutic strategy.

Survival trend and outcome prediction for pediatric Hodgkin and non-Hodgkin lymphomas based on machine learning

Pediatric Hodgkin and non-Hodgkin lymphomas differ from adult cases in biology and management, yet there is a lack of survival analysis tailored to pediatric lymphoma. We analyzed lymphoma data from 1975 to 2018, comparing survival trends between 7,871 pediatric and 226,211 adult patients, identified key risk factors for pediatric lymphoma survival, developed a predictive nomogram, and utilized machine learning to predict long-term lymphoma-specific mortality risk. Between 1975 and 2018, we observed substantial increases in 1-year (19.3%), 5-year (41.9%), and 10-year (48.8%) overall survival rates in pediatric patients with lymphoma. Prognostic factors such as age, sex, race, Ann Arbor stage, lymphoma subtypes, and radiotherapy were incorporated into the nomogram. The nomogram exhibited excellent predictive performance with area under the curve (AUC) values of 0.766, 0.724, and 0.703 for one-year, five-year, and ten-year survival, respectively, in the training cohort, and AUC values of 0.776, 0.712, and 0.696 in the validation cohort. Importantly, the nomogram outperformed the Ann Arbor staging system in survival prediction. Machine learning models achieved AUC values of approximately 0.75, surpassing the conventional method (AUC =  ~ 0.70) in predicting the risk of lymphoma-specific death. We also observed that pediatric lymphoma survivors had a substantially reduced risk of lymphoma after ten years b,ut faced an increasing risk of non-lymphoma diseases. The study highlights substantial improvements in pediatric lymphoma survival, offers reliable predictive tools, and underscores the importance of long-term monitoring for non-lymphoma health issues in pediatric patients.