A guide to machine learning for biologists

Suicide among lymphoma patients

BACKGROUND

Higher suicide rates were observed in patients diagnosed with lymphoma. In this study, we accurately identified patients with high-risk lymphoma for suicide by constructing a nomogram with a view to effective interventions and reducing the risk of suicide.

METHODS

235,806 patients diagnosed with lymphoma between 2000 and 2020 were picked from the Surveillance, Epidemiology, and End Results (SEER) database and randomly divided into training (N = 165,064) and validation set (N = 70,742). A combination of the Least absolute shrinkage and selection operator (LASSO) and Cox proportional hazards regression identified the predictors that constructed the nomogram. To assess the discrimination, calibration, clinical applicability, and generalization of this nomogram, we implemented receiver operating characteristic curves (ROC), calibration curves, decision curve analysis (DCA), and internal validation. The robustness of the results was assessed by the competing risks regression model.

RESULTS

Age at diagnosis, gender, ethnicity, marital status, stage, surgery, radiotherapy, and annual household income were key predictors of suicide in lymphoma patients. A nomogram was created to visualize the risk of suicide after a lymphoma diagnosis. The c-index for the training set was 0.773, and the validation set was 0.777. The calibration curve for the nomogram fitted well with the diagonal and the clinical decision curve indicated its clinical benefit.

LIMITATION

The effects of unmeasured and unnoticed biases and confounders were difficult to eliminate due to retrospective studies.

CONCLUSION

A convenient and reliable model has been constructed that will help to individualize and accurately quantify the risk of suicide in patients diagnosed with lymphoma.

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.

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.

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.

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.

An explainable machine learning-based model to predict intensive care unit admission among patients with community-acquired pneumonia and connective tissue disease

BACKGROUND

There is no individualized prediction model for intensive care unit (ICU) admission on patients with community-acquired pneumonia (CAP) and connective tissue disease (CTD) so far. In this study, we aimed to establish a machine learning-based model for predicting the need for ICU admission among those patients.

METHODS

This was a retrospective study on patients admitted into a University Hospital in China between November 2008 and November 2021. Patients were included if they were diagnosed with CAP and CTD during admission and hospitalization. Data related to demographics, CTD types, comorbidities, vital signs and laboratory results during the first 24 h of hospitalization were collected. The baseline variables were screened to identify potential predictors via three methods, including univariate analysis, least absolute shrinkage and selection operator (Lasso) regression and Boruta algorithm. Nine supervised machine learning algorithms were used to build prediction models. We evaluated the performances of differentiation, calibration, and clinical utility of all models to determine the optimal model. The Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) techniques were performed to interpret the optimal model.

RESULTS

The included patients were randomly divided into the training set (1070 patients) and the testing set (459 patients) at a ratio of 70:30. The intersection results of three feature selection approaches yielded 16 predictors. The eXtreme gradient boosting (XGBoost) model achieved the highest area under the receiver operating characteristic curve (AUC) (0.941) and accuracy (0.913) among various models. The calibration curve and decision curve analysis (DCA) both suggested that the XGBoost model outperformed other models. The SHAP summary plots illustrated the top 6 features with the greatest importance, including higher N-terminal pro-B-type natriuretic peptide (NT-proBNP) and C-reactive protein (CRP), lower level of CD4 + T cell, lymphocyte and serum sodium, and positive serum (1,3)-β-D-glucan test (G test).

CONCLUSION

We successfully developed, evaluated and explained a machine learning-based model for predicting ICU admission in patients with CAP and CTD. The XGBoost model could be clinical referenced after external validation and improvement.

Development of an immunoinflammatory indicator-related dynamic nomogram based on machine learning for the prediction of intravenous immunoglobulin-resistant Kawasaki disease patients

BACKGROUND

Approximately 10-20% of Kawasaki disease (KD) patients suffer from intravenous immunoglobulin (IVIG) resistance, placing them at higher risk of developing coronary artery aneurysms. Therefore, we aimed to construct an IVIG resistance prediction tool for children with KD in Shanghai, China.

METHODS

Retrospective analysis was conducted on data from 1271 patients diagnosed with KD and the patients were randomly divided into a training set and a validation set in a 2:1 ratio. Machine learning algorithms were employed to identify important predictors associated with IVIG resistance and to build a predictive model. The best-performing model was used to construct a dynamic nomogram. Moreover, receiver operating characteristic curves, calibration plots, and decision-curve analysis were utilized to measure the discriminatory power, accuracy, and clinical utility of the nomogram.

RESULTS

Six variables were identified as important predictors, including C-reactive protein, neutrophil ratio, procalcitonin, CD3 ratio, CD19 count, and IgM level. A dynamic nomogram constructed with these factors was available at https://hktk.shinyapps.io/dynnomapp/. The nomogram demonstrated good diagnostic performance in the training and validation sets (area under the receiver operating characteristic curve = 0.816 and 0.800, respectively). Moreover, the calibration curves and decision curves analysis indicated that the nomogram showed good consistency between predicted and actual outcomes and had good clinical benefits.

CONCLUSION

A web-based dynamic nomogram for IVIG resistance was constructed with good predictive performance, which can be used as a practical approach for early screening to assist physicians in personalizing the treatment of KD patients in Shanghai.

A prospective cohort-based artificial intelligence evaluation system for the protective efficacy and immune response of SARS-CoV-2 inactivated vaccines

BACKGROUND

Novel coronaviruses constitute a significant health threat, prompting the adoption of vaccination as the primary preventive measure. However, current evaluations of immune response and vaccine efficacy are deemed inadequate.

OBJECTIVES

The study sought to explore the evolving dynamics of immune response at various vaccination time points and during breakthrough infections. It aimed to elucidate the synergistic effects of epidemiological factors, humoral immunity, and cellular immunity. Additionally, regression curves were used to determine the correlation between the protective efficacy of the vaccine and the stimulated immune response.

METHODS

Employing LASSO for high-dimensional data analysis, the study utilised four machine learning algorithms-logistical regression, random forest, LGBM classifier, and AdaBoost classifier-to comprehensively assess the immune response following booster vaccination.

RESULTS

Neutralising antibody levels exhibited a rapid surge post-booster, escalating to 102.38 AU/mL at one week and peaking at 298.02 AU/mL at two weeks. Influential factors such as sex, age, disease history, and smoking status significantly impacted post-booster antibody levels. The study further constructed regression curves for neutralising antibodies, non-switched memory B cells, CD4+T cells, and CD8+T cells using LASSO combined with the random forest algorithm.

CONCLUSION

The establishment of an artificial intelligence evaluation system emerges as pivotal for predicting breakthrough infection prognosis after the COVID-19 booster vaccination. This research underscores the intricate interplay between various components of immunity and external factors, elucidating key insights to enhance vaccine effectiveness. 3D modelling discerned distinctive interactions between humoral and cellular immunity within prognostic groups (Class 0-2). This underscores the critical role of the synergistic effect of humoral immunity, cellular immunity, and epidemiological factors in determining the protective efficacy of COVID-19 vaccines post-booster administration.

Machine learning in time-lapse imaging to differentiate embryos from young vs old mice†

Time-lapse microscopy for embryos is a non-invasive technology used to characterize early embryo development. This study employs time-lapse microscopy and machine learning to elucidate changes in embryonic growth kinetics with maternal aging. We analyzed morphokinetic parameters of embryos from young and aged C57BL6/NJ mice via continuous imaging. Our findings show that aged embryos accelerated through cleavage stages (from 5-cells) to morula compared to younger counterparts, with no significant differences observed in later stages of blastulation. Unsupervised machine learning identified two distinct clusters comprising of embryos from aged or young donors. Moreover, in supervised learning, the extreme gradient boosting algorithm successfully predicted the age-related phenotype with 0.78 accuracy, 0.81 precision, and 0.83 recall following hyperparameter tuning. These results highlight two main scientific insights: maternal aging affects embryonic development pace, and artificial intelligence can differentiate between embryos from aged and young maternal mice by a non-invasive approach. Thus, machine learning can be used to identify morphokinetics phenotypes for further studies. This study has potential for future applications in selecting human embryos for embryo transfer, without or in complement with preimplantation genetic testing.

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.

Identification and Construction of a Disulfidptosis-Mediated Diagnostic Model and Associated Immune Microenvironment of Osteoarthritis from the Perspective of PPPM

Background

Osteoarthritis (OA) is a major cause of human disability. Despite receiving treatment, patients with the middle and late stage of OA have poor survival outcomes. Therefore, within the framework of predictive, preventive, and personalized medicine (PPPM/3PM), early personalized diagnosis of OA is particularly prominent. PPPM aims to accurately identify disease by integrating multiple omic techniques; however, the efficiency of currently available methods and biomarkers in predicting and diagnosing OA should be improved. Disulfidptosis, a novel programmed cell death mechanism and appeared in particular metabolic status, plays a mysterious characteristic in the occurrence and development of OA, which warrants further investigation.

Methods

In this study, we integrated three public datasets from the Gene Expression Omnibus (GEO) database, including 26 OA samples and 20 normal samples. Via a series of bioinformatic analysis and machine learning, we identified the diagnostic biomarkers and several subtypes of OA. Moreover, the expression of these biomarkers were verified in our in-house cohort and the single cell dataset.

Results

Three significant regulators of disulfidptosis (NCKAP1, OXSM, and SLC3A2) were identified through differential expression analysis and machine learning. And a nomogram constructed based on these three regulators exhibited ideal efficiency in predicting early- and late-stage OA. Furthermore, based on the expression of three regulators, we identified two disulfidptosis-related subtypes of OA with different infiltration of immune cells and personalized expression level of immune checkpoints. Notably, the expression of the three regulators was demonstrated in a single-cell RNA profile and verified in the synovial tissue in our in-house cohort including 6 OA patients and 6 normal people. Finally, an efficient disulfidptosis-mediated diagnostic model was constructed for OA, with the AUC value of 97.6923% in the training set and 93.3333% and 100% in two validation sets.

Conclusion

Overall, with regard to PPPM, this study provided novel insights into the role of disulfidptosis regulators in the personalized diagnosis and treatment of OA.

Unraveling the significance of AGPAT4 for the pathogenesis of endometriosis via a multi-omics approach

Endometriosis is characterized by the ectopic proliferation of endometrial cells, posing considerable diagnostic and therapeutic challenges. Our study investigates AGPAT4's involvement in endometriosis pathogenesis, aiming to unveil new therapeutic targets. Our investigation by analyzing eQTL data from GWAS for preliminary screening. Subsequently, within the GEO dataset, we utilized four machine learning algorithms to precisely identify risk-associated genes. Gene validity was confirmed through five Mendelian Randomization methods. AGPAT4 expression was measured by Single-Cell Analysis, ELISA and immunohistochemistry. We investigated AGPAT4's effect on endometrial stromal cells using RNA interference, assessing cell proliferation, invasion, and migration with CCK8, wound-healing, and transwell assays. Protein expression was analyzed by western blot, and AGPAT4 interactions were explored using AutoDock. Our investigation identified 11 genes associated with endometriosis risk, with AGPAT4 and COMT emerging as pivotal biomarkers through machine learning analysis. AGPAT4 exhibited significant upregulation in both ectopic tissues and serum samples from patients with endometriosis. Reduced expression of AGPAT4 was observed to detrimentally impact the proliferation, invasion, and migration capabilities of endometrial stromal cells, concomitant with diminished expression of key signaling molecules such as Wnt3a, β-Catenin, MMP-9, and SNAI2. Molecular docking analyses further underscored a substantive interaction between AGPAT4 and Wnt3a.Our study highlights AGPAT4's key role in endometriosis, influencing endometrial stromal cell behavior, and identifies AGPAT4 pathways as promising therapeutic targets for this condition.

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.

Research advances in predicting the expansion of hypertensive intracerebral hemorrhage based on CT images: an overview

Hematoma expansion (HE) is an important risk factor for death or poor prognosis in patients with hypertensive intracerebral hemorrhage (HICH). Accurately predicting the risk of HE in patients with HICH is of great clinical significance for timely intervention and improving patient prognosis. Many imaging signs reported in literatures showed the important clinical value for predicting HE. In recent years, the development of radiomics and artificial intelligence has provided new methods for HE prediction with high accuracy. Therefore, this article reviews the latest research progress in CT imaging, radiomics, and artificial intelligence of HE, in order to help identify high-risk patients for HE in clinical practice.

Classification of Long Non-Coding RNAs s Between Early and Late Stage of Liver Cancers From Non-coding RNA Profiles Using Machine-Learning Approach

Long non-coding RNAs (lncRNAs), which are RNA sequences greater than 200 nucleotides in length, play a crucial role in regulating gene expression and biological processes associated with cancer development and progression. Liver cancer is a major cause of cancer-related mortality worldwide, notably in Thailand. Although machine learning has been extensively used in analyzing RNA-sequencing data for advanced knowledge, the identification of potential lncRNA biomarkers for cancer, particularly focusing on lncRNAs as molecular biomarkers in liver cancer, remains comparatively limited. In this study, our objective was to identify candidate lncRNAs in liver cancer. We employed an expression data set of lncRNAs from patients with liver cancer, which comprised 40 699 lncRNAs sourced from The CancerLivER database. Various feature selection methods and machine-learning approaches were used to identify these candidate lncRNAs. The results showed that the random forest algorithm could predict lncRNAs using features extracted from the database, which achieved an area under the curve (AUC) of 0.840 for classifying lncRNAs between early (stage 1) and late stages (stages 2, 3, and 4) of liver cancer. Five of 23 significant lncRNAs (WAC-AS1, MAPKAPK5-AS1, ARRDC1-AS1, AC133528.2, and RP11-1094M14.11) were differentially expressed between early and late stage of liver cancer. Based on the Gene Expression Profiling Interactive Analysis (GEPIA) database, higher expression of WAC-AS1, MAPKAPK5-AS1, and ARRDC1-AS1 was associated with shorter overall survival. In conclusion, the classification model could predict the early and late stages of liver cancer using the signature expression of lncRNA genes. The identified lncRNAs might be used as early diagnostic and prognostic biomarkers for patients with liver cancer.

Forecasting Myopic Maculopathy Risk Over a Decade: Development and Validation of an Interpretable Machine Learning Algorithm

Purpose

The purpose of this study was to develop and validate prediction model for myopic macular degeneration (MMD) progression in patients with high myopia.

Methods

The Zhongshan High Myopia Cohort for model development included 660 patients aged 7 to 70 years with a bilateral sphere of ≤-6.00 diopters (D). Two hundred twelve participants with an axial length (AL) ≥25.5 mm from the Chinese Ocular Imaging Project were used for external validation. Thirty-four clinical variables, including demographics, lifestyle, myopia history, and swept source optical coherence tomography data, were analyzed. Sequential forward selection was used for predictor selection, and binary classification models were created using five machine learning algorithms to forecast the risk of MMD progression over 10 years.

Results

Over a median follow-up of 10.9 years, 133 patients (20.2%) showed MMD progression in the development cohort. Among them, 69 (51.9%) developed newly-onset MMD, 11 (8.3%) developed patchy atrophy from diffuse atrophy, 54 (40.6%) showed an enlargement of lesions, and 9 (6.8%) developed plus signs. Top six predictors for MMD progression included thinner subfoveal choroidal thickness, longer AL, worse best-corrected visual acuity, older age, female gender, and shallower anterior chamber depth. The eXtreme Gradient Boosting algorithm yielded the best discriminative performance (area under the receiver operating characteristic curve [AUROC] = 0.87 ± 0.02) with good calibration in the training cohort. In a less myopic external validation group (median -5.38 D), 48 patients (22.6%) developed MMD progression over 4 years, with the model's AUROC validated at 0.80 ± 0.008.

Conclusions

Machine learning model effectively predicts MMD progression a decade ahead using clinical and imaging indicators. This tool shows promise for identifying "at-risk" high myopes for timely intervention and vision protection.

Deep generative models in single-cell omics

Deep Generative Models (DGMs) are becoming instrumental for inferring probability distributions inherent to complex processes, such as most questions in biomedical research. For many years, there was a lack of mathematical methods that would allow this inference in the scarce data scenario of biomedical research. The advent of single-cell omics has finally made square the so-called "skinny matrix", allowing to apply mathematical methods already extensively used in other areas. Moreover, it is now possible to integrate data at different molecular levels in thousands or even millions of samples, thanks to the number of single-cell atlases being collaboratively generated. Additionally, DGMs have proven useful in other frequent tasks in single-cell analysis pipelines, from dimensionality reduction, cell type annotation to RNA velocity inference. In spite of its promise, DGMs need to be used with caution in biomedical research, paying special attention to its use to answer the right questions and the definition of appropriate error metrics and validation check points that confirm not only its correct use but also its relevance. All in all, DGMs provide an exciting tool that opens a bright future for the integrative analysis of single-cell -omics to understand health and disease.

RNAirport: a deep neural network-based database characterizing representative gene models in plants

A 5'-leader, known initially as the 5'-untranslated region, contains multiple isoforms due to alternative splicing (aS) and alternative transcription start site (aTSS). Therefore, a representative 5'-leader is demanded to examine the embedded RNA regulatory elements in controlling translation efficiency. Here, we develop a ranking algorithm and a deep-learning model to annotate representative 5'-leaders for five plant species. We rank the intra-sample and inter-sample frequency of aS-mediated transcript isoforms using the Kruskal-Wallis test-based algorithm and identify the representative aS-5'-leader. To further assign a representative 5'-end, we train the deep-learning model 5'leaderP to learn aTSS-mediated 5'-end distribution patterns from cap-analysis gene expression data. The model accurately predicts the 5'-end, confirmed experimentally in Arabidopsis and rice. The representative 5'-leader-contained gene models and 5'leaderP can be accessed at RNAirport (http://www.rnairport.com/leader5P/). The Stage 1 annotation of 5'-leader records 5'-leader diversity and will pave the way to Ribo-Seq open-reading frame annotation, identical to the project recently initiated by human GENCODE.

Personalized decision support system for tailoring IgA nephropathy treatment strategies

BACKGROUND

The ongoing debate surrounding the use of immunosuppressive treatments for IgA nephropathy (IgAN) underscores the demand for personalized and effective strategies.

METHODS

Analyzed data from 807 IgAN patients over 5+ years using three methods: Random Forest with molecular biomarkers, network biomarkers with graph engineering, and an auto-encoder model. All models were trained using identical demographic, clinical, and pathological data, employing an 80-20 split for training and testing purposes.

RESULTS

In the comprehensive assessment of IgAN prognosis, the Random Forest model, employing molecular biomarkers, demonstrated strong performance metrics (AUC = 0.83, sensitivity = 0.51, specificity = 0.96). However, traditional graph feature engineering on patient-specific networks outperformed these results with an AUC of 0.90, sensitivity of 0.64, and specificity of 0.94. The Auto-encoder model showed the best accuracy (AUC = 0.91, sensitivity = 0.46, specificity = 0.96). The findings highlighted the superior predictive capabilities of network biomarkers over molecular biomarkers for adverse renal outcome prediction in IgAN. Consequently, we integrated Auto-encoder-derived Network Biomarkers with Random Forest Models to enhance prognostic precision in diverse IgAN treatment scenarios. The prediction for the prognosis of patients receiving supportive care, glucocorticoid therapy, and immunosuppressant treatment yielded AUC values of 0.95, 0.96, and 1, respectively, indicating high specificity. Drawing from these insights, we pioneered the development of an innovative decision support model for IgAN treatment. This model demonstrated the ability to make medical decisions comparable to those by experienced nephrologists, enabling the customization of personalized disease management strategies.

CONCLUSION

Our system accurately predicted IgAN prognosis and evaluated various treatment efficacies, aiding physicians in devising optimal therapeutic strategies for patients.

Computational Approaches for Connecting Maternal Stress to Preterm Birth

Multiple studies have hinted at a complex connection between maternal stress and preterm birth (PTB). This article describes the potential of computational methods to provide new insights into this relationship. For this, we outline existing approaches for stress assessments and various data modalities available for profiling stress responses, and review studies that sought either to establish a connection between stress and PTB or to predict PTB based on stress-related factors. Finally, we summarize the challenges of computational methods, highlighting potential future research directions within this field.

Live-cell imaging powered by computation

The proliferation of microscopy methods for live-cell imaging offers many new possibilities for users but can also be challenging to navigate. The prevailing challenge in live-cell fluorescence microscopy is capturing intra-cellular dynamics while preserving cell viability. Computational methods can help to address this challenge and are now shifting the boundaries of what is possible to capture in living systems. In this Review, we discuss these computational methods focusing on artificial intelligence-based approaches that can be layered on top of commonly used existing microscopies as well as hybrid methods that integrate computation and microscope hardware. We specifically discuss how computational approaches can improve the signal-to-noise ratio, spatial resolution, temporal resolution and multi-colour capacity of live-cell imaging.

Improving the classification of multiple sclerosis and cerebral small vessel disease with interpretable transfer attention neural network

As an autoimmune-mediated inflammatory demyelinating disease of the central nervous system, multiple sclerosis (MS) is often confused with cerebral small vessel disease (cSVD), which is a regional pathological change in brain tissue with unknown pathogenesis. This is due to their similar clinical presentations and imaging manifestations. That misdiagnosis can significantly increase the occurrence of adverse events. Delayed or incorrect treatment is one of the most important causes of MS progression. Therefore, the development of a practical diagnostic imaging aid could significantly reduce the risk of misdiagnosis and improve patient prognosis. We propose an interpretable deep learning (DL) model that differentiates MS and cSVD using T2-weighted fluid-attenuated inversion recovery (FLAIR) images. Transfer learning (TL) was utilized to extract features from the ImageNet dataset. This pioneering model marks the first of its kind in neuroimaging, showing great potential in enhancing differential diagnostic capabilities within the field of neurological disorders. Our model extracts the texture features of the images and achieves more robust feature learning through two attention modules. The attention maps provided by the attention modules provide model interpretation to validate model learning and reveal more information to physicians. Finally, the proposed model is trained end-to-end using focal loss to reduce the influence of class imbalance. The model was validated using clinically diagnosed MS (n=112) and cSVD (n=321) patients from the Beijing Tiantan Hospital. The performance of the proposed model was better than that of two commonly used DL approaches, with a mean balanced accuracy of 86.06 % and a mean area under the receiver operating characteristic curve of 98.78 %. Moreover, the generated attention heat maps showed that the proposed model could focus on the lesion signatures in the image. The proposed model provides a practical diagnostic imaging aid for the use of routinely available imaging techniques such as magnetic resonance imaging to classify MS and cSVD by linking DL to human brain disease. We anticipate a substantial improvement in accurately distinguishing between various neurological conditions through this novel model.

Predicting T-Cell Lymphoma in Children From 18F-FDG PET-CT Imaging With Multiple Machine Learning Models

This study aimed to examine the feasibility of utilizing radiomics models derived from 18F-FDG PET/CT imaging to screen for T-cell lymphoma in children with lymphoma. All patients had undergone 18F-FDG PET/CT scans. Lesions were extracted from PET/CT and randomly divided into training and validation sets. Two different types of models were constructed as follows: features that are extracted from standardized uptake values (SUV)-associated parameters, and CT images were used to build SUV/CT-based model. Features that are derived from PET and CT images were used to build PET/CT-based model. Logistic regression (LR), linear support vector machine, support vector machine with the radial basis function kernel, neural networks, and adaptive boosting were performed as classifiers in each model. In the training sets, 77 patients, and 247 lesions were selected for building the models. In the validation sets, PET/CT-based model demonstrated better performance than that of SUV/CT-based model in the prediction of T-cell lymphoma. LR showed highest accuracy with 0.779 [0.697, 0.860], area under the receiver operating characteristic curve (AUC) with 0.863 [0.762, 0.963], and preferable goodness-of-fit in PET/CT-based model at the patient level. LR also showed best performance with accuracy of 0.838 [0.741, 0.936], AUC of 0.907 [0.839, 0.976], and preferable goodness-of-fit in PET/CT-based model at the lesion level. 18F-FDG PET/CT-based radiomics models with different machine learning classifiers were able to screen T-cell lymphoma in children with high accuracy, AUC, and preferable goodness-of-fit, providing incremental value compared with SUV-associated features.

Current perioperative nociception monitoring and potential directions

Perioperative nociception-antinociception balance is essential for the prevention of adverse postoperative events. Estimating the nociception level helps optimize intraoperative management. In the past two decades, various nociception monitoring devices have been developed for the identification of intraoperative nociception. However, each type of nociception monitoring device has advantages and disadvantages, limiting their clinical application in particular patients and settings. Therefore, this review aimed to summarize the information on nociceptor monitoring in current clinical settings, explore each technique's particularities, and possible future directions to provide a reference for clinicians and researchers.

Interpretable machine learning models for predicting the incidence of antibiotic- associated diarrhea in elderly ICU patients

BACKGROUND

Antibiotic-associated diarrhea (AAD) can prolong hospitalization, increase medical costs, and even lead to higher mortality rates. Therefore, it is essential to predict the incidence of AAD in elderly intensive care unit(ICU) patients. The objective of this study was to create a prediction model that is both interpretable and generalizable for predicting the incidence of AAD in elderly ICU patients.

METHODS

We retrospectively analyzed data from the First Medical Center of the People's Liberation Army General Hospital (PLAGH) in China. We utilized the machine learning model Extreme Gradient Boosting (XGBoost) and Shapley's additive interpretation method to predict the incidence of AAD in elderly ICU patients in an interpretable manner.

RESULTS

A total of 848 adult ICU patients were eligible for this study. The XGBoost model predicted the incidence of AAD with an area under the receiver operating characteristic curve (ROC) of 0.917, sensitivity of 0.889, specificity of 0.806, accuracy of 0.870, and an F1 score of 0.780. The XGBoost model outperformed the other models, including logistic regression, support vector machine (AUC = 0.809), K-nearest neighbor algorithm (AUC = 0.872), and plain Bayes (AUC = 0.774).

CONCLUSIONS

While the XGBoost model may not excel in absolute performance, it demonstrates superior predictive capabilities compared to other models in forecasting the incidence of AAD in elderly ICU patients categorized based on their characteristics.

Machine learning-based characterization of the gut microbiome associated with the progression of primary biliary cholangitis to cirrhosis

BACKGROUND

Primary biliary cholangitis (PBC) is associated closely with the gut microbiota. This study aimed to explore the characteristics of the gut microbiota after the progress of PBC to cirrhosis.

METHOD

This study focuses on utilizing the 16S rRNA gene sequencing method to screen for differences in gut microbiota in PBC patients who progress to cirrhosis. Then, we divided the data into training and verification sets and used seven different machine learning (ML) models to validate them respectively, calculating and comparing the accuracy, F1 score, precision, and recall, and screening the dominant intestinal flora affecting PBC cirrhosis.

RESULT

PBC cirrhosis patients showed decreased diversity and richness of gut microbiota. Additionally, there are alterations in the composition of gut microbiota in PBC cirrhosis patients. The abundance of Faecalibacterium and Gemmiger bacteria significantly decreases, while the abundance of Veillonella and Streptococcus significantly increases. Furthermore, machine learning methods identify Streptococcus and Gemmiger as the predominant gut microbiota in PBC patients with cirrhosis, serving as non-invasive biomarkers (AUC = 0.902).

CONCLUSION

Our study revealed that PBC cirrhosis patients gut microbiota composition and function have significantly changed. Streptococcus and Gemmiger may become a non-invasive biomarker for predicting the progression of PBC progress to cirrhosis.

A comprehensive benchmarking with interpretation and operational guidance for the hierarchy of topologically associating domains

Topologically associating domains (TADs), megabase-scale features of chromatin spatial architecture, are organized in a domain-within-domain TAD hierarchy. Within TADs, the inner and smaller subTADs not only manifest cell-to-cell variability, but also precisely regulate transcription and differentiation. Although over 20 TAD callers are able to detect TAD, their usability in biomedicine is confined by a disagreement of outputs and a limit in understanding TAD hierarchy. We compare 13 computational tools across various conditions and develop a metric to evaluate the similarity of TAD hierarchy. Although outputs of TAD hierarchy at each level vary among callers, data resolutions, sequencing depths, and matrices normalization, they are more consistent when they have a higher similarity of larger TADs. We present comprehensive benchmarking of TAD hierarchy callers and operational guidance to researchers of life science researchers. Moreover, by simulating the mixing of different types of cells, we confirm that TAD hierarchy is generated not simply from stacking Hi-C heatmaps of heterogeneous cells. Finally, we propose an air conditioner model to decipher the role of TAD hierarchy in transcription.

A Theoretical Exploration of Artificial Intelligence's Impact on Feto-Maternal Health from Conception to Delivery

The implementation of Artificial Intelligence (AI) in healthcare is enhancing diagnostic accuracy in clinical setups. The use of AI in healthcare is steadily increasing with advancing technology, extending beyond disease diagnosis to encompass roles in feto-maternal health. AI harnesses Machine Learning (ML), Natural Language Processing (NLP), Artificial Neural Networks (ANN), and computer vision to analyze data and draw conclusions. Considering maternal health, ML analyzes vast datasets to predict maternal and fetal health outcomes, while NLP interprets medical texts and patient records to assist in diagnosis and treatment decisions. ANN models identify patterns in complex feto-maternal medical data, aiding in risk assessment and intervention planning whereas, computer vision enables the analysis of medical images for early detection of feto-maternal complications. AI facilitates early pregnancy detection, genetic screening, and continuous monitoring of maternal health parameters, providing real-time alerts for deviations, while also playing a crucial role in the early detection of fetal abnormalities through enhanced ultrasound imaging, contributing to informed decision-making. This review investigates into the application of AI, particularly through predictive models, in addressing the monitoring of feto-maternal health. Additionally, it examines potential future directions and challenges associated with these applications.

Early prediction of growth patterns after pediatric kidney transplantation based on height-related single-nucleotide polymorphisms

BACKGROUND

Growth retardation is a common complication of chronic kidney disease in children, which can be partially relieved after renal transplantation. This study aimed to develop and validate a predictive model for growth patterns of children with end-stage renal disease (ESRD) after kidney transplantation using machine learning algorithms based on genomic and clinical variables.

METHODS

A retrospective cohort of 110 children who received kidney transplants between May 2013 and September 2021 at the First Affiliated Hospital of Zhengzhou University were recruited for whole-exome sequencing (WES), and another 39 children who underwent transplant from October 2021 to March 2022 were enrolled for external validation. Based on previous studies, we comprehensively collected 729 height-related single-nucleotide polymorphisms (SNPs) in exon regions. Seven machine learning algorithms and 10-fold cross-validation analysis were employed for model construction.

RESULTS

The 110 children were divided into two groups according to change in height-for-age Z -score. After univariate analysis, age and 19 SNPs were incorporated into the model and validated. The random forest model showed the best prediction efficacy with an accuracy of 0.8125 and an area under curve (AUC) of 0.924, and also performed well in the external validation cohort (accuracy, 0.7949; AUC, 0.796).

CONCLUSIONS

A model with good performance for predicting post-transplant growth patterns in children based on SNPs and clinical variables was constructed and validated using machine learning algorithms. The model is expected to guide clinicians in the management of children after renal transplantation, including the use of growth hormone, glucocorticoid withdrawal, and nutritional supplementation, to alleviate growth retardation in children with ESRD.

Subcellular Feature-Based Classification of α and β Cells Using Soft X-ray Tomography

The dysfunction of α and β cells in pancreatic islets can lead to diabetes. Many questions remain on the subcellular organization of islet cells during the progression of disease. Existing three-dimensional cellular mapping approaches face challenges such as time-intensive sample sectioning and subjective cellular identification. To address these challenges, we have developed a subcellular feature-based classification approach, which allows us to identify α and β cells and quantify their subcellular structural characteristics using soft X-ray tomography (SXT). We observed significant differences in whole-cell morphological and organelle statistics between the two cell types. Additionally, we characterize subtle biophysical differences between individual insulin and glucagon vesicles by analyzing vesicle size and molecular density distributions, which were not previously possible using other methods. These sub-vesicular parameters enable us to predict cell types systematically using supervised machine learning. We also visualize distinct vesicle and cell subtypes using Uniform Manifold Approximation and Projection (UMAP) embeddings, which provides us with an innovative approach to explore structural heterogeneity in islet cells. This methodology presents an innovative approach for tracking biologically meaningful heterogeneity in cells that can be applied to any cellular system.

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.

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.

Development and application of a machine learning-based predictive model for obstructive sleep apnea screening

Objective

To develop a robust machine learning prediction model for the automatic screening and diagnosis of obstructive sleep apnea (OSA) using five advanced algorithms, namely Extreme Gradient Boosting (XGBoost), Logistic Regression (LR), Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) to provide substantial support for early clinical diagnosis and intervention.

Methods

We conducted a retrospective analysis of clinical data from 439 patients who underwent polysomnography at the Affiliated Hospital of Xuzhou Medical University between October 2019 and October 2022. Predictor variables such as demographic information [age, sex, height, weight, body mass index (BMI)], medical history, and Epworth Sleepiness Scale (ESS) were used. Univariate analysis was used to identify variables with significant differences, and the dataset was then divided into training and validation sets in a 4:1 ratio. The training set was established to predict OSA severity grading. The validation set was used to assess model performance using the area under the curve (AUC). Additionally, a separate analysis was conducted, categorizing the normal population as one group and patients with moderate-to-severe OSA as another. The same univariate analysis was applied, and the dataset was divided into training and validation sets in a 4:1 ratio. The training set was used to build a prediction model for screening moderate-to-severe OSA, while the validation set was used to verify the model's performance.

Results

Among the four groups, the LightGBM model outperformed others, with the top five feature importance rankings of ESS total score, BMI, sex, hypertension, and gastroesophageal reflux (GERD), where Age, ESS total score and BMI played the most significant roles. In the dichotomous model, RF is the best performer of the five models respectively. The top five ranked feature importance of the best-performing RF models were ESS total score, BMI, GERD, age and Dry mouth, with ESS total score and BMI being particularly pivotal.

Conclusion

Machine learning-based prediction models for OSA disease grading and screening prove instrumental in the early identification of patients with moderate-to-severe OSA, revealing pertinent risk factors and facilitating timely interventions to counter pathological changes induced by OSA. Notably, ESS total score and BMI emerge as the most critical features for predicting OSA, emphasizing their significance in clinical assessments. The dataset will be publicly available on my Github.

Interpretable machine learning framework to predict gout associated with dietary fiber and triglyceride-glucose index

BACKGROUND

Gout prediction is essential for the development of individualized prevention and treatment plans. Our objective was to develop an efficient and interpretable machine learning (ML) model using the SHapley Additive exPlanation (SHAP) to link dietary fiber and triglyceride-glucose (TyG) index to predict gout.

METHODS

Using datasets from the National Health and Nutrition Examination Survey (NHANES) (2005-2018) population to study dietary fiber, the TyG index was used to predict gout. After evaluating the performance of six ML models and selecting the Light Gradient Boosting Machine (LGBM) as the optimal algorithm, we interpret the LGBM model for predicting gout using SHAP and reveal the decision-making process of the model.

RESULTS

An initial survey of 70,190 participants was conducted, and after a gradual exclusion process, 12,645 cases were finally included in the study. Selection of the best performing LGBM model for prediction of gout associated with dietary fiber and TyG index (Area under the ROC curve (AUC): 0.823, 95% confidence interval (CI): 0.798-0.848, Accuracy: 95.3%, Brier score: 0.077). The feature importance of SHAP values indicated that age was the most important feature affecting the model output, followed by uric acid (UA). The SHAP values showed that lower dietary fiber values had a more pronounced effect on the positive prediction of the model, while higher values of the TyG index had a more pronounced effect on the positive prediction of the model.

CONCLUSION

The interpretable LGBM model associated with dietary fiber and TyG index showed high accuracy, efficiency, and robustness in predicting gout. Increasing dietary fiber intake and lowering the TyG index are beneficial in reducing the potential risk of gout.

Publication Trends and Research Hotspots of the Cardiorenal Syndrome: A Bibliometrics and Visual Analysis from 2003 to 2023

INTRODUCTION

Cardiorenal syndrome encompasses a range of disorders involving both the heart and kidneys, wherein dysfunction in one organ may induce dysfunction in the other, either acutely or chronically.

METHODS

This study conducted a literature search on cardiorenal syndrome from January 1, 2003, to September 8, 2023. Meanwhile, a quantitative analysis of the developmental trajectory, research hotspots and evolutionary trends in the field of cardiorenal syndrome through bibliometric analysis and knowledge mapping was carried out.

RESULTS

The annual publication trend analysis revealed a consistent annual increase in cardiorenal syndrome literature over the last 20 years. The IL6, REN, and INS genes were identified as the current research hotspots.

CONCLUSION

The field of cardiorenal syndrome exhibits promising potential to grow and is emerging as a prominent research area. Future endeavours should prioritise a comprehensive understanding of the field and foster multi-centre co-operation among different countries and regions.

Hspb1 and Lgals3 in spinal neurons are closely associated with autophagy following excitotoxicity based on machine learning algorithms

Excitotoxicity represents the primary cause of neuronal death following spinal cord injury (SCI). While autophagy plays a critical and intricate role in SCI, the specific mechanism underlying the relationship between excitotoxicity and autophagy in SCI has been largely overlooked. In this study, we isolated primary spinal cord neurons from neonatal rats and induced excitotoxic neuronal injury by high concentrations of glutamic acid, mimicking an excitotoxic injury model. Subsequently, we performed transcriptome sequencing. Leveraging machine learning algorithms, including weighted correlation network analysis (WGCNA), random forest analysis (RF), and least absolute shrinkage and selection operator analysis (LASSO), we conducted a comprehensive investigation into key genes associated with spinal cord neuron injury. We also utilized protein-protein interaction network (PPI) analysis to identify pivotal proteins regulating key gene expression and analyzed key genes from public datasets (GSE2599, GSE20907, GSE45006, and GSE174549). Our findings revealed that six genes-Anxa2, S100a10, Ccng1, Timp1, Hspb1, and Lgals3-were significantly upregulated not only in vitro in neurons subjected to excitotoxic injury but also in rats with subacute SCI. Furthermore, Hspb1 and Lgals3 were closely linked to neuronal autophagy induced by excitotoxicity. Our findings contribute to a better understanding of excitotoxicity and autophagy, offering potential targets and a theoretical foundation for SCI diagnosis and treatment.

Screening mitochondria-related biomarkers in skin and plasma of atopic dermatitis patients by bioinformatics analysis and machine learning

Background

There is a significant imbalance of mitochondrial activity and oxidative stress (OS) status in patients with atopic dermatitis (AD). This study aims to screen skin and peripheral mitochondria-related biomarkers, providing insights into the underlying mechanisms of mitochondrial dysfunction in AD.

Methods

Public data were obtained from MitoCarta 3.0 and GEO database. We screened mitochondria-related differentially expressed genes (MitoDEGs) using R language and then performed GO and KEGG pathway analysis on MitoDEGs. PPI and machine learning algorithms were also used to select hub MitoDEGs. Meanwhile, the expression of hub MitoDEGs in clinical samples were verified. Using ROC curve analysis, the diagnostic performance of risk model constructed from these hub MitoDEGs was evaluated in the training and validation sets. Further computer-aided algorithm analyses included gene set enrichment analysis (GSEA), immune infiltration and mitochondrial metabolism, centered on these hub MitoDEGs. We also used real-time PCR and Spearman method to evaluate the relationship between plasma circulating cell-free mitochondrial DNA (ccf-mtDNA) levels and disease severity in AD patients.

Results

MitoDEGs in AD were significantly enriched in pathways involved in mitochondrial respiration, mitochondrial metabolism, and mitochondrial membrane transport. Four hub genes (BAX, IDH3A, MRPS6, and GPT2) were selected to take part in the creation of a novel mitochondrial-based risk model for AD prediction. The risk score demonstrated excellent diagnostic performance in both the training cohort (AUC = 1.000) and the validation cohort (AUC = 0.810). Four hub MitoDEGs were also clearly associated with the innate immune cells' infiltration and the molecular modifications of mitochondrial hypermetabolism in AD. We further discovered that AD patients had considerably greater plasma ccf-mtDNA levels than controls (U = 92.0, p< 0.001). Besides, there was a significant relationship between the up-regulation of plasma mtDNA and the severity of AD symptoms.

Conclusions

The study highlights BAX, IDH3A, MRPS6 and GPT2 as crucial MitoDEGs and demonstrates their efficiency in identifying AD. Moderate to severe AD is associated with increased markers of mitochondrial damage and cellular stress (ccf=mtDNA). Our study provides data support for the variation in mitochondria-related functional characteristics of AD patients.

Data augmentation for generating synthetic electrogastrogram time series

To address an emerging need for large number of diverse datasets for rigor evaluation of signal processing techniques, we developed and evaluated a new method for generating synthetic electrogastrogram time series. We used electrogastrography (EGG) data from an open database to set model parameters and statistical tests to evaluate synthesized data. Additionally, we illustrated method customization for generating artificial EGG time series alterations caused by the simulator sickness. Proposed data augmentation method generates synthetic EGG data with specified duration, sampling frequency, recording state (postprandial or fasting state), overall noise and breathing artifact injection, and pauses in the gastric rhythm (arrhythmia occurrence) with statistically significant difference between postprandial and fasting states in > 70% cases while not accounting for individual differences. Features obtained from the synthetic EGG signal resembling simulator sickness occurrence displayed expected trends. The code for generation of synthetic EGG time series is not only freely available and can be further customized to assess signal processing algorithms but also may be used to increase data diversity for training artificial intelligence (AI) algorithms. The proposed approach is customized for EGG data synthesis but can be easily utilized for other biosignals with similar nature such as electroencephalogram.

Deciphering silver nanoparticles perturbation effects and risks for soil enzymes worldwide: Insights from machine learning and soil property integration

Globally extensive research into how silver nanoparticles (AgNPs) affect enzyme activity in soils with differing properties has been limited by cost-prohibitive sampling. In this study, customized machine learning (ML) was used to extract data patterns from complex research, with a hit rate of Random Forest > Multiple Imputation by Chained Equations > Decision Tree > K-Nearest Neighbors. Results showed that soil properties played a pivotal role in determining AgNPs' effect on soil enzymes, with the order being pH > organic matter (OM) > soil texture ≈ cation exchange capacity (CEC). Notably, soil enzyme activity was more sensitive to AgNPs in acidic soil (pH < 5.5), while elevated OM content (>1.9 %) attenuated AgNPs toxicity. Compared to soil acidification, reducing soil OM content is more detrimental in exacerbating AgNPs' toxicity and it emerged that clay particles were deemed effective in curbing their toxicity. Meanwhile sand particles played a very different role, and a sandy soil sample at > 40 % of the water holding capacity (WHC), amplified the toxicity of AgNPs. Perturbation mapping of how soil texture alters enzyme activity under AgNPs exposure was generated, where soils with sand (45-65 %), silt (< 22 %), and clay (35-55 %) exhibited even higher probability of positive effects of AgNPs. The average calculation results indicate the sandy clay loam (75.6 %), clay (74.8 %), silt clay (65.8 %), and sandy clay (55.9 %) texture soil demonstrate less AgNPs inhibition effect. The results herein advance the prediction of the effect of AgNPs on soil enzymes globally and determine the soil types that are more sensitive to AgNPs worldwide.

Persistent T cell unresponsiveness associated with chronic visceral leishmaniasis in HIV-coinfected patients

A large proportion of HIV-coinfected visceral leishmaniasis (VL-HIV) patients exhibit chronic disease with frequent VL recurrence. However, knowledge on immunological determinants underlying the disease course is scarce. We longitudinally profiled the circulatory cellular immunity of an Ethiopian HIV cohort that included VL developers. We show that chronic VL-HIV patients exhibit high and persistent levels of TIGIT and PD-1 on CD8+/CD8- T cells, in addition to a lower frequency of IFN-γ+ TIGIT- CD8+/CD8- T cells, suggestive of impaired T cell functionality. At single T cell transcriptome and clonal resolution, the patients show CD4+ T cell anergy, characterised by a lack of T cell activation and lymphoproliferative response. These findings suggest that PD-1 and TIGIT play a pivotal role in VL-HIV chronicity, and may be further explored for patient risk stratification. Our findings provide a strong rationale for adjunctive immunotherapy for the treatment of chronic VL-HIV patients to break the recurrent disease cycle.

Inferring gene regulatory networks from single-cell transcriptomics based on graph embedding

MOTIVATION

Gene regulatory networks (GRNs) encode gene regulation in living organisms, and have become a critical tool to understand complex biological processes. However, due to the dynamic and complex nature of gene regulation, inferring GRNs from scRNA-seq data is still a challenging task. Existing computational methods usually focus on the close connections between genes, and ignore the global structure and distal regulatory relationships.

RESULTS

In this study, we develop a supervised deep learning framework, IGEGRNS, to infer GRNs from scRNA-seq data based on graph embedding. In the framework, contextual information of genes is captured by GraphSAGE, which aggregates gene features and neighborhood structures to generate low-dimensional embedding for genes. Then, the k most influential nodes in the whole graph are filtered through Top-k pooling. Finally, potential regulatory relationships between genes are predicted by stacking CNNs. Compared with nine competing supervised and unsupervised methods, our method achieves better performance on six time-series scRNA-seq datasets.

AVAILABILITY AND IMPLEMENTATION

Our method IGEGRNS is implemented in Python using the Pytorch machine learning library, and it is freely available at https://github.com/DHUDBlab/IGEGRNS.

Sesamolin serves as an MYH14 inhibitor to sensitize endometrial cancer to chemotherapy and endocrine therapy via suppressing MYH9/GSK3β/β-catenin signaling

BACKGROUND

Endometrial cancer (EC) is one of the most common gynecological cancers. Herein, we aimed to define the role of specific myosin family members in EC because this protein family is involved in the progression of various cancers.

METHODS

Bioinformatics analyses were performed to reveal EC patients' prognosis-associated genes in patients with EC. Furthermore, colony formation, immunofluorescence, cell counting kit 8, wound healing, and transwell assays as well as coimmunoprecipitation, cycloheximide chase, luciferase reporter, and cellular thermal shift assays were performed to functionally and mechanistically analyze human EC samples, cell lines, and a mouse model, respectively.

RESULTS

Machine learning techniques identified MYH14, a member of the myosin family, as the prognosis-associated gene in patients with EC. Furthermore, bioinformatics analyses based on public databases showed that MYH14 was associated with EC chemoresistance. Moreover, immunohistochemistry validated MYH14 upregulation in EC cases compared with that in normal controls and confirmed that MYH14 was an independent and unfavorable prognostic indicator of EC. MYH14 impaired cell sensitivity to carboplatin, paclitaxel, and progesterone, and increased cell proliferation and metastasis in EC. The mechanistic study showed that MYH14 interacted with MYH9 and impaired GSK3β-mediated β-catenin ubiquitination and degradation, thus facilitating the Wnt/β-catenin signaling pathway and epithelial-mesenchymal transition. Sesamolin, a natural compound extracted from Sesamum indicum (L.), directly targeted MYH14 and attenuated EC progression. Additionally, the compound disrupted the interplay between MYH14 and MYH9 and repressed MYH9-regulated Wnt/β-catenin signaling. The in vivo study further verified sesamolin as a therapeutic drug without side effects.

CONCLUSIONS

Herein, we identified that EC prognosis-associated MYH14 was independently responsible for poor overall survival time of patients, and it augmented EC progression by activating Wnt/β-catenin signaling. Targeting MYH14 by sesamolin, a cytotoxicity-based approach, can be applied synergistically with chemotherapy and endocrine therapy to eventually mitigate EC development. This study emphasizes MYH14 as a potential target and sesamolin as a valuable natural drug for EC therapy.