Bridging biological cfDNA features and machine learning approaches.

Liquid biopsies (LBs), particularly using circulating tumor DNA (ctDNA), are expected to revolutionize precision oncology and blood-based cancer screening. Recent technological improvements, in combination with the ever-growing understanding of cell-free DNA (cfDNA) biology, are enabling the detection of tumor-specific changes with extremely high resolution and new analysis concepts beyond genetic alterations, including methylomics, fragmentomics, and nucleosomics. The interrogation of a large number of markers and the high complexity of data render traditional correlation methods insufficient. In this regard, machine learning (ML) algorithms are increasingly being used to decipher disease- and tissue-specific signals from cfDNA. Here, we review recent insights into biological ctDNA features and how these are incorporated into sophisticated ML applications.

PlasmidHunter: accurate and fast prediction of plasmid sequences using gene content profile and machine learning.

Plasmids are extrachromosomal DNA found in microorganisms. They often carry beneficial genes that help bacteria adapt to harsh conditions. Plasmids are also important tools in genetic engineering, gene therapy, and drug production. However, it can be difficult to identify plasmid sequences from chromosomal sequences in genomic and metagenomic data. Here, we have developed a new tool called PlasmidHunter, which uses machine learning to predict plasmid sequences based on gene content profile. PlasmidHunter can achieve high accuracies (up to 97.6%) and high speeds in benchmark tests including both simulated contigs and real metagenomic plasmidome data, outperforming other existing tools.

Generative models for protein sequence modeling: recent advances and future directions.

The widespread adoption of high-throughput omics technologies has exponentially increased the amount of protein sequence data involved in many salient disease pathways and their respective therapeutics and diagnostics. Despite the availability of large-scale sequence data, the lack of experimental fitness annotations underpins the need for self-supervised and unsupervised machine learning (ML) methods. These techniques leverage the meaningful features encoded in abundant unlabeled sequences to accomplish complex protein engineering tasks. Proficiency in the rapidly evolving fields of protein engineering and generative AI is required to realize the full potential of ML models as a tool for protein fitness landscape navigation. Here, we support this work by (i) providing an overview of the architecture and mathematical details of the most successful ML models applicable to sequence data (e.g. variational autoencoders, autoregressive models, generative adversarial neural networks, and diffusion models), (ii) guiding how to effectively implement these models on protein sequence data to predict fitness or generate high-fitness sequences and (iii) highlighting several successful studies that implement these techniques in protein engineering (from paratope regions and subcellular localization prediction to high-fitness sequences and protein design rules generation). By providing a comprehensive survey of model details, novel architecture developments, comparisons of model applications, and current challenges, this study intends to provide structured guidance and robust framework for delivering a prospective outlook in the ML-driven protein engineering field.

Structural mechanisms for the activation of human cardiac KCNQ1 channel by electro-mechanical coupling enhancers.

The cardiac KCNQ1 potassium channel carries the important IKs current and controls the heart rhythm. Hundreds of mutations in KCNQ1 can cause life-threatening cardiac arrhythmia. Although KCNQ1 structures have been recently resolved, the structural basis for the dynamic electro-mechanical coupling, also known as the voltage sensor domain-pore domain (VSD-PD) coupling, remains largely unknown. In this study, utilizing two VSD-PD coupling enhancers, namely, the membrane lipid phosphatidylinositol 4,5-bisphosphate (PIP2) and a small-molecule ML277, we determined 2.5-3.5 Å resolution cryo-electron microscopy structures of full-length human KCNQ1-calmodulin (CaM) complex in the apo closed, ML277-bound open, and ML277-PIP2-bound open states. ML277 binds at the "elbow" pocket above the S4-S5 linker and directly induces an upward movement of the S4-S5 linker and the opening of the activation gate without affecting the C-terminal domain (CTD) of KCNQ1. PIP2 binds at the cleft between the VSD and the PD and brings a large structural rearrangement of the CTD together with the CaM to activate the PD. These findings not only elucidate the structural basis for the dynamic VSD-PD coupling process during KCNQ1 gating but also pave the way to develop new therapeutics for anti-arrhythmia.

A gastrointestinal locally activating Janus kinase inhibitor to treat ulcerative colitis.

In this study, we integrated machine learning (ML), structure-tissue selectivity-activity-relationship (STAR), and wet lab synthesis/testing to design a gastrointestinal (GI) locally activating JAK inhibitor for ulcerative colitis treatment. The JAK inhibitor achieves site-specific efficacy through high local GI tissue selectivity while minimizing the requirement for JAK isoform specificity to reduce systemic toxicity. We used the ML model (CoGT) to classify whether the designed compounds were inhibitors or noninhibitors. Then we used the regression ML model (MTATFP) to predict their IC50 against related JAK isoforms of predicted JAK inhibitors. The ML model predicted MMT3-72, which was retained in the GI tract, to be a weak JAK1 inhibitor, while MMT3-72-M2, which accumulated in only GI tissues, was predicted to be an inhibitor of JAK1/2 and TYK2. ML docking methods were applied to simulate their docking poses in JAK isoforms. Application of these ML models enabled us to limit our synthetic efforts to MMT3-72 and MMT3-72-M2 for subsequent wet lab testing. The kinase assay confirmed MMT3-72 weakly inhibited JAK1, and MMT3-72-M2 inhibited JAK1/2 and TYK2. We found that MMT3-72 accumulated in the GI lumen, but not in GI tissue or plasma, but released MMT3-72-M2 accumulated in colon tissue with minimal exposure in the plasma. MMT3-72 achieved superior efficacy and reduced p-STAT3 in DSS-induced colitis. Overall, the integration of ML, the structure-tissue selectivity-activity-relationship system, and wet lab synthesis/testing could minimize the effort in the optimization of a JAK inhibitor to treat colitis. This site-specific inhibitor reduces systemic toxicity by minimizing the need for JAK isoform specificity.

Alox15/15-HpETE Aggravates Myocardial Ischemia-Reperfusion Injury by Promoting Cardiomyocyte Ferroptosis.

BACKGROUND: Myocardial ischemia-reperfusion (I/R) injury causes cardiac dysfunction to myocardial cell loss and fibrosis. Prevention of cell death is important to protect cardiac function after I/R injury. The process of reperfusion can lead to multiple types of cardiomyocyte death, including necrosis, apoptosis, autophagy, and ferroptosis. However, the time point at which the various modes of cell death occur after reperfusion injury and the mechanisms underlying ferroptosis regulation in cardiomyocytes are still unclear. METHODS: Using a left anterior descending coronary artery ligation mouse model, we sought to investigate the time point at which the various modes of cell death occur after reperfusion injury. To discover the key molecules involved in cardiomyocyte ferroptosis, we performed a metabolomics study. Loss/gain-of-function approaches were used to understand the role of 15-lipoxygenase (Alox15) and peroxisome proliferator-activated receptor gamma coactivator 1-alpha (Pgc1α) in myocardial I/R injury. RESULTS: We found that apoptosis and necrosis occurred in the early phase of I/R injury, and that ferroptosis was the predominant form of cell death during the prolonged reperfusion. Metabolomic profiling of eicosanoids revealed that Alox15 metabolites accumulated in ferroptotic cardiomyocytes. We demonstrated that Alox15 expression was specifically increased in the injured area of the left ventricle below the suture and colocalized with cardiomyocytes. Furthermore, myocardial-specific knockout of Alox15 in mice alleviated I/R injury and restored cardiac function. 15-Hydroperoxyeicosatetraenoic acid (15-HpETE), an intermediate metabolite derived from arachidonic acid by Alox15, was identified as a trigger for cardiomyocyte ferroptosis. We explored the mechanism underlying its effects and found that 15-HpETE promoted the binding of Pgc1α to the ubiquitin ligase ring finger protein 34, leading to its ubiquitin-dependent degradation. Consequently, attenuated mitochondrial biogenesis and abnormal mitochondrial morphology were observed. ML351, a specific inhibitor of Alox15, increased the protein level of Pgc1α, inhibited cardiomyocyte ferroptosis, protected the injured myocardium, and caused cardiac function recovery. CONCLUSIONS: Together, our results established that Alox15/15-HpETE-mediated cardiomyocyte ferroptosis plays an important role in prolonged I/R injury.

UBA2 SUMOylates NQO1 and promotes the proliferation of hepatocellular carcinoma by modulating the MAPK pathway.

In our previous study, we found that small ubiquitin-related modifier (SUMO)-activating enzyme ubiquitin-associated-2 domain (UBA2) was upregulated in hepatocellular carcinoma (HCC) patients who were insensitive to chemoembolization. In this study, we aimed to investigate the role of UBA2 in HCC progression. Three cohorts were used to evaluate the efficacy of UBA2 as a prognostic factor for HCC. Our results indicated that UBA2 was associated with aggressive clinical behaviors and was a strong indicator of poor prognosis in HCC. In vitro experiments demonstrated that UBA2 accelerated cell growth, invasion, and migration. These results were further supported by in vivo experiments. RNA-sequencing analysis indicated NQO1 as a target of UBA2, with its levels altering following UBA2 manipulation. The results were verified by western blotting (WB) and quantitative PCR. The SUMOplot Analysis Program predicted lysine residue K240 as a modification target of UBA2, which was confirmed by immunoprecipitation (IP) assays. Subsequent mutation of NQO1 at K240 in HCC cell lines and functional assays revealed the significance of this modification. In addition, the oncogenic effect of UBA2 could be reversed by the SUMO inhibitor ML792 in vivo and in vitro. In conclusion, our study elucidated the regulatory mechanism of UBA2 in HCC and suggested that the SUMO inhibitor ML792 may be an effective combinatory treatment for patients with aberrant UBA2 expression.

Realizing Near Infrared Mechanoluminescence Switch in LAGO:Cr Based on Oxygen Vacancy.

Mechanoluminescence (ML) materials are featured with the characteristic of "force to light" in response to external stimuli, which have made great progress in artificial intelligence and optical sensing. However, how to effectively enable ML in the material is a daunting challenge. Here, a Lu3 Al2 Ga3 O12 :Cr3+ (LAGO: Cr3+ ) near infrared (NIR) ML material peaked at 706 nm is reported, which successfully realizes the key to unlock ML by the lattice-engineering strategy Ga3+ substitution for Al3+ to "grow" oxygen vacancy (Ov ) defects. Combined with thermoluminescence measurements, the observed ML is due to the formation of defect levels and the ML intensity is proportional to it. It is confirmed by X-ray photoelectron spectroscopy and electron paramagnetic resonance that such a process is dominated by Ov , which plays a crucial role in turning on ML in this compound. In addition, potential ML emissions from 4 T2 and 2 E level transitions are discussed from both experimental and theoretical aspects. This study reveals the mechanism of the change in ML behavior after cation substitution, and it may have important implications for the practical application of Ov defect-regulated turn-on of ML.

Emerging Vanadium-Doped Cobalt Chloride Carbonate Hydroxide for Flexible Electrochromic Micro-Supercapacitor: Charged-State Prediction from RGB Input by ANN Model.

Multifunctional devices integrated with electrochromic and supercapacitance properties are fascinating because of their extensive usage in modern electronic applications. In this work, vanadium-doped cobalt chloride carbonate hydroxide hydrate nanostructures (V-C3H NSs) are successfully synthesized and show unique electrochromic and supercapacitor properties. The V-C3H NSs material exhibits a high specific capacitance of 1219.9 F g-1 at 1 mV s-1 with a capacitance retention of 100% over 30 000 CV cycles. The electrochromic performance of the V-C3H NSs material is confirmed through in situ spectroelectrochemical measurements, where the switching time, coloration efficiency (CE), and optical modulation (∆T) are found to be 15.7 and 18.8 s, 65.85 cm2 C-1 and 69%, respectively. A coupled multilayer artificial neural network (ANN) model is framed to predict potential and current from red (R), green (G), and blue (B) color values. The optimized V-C3H NSs are used as the active materials in the fabrication of flexible/wearable electrochromic micro-supercapacitor devices (FEMSDs) through a cost-effective mask-assisted vacuum filtration method. The fabricated FEMSD exhibits an areal capacitance of 47.15 mF cm-2 at 1 mV s-1 and offers a maximum areal energy and power density of 104.78 Wh cm-2 and 0.04 mW cm-2, respectively. This material's interesting energy storage and electrochromic properties are promising in multifunctional electrochromic energy storage applications.

Advancements in nanobody generation: Integrating conventional, in silico, and machine learning approaches.

Nanobodies, derived from camelids and sharks, offer compact, single-variable heavy-chain antibodies with diverse biomedical potential. This review explores their generation methods, including display techniques on phages, yeast, or bacteria, and computational methodologies. Integrating experimental and computational approaches enhances understanding of nanobody structure and function. Future trends involve leveraging next-generation sequencing, machine learning, and artificial intelligence for efficient candidate selection and predictive modeling. The convergence of traditional and computational methods promises revolutionary advancements in precision biomedical applications such as targeted drug delivery and diagnostics. Embracing these technologies accelerates nanobody development, driving transformative breakthroughs in biomedicine and paving the way for precision medicine and biomedical innovation.

Action and therapeutic targets of myosin light chain kinase, an important cardiovascular signaling mechanism.

The global incidence of cardiac diseases is increasing, imposing a substantial socioeconomic burden on healthcare systems. The pathogenesis of cardiovascular disease is complex and not fully understood, and the physiological function of the heart is inextricably linked to well-regulated cardiac muscle movement. Myosin light chain kinase (MLCK) is essential for myocardial contraction and diastole, cardiac electrophysiological homeostasis, vasoconstriction of vascular nerves and blood pressure regulation. In this sense, MLCK appears to be an attractive therapeutic target for cardiac diseases. MLCK participates in myocardial cell movement and migration through diverse pathways, including regulation of calcium homeostasis, activation of myosin light chain phosphorylation, and stimulation of vascular smooth muscle cell contraction or relaxation. Recently, phosphorylation of myosin light chains has been shown to be closely associated with the activation of myocardial exercise signaling, and MLCK mediates systolic and diastolic functions of the heart through the interaction of myosin thick filaments and actin thin filaments. It works by upholding the integrity of the cytoskeleton, modifying the conformation of the myosin head, and modulating innervation. MLCK governs vasoconstriction and diastolic function and is associated with the activation of adrenergic and sympathetic nervous systems, extracellular transport, endothelial permeability, and the regulation of nitric oxide and angiotensin II. Additionally, MLCK plays a crucial role in the process of cardiac aging. Multiple natural products/phytochemicals and chemical compounds, such as quercetin, cyclosporin, and ML-7 hydrochloride, have been shown to regulate cardiomyocyte MLCK. The MLCK-modifying capacity of these compounds should be considered in designing novel therapeutic agents. This review summarizes the mechanism of action of MLCK in the cardiovascular system and the therapeutic potential of reported chemical compounds in cardiac diseases by modifying MLCK processes.

Targeting epigenetic and post-translational modifications regulating pyroptosis for the treatment of inflammatory diseases.

Inflammatory diseases, including infectious diseases, diabetes-related diseases, arthritis-related diseases, neurological diseases, digestive diseases, and tumor, continue to threaten human health and impose a significant financial burden despite advancements in clinical treatment. Pyroptosis, a pro-inflammatory programmed cell death pathway, plays an important role in the regulation of inflammation. Moderate pyroptosis contributes to the activation of native immunity, whereas excessive pyroptosis is associated with the occurrence and progression of inflammation. Pyroptosis is complicated and tightly controlled by various factors. Accumulating evidence has confirmed that epigenetic modifications and post-translational modifications (PTMs) play vital roles in the regulation of pyroptosis. Epigenetic modifications, which include DNA methylation and histone modifications (such as methylation and acetylation), and post-translational modifications (such as ubiquitination, phosphorylation, and acetylation) precisely manipulate gene expression and protein functions at the transcriptional and post-translational levels, respectively. In this review, we summarize the major pathways of pyroptosis and focus on the regulatory roles and mechanisms of epigenetic and post-translational modifications of pyroptotic components. We also illustrate these within pyroptosis-associated inflammatory diseases. In addition, we discuss the effects of novel therapeutic strategies targeting epigenetic and post-translational modifications on pyroptosis, and provide prospective insight into the regulation of pyroptosis for the treatment of inflammatory diseases.

Artificial intelligence innovations in neurosurgical oncology: a narrative review.

PURPOSE: Artificial Intelligence (AI) has become increasingly integrated clinically within neurosurgical oncology. This report reviews the cutting-edge technologies impacting tumor treatment and outcomes. METHODS: A rigorous literature search was performed with the aid of a research librarian to identify key articles referencing AI and related topics (machine learning (ML), computer vision (CV), augmented reality (AR), virtual reality (VR), etc.) for neurosurgical care of brain or spinal tumors. RESULTS: Treatment of central nervous system (CNS) tumors is being improved through advances across AI-such as AL, CV, and AR/VR. AI aided diagnostic and prognostication tools can influence pre-operative patient experience, while automated tumor segmentation and total resection predictions aid surgical planning. Novel intra-operative tools can rapidly provide histopathologic tumor classification to streamline treatment strategies. Post-operative video analysis, paired with rich surgical simulations, can enhance training feedback and regimens. CONCLUSION: While limited generalizability, bias, and patient data security are current concerns, the advent of federated learning, along with growing data consortiums, provides an avenue for increasingly safe, powerful, and effective AI platforms in the future.

Treatment intensification following glucagon-like peptide-1 receptor agonists in type 2 diabetes: Comparative effectiveness analyses between different basal insulins. RESTORE-G real-world study.

AIM: To compare the effectiveness of different basal insulins (BI) prescribed as an add-on to or switch from glucagon-like peptide-1 receptor agonist (GLP-1 RA) therapy. MATERIALS AND METHODS: Retrospective, real-world data from electronic medical records of 32 Italian diabetes clinics were used, after propensity score adjustment, to compare effectiveness after 6 months of treatment with second- versus first-generation BI (2BI vs. 1BI) or glargine 300 U/ml versus degludec 100 U/ml (Gla-300 vs. Deg-100), when added to (ADD-ON) or in substitution of (SWITCH) GLP-1 RA. Only comparisons, including a minimum of 100 patients per group, were performed to ensure adequate robustness of the analyses. RESULTS: In the ADD-ON cohort (N = 700), greater benefits of 2BI versus 1BI were found in glycated haemoglobin {HbA1c; estimated mean difference: -0.32% [95% confidence interval (CI) -0.62; -0.02]; p = .04} and fasting blood glucose [FBG; -20.73 mg/dl (95% CI -35.62; -5.84); p = .007]. In the SWITCH cohort (N = 2097), greater benefits of 2BI versus 1BI were found in HbA1c [-0.22% (95% CI -0.42; -0.02); p = .03], FBG [-10.15 mg/dl (95% CI -19.04; -1.26); p = .03], and body weight [-0.67 kg (95% CI -1.30; -0.04); p = .04]. In the SWITCH cohort starting 2BI (N = 688), marked differences in favour of Gla-300 versus Deg-100 were documented in HbA1c [-0.89% (95% CI -1.26; -0.52); p < .001] and FBG [-17.89 mg/dl (95% CI -32.45; -3.33); p = .02]. Using propensity score matching as a sensitivity analysis, the benefit on HbA1c was confirmed [-0.55% (95% CI -1.02; -0.08); p = .02]. BI titration was suboptimal in all examined cohorts. CONCLUSIONS: 2BI are a valuable option to intensify GLP-1 RA therapy. Switching to Gla-300 versus Deg-100 was associated with greater HbA1c improvement.

Convolutional Neural Networks Guided Raman Spectroscopy as a Process Analytical Technology (PAT) Tool for Monitoring and Simultaneous Prediction of Monoclonal Antibody Charge Variants.

BACKGROUND: Charge related heterogeneities of monoclonal antibody (mAb) based therapeutic products are increasingly being considered as a critical quality attribute (CQA). They are typically estimated using analytical cation exchange chromatography (CEX), which is time consuming and not suitable for real time control. Raman spectroscopy coupled with artificial intelligence (AI) tools offers an opportunity for real time monitoring and control of charge variants. OBJECTIVE: We present a process analytical technology (PAT) tool for on-line and real-time charge variant determination during process scale CEX based on Raman spectroscopy employing machine learning techniques. METHOD: Raman spectra are collected from a reference library of samples with distribution of acidic, main, and basic species from 0-100% in a mAb concentration range of 0-20 g/L generated from process-scale CEX. The performance of different machine learning techniques for spectral processing is compared for predicting different charge variant species. RESULT: A convolutional neural network (CNN) based model was successfully calibrated for quantification of acidic species, main species, basic species, and total protein concentration with R2 values of 0.94, 0.99, 0.96 and 0.99, respectively, and the Root Mean Squared Error (RMSE) of 0.1846, 0.1627, and 0.1029 g/L, respectively, and 0.2483 g/L for the total protein concentration. CONCLUSION: We demonstrate that Raman spectroscopy combined with AI-ML frameworks can deliver rapid and accurate determination of product related impurities. This approach can be used for real time CEX pooling decisions in mAb production processes, thus enabling consistent charge variant profiles to be achieved.

Reactivities of acrylamide warheads toward cysteine targets: a QM/ML approach to covalent inhibitor design.

Covalent inhibition offers many advantages over non-covalent inhibition, but covalent warhead reactivity must be carefully balanced to maintain potency while avoiding unwanted side effects. While warhead reactivities are commonly measured with assays, a computational model to predict warhead reactivities could be useful for several aspects of the covalent inhibitor design process. Studies have shown correlations between covalent warhead reactivities and quantum mechanic (QM) properties that describe important aspects of the covalent reaction mechanism. However, the models from these studies are often linear regression equations and can have limitations associated with their usage. Applications of machine learning (ML) models to predict covalent warhead reactivities with QM descriptors are not extensively seen in the literature. This study uses QM descriptors, calculated at different levels of theory, to train ML models to predict reactivities of covalent acrylamide warheads. The QM/ML models are compared with linear regression models built upon the same QM descriptors and with ML models trained on structure-based features like Morgan fingerprints and RDKit descriptors. Experiments show that the QM/ML models outperform the linear regression models and the structure-based ML models, and literature test sets demonstrate the power of the QM/ML models to predict reactivities of unseen acrylamide warhead scaffolds. Ultimately, these QM/ML models are effective, computationally feasible tools that can expedite the design of new covalent inhibitors.

MDFit: automated molecular simulations workflow enables high throughput assessment of ligands-protein dynamics.

Molecular dynamics (MD) simulation is a powerful tool for characterizing ligand-protein conformational dynamics and offers significant advantages over docking and other rigid structure-based computational methods. However, setting up, running, and analyzing MD simulations continues to be a multi-step process making it cumbersome to assess a library of ligands in a protein binding pocket using MD. We present an automated workflow that streamlines setting up, running, and analyzing Desmond MD simulations for protein-ligand complexes using machine learning (ML) models. The workflow takes a library of pre-docked ligands and a prepared protein structure as input, sets up and runs MD with each protein-ligand complex, and generates simulation fingerprints for each ligand. Simulation fingerprints (SimFP) capture protein-ligand compatibility, including stability of different ligand-pocket interactions and other useful metrics that enable easy rank-ordering of the ligand library for pocket optimization. SimFPs from a ligand library are used to build & deploy ML models that predict binding assay outcomes and automatically infer important interactions. Unlike relative free-energy methods that are constrained to assess ligands with high chemical similarity, ML models based on SimFPs can accommodate diverse ligand sets. We present two case studies on how SimFP helps delineate structure-activity relationship (SAR) trends and explain potency differences across matched-molecular pairs of (1) cyclic peptides targeting PD-L1 and (2) small molecule inhibitors targeting CDK9.

Cross-column density functional theory-based quantitative structure-retention relationship model development powered by machine learning.

Quantitative structure-retention relationship (QSRR) modeling has emerged as an efficient alternative to predict analyte retention times using molecular descriptors. However, most reported QSRR models are column-specific, requiring separate models for each high-performance liquid chromatography (HPLC) system. This study evaluates the potential of machine learning (ML) algorithms and quantum mechanical (QM) descriptors to develop QSRR models that can predict retention times across three different reversed-phase HPLC columns under varying conditions. Four machine learning methods-partial least squares (PLS) regression, ridge regression (RR), random forest (RF), and gradient boosting (GB)-were compared on a dataset of 360 retention times for 15 aromatic analytes. Molecular descriptors were calculated using density functional theory (DFT). Column characteristics like particle size and pore size and experimental conditions like temperature and gradient time were additionally used as descriptors. Results showed that the GB-QSRR model demonstrated the best predictive performance, with Q2 of 0.989 and root mean square error of prediction (RMSEP) of 0.749 min on the test set. Feature analysis revealed that solvation energy (SE), HOMO-LUMO energy gap (∆E HOMO-LUMO), total dipole moment (Mtot), and global hardness (η) are among the most influential predictors for retention time prediction, indicating the significance of electrostatic interactions and hydrophobicity. Our findings underscore the efficiency of ensemble methods, GB and RF models employing non-linear learners, in capturing local variations in retention times across diverse experimental setups. This study emphasizes the potential of cross-column QSRR modeling and highlights the utility of ML models in optimizing chromatographic analysis.

Comparative performance analysis of Boruta, SHAP, and Borutashap for disease diagnosis: A study with multiple machine learning algorithms.

Interpretable machine learning models are instrumental in disease diagnosis and clinical decision-making, shedding light on relevant features. Notably, Boruta, SHAP (SHapley Additive exPlanations), and BorutaShap were employed for feature selection, each contributing to the identification of crucial features. These selected features were then utilized to train six machine learning algorithms, including LR, SVM, ETC, AdaBoost, RF, and LR, using diverse medical datasets obtained from public sources after rigorous preprocessing. The performance of each feature selection technique was evaluated across multiple ML models, assessing accuracy, precision, recall, and F1-score metrics. Among these, SHAP showcased superior performance, achieving average accuracies of 80.17%, 85.13%, 90.00%, and 99.55% across diabetes, cardiovascular, statlog, and thyroid disease datasets, respectively. Notably, the LGBM emerged as the most effective algorithm, boasting an average accuracy of 91.00% for most disease states. Moreover, SHAP enhanced the interpretability of the models, providing valuable insights into the underlying mechanisms driving disease diagnosis. This comprehensive study contributes significant insights into feature selection techniques and machine learning algorithms for disease diagnosis, benefiting researchers and practitioners in the medical field. Further exploration of feature selection methods and algorithms holds promise for advancing disease diagnosis methodologies, paving the way for more accurate and interpretable diagnostic models.

Data-driven modelling for assessing trophic status in marine ecosystems using machine learning approaches.

Assessing eutrophication in coastal and transitional waters is of utmost importance, yet existing Trophic Status Index (TSI) models face challenges like multicollinearity, data redundancy, inappropriate aggregation methods, and complex classification schemes. To tackle these issues, we developed a novel tool that harnesses machine learning (ML) and artificial intelligence (AI), enhancing the reliability and accuracy of trophic status assessments. Our research introduces an improved data-driven methodology specifically tailored for transitional and coastal (TrC) waters, with a focus on Cork Harbour, Ireland, as a case study. Our innovative approach, named the Assessment Trophic Status Index (ATSI) model, comprises three main components: the selection of pertinent water quality indicators, the computation of ATSI scores, and the implementation of a new classification scheme. To optimize input data and minimize redundancy, we employed ML techniques, including advanced deep learning methods. Specifically, we developed a CHL prediction model utilizing ten algorithms, among which XGBoost demonstrated exceptional performance, showcasing minimal errors during both training (RMSE = 0.0, MSE = 0.0, MAE = 0.01) and testing (RMSE = 0.0, MSE = 0.0, MAE = 0.01) phases. Utilizing a novel linear rescaling interpolation function, we calculated ATSI scores and evaluated the model's sensitivity and efficiency across diverse application domains, employing metrics such as R2, the Nash-Sutcliffe efficiency (NSE), and the model efficiency factor (MEF). The results consistently revealed heightened sensitivity and efficiency across all application domains. Additionally, we introduced a brand new classification scheme for ranking the trophic status of transitional and coastal waters. To assess spatial sensitivity, we applied the ATSI model to four distinct waterbodies in Ireland, comparing trophic assessment outcomes with the Assessment of Trophic Status of Estuaries and Bays in Ireland (ATSEBI) System. Remarkably, significant disparities between the ATSI and ATSEBI System were evident in all domains, except for Mulroy Bay. Overall, our research significantly enhances the accuracy of trophic status assessments in marine ecosystems. The ATSI model, combined with cutting-edge ML techniques and our new classification scheme, represents a promising avenue for evaluating and monitoring trophic conditions in TrC waters. The study also demonstrated the effectiveness of ATSI in assessing trophic status across various waterbodies, including lakes, rivers, and more. These findings make substantial contributions to the field of marine ecosystem management and conservation.