SEARCH · PubMed Health

Results for “Predictive Learning Models”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4Linked to original sources

PubMed2025

An adjuvant database for preclinical evaluation of vaccines and immunotherapeutics.

Adjuvants are immunostimulators used to enhance vaccine efficacy against infectious diseases. However, current methods for evaluating their efficacy and safety are limited, hindering large-scale screening. To address this, we developed a prototype Adjuvant Database (ADB) containing transcriptome data, generated using the same protocols as the widely used Open TG-GATEs (OTG) toxicogenomics database, covering 25 adjuvants across multiple species, organs, time points, and doses. This enabled cross-database integration of ADB and OTG. Transcriptomic patterns successfully distinguished each adjuvant regardless of organs or species. Using both databases, we built machine learning models to predict adjuvanticity and hepatotoxicity. Notably, we identified colchicine's adjuvant activity and FK565's liver toxicity through data-driven analysis. Overall, ADB combined with OTG offers a framework for transcriptomics-based, data-driven screening of adjuvant candidates.

Animals↗

PubMed2025

Integration of Genetic Information to Improve Brain Age Gap Estimation Models in the UK Biobank.

Neurodegeneration occurs when the body's central nervous system becomes impaired as a person ages, which can happen at an accelerated pace. Neurodegeneration impairs quality of life, affecting essential functions, including memory and the ability to self-care. Genetics play an important role in neurodegeneration and longevity. Brain age gap estimation (BrainAGE) is a biomarker that quantifies the difference between a machine learning model-predicted biological age of the brain and the true chronological age for healthy subjects; however, a large portion of the variance remains unaccounted for in these models, attributed to individual differences. This study focuses on predicting the BrainAGE more accurately, aided by genetic information associated with neurodegeneration. To achieve this, a BrainAGE model was developed based on MRI measures, and then the associated genes were determined with a Genome-Wide Association Study. Subsequently, genetic information was incorporated into the models. The incorporation of genetic information yielded improvements in the model performances by 7% to 12%, showing that the incorporation of genetic information can notably reduce unexplained variance. This work helps to define new ways of determining persons susceptible to neurological aging decline and reveals genes for targeted precision medicine therapies.

Humans↗

PubMed2024

A comprehensive meta-analysis of tissue resident memory T cells and their roles in shaping immune microenvironment and patient prognosis in non-small cell lung cancer.

Tissue-resident memory T cells (TRM) are a specialized subset of long-lived memory T cells that reside in peripheral tissues. However, the impact of TRM-related immunosurveillance on the tumor-immune microenvironment (TIME) and tumor progression across various non-small-cell lung cancer (NSCLC) patient populations is yet to be elucidated. Our comprehensive analysis of multiple independent single-cell and bulk RNA-seq datasets of patient NSCLC samples generated reliable, unique TRM signatures, through which we inferred the abundance of TRM in NSCLC. We discovered that TRM abundance is consistently positively correlated with CD4+ T helper 1 cells, M1 macrophages, and resting dendritic cells in the TIME. In addition, TRM signatures are strongly associated with immune checkpoint and stimulatory genes and the prognosis of NSCLC patients. A TRM-based machine learning model to predict patient survival was validated and an 18-gene risk score was further developed to effectively stratify patients into low-risk and high-risk categories, wherein patients with high-risk scores had significantly lower overall survival than patients with low-risk. The prognostic value of the risk score was independently validated by the Cancer Genome Atlas Program (TCGA) dataset and multiple independent NSCLC patient datasets. Notably, low-risk NSCLC patients with higher TRM infiltration exhibited enhanced T-cell immunity, nature killer cell activation, and other TIME immune responses related pathways, indicating a more active immune profile benefitting from immunotherapy. However, the TRM signature revealed low TRM abundance and a lack of prognostic association among lung squamous cell carcinoma patients in contrast to adenocarcinoma, indicating that the two NSCLC subtypes are driven by distinct TIMEs. Altogether, this study provides valuable insights into the complex interactions between TRM and TIME and their impact on NSCLC patient prognosis. The development of a simplified 18-gene risk score provides a practical prognostic marker for risk stratification.

Humans↗

PubMed2026

Engineering Bacillus Subtilis for Efficient Biosynthesis of Riboflavin: Current Knowledge and Future Perspectives.

Riboflavin is an essential water-soluble vitamin that serves as a precursor for the biosynthesis of the flavin cofactors FMN and FAD, which play pivotal roles in numerous redox and energy metabolism reactions. With the growing global demand for sustainable vitamin production, microbial fermentation has become an attractive alternative to chemical synthesis due to its environmental and economic advantages. Among microbial hosts, Bacillus subtilis has emerged as a leading cell factory for riboflavin production owing to its GRAS status, well-characterized genetics, and efficient protein secretion system. This review provides a comprehensive overview of recent advances in metabolic engineering strategies to enhance riboflavin biosynthesis in B. subtilis. Key topics include strengthening biosynthetic and precursor pathways, relieving feedback inhibition, balancing metabolic flux and cell growth, employing adaptive laboratory evolution, and utilizing omics-guided optimization and 13C metabolic flux analysis. Moreover, the integration of synthetic biology tools such as riboswitch engineering, regulatory element design, and high-throughput screening has significantly accelerated strain improvement. Despite remarkable progress, challenges remain in achieving precise regulatory control, optimizing multi-gene expression, and enhancing genome integration efficiency. Future research combining multi-omics data, synthetic regulatory design, and machine learning-driven predictive modeling is expected to further advance the development of intelligent B. subtilis cell factories. However, the practical implementation of these systems remains constrained by the metabolic burden of overproduction and the lack of universal regulatory models that can predict strain performance across varying industrial scales.

Bacillus subtilis↗

PubMed2025

Integrating RNA sequencing with deep learning-based metabolic toxicity prediction: A new perspective on screening prioritized liquid crystal monomers.

Nearly 99 % of liquid crystal monomers (LCMs) toxicological data remains gaps, especially to aquatic organisms. Herein, this study proposes a rapid and high-throughput screening method for identifying priority LCMs in natural water. Using six fluorinated LCMs (LCMsF) with significant enrichment characteristics in zebrafish as examples, RNA sequencing revealed that LCMsF-induced metabolic disturbances are predominant, including 28 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway abnormalities attributed to 498 differentially expressed genes. Notably, the intricate sequencing process resulted in the inability to rapid identify additional 857 LCMsF that may induce metabolic disturbances. To address this, LCMsT-MTP, a predictive deep learning model based on RNA sequencing, was developed. This model integrates a comprehensive representation of LCMsF structures and metabolic toxicity target sequences. LCMsT-MTP improves upon traditional methods that are limited to single targets and mechanisms by facilitating the simultaneous identification of 21 metabolic toxicities induced by LCMsF. In addition, the LCMsT-MTP model was further applied to non-fluorinated LCMs (LCMsNone F) that satisfy the applicability domains test. Accordingly, a metabolic toxicity priority list of LCMs was proposed, with ∼95 % of LCMs classified as high or medium risk. Priority list validation by molecular dynamics confirmed that the interactions of LCMsF/LCMsNone F and metabolic toxicity targets in representative KEGG pathways were distinct.

Animals↗

PubMed2026

Sequence optimization targeting mRNA stability enhances monoclonal antibody titers in CHO cells.

This study presents a DNA sequence optimization approach that integrates mRNA stability as a tunable design parameter to enhance monoclonal antibody expression in Chinese hamster ovary (CHO) cells. A comprehensive combinatorial library of synonymous coding-sequence variants of an IgG1 light chain was integrated as single copies at a defined genomic locus in CHO cells with identical regulatory elements. Steady-state mRNA abundance, quantified by deep sequencing of gDNA and mRNA, served as a proxy for mRNA stability. These data were used to train a machine learning model that predicts mRNA abundance from coding sequence using embeddings from a pre-trained nucleotide transformer. This abundance predictor, together with established translational metrics, was incorporated into a genetic algorithm for multi-objective codon optimization. As proof-of-concept, we optimized sequences encoding Trastuzumab to either maximize or minimize the abundance criterion and obtained benchmark sequences from two commercial providers. Using targeted integration, we generated CHO cell lines and measured protein titer and cell-specific productivity. Sequences optimized for high abundance significantly increased intracellular mRNA levels (+41%), protein titer (+59%), and cell-specific productivity (+85%) relative to low-abundance designs, while viable cell densities remained comparable. Compared to commercial benchmarks, high-abundance sequences achieved significantly higher titer (+70%) and cell-specific productivity (+98%). These findings establish mRNA stability as a practical and complementary design parameter for codon optimization in monoclonal antibody production, with potential applicability to other proteins and expression systems.

CHO↗

PubMed2024

ERCC2 mutations alter the genomic distribution pattern of somatic mutations and are independently prognostic in bladder cancer.

Excision repair cross-complementation group 2 (ERCC2) encodes the DNA helicase xeroderma pigmentosum group D, which functions in transcription and nucleotide excision repair. Point mutations in ERCC2 are putative drivers in around 10% of bladder cancers (BLCAs) and a potential positive biomarker for cisplatin therapy response. Nevertheless, the prognostic significance directly attributed to ERCC2 mutations and its pathogenic role in genome instability remain poorly understood. We first demonstrated that mutant ERCC2 is an independent predictor of prognosis in BLCA. We then examined its impact on the somatic mutational landscape using a cohort of ERCC2 wild-type (n = 343) and mutant (n = 39) BLCA whole genomes. The genome-wide distribution of somatic mutations is significantly altered in ERCC2 mutants, including T[C>T]N enrichment, altered replication time correlations, and CTCF-cohesin binding site mutation hotspots. We leverage these alterations to develop a machine learning model for predicting pathogenic ERCC2 mutations, which may be useful to inform treatment of patients with BLCA.

Humans↗

PubMed2026

Clinical translation of senescence-related pan-cancer multi-omics: tools for assessment and immunotherapy prediction.

Cellular senescence (CS) exerts dual roles in tumorigenesis, yet its pan-cancer molecular characteristics and clinical value remain unclear, hindering its translation to oncology and personalized therapy. To address the lack of specific and universal tools for senescence assessment and immunotherapy response prediction, this study systematically analyzed 1259 CS-related genes from the CellAge database across 31 cancer types by integrating multi-omics data, including bulk RNA-seq, single-cell/spatial transcriptomics, and CRISPR screening. We developed a rank-based algorithm SenScoreR (publicly available at https://gxhub.shinyapps.io/SenScoreR/ ) for senescence quantification, validated with 10 independent datasets, and constructed a machine learning-based predictive model CS.Sig for immunotherapy response. Results showed that tumors had significantly lower Rank-based Senescence Score (RSS) than normal tissues across 31 cancers (average diagnostic AUC = 0.895), with low RSS linked to poor survival; high RSS correlated with reduced genomic instability, enriched CD8⁺ T/NK cell/macrophage infiltration, upregulated PD-L1 expression, and elevated immune cytolytic activity. CS.Sig demonstrated robust performance in predicting ICI response (AUC = 0.716 across 10 cohorts), outperforming 13 existing signatures, while CRISPR screening identified 17 senescence-related targets (e.g., CEP55, PPP1CC) whose knockout enhanced anti-tumor immunity. Our findings clarify CS's role in maintaining tumor genomic stability and shaping immune microenvironments, and the developed SenScoreR, CS.Sig, and identified targets bridge basic CS research with clinical oncology, providing a translational resource and hypothesis basis for future experimental and clinical validation.

Journal Article↗

PubMed2022

Scalable approaches for functional analyses of whole-genome sequencing non-coding variants.

Non-coding genetic variants outside of protein-coding genome regions play an important role in genetic and epigenetic regulation. It has become increasingly important to understand their roles, as non-coding variants often make up the majority of top findings of genome-wide association studies (GWAS). In addition, the growing popularity of disease-specific whole-genome sequencing (WGS) efforts expands the library of and offers unique opportunities for investigating both common and rare non-coding variants, which are typically not detected in more limited GWAS approaches. However, the sheer size and breadth of WGS data introduce additional challenges to predicting functional impacts in terms of data analysis and interpretation. This review focuses on the recent approaches developed for efficient, at-scale annotation and prioritization of non-coding variants uncovered in WGS analyses. In particular, we review the latest scalable annotation tools, databases and functional genomic resources for interpreting the variant findings from WGS based on both experimental data and in silico predictive annotations. We also review machine learning-based predictive models for variant scoring and prioritization. We conclude with a discussion of future research directions which will enhance the data and tools necessary for the effective functional analyses of variants identified by WGS to improve our understanding of disease etiology.

Genome-Wide Association Study↗

PubMed2026

Machine learning analysis of the human initiator region reveals key features of different types of core promoters.

The initiator (Inr) is the starting point for the transcription of many genes. Here, we generated highly predictive machine learning models of the human Inr region, and determined that the Inr is present in ∼60% of focused human promoters, identified a novel TATA-specific Inr, and detected the overlapping but functionally distinct TCT motif. Quantitative genome-wide analyses revealed a strict and synergistic interaction between the Inr and DPR, an inverse relationship between the TATA and DPR, a flexible and sometimes independent function of the TATA box in relation to the Inr, and different properties of the TCT motif in humans versus Drosophila.

Humans↗

PubMed2026

Future promise, current clinical ambiguity: a systematic review of machine learning algorithm outputs predicting risk of cardiovascular disease.

OBJECTIVE: To examine whether the outputs of machine learning algorithms designed to predict risk of cardiovascular disease (CVD) address known deficiencies of the Framingham Risk Score (FRS) and improve risk estimates. METHODS: For this critical review, Medline, Embase and IEEE were searched from inception to 1 January 2025. Included were studies describing machine learning algorithms designed to specifically compare output of cardiovascular risk assessment with the FRS. Commentaries, letters, unpublished work or non-peer-reviewed papers were excluded.Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, two reviewers screened titles and abstracts independently, then populated a purpose-built data extraction form. A subsequent qualitative thematic analysis focused on algorithms' strengths, added value, potential harms, unintended consequences and equity implications.The main outcome assessed was whether, among healthy adults, the algorithm improved CVD risk prediction relative to the FRS. RESULTS: Of 707 studies retrieved, 29 met inclusion criteria. 23 reported improved predictive ability relative to the FRS. Most datasets and/or medical records used included sociodemographic predictors of CVD not included among FRS inputs. Some added costly diagnostic tests like CT angiography to FRS screening indicators. When they were defined, inputs and outcomes such as hypertension or myocardial infarction did not always adhere to FRS values. Statistical significance was generally taken as a proxy for clinical significance. Some algorithms overestimated the number at risk compared with the FRS without discussing whether that larger proportion might be at risk of overdiagnosis rather than CVD, while a few decreased the proportion found to be at risk. CONCLUSIONS: Use of artificial intelligence to improve accuracy of risk assessment for CVD demonstrates the technological capacity to merge known sociodemographic predictors with biologic variables and examine non-linear interactions among these. Still needed to achieve patient benefit is clinical insight, adherence to screening principles and cost-benefit assessment of inputs selected.

Humans↗

PubMed2026

New Insights into Genomic Variations and Mutational Events Associated with Plant-Pathogen Interactions.

Plant diseases threaten global food security, causing up to 40% crop yield losses and more than $220 billion in annual economic damage. This review synthesizes recent advances in understanding the genomic variations and mutational events underlying plant-pathogen interactions and durable plant disease resistance. Key insights into evolutionary dynamics, genetic variability, and coadaptive strategies reveal the complexity of host-pathogen relationships and the implications for developing durable disease resistance. Integrative approaches combining genome-wide association studies and functional genomics have uncovered the polygenic and epistatic architecture of quantitative resistance. Advances in pan-genomics and high-throughput sequencing have revealed extensive genetic variability in cultivated/elite germplasm and wild relatives. Emerging technologies, including gene editing, multi-omics, and machine learning, enable predictive modeling of resistance traits and support evolution that informs plant breeding strategies. Collectively, these advances provide a robust framework for developing durable resistance and sustainable crop protection in the face of global agricultural challenges.

Host-Pathogen Interactions↗

PubMed2026

Radiogenomics predicts immune microenvironment heterogeneity and response to combination immunotherapy in hepatocellular carcinoma.

BACKGROUND: The combination of immune checkpoint inhibitors (ICIs) with anti-angiogenic agents is the preferred first-line therapy option for patients with advanced hepatocellular carcinoma (HCC), yet only a subset of patients responds, urging the quest for prediction biomarkers. We aimed to integrate genomics with radiology to propose an immune-derived radiogenomics biomarker of response to such combination immunotherapy and evaluate its added value in clinical context. METHODS: We integrated bulk RNA sequencing (RNA-seq) and proteomics data of 994 HCC patients with single-cell RNA-seq data of 11 samples across multiple datasets to identify an immune-related signature (IRS) that may influence sensitivity or resistance to such combined immunotherapy strategy, followed by verification of selected marker genes using immunohistochemistry and cytological experiments. We then trained/validated a cross-modality radiogenomics biomarker using machine learning based on TCIA database that was further tested in multi-scale independent cohorts covering 754 HCC patients. RESULTS: Integrative multi-omics analysis identifed a parsimonious 2-gene prognostic signature including KPNA2 and SMG5 that was significantly associated with immune heterogeneity and response to combination immunotherapy. Machine-learning pipeline exported the optimal 4-feature radiogenomics biomarker using support vector machine that significantly discriminated prognosis (hazard ratio 1.415–1.890; p < 0.05 for all) and modestly predicted response to ICI plus anti-angiogenic therapy (area under the curve 0.720–0.829) in independent retrospective series across major imaging modalities (computed tomography/magnetic resonance imaging). In a prospective neoadjuvant cohort, this biomarker also showed favorable performance for predicting pathological response and tumor recurrence, accompanied by biological validation through single-cell RNA-seq analysis of pre-treatment biopsies. CONCLUSIONS: Our study provides a cross-device-cross-modal radiogenomics biomarker that can improve patient selection for emerging ICI plus anti-angiogenic therapy with novel potential therapeutic targets in HCC.

Humans↗

PubMed2026

Unveiling m7G modification patterns and causal drivers governing intracranial aneurysm rupture risk through multi-omics validation and m7G-MeRIP-seq profiling.

Intracranial aneurysm (IA) rupture causes severe brain hemorrhage with high mortality, yet its molecular drivers remain unclear and better risk prediction is urgently needed. Using transcriptomics, single-cell analysis, and genetic data, we investigated the role of N7-methylguanosine (m7G) RNA modification in IA. We identified distinct m7G modification patterns, validated their methylation features in patient samples, and incorporated these patterns into a machine learning-based rupture prediction model. The presence and characteristics of m7G patterns significantly improved model performance, achieving high predictive accuracy across three independent cohorts (AUC 0.91-0.95). Genetic analyses further identified three causal m7G-related genes (NSUN2, IFIT5, SNUPN), and laboratory experiments confirmed their altered expression and methylation in ruptured aneurysms. Overall, our findings demonstrate that m7G modifications play a key role in IA rupture. The validated prediction model offers strong clinical potential for rupture risk assessment, and the identified genes represent promising therapeutic targets.

Humans↗

PubMed2025

Assessing individual genetic susceptibility to metabolic syndrome: interpretable machine learning method.

BACKGROUND: Genome-wide association studies have provided profound insights into the genetic aetiology of metabolic syndrome (MetS). However, there is a lack of machine-learning (ML)-based predictive models to assess individual genetic susceptibility to MetS. This study utilized single-nucleotide polymorphisms (SNPs) as variables and employed ML-based genetic risk score (GRS) models to predict the occurrence of MetS, bringing it closer to clinical application. METHODS: Feature selection was performed using Least Absolute Shrinkage and Selection Operator. Six ML algorithms were employed to construct GRS models. A fivefold cross-validation was utilized to aid in the internal validation of models. The receiver operating characteristic (ROC) curve was used to select the better-performing GRS model. The SHapley Additive exPlanations (SHAP) was then applied to interpret the model. After extracting GRS, stratified analysis of BMI, age and gender was performed. Finally, these conventional risk factors and GRS were integrated through multivariate logistic regression to establish a combined model. RESULTS: A total of 17 SNPs were selected for analysis. Among the GRS models, the extreme gradient boosting (XGBoost) model demonstrated superior discriminative performance (AUC = 0.837). The XGBoost's optimal robustness was also validated through five-fold cross-validation (mean ROC-AUC = 0.706). The XGBoost-based SHAP algorithm not only elucidated the global effects of 17 SNPs across all samples, but also described the interaction between SNPs, providing a visual representation of how SNPs impact the prediction of MetS in an individual. There was a strong correlation between GRS and MetS risk, particularly observed among young individuals, males and overweight individuals. Furthermore, the model combining conventional risk factors and GRS exhibited excellent discriminative performance (AUC = 0.962) and outstanding robustness (mean ROC-AUC = 0.959). CONCLUSION: This study established a reliable XGBoost-based GRS model and a GRS prediction platform (https://metabolicsyndromeapps.shinyapps.io/geneticriskscore/) to assess individual genetic susceptibility to MetS. This model has high interpretability and can provide personalized reference for determining the necessity of primary prevention measures for MetS. Additionally, there may be interactions between traditional risk factors and GRS, and the integration of both in a comprehensive model is useful in the prediction of MetS occurrence.

Humans↗

PubMed2026

Machine learning vs. traditional methods for predicting postoperative cardiac complications after non-cardiac surgery: a systematic review and Bayesian network meta-analysis.

INTRODUCTION: Accurate prediction of peri-operative cardiac complications is critical to optimise pre-operative decision-making. Traditional risk prediction scores, such as the Revised Cardiac Risk Index, show only modest discrimination. Machine learning can model complex, non-linear relationships but their predictive performance compared with traditional scores remains unclear. METHODS: We performed a systematic review and Bayesian network meta-analysis. The primary outcome was postoperative adverse cardiac events following non-cardiac surgery. Prediction models were assessed relative to the Revised Cardiac Risk Index. As many studies evaluated multiple versions of each model type, the highest performing ('best version') and lowest performing ('worst version') results were analysed. Models were ranked using the surface under the cumulative ranking curve (SUCRA). RESULTS: Thirteen studies evaluating 54 models and 927,113 patients were included. Machine learning approaches generally outperformed traditional risk scores. Automated machine learning ranked highest (SUCRA 96.6) showed the greatest improvement in the best version analysis (mean difference (MD) 0.28 (95%CrI 0.16-0.40)) and remained superior in the sensitivity analysis (MD 0.30 (95%CrI 0.14-0.45)). Gradient boosting models showed superior performance over the Revised Cardiac Risk Index across analysis (best version: MD 0.20 (95%CrI 0.14-0.26), worst version: MD 0.18 (95%CrI 0.12-0.25), SUCRA 82.4). The Gupta Perioperative Risk for Myocardial Infarction or Cardiac Arrest score outperformed the Revised Cardiac Risk Index in the best version analysis (MD 0.16 (95%CrI 0.01-0.32)). Between-study heterogeneity was low. None of the included studies externally validated their machine learning models and only six were judged to be at low risk of bias. DISCUSSION: Most machine learning models showed better discrimination than traditional risk scores, with automated machine learning and gradient boosting models ranking highest. However, study quality, calibration reporting and absence of external validation limit immediate clinical adoption. Prospective, multicentre evaluation is required before integration of these models into peri-operative practice.

Humans↗

PubMed2026

Predicting gene-specific regulation with transcriptomic and epigenetic single-cell data.

MOTIVATION: Analysis of single cell ATAC-seq and RNA-seq data has allowed to gain unprecedented insights into gene regulation by allowing to define cell type-specific regulatory regions and their effects on gene expression. While powerful, such analysis is challenging due to the inherent sparsity of single cell data. RESULTS: We present a new approach, MetaFR, to learn gene-specific models that link open-chromatin variation from scATAC-seq data to gene expression from scRNA-seq. Using efficient regression trees, we illustrate that accurate expression prediction models can be learned on the single-cell or meta-cell level. Validation was done using fine-mapped eQTLs. Meta-cell models were found to outperform single-cell models for most genes. Comparison to the SOTA method SCARlink revealed advantages of MetaFR in terms of runtime and prediction performance. MetaFR thus allows time-efficient analysis and obtains reliable models of gene expression prediction, which can be used to study gene regulation in any organism for which scRNA-seq and scATAC-seq data is available. AVAILABILITY AND IMPLEMENTATION: MetaFR is available under https://github.com/SchulzLab/MetaFR.

Single-Cell Analysis↗

PubMed2026

Prediction of bacterial protein-compound interactions with only positive samples.

MOTIVATION: Prediction of Compound-Protein Interactions (CPI) in bacteria is crucial to advance various pharmaceutical and chemical engineering fields, including biocatalysis, drug discovery, and industrial processing. However, current CPI models cannot be applied for bacterial CPI prediction due to the lack of curated negative interaction samples. RESULTS: We propose a novel Positive-Unlabeled (PU) learning framework, named BIN-PU, to address this limitation. BIN-PU generates pseudo positive and negative labels from known positive interaction data, enabling effective training of deep learning models for CPI prediction. We also propose a weighted positive loss function that weights to truly positive samples. We have validated BIN-PU coupled with multiple CPI backbone models, comparing the performance with the existing PU models using bacterial cytochrome P450 (CYP) data. Extensive experiments demonstrate the superiority of BIN-PU over the benchmark models in predicting CPIs with only truly positive samples. Furthermore, we have validated BIN-PU on additional bacterial proteins obtained from literature review, human CYP datasets, and uncurated data for its reproducibility. We have also validated the CPI prediction for the uncurated CYP data with biological and biophysical experiments. BIN-PU represents a significant advancement in CPI prediction for bacterial proteins, opening new possibilities for improving predictive models in related biological interaction tasks. AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/datax-lab/CYP.

Bacterial Proteins↗