Mol Med. 2025 Feb 20;31(1):70. doi: 10.1186/s10020-025-01128-2.

ABSTRACT

BACKGROUND: Lack of understanding of interstitial lung disease (ILD) associated with systemic sclerosis (SSc) and rheumatoid arthritis (RA) hinders the early and accurate identification of these devastating diseases. Current clinical tools limitations highlight the need to complement them with accessible and non-invasive methods. Accordingly, we focused on identifying useful matrix metalloproteinases (MMPs) and their tissue inhibitors (TIMPs) as new biomarkers with clinical value in the diagnosis and prognosis of RA-ILD+ and SSc-ILD+.

METHODS: Peripheral blood was collected from patients with RA-ILD+ (n = 49) and SSc-ILD+ (n = 38); as well as with RA-ILD- (n = 25), SSc-ILD- (n = 20) and idiopathic pulmonary fibrosis (IPF) (n = 39). MMP-1, MMP-2, MMP-3, MMP-7, MMP-9, MMP-10, MMP-12, TIMP-1, and TIMP-2 serum levels were measured using xMAP Technology.

RESULTS: Concerning early connective tissue disease (CTD)-ILD+ diagnosis, increased MMP-7, MMP-9, MMP-10, and MMP-12 levels were found in RA-ILD+ and SSc-ILD+ patients in relation to RA-ILD- and SSc-ILD- patients, respectively. RA-ILD+ patients showed higher MMP-2 levels and lower TIMP-1 levels than RA-ILD- patients. Interestingly, a reliable utility for identifying ILD in CTD was confirmed for the MMP-2, MMP-7, MMP-9, MMP-10, MMP-12, and TIMP-1 combination in RA and MMP-7, MMP-9, MMP-10, and MMP-12 combinatorial signature in SSc. Regarding accurate CTD-ILD+ diagnosis, RA-ILD+ and SSc-ILD+ patients showed lower MMP-7 and MMP-10 levels than IPF patients. Lower MMP-9 and TIMP-1 levels and higher MMP-3 levels were found in RA-ILD+ compared to IPF. Remarkably, effectively better differentiation between CTD-ILD+ and IPF was confirmed for a 5-biomarker signature consisting of MMP-3, MMP-7, MMP-9, MMP-10, and TIMP-1 in RA as well as for the MMP-7 and MMP-10 combination in SSc. Finally, in RA-ILD+ patients, higher MMP-10 levels were associated with worse pulmonary function, increased MMP-2 levels were related to the treatment with conventional synthetic disease-modifying anti-rheumatic drugs, and decreased TIMP-1 levels were linked with positivity rheumatoid factor status.

CONCLUSIONS: MMPs and TIMPs form combinatorial biomarker signatures with clinical value for non-invasive, early, and accurate diagnosis of RA-ILD+ and SSc-ILD+, constituting promising screening tools in clinical practice.

PMID:39979794 | DOI:10.1186/s10020-025-01128-2

Eur Respir J. 2025 Feb 20:2401114. doi: 10.1183/13993003.01114-2024. Online ahead of print.

ABSTRACT

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is characterized by significant, but poorly understood immune and antibody responses. This study examines the spatial transcriptomes and microenvironmental niches of antibody-producing plasma cells and tertiary lymphoid structures (TLS) in IPF lungs, and the molecular pathways influencing antibody accumulation and pulmonary fibrosis.

METHODS: Explant lung tissues from IPF patients and control normal lungs were used for spatial transcriptome assays and validating RNA-scope and immunofluorescence assays. Fibroblasts derived from IPF and control lungs were examined for their capability to attract plasma cells. Neutralizing antibodies were administered to investigate molecules affecting pulmonary plasma cell accumulation and fibrosis in bleomycin-treated mice.

RESULTS: Human IPF lungs exhibited a remarkably widespread distribution of plasma cells and local antibodies in the fibrotic regions, disseminating from plasma cell-generating TLS. Novel mural cells wrapped the vessels in TLS regions, expressing CCR7 ligands that attracted T cells into TLS to promote plasma cell generation. Distinct IPF-associated fibroblasts further secreted CXCL12, providing an extramedullary niche to foster the dissemination and accumulation of plasma cells in the fibrotic regions. Neutralization of CCR7 ligands or CXCL12 reduced plasma cell and local antibody accumulation in the lungs of bleomycin-treated mice, leading to reduced TGFβ concentrations and alleviated pulmonary fibrosis.

CONCLUSIONS: Plasma cells and local antibodies are widely distributed in the fibrotic regions of IPF lungs. Distinct subsets of IPF-associated mural cells and fibroblasts promote pathological plasma cell and antibody accumulation. These findings have potential implications for strategies aimed at targeting immune and antibody responses to combat IPF.

PMID:39978854 | DOI:10.1183/13993003.01114-2024

Genome Biol. 2025 Feb 20;26(1):33. doi: 10.1186/s13059-025-03497-7.

ABSTRACT

Liquid-liquid phase separation (LLPS) enables the formation of membraneless organelles, essential for cellular organization and implicated in diseases. We introduce catGRANULE 2.0 ROBOT, an algorithm integrating physicochemical properties and AlphaFold-derived structural features to predict LLPS at single-amino-acid resolution. The method achieves high performance and reliably evaluates mutation effects on LLPS propensity, providing detailed predictions of how specific mutations enhance or inhibit phase separation. Supported by experimental validations, including microscopy data, it predicts LLPS across diverse organisms and cellular compartments, offering valuable insights into LLPS mechanisms and mutational impacts. The tool is freely available at https://tools.tartaglialab.com/catgranule2 and https://doi.org/10.5281/zenodo.14205831 .

PMID:39979996 | DOI:10.1186/s13059-025-03497-7

BMC Vet Res. 2025 Feb 20;21(1):81. doi: 10.1186/s12917-025-04517-1.

ABSTRACT

BACKGROUND: The therapeutic potential of exosomes derived from mesenchymal stem cells (MSCs) is increasingly recognized in veterinary medicine. This study explored the feasibility of a microcarrier-based three-dimensional (3D) culture system for producing the exosomes (cEXO). Investigations were conducted to enhance production efficiency, ensure stability, and evaluate the therapeutic potential of cEXO for anti-inflammatory applications while assessing their safety profile.

RESULTS: The microcarrier-based 3D culture system improved efficient production of cEXO, yielding exosomes with acceptable profiles, including a size of approximately 81.22 nm, negative surface charge, and high particle concentration (1.32 × 109 particles/mL). Confocal imaging proved dynamic changes in cell viability across culture phases, highlighting the challenges of maintaining cell viability during repeated exosome collection cycles. Characterization via transmission electron microscopy, nanoparticle tracking analysis, and zeta-potential measurements confirmed the stability and functionality of cEXO, particularly when stored at -20 °C. Functional assays showed that cEXO exerted significant anti-inflammatory activity in RAW264.7 macrophages in an inverse dose-dependent manner, with no observed cytotoxicity to fibroblasts or macrophages. Acute toxicity testing in rats revealed no adverse effects on clinical parameters, organ health, or body weight, supporting the safety of cEXO for therapeutic use.

CONCLUSIONS: This study highlights the potential of a microcarrier-based 3D culture system for scalable cEXO production with robust anti-inflammatory activity, stability, and safety profiles. These findings advance the development of cEXO-based therapies and support their application in veterinary regenerative medicine.

PMID:39979916 | DOI:10.1186/s12917-025-04517-1

BMC Genomics. 2025 Feb 20;26(1):169. doi: 10.1186/s12864-025-11309-2.

ABSTRACT

Common bean (Phaseolus vulgaris), a staple food in Latin America and Africa, serves as a vital source of energy, protein, and essential minerals for millions of people. However, genomics knowledge that breeders could leverage for improvement of this crop is scarce. We have developed and validated a comparative genomics approach to predict conserved transcription factor binding sites (TFBS) in common bean and studied gene regulatory networks. We analyzed promoter regions and identified TFBS for 12,631 bean genes with an average of 6 conserved motifs per gene. Moreover, we discovered a statistically significant relationship between the number of conserved motifs and amount of available experimental evidence of gene regulation. Notably, ERF, MYB, and bHLH transcription factor families dominated conserved motifs, with implications for starch biosynthesis regulation. Furthermore, we provide gene regulatory data as a resource that can be interrogated for the regulatory landscape of any set of genes. Our results underscore the significance of TFBS conservation in legumes and aligns with the notion that core genes often exhibit a more conserved regulatory makeup. The study demonstrates the effectiveness of a comparative genomics approach for addressing genome information gaps in non-model organisms and provides valuable insights into the regulatory networks governing starch biosynthesis genes that can support crop improvement programs.

PMID:39979816 | DOI:10.1186/s12864-025-11309-2

BMC Plant Biol. 2025 Feb 20;25(1):232. doi: 10.1186/s12870-025-06248-9.

ABSTRACT

BACKGROUND: Ca2+ and H2O2 are second messengers that regulate a wide range of cellular events in response to different environmental and developmental cues. In plants, stress-induced H2O2 has been shown to initiate characteristic Ca2+ signatures; however, a clear picture of the molecular connection between H2O2-induced Ca2+ signals and H2O2-induced cellular responses is missing, particularly in cereal crops such as barley. Here, we employed RNA-seq analyses to identify transcriptome changes in roots and leaves of barley after H2O2 treatment under conditions that inhibited the formation of cytosolic Ca2+ transients. To that end, plasma membrane Ca2+ channels were blocked by LaCl3 application prior to stimulation of barley tissues with H2O2.

RESULTS: We examined the expression patterns of 4246 genes that had previously been shown to be differentially expressed upon H2O2 application. Here, we further compared their expression between H2O2 and LaCl3 + H2O2 treatment. Genes showing expression patterns different to the previous study were considered to be Ca2+-dependent H2O2-responsive genes. These genes, numbering 331 in leaves and 1320 in roots, could be classified in five and four clusters, respectively. Expression patterns of several genes from each cluster were confirmed by RT-qPCR. We furthermore performed a network analysis to identify potential regulatory paths from known Ca2+-related genes to the newly identified Ca2+-dependent H2O2 responsive genes, using the recently described Stress Knowledge Map. This analysis indicated several transcription factors as key points of the responses mediated by the cross-talk between H2O2 and Ca2+.

CONCLUSION: Our study indicates that about 70% of the H2O2-responsive genes in barley roots require a transient increase in cytosolic Ca2+ concentrations for alteration in their transcript abundance, whereas in leaves, the Ca2+ dependency was much lower at about 33%. Targeted gene analysis and pathway modeling identified not only known components of the Ca2+ signaling cascade in plants but also genes that are not yet connected to stimuli-associated signaling. Potential key transcription factors identified in this study can be further analyzed in barley and other crops to ultimately disentangle the underlying mechanisms of H2O2-associated signal transduction mechanisms. This could aid breeding for improved stress resistance to optimize performance and productivity under increasing climate challenges.

PMID:39979811 | DOI:10.1186/s12870-025-06248-9

Mol Syst Biol. 2025 Feb 20. doi: 10.1038/s44320-025-00086-5. Online ahead of print.

ABSTRACT

Understanding the biochemistry behind whole-organism traits such as flowering time is a longstanding challenge, where mathematical models are critical. Very few models of plant gene circuits use the absolute units required for comparison to biochemical data. We refactor two detailed models of the plant circadian clock from relative to absolute units. Using absolute RNA quantification, a simple model predicted abundant clock protein levels in Arabidopsis thaliana, up to 100,000 proteins per cell. NanoLUC reporter protein fusions validated the predicted levels of clock proteins in vivo. Recalibrating the detailed models to these protein levels estimated their DNA-binding dissociation constants (Kd). We estimate the same Kd from multiple results in vitro, extending the method to any promoter sequence. The detailed models simulated the Kd range estimated from LUX DNA-binding in vitro but departed from the data for CCA1 binding, pointing to further circadian mechanisms. Our analytical and experimental methods should transfer to understand other plant gene regulatory networks, potentially including the natural sequence variation that contributes to evolutionary adaptation.

PMID:39979593 | DOI:10.1038/s44320-025-00086-5

NPJ Sci Food. 2025 Feb 20;9(1):24. doi: 10.1038/s41538-025-00385-z.

ABSTRACT

Amylase/trypsin-inhibitors (ATIs) are triggers for wheat-related disorders like baker's asthma and non-celiac wheat sensitivity. With the rise of wheat-related disorders among the population, the hypothesis that breeding may have resulted in changes in the protein composition of wheat was put forward. The ATI content of 14 German common wheat landraces and six modern varieties harvested in three consecutive years was analyzed by liquid chromatography-tandem mass spectrometry, and the inhibitory activity against α-amylase was measured with an enzymatic assay. The mean ATI content and proportion of crude protein of both groups did not differ. There were also only small differences in the content and proportion of single ATIs. The mean values for the inhibitory activity of both groups were also similar. These results indicate that breeding might not have led to changes in the protein composition and landraces are unlikely to be better tolerated than modern varieties.

PMID:39979280 | DOI:10.1038/s41538-025-00385-z

Adv Protein Chem Struct Biol. 2025;144:33-76. doi: 10.1016/bs.apcsb.2024.10.011. Epub 2025 Jan 31.

ABSTRACT

Immunotherapy, harnessing components like antibodies, cells, and cytokines, has become a cornerstone in treating diseases such as cancer and autoimmune disorders. Therapeutic antibodies, in particular, have transformed modern medicine, providing a targeted approach that destroys disease-causing cells while sparing healthy tissues, thereby reducing the side effects commonly associated with chemotherapy. Beyond oncology, these antibodies also hold promise in addressing chronic infections where conventional therapeutics may fall short. However, antibodies identified through in vivo or in vitro methods often require extensive engineering to enhance their therapeutic potential. This optimization process, aimed at improving affinity, specificity, and reducing immunogenicity, is both challenging and costly, often involving trade-offs between critical properties. Traditional methods of antibody development, such as hybridoma technology and display techniques, are resource-intensive and time-consuming. In contrast, computational approaches offer a faster, more efficient alternative, enabling the precise design and analysis of therapeutic antibodies. These methods include sequence and structural bioinformatics approaches, next-generation sequencing-based data mining, machine learning algorithms, systems biology, immuno-informatics, and integrative approaches. These approaches are advancing the field by providing new insights and enhancing the accuracy of antibody design and analysis. In conclusion, computational approaches are essential in the development of therapeutic antibodies, significantly improving the precision and speed of discovery, optimization, and validation. Integrating these methods with experimental approaches accelerates therapeutic antibody development, paving the way for innovative strategies and treatments for various diseases ranging from cancers to autoimmune and infectious diseases.

PMID:39978970 | DOI:10.1016/bs.apcsb.2024.10.011

Curr Opin Biotechnol. 2025 Feb 19;92:103268. doi: 10.1016/j.copbio.2025.103268. Online ahead of print.

ABSTRACT

Bacterial microcompartments (BMCs) are protein shells encapsulating multiple enzymes of a metabolic pathway. Interpretations of early experiments on carboxysomes led to the narrative that transport of small gases (CO2, O2) across the shell membrane is restricted. Since then, this notion has been largely contradicted by studies of engineered shells, although these shell constructs lack important proteins present in the native BMCs, altering the synthetic shells' topology, surface and mechanical properties. We discuss here an updated model of gas permeability that informs the design of engineered shells for catalysis on gas substrates and outline how nonshell suprastructures of BMC shell proteins could be used in formulating sustainable biomaterials for hydrogen generation via methane pyrolysis and for other greenhouse gas mitigations.

PMID:39978296 | DOI:10.1016/j.copbio.2025.103268

Drug Saf. 2025 Feb 20. doi: 10.1007/s40264-025-01520-1. Online ahead of print.

ABSTRACT

BACKGROUND: Drug adverse events (AEs) represent a significant public health concern. US Food and Drug Administration (FDA) drug labeling documents are an essential resource for studying drug safety such as assessing a drug's likelihood to cause certain organ toxicities; however, the manual extraction of AEs is labor-intensive, requires specialized expertise, and is challenging to maintain, due to frequent updates of the labeling documents.

OBJECTIVE: To automate the extraction of AE data from FDA drug labeling documents, we developed a workflow based on AskFDALabel, a large language model (LLM)-powered framework, and its demonstration in drug safety studies.

METHODS: This framework incorporates a retrieval-augmented generation (RAG) component based on FDALabel to enhance standard LLM inference. Key steps include (1) selection of a task-specific template, (2) FDALabel database querying, and (3) content preparation for LLM processing. We evaluated the performance of the framework in three benchmark experiments, including drug-induced liver injury (DILI) classification, drug-induced cardiotoxicity (DICT) classification, and AE term recognition.

RESULTS: AskFDALabel achieved F1-scores of 0.978 for DILI, 0.931 for DICT, and 0.911 for AE annotation, outperforming other traditional methods. It also provided cited labeling content and detailed explanations, facilitating manual verification.

CONCLUSION: AskFDALabel exhibited high consistency with human AE annotation, particularly in classifying and profiling DILI and DICT. Thus, it can significantly enhance the efficiency and accuracy of AE annotation, with promising potential for advanced AE surveillance and drug safety research.

PMID:39979771 | DOI:10.1007/s40264-025-01520-1

Lancet Oncol. 2025 Feb 17:S1470-2045(24)00737-X. doi: 10.1016/S1470-2045(24)00737-X. Online ahead of print.

ABSTRACT

BACKGROUND: We proposed in 2005 that androgens replace oestrogens as the driver steroids in a subgroup of triple-negative breast cancer (TNBC) with androgen receptor (AR) expression called molecular apocrine (MA) or luminal androgen receptor (LAR). Here, we report the analysis of a clinical trial evaluating the antitumour activity of the anti-androgen darolutamide in MA breast cancer. Our aim was to assess the clinical benefit in patients with AR-positive TNBCs defined by immunohistochemistry and by RNA profiling.

METHODS: In this multicentre, non-comparative, randomised, phase 2 trial, women aged 18 years or older with an Eastern Cooperative Oncology Group performance status of 0-1 and with advanced TNBC that was previously treated with a maximum of one line of chemotherapy were recruited from 45 hospitals in France. After central confirmation of TNBC status and AR positivity (≥10%; SP107 antibody), participants were randomly assigned (2:1) to receive darolutamide 600 mg orally twice daily or capecitabine minimum 1000 mg/m2 twice daily for 2 weeks on and 1 week off, until disease progression, unacceptable toxicity, lost to follow-up, or withdrawal of consent. Randomisation was done centrally using the minimisation procedure and was stratified according to the number of previous lines of chemotherapy. Transcriptomic analysis was used to classify tumours into groups with high and low AR activity (MAhigh and MAlow). The primary clinical endpoint was clinical benefit rate at 16 weeks (confirmed complete response, partial response, or stable disease). The primary translational endpoint was clinical benefit rate in the darolutamide group in MAhigh tumours versus all other tumours. Analyses were done per protocol. This trial is registered with ClinicalTrials.gov (NCT03383679), and is closed to recruitment.

FINDINGS: Between April 9, 2018, and July 20, 2021, 254 women were screened and 94 were randomly assigned to darolutamide (n=61) or capecitabine (n=33), of whom 90 were evaluable for efficacy analyses. Median follow-up at the data cutoff on July 20, 2022, was 22·5 months (IQR 16·5-30·5). The clinical benefit rate was 29% (17 of 58; 90% CI 19-39) with darolutamide and 59% (19 of 32; 90% CI 45-74) with capecitabine. In patients treated with darolutamide, the clinical benefit rate was 57% (12 of 21; 95% CI 36-78) in MAhigh tumours, and 16% (five of 31; 95% CI 3-29; p=0·0020) in other tumours. The most common grade 3 adverse events were palmar-plantar erythrodysaesthesia syndrome (none of 60 in the darolutamide group vs two [6%] of 33 in the capecitabine group), and headache (three [5%] vs none). No grade 4 or 5 adverse events were observed. Drug-related serious adverse events occurred in three (5%) patients in the darolutamide group and three (9%) in the capecitabine group, which were toxicoderma (n=1) and headache (n=2) in the darolutamide group, and diarrhoea, general physical deterioration, and hepatic cytolysis in the capecitabine group (n=1 each).

INTERPRETATION: This study did not reach its prespecified endpoint for darolutamide activity in patients with triple-negative breast cancer selected on the basis of immunohistochemistry for AR. Further studies selecting patients based on RNA profiling might allow better identification of tumours sensitive to anti-androgens.

FUNDING: Bayer and Fondation Bergonié.

PMID:39978376 | DOI:10.1016/S1470-2045(24)00737-X

Am J Manag Care. 2025 Feb 1;31(2):e47-e55. doi: 10.37765/ajmc.2025.89683.

ABSTRACT

OBJECTIVES: To evaluate medical policy determinations for pharmacogenetic (PGx) testing for 65 clinically relevant drug-gene pairs and evidence cited to support determinations across major US health plans and laboratory benefit managers (LBMs).

STUDY DESIGN: Landscape analysis of available PGx medical policies to determine coverage status of certain drug-gene pairs.

METHODS: PGx medical policies as of February 1, 2024, were ascertained through Policy Reporter for top national insurers, LBMs, and the Palmetto GBA Molecular Diagnostic Services (MolDX) Program, which determines whether a molecular diagnostic test is covered by Medicare. Data elements included date of last policy update, coverage status for each drug-gene pair, and evidence cited for or against coverage. A drug-gene pair was considered covered if the policy indicated that a PGx test was deemed medically necessary and/or meets coverage criteria.

RESULTS: Policies from 8 insurers, 3 LBMs, and MolDX were available and reviewed. MolDX covered all 65 individual drug-gene pairs, followed by Avalon Healthcare Solutions (n = 50) and UnitedHealthcare (n = 45); these 3 also covered multigene panels. Eight policies covered 10 or fewer drug-gene pairs. HLA-B*57:01 testing prior to abacavir initiation and HLA-B*15:02 testing prior to carbamazepine initiation were covered across all policies. Drug-gene pairs with Clinical Pharmacogenetics Implementation Consortium guidelines and/or included in the FDA's Table of Pharmacogenetic Associations Section 1 were more commonly covered. Society guidelines were the most frequently cited evidence (413 times), and cost-effectiveness studies were infrequently cited (43 times).

CONCLUSIONS: We found significant variability in medical policy determinations and evidence cited for clinically relevant PGx tests among major US health insurers and LBMs. A collaborative effort between payers and the PGx community to standardize evidence evaluation may lead to more consistent coverage and improve patient access to PGx tests meeting evidence requirements.

PMID:39977287 | DOI:10.37765/ajmc.2025.89683

J Clin Endocrinol Metab. 2025 Feb 20:dgaf099. doi: 10.1210/clinem/dgaf099. Online ahead of print.

ABSTRACT

BACKGROUND: Highly effective CFTR modulators, such as elexacaftor/tezacaftor/ivacaftor (ETI), herald a new era in therapeutic strategy of cystic fibrosis (CF). ETI impact on glucose tolerance remains controversial.

METHODS: All the participants underwent a baseline oral glucose tolerance test (OGTT) before ETI initiation (M0) and 12 months (M12), and at 24 months if possible. The cohort was stratified in two subgroups based on the baseline OGTT: normal glucose tolerance (NGT) and abnormal glucose tolerance (AGT) defined by impaired fasting glucose or impaired glucose tolerance or diabetes not requiring insulin treatment.

RESULTS: We included 106 adolescents with CF (age 14.1±1.5 years), 75 with NGT, 31 with AGT. The baseline characteristics of the two groups were similar except for a higher glucose level at 1 and 2-h OGTT in the AGT group. ETI induced an increase in BMIz-score and in Forced Expiratory Volume in 1 second (FEV1) (p<0.001). After 12 months, participants with NGT did not experience any change of 1-h and 2-h glucose. By contrast, those with AGT displayed a reduction of 2-h glucose at M12 (p=0.006). 15out of the 31 (48%) adolescents in the AGT group reversed to NGT but 9/75 (17%) in the NGT group progressed to AGT. 3 participants with CF related diabetes at baseline reversed to AGT. 1-hour glucose concentrations at or above 8.7 mmol/L (157mg/dL) during baseline OGTT had 80% sensitivity to identify those with AGT at 12 months (OR 1.51 [1.20, 1.92], p=0.001). 20 participants had a 24-month OGTT that confirmed preserved insulin secretion.

CONCLUSION: ETI may improve glucose tolerance in adolescents with CF by preserving insulin secretion. 1-hour glucose during the OGTT helps to detect risk for AGT after ETI treatment.

PMID:39977216 | DOI:10.1210/clinem/dgaf099

JCO Clin Cancer Inform. 2025 Feb;9:e2400198. doi: 10.1200/CCI-24-00198. Epub 2025 Feb 20.

ABSTRACT

PURPOSE: Primary barriers to application of immune checkpoint inhibitor (ICI) therapy for cancer include severe side effects (such as potentially life threatening pneumonitis [PN]), which can cause the discontinuation of treatment. Predicting which patients may develop PN while on ICI would improve both safety and potential efficacy because treatments could be safely administered for longer or discontinued before severe toxicity.

METHODS: Starting from a cohort of 3,351 patients with cancer who received previous ICI therapy at the Vanderbilt University Medical Center, we curated 2,700 contrast chest computed tomography (CT) volumes for 671 patients. Three different pure imaging models predicted the potential for PN using only a single time point before the first ICI dose.

RESULTS: The first model used 109 radiomics features only and achieved an AUC of 0.747 (CI, 0.705 to 0.789) with a positive predictive value (PPV) of 0.244 (CI, 0.211 to 0.276) at a sensitivity of 0.553 (CI, 0.485 to 0.621) using mainly features describing the global lung properties. The second model used a convolutional neural network (CNN) on the raw CTs to improve to an AUC of 0.819 (CI, 0.781 to 0.857) with a PPV of 0.244 (CI, 0.203 to 0.284) at a sensitivity of 0.743 (CI, 0.681 to 0.806). The third model combined both radiomics and deep learning but, with an AUC of 0.829 (CI, 0.797 to 0.862) and a PPV of 0.254 (CI, 0.228 to 0.281) at a sensitivity of 0.780 (CI, 0.721 to 0.840), did not show a significant improvement on the CNN-only model.

CONCLUSION: This new model suggests the utility of deep learning in PN prediction over traditional pure radiomics and promises better management for patients receiving ICI and the ability to better stratify patients in immunotherapy drug trials.

PMID:39977708 | DOI:10.1200/CCI-24-00198

Hum Reprod Update. 2025 Feb 20:dmaf002. doi: 10.1093/humupd/dmaf002. Online ahead of print.

ABSTRACT

BACKGROUND: Ovarian aging occurs earlier than the aging of many other organs and has a lasting impact on women's overall health and well-being. However, effective interventions to slow ovarian aging remain limited, primarily due to an incomplete understanding of the underlying molecular mechanisms and drug targets. Recent advances in omics data resources, combined with innovative computational tools, are offering deeper insight into the molecular complexities of ovarian aging, paving the way for new opportunities in drug discovery and development.

OBJECTIVE AND RATIONALE: This review aims to synthesize the expanding multi-omics data, spanning genome, transcriptome, proteome, metabolome, and microbiome, related to ovarian aging, from both tissue-level and single-cell perspectives. We will specially explore how the analysis of these emerging omics datasets can be leveraged to identify novel drug targets and guide therapeutic strategies for slowing and reversing ovarian aging.

SEARCH METHODS: We conducted a comprehensive literature search in the PubMed database using a range of relevant keywords: ovarian aging, age at natural menopause, premature ovarian insufficiency (POI), diminished ovarian reserve (DOR), genomics, transcriptomics, epigenomics, DNA methylation, RNA modification, histone modification, proteomics, metabolomics, lipidomics, microbiome, single-cell, genome-wide association studies (GWAS), whole-exome sequencing, phenome-wide association studies (PheWAS), Mendelian randomization (MR), epigenetic target, drug target, machine learning, artificial intelligence (AI), deep learning, and multi-omics. The search was restricted to English-language articles published up to September 2024.

OUTCOMES: Multi-omics studies have uncovered key mechanisms driving ovarian aging, including DNA damage and repair deficiencies, inflammatory and immune responses, mitochondrial dysfunction, and cell death. By integrating multi-omics data, researchers can identify critical regulatory factors and mechanisms across various biological levels, leading to the discovery of potential drug targets. Notable examples include genetic targets such as BRCA2 and TERT, epigenetic targets like Tet and FTO, metabolic targets such as sirtuins and CD38+, protein targets like BIN2 and PDGF-BB, and transcription factors such as FOXP1.

WIDER IMPLICATIONS: The advent of cutting-edge omics technologies, especially single-cell technologies and spatial transcriptomics, has provided valuable insights for guiding treatment decisions and has become a powerful tool in drug discovery aimed at mitigating or reversing ovarian aging. As technology advances, the integration of single-cell multi-omics data with AI models holds the potential to more accurately predict candidate drug targets. This convergence offers promising new avenues for personalized medicine and precision therapies, paving the way for tailored interventions in ovarian aging.

REGISTRATION NUMBER: Not applicable.

PMID:39977580 | DOI:10.1093/humupd/dmaf002

PLoS One. 2025 Feb 20;20(2):e0317461. doi: 10.1371/journal.pone.0317461. eCollection 2025.

ABSTRACT

Coal and gas outburst (CGO) is a complicated natural disaster in underground coal mine production. In constructing smart mines, predicting CGO risks efficiently and accurately is necessary. This paper proposes a CGO risk prediction method based on data augmentation and a neuroevolution algorithm, denoted as ANEAT. First, sample features are applied to the transfer function using a pointwise intensity transformation to obtain new feature samples. It solves the problems of imbalanced data samples and insufficient diversity. Second, the feature importance score sorting and Sparse PCA dimensionality reduction are performed on the data-augmented samples. It provides the initial genome code for the evolutionary neural network. Finally, an evolutionary neural network for CGO prediction is constructed through population initialization, fitness evaluation, species differentiation, genome mutation, and recombination. The optimal phenotype is obtained in the evolutionary generations. In the experiment, we verify the effectiveness of ANEAT from multiple aspects such as data augmentation effectiveness analysis, deep learning model comparison, swarm intelligence optimization algorithm comparison, and other method comparisons. The results show that the MAE, RMSE, and EVAR indexes of ANEAT on the test set are 0.0816, 0.1322, and 0.8972, respectively. It has the optimal CGO prediction effect. ANEAT realizes the high-precision mapping of feature parameters and outburst risk with a lightweight network architecture, which can be well applied to CGO prediction.

PMID:39977390 | DOI:10.1371/journal.pone.0317461

Bioinformatics. 2025 Feb 20:btaf078. doi: 10.1093/bioinformatics/btaf078. Online ahead of print.

ABSTRACT

MOTIVATION: S-sulfhydration, a crucial post-translational protein modification, is pivotal in cellular recognition, signaling processes, and the development and progression of cardiovascular and neurological disorders, so identifying S-sulfhydration sites is crucial for studies in cell biology. Deep learning shows high efficiency and accuracy in identifying protein sites compared to traditional methods that often lack sensitivity and specificity in accurately locating nonsulfhydration sites. Therefore, we employ deep learning methods to tackle the challenge of pinpointing S-sulfhydration sites.

RESULTS: In this work, we introduce a deep learning approach called Sul-BertGRU, designed specifically for predicting S-sulfhydration sites in proteins, that integrates multi-directional gated recurrent unit (GRU) and BERT. First, Sul-BertGRU proposes an information entropy-enhanced BERT (IE-BERT) to preprocess protein sequences and extract initial features. Subsequently, confidence learning is employed to eliminate potential S-sulfhydration samples from the nonsulfhydration samples and select reliable negative samples. Then, considering the directional nature of the modification process, protein sequences are categorized into left, right, and full sequences centred on cysteines. We build a multi-directional GRU to enhance the extraction of directional sequence features and model the details of the enzymatic reaction involved in S-sulfhydration. Ultimately, we apply a parallel multi-head self-attention mechanism alongside a convolutional neural network (CNN) to deeply analyze sequence features that might be missed at a local level. Sul-BertGRU achieves sensitivity, specificity, precision, accuracy, Matthews correlation coefficient, and area under the curve scores of 85.82%, 68.24%, 74.80%, 77.44%, 55.13%, and 77.03%, respectively. Sul-BertGRU demonstrates exceptional performance and proves to be a reliable method for predicting protein S-sulfhydration sites.

AVAILABILITY AND IMPLEMENTATION: The source code and data are available at https://github.com/Severus0902/Sul-BertGRU/.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

PMID:39977366 | DOI:10.1093/bioinformatics/btaf078

Proc Natl Acad Sci U S A. 2025 Feb 25;122(8):e2411492122. doi: 10.1073/pnas.2411492122. Epub 2025 Feb 20.

ABSTRACT

Longitudinal imaging data are routinely acquired for health studies and patient monitoring. A central goal in longitudinal studies is tracking relevant change over time. Traditional methods remove nuisance variation with custom pipelines to focus on significant changes. In this work, we present a machine learning-based method that automatically ignores irrelevant changes and extracts the time-varying signal of interest. Our method, called Learning-based Inference of Longitudinal imAge Changes (LILAC), performs a pairwise comparison of longitudinal images in order to make a temporal difference prediction. LILAC employs a convolutional Siamese architecture to extract feature pairs, followed by subtraction and a bias-free fully connected layer to learn meaningful temporal image differences. We first showcase LILAC's ability to capture key longitudinal changes by simply training it to predict the temporal ordering of images. In our experiments, temporal ordering accuracy exceeded 0.98, and predicted time differences were strongly correlated with actual changes in relevant variables (Pearson Correlation Coefficient r = 0.911 with embryo phase change, and r = 0.875 with time interval in wound healing). Next, we trained LILAC to explicitly predict specific targets, such as the change in clinical scores in patients with mild cognitive impairment. LILAC models achieved over a 40% reduction in root mean square error compared to baseline methods. Our empirical results demonstrate that LILAC effectively localizes and quantifies relevant individual-level changes in longitudinal imaging data, offering valuable insights for studying temporal mechanisms or guiding clinical decisions.

PMID:39977323 | DOI:10.1073/pnas.2411492122

Science. 2025 Feb 21;387(6736):eadp2407. doi: 10.1126/science.adp2407. Epub 2025 Feb 21.

ABSTRACT

Clinical diagnosis typically incorporates physical examination, patient history, various laboratory tests, and imaging studies but makes limited use of the human immune system's own record of antigen exposures encoded by receptors on B cells and T cells. We analyzed immune receptor datasets from 593 individuals to develop MAchine Learning for Immunological Diagnosis, an interpretive framework to screen for multiple illnesses simultaneously or precisely test for one condition. This approach detects specific infections, autoimmune disorders, vaccine responses, and disease severity differences. Human-interpretable features of the model recapitulate known immune responses to severe acute respiratory syndrome coronavirus 2, influenza, and human immunodeficiency virus, highlight antigen-specific receptors, and reveal distinct characteristics of systemic lupus erythematosus and type-1 diabetes autoreactivity. This analysis framework has broad potential for scientific and clinical interpretation of immune responses.

PMID:39977494 | DOI:10.1126/science.adp2407