Genomics, Proteomics & Bioinformatics

Ancestry-related genomic variation may contribute to phenotypic diversity. However, its cellular consequences remain difficult to evaluate. To address this, we developed a human induced pluripotent stem cell (hiPSC)-based framework for investigating such phenotypes. We used the Japanese population as a model of Jomon-related and continental East Asian ancestry admixture. Jomon ancestry, estimated using the Jomon allele score (JAS), was associated with clinical measures, including renal-related traits and serum triglycerides in 34,152 Tohoku Medical Megabank participants. Peripheral blood mononuclear cell transcriptomics of donors from the upper and lower extremes of the JAS distribution (n = 10) suggested group-level differences in immune-related gene expression. To test whether the serum triglyceride association coincided with hepatic cellular phenotypes, we differentiated hiPSCs from these donors into hepatocyte-like cells. Neither intracellular triglycerides nor lipid-related gene expression differed between groups. These findings highlight the value of a genetically characterized hiPSC-based framework for investigating ancestry-associated phenotypes across cellular contexts.

Background: Alpha-mannosidosis (AM) is a debilitating lysosomal storage disorder (LSD) caused by insufficient activity of alpha-mannosidase, an enzyme responsible for cleavage of alpha-linked mannose residues from N-glycan-type oligosaccharides during their degradation. As a result, specific oligosaccharides accumulate in tissues and are also detectable in body fluids. AM is a progressive multi-organ disease for which hematopoietic stem cell transplantation (HSCT) and enzyme replacement therapy (ERT) are therapeutic options, however, treatment results depend considerably on early diagnosis. Therefore, inclusion of AM into newborn screening panels would significantly contribute to improving therapeutic outcome. Methods: A rapid and fully quantitative method for the specific AM oligosaccharide biomarker Man2GlcNAc in dried blood spots (DBS) using ultra-performance liquid chromatography coupled to tandem-mass spectrometry was developed. DBS from 420 controls, 27 AM patients (including five newborn screening samples), and 35 patients with other LSDs were analyzed. Results: A distinct separation in biomarker concentrations was observed between unaffected individuals and untreated AM patients (0.1 - 0.8 vs 3.2 - 11.3 mol Man2GlcNAc/L, p<0.0001). Furthermore, Man2GlcNAc concentrations significantly differed between untreated patients and those on ERT (n = 17, p<0.0001) or after HSCT (n = 15, p<0.0001), and between both treatment groups (p<0.0001). Moreover, we demonstrated that this method is appropriate for monitoring treatment efficacy by analysis of samples from individual patients before and after initiation of therapy. We retrospectively analyzed residual samples of dried blood spots (DBS) from routine newborn screening that had been stored from patients with later-confirmed AM, which resulted in clear separation from the concentrations observed in a newborn screening control cohort (7.7 - 11.3 vs 0.1 - 0.8 mol Man2GlcNAc/L, p=0.0001). Conclusion: We present a simple and rapid method for quantitative analysis of the specific AM oligosaccharide biomarker Man2GlcNAc, which is remarkably stable compared to enzymatic assays. Thus, the method is useful for selective screening in suspected cases as well as for monitoring the response to different forms of treatment. Furthermore, Man2GlcNAc has the potential to serve as a useful biomarker for newborn screening offering the prospect of earlier treatment initiation, improved therapeutic outcome and higher quality of life for AM patients.

Detecting somatic mutations is a cornerstone of cancer genomics and clinical genotyping, traditionally relying on whole exome (WES) or whole genome sequencing (WGS) data. While RNA sequencing (RNA-seq) is primarily used to assess gene expression, it can also be utilized for somatic variant detection. RNA-seq inherently captures expressed variants, thereby reducing the identification of passenger mutations and mitigating the annotation biases associated with WES. We performed somatic variant calling and cancer driver detection from tumor RNA-seq data from 1,359 RNA-seq samples with matched WGS from the Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium of the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA). Our approach using RNA-seq data, alone, identified at least one putative driver gene in 15 of 16 cancer types, consistent with driver predictions from WGS. We further observed that the variant allele frequency (VAF) of RNA-seq-derived variants reflects their predicted functional impact, providing information specific to transcriptomic data. Because RNA-seq data can be generated and analyzed at lower computational cost and time than WGS or WES, it represents a resource-efficient alternative for cancer driver detection. This study provides an extensive pan-cancer resource of RNA-seq-derived variants from the PCAWG consortium and supports the utility of RNA-seq as a complementary approach for characterizing expressed somatic variation in cancer.

Biomarker discovery from high-dimensional RNA sequencing data remains challenging. Conventional methods such as differential expression analysis, pairwise protein-protein interaction networks, and weighted gene co-expression network analysis suffer from false-positive interactions, transitivity-driven noise, and arbitrary thresholds for feature selection. Addressing these limitations, this study proposed a novel framework, Hypergraph Regularised Fuzzy Rough Gene Selection (HR-FRGS), for knowledge-driven biomarker discovery. This pipeline integrates information-rich protein clustering with entropy filtering and PPI-pruned co-expression interactions to form a dual-layer hypergraph. A hypergraph-based scoring method that combines Random Walk with Restart diffusion and Hypergraph Betweenness Centrality is used to identify genes that are central in the biological network. Furthermore an autonomous fuzzy rough set selection eliminates arbitrary threshold dependency for gene selection. HR-FRGS was applied to four TCGA cancer cohorts: Lung Adenocarcinoma, Head and Neck Cancer, Kidney Clear Cell Carcinoma, and Colon Cancer, which reduced over 60,000 transcripts to compact biomarker panels. Validation using classical Machine Learning algorithms with cross-validation demonstrated that biomarker panels matched or exceeded the classification performance of the full transcriptome (AUC > 0.99, MCC > 0.94) and confirmed generalizability (MCC $\geq$ 0.893). Benchmarking against baseline methods and an ablation study showed the contribution of major parts of the algorithm. Functional enrichment analysis captures established pan-cancer hallmarks and cohort-specific oncogenic mechanisms, confirming the biological relevance of the identified genes.

Although Cinnamomum includes globally important spice and medicinal plants, genome-scale knowledge of Cinnamomum species native to Japan remains limited. The Nansei Islands are an approximately 1,200-km-long archipelago located between the Pacific Ocean and the East China Sea and represent a key biogeographic region shaped by deep-sea barriers such as the Tokara and Kerama Gaps. Here, we integrated chloroplast and nuclear genome data generated in this study with public datasets to examine the phylogenetic relationships of four Cinnamomum species native to the Nansei Islands and ten related species. Chloroplast genomes showed no major structural differences among the four island species, whereas nuclear genome data resolved two distinct evolutionary lineages in the Nansei Islands: C. yabunikkei, C. x durifruticeticola, and C. daphnoides formed a distinct Nansei Islands lineage separate from Sri Lankan, Indonesian, and Taiwanese lineages, whereas C. sieboldii was placed in a Taiwanese lineage. Ancestry estimation indicated that C. x durifruticeticola and C. daphnoides share a common ancestral component, while C. sieboldii exhibited a single homogeneous ancestral component, suggesting reduced ancestral diversity after divergence from a Taiwanese lineage. These findings reveal previously unrecognized genomic differentiation among Japanese Cinnamomum species and suggest that deep-sea barriers, dispersal, and long-term isolation shaped their diversification.

Increasing evidence highlights the important role the oral ecosystem plays in systemic health. Despite the fact that oral diseases affect nearly 3.5 billion people globally, our understanding of the precise drivers of these diseases remains limited. To bridge this gap and provide broader understanding of oral public health, a clinical study involving 595 participants 20-78 years of age was conducted over 8 weeks. Characterization of the oral ecosystem using metabolomics, metagenomics, and targeted immune markers were analyzed in conjunction with demographic, lifestyle, and medical history metadata. This comprehensive approach allowed for the identification of specific links between microbial and metabolic signatures and overall wellness, providing a contemporary baseline to enable the development of personalized prevention and treatment strategies to help safeguard oral and systemic public health.

Chromosome was "self-assembled" into a complex three-dimensional topology in the nucleus, which provided the structural basis for important biological processes such as gene expression regulation and cell differentiation. The current understanding of the three-dimensional organization of the genome is based on high-throughput sequencing and imaging technologies to visualize the conformation of chromatin in its native environment. This study proposes a new research perspective and technical means to use fusion genes to determine the interaction information and three-dimensional structure of chromosomes. This three-dimensional information provided by the fusion gene spectrum not only shows the universality of the spatial layout of chromosomes, but also increases the interpretability of the occurrence of fusion genes. The chromatin conformation capture data of multiple tissues and periods is significantly correlated with the strength of fusion genes. For example, the frequency of trans-interaction between chromosomes 11 and 17 was the highest, and the frequency of fusion gene occurrence corresponding to KMT2A on chromosome 11 was the highest. Therefore, we infer that this structural universality is a common feature of the human genome, which provides a theoretical basis and data for predicting chromosome fusion events.

Phenylketonuria (PKU) is an autosomal recessive disorder caused by PAH gene defects and can cause irreversible neurological damage as early as the fetal period; however, non-invasive prenatal monitoring methods are lacking. In this study, Pah+/- female mice were mated with Pah+/-; male mice and wild-type male mice, respectively. Urine samples were collected longitudinally from pregnant mice at 10 time points during gestation from Day 1 to Day 19. Data-independent acquisition (DIA) quantitative proteomics combined with GO/KEGG analysis, WGCNA, and a dual-strategy LASSO-random forest approach was used to screen candidate biomarkers. The results showed that stable differentially expressed proteins between groups were detectable as early as Day 1, and the differences persisted throughout gestation and exhibited temporal dynamics. Permutation tests indicated that the probability of random generation of the differential protein combination was low (0.04-0.06), suggesting that it was not randomly generated. The intersection of the two strategies yielded five proteins, GINM1, PRG4, LY6A, NTM, and YIPF3, and after including GLO1, a total of six candidate biomarkers were obtained. The candidate proteins had interaction or co-expression associations with 14 proteins involved in PKU mechanisms, with GLO1 serving as a network hub. This study found that the maternal urine proteome can non-invasively reflect the systemic response induced by fetal-origin PKU, providing proof of concept and candidate biomarker resources for non-invasive early-pregnancy screening of PKU.

Nucleosomes regulate DNA accessibility and thereby influence gene expression, DNA repair, and mutagenesis. Although DNA sequence strongly determines nucleosome positioning, the higher-order sequence grammar underlying nucleosome organization and its relationship to cancer-associated mutational and epigenetic processes remain poorly understood. We developed DeepND, an interpretable deep learning framework that distinguishes nucleosomal from inter-nucleosomal DNA and identifies sequence features associated with nucleosome architecture. Our interpretable framework enabled analysis of sequence patterns and identified 210 sequence motifs of 2-16 bp length that were significantly enriched or depleted in nucleosomal DNA, substantially extending the previously characterized nucleosomal motifs. These motifs revealed distinct sequence grammars within nucleosomal footprints and linker regions, including patterns associated with inward- and outward-facing minor grooves. Forty-four of these motifs showed cancer-type-specific enrichment or depletion of somatic mutations, and six motifs were associated with differential DNA methylation levels. In lung and endometrial cancers, mutations exhibited a significant ~10-bp periodic enrichment pattern across distinct minor-groove orientations, consistent with differential sensitivity of mutational and DNA repair processes to nucleosomal rotational positioning. We further identified sequence-specific methylation patterns consistent with reduced accessibility of nucleosomal DNA to DNA methyltransferases, including differential methylation at inward- and outward-facing CpG motifs. Together, these findings provide a sequence-resolved characterization of nucleosome-level organization and its link to cancer-specific mutational processes and epigenetic landscapes.

Micro-RNAs (miRNAs) are key post-transcriptional regulators of gene expression that influence cancer progression and outcome. Whereas transcriptional dysregulation of miRNA abundance underlies abnormal functionality of some miRNAs in cancer, emerging data points to RNA-binding proteins (RBPs) as prominent post-transcriptional regulators of miRNA activity. Here, by modelling the regulon activities of well-characterized miRNA families in RNA-seq data of a comprehensive collection of RBP inhibition experiments, human cell lines and tissues, we report a map of regulatory connections between 34 RBPs and 28 miRNAs. Furthermore, through a global analysis of the abundance as well as the activity of miRNAs in thousands of tumor and control samples from 17 human cancers, we show that RBP-driven regulation of miRNA activity is common in tumors and contributes to the heterogeneity in miRNA activity profiles. We uncover a set of RBPs that regulate the activity of tumor-suppressor and oncogenic miRNAs, including miR-29-3p, miR-17-5p and miR-19-3p. Of particular interest, we describe a pan-cancer negative regulatory role for DDX55 on the activity of the miR-29-3p family, a critical miRNA family with tumor suppressor functions that is involved in most human cancers. Our functional studies confirm that DDX55 inhibition restores the gene-silencing activity of miR-29-3p and reduces cancer cell viability. Overall, our study provides the first pan-cancer investigation of functional regulatory connections between RBPs and miRNAs, and highlights RBPs whose interventional modulation may serve as a new approach to reprogram abnormal miRNA activities in cancer.

Background: Induced pluripotent stem cell (iPSC)-derived kidney organoids hold great promise for disease modeling, drug screening, and regenerative medicine. However, since these organoids are synthetic constructs, it is essential to evaluate how faithfully their constituent cell populations recapitulate the corresponding cell types in the native kidney. Single-cell transcriptomic label-transfer tools, which assign cell-type labels by integrating cells with well-annotated reference data and classifying them, are increasingly used for this purpose. Yet the reliability of the resulting labels - particularly for immature or partially differentiated cells that might have no clear in vivo counterpart - has not been systematically addressed. Methodology: To quantify the reliability of cell-type labels assigned by label-transfer algorithms, we introduce two complementary robustness measures for each cell type - the classification stability score, which assesses label stability under simulated Poisson noise, and the prediction specificity score, which assesses how well the predicted cell-type label probabilities match the assigned labels. We apply this methodology to scRNA-seq datasets from the human fetal kidney and four iPSC-derived kidney organoid protocols, using a mouse fetal kidney dataset as a reference. Results: We find that label-transfer robustness scores are generally high in most human fetal kidney cell types, except for cells of immature epithelial structures. In the organoid-derived cell subpopulations, robustness scores are high for the cap mesenchyme but vary for epithelial lineages according to each protocol's specific differentiation strategy. These observations are consistent across both classification stability and prediction specificity scores, which are generally well correlated with each other. We further validate our approach through a simulated cell-removal experiment, confirming that the proposed measures correctly identify unreliable classifications. Significance: These robustness measures provide a generalizable framework for assessing the reliability of cell-type label transfer in single-cell transcriptomic datasets, and can be extended to other biomedical settings that rely on automated single-cell classification.

Aging is characterized by a progressive loss of proteostasis. Transfer RNAs (tRNAs) are essential regulators of translation, yet their dynamics during aging remain poorly understood due to challenges in sequencing highly modified RNAs. Here we present a benchmarked Nanopore direct RNA sequencing (RNA004 chemistry) resource that profiles the Saccharomyces cerevisiae tRNAome during replicative aging at single-molecule resolution. Using in vitro transcribed tRNA controls, we establish modification detection thresholds and validate key findings with orthogonal Illumina sequencing. While overall tRNA abundance remains largely stable, our resource reveals age-associated terminal A cleavage at the 3' CCA tail of mature tRNAs, targeted T-loop and anticodon modification changes, and single-molecule evidence of modification co-occurrence. This dataset provides a resource for exploring tRNA regulation, translation fidelity, and longevity.

A central question in developmental biology is how spatiotemporal embryo morphological events and cell differentiation are precisely coordinated to eventually develop into a mature organism. Previous research has shown cell positions and asymmetric division stages are related to cell lineage specification since morula stage. However, the detailed spatiotemporal dynamics and histories of embryonic cells and their relations with cell lineage specification remain incompletely understood from the onset of embryo development onward. My study on in-vitro embryos showed that continuous live cell tracking mapped community-like patterns in cell origin and differentiation. Cell positions, cell temporal factors (such as cell division order and cell cycle) and their histories intricately interacted over pre- and peri-implantation stages. These interactions of spatiotemporal cellular activities directed embryo morphological events and asymmetric cell lineage origin and differentiation throughout 2-cell to around 100-cell stage. In conclusion, this study provides comprehensive insights into the cellular spatiotemporal dynamics of cell inheritance and differentiation during pre- and peri-implantation morphological events and cell lineage specification. By longitudinally integrating spatial and temporal parameters relating to early embryogenesis, the findings not only bridge divergent explanations stemmed from different studies in the field but also offers a refined foundation for evaluating embryo potential and improving outcomes in assisted reproductive technologies, stem cell research, and regenerative medicine.

ABSTRACT Objective: Skeletal muscle growth rate differs substantially among diverse pig breeds. In the present study, RNA-seq was performed to identify differentially expressed genes (DEGs) across pig breeds with distinct growth rates. CCND2 showed obvious differential expression among pig breeds. Although CCND2 is essential for cell cycle control, its biological function in skeletal muscle differentiation has rarely been reported. This work aims to identify DEGs in pig breeds with different growth rates and explore CCND2 role in porcine skeletal muscle development. Methods: RNA-seq was performed to identify differentially expressed genes (DEGs) across pig breeds with distinct growth rates. Weighted gene co-expression network analysis (WGCNA) was used to identify gene modules potentially associated with skeletal muscle growth and development. Quantitative reverse transcription polymerase chain reaction (qRT-PCR) analysis was performed to validate the role of CCND2 in skeletal muscle differentiation. Results We identified 5,416, 4,846, and 2,777 DEGs in the Duroc pig (DU) vs. Jiangquan black pig (JQ), DU vs. Laiwu pigs (LW), and JQ vs. LW comparison groups, respectively. WGCNA identified two gene modules (lightgreen and darkmagenta) potentially associated with skeletal muscle growth and development. CCND2 exhibited differential expression in comparisons between DU vs JQ and DU vs LW, with higher expression observed in Duroc pigs. qRT-PCR analysis revealed that overexpression of CCND2 at day 6 (D6) of cell differentiation significantly increased the expression levels of CCND2 gene and markers of myogenic differentiation (p < 0.05). Conversely, knockdown of CCND2 significantly decreased the expression levels of CCND2 gene and myogenic differentiation markers (p < 0.05). Conclusions This study identified breed-specific DEGs and key gene modules in porcine skeletal muscle and verified that CCND2 promotes myogenic differentiation. These findings provide a genetic theoretical basis for further investigations into skeletal muscle growth and development. Keywords pig, skeletal muscle, transcriptome, WGCNA, CCND2

Background: The yak (Bos grunniens) is an essential livestock species in high-altitude alpine ecosystems, serving key roles in meat, milk, and wool production as well as ecological maintenance. However, traditional yak breeding systems face several limitations, including fragmented herd data management, inefficient phenotypic collection, missing pedigree records, and high technical barriers to applying genomic technologies. These factors constrain the widespread application of modern genetic evaluation methods in yak breeding programs. Description: We developed the Yak Genomic Evaluation Platform (YGEP, https://yakbreeding.swun.edu.cn/en/), an integrated digital system for yak genetic selection and herd management. YGEP integrates three core analytical modules: pedigree reconstruction, genotype imputation and genomic breeding value estimation. Benchmarking on 706 yaks showed that GBLUP achieved a prediction accuracy of r = 0.96 for cannon bone circumference (CCB), and KBeagle reached 84.0% imputation accuracy with the combined reference panel. Conclusion: YGEP bridges the gap between advanced genomic analytics and practical yak breeding. By integrating pedigree reconstruction, genotype imputation, and GEBV estimation into a user-friendly cloud platform, YGEP effectively eliminates technical and data bottlenecks. Overall, it provides an accessible, scalable, and standardized solution to advance digital herd management and precision genetic improvement in alpine livestock.

Deciphering the functions of post-translational modifications (PTMs) is a critical bridge connecting large-scale modification proteomics data to mechanistic studies. However, most existing tools for visualizing PTM omics data are limited to site catalogs or single-dimensional feature displays. They lack the capability to simultaneously map user-derived differential modification sites onto multi-dimensional contexts, including protein three-dimensional (3D) structure, evolutionary conservation, functional sites, and disease associations. This limitation makes it difficult for researchers to rapidly assess the biological importance of candidate sites from among a vast number of differentially modified sites. Here, we present PTMExplorer, an interactive platform for the multi-dimensional visualization of protein PTMs. PTMExplorer comprises three core modules: PTM Inspector, built upon ProtVista, provides a multi-track, sequence-feature integrated view incorporating intrinsically disordered region (IDR) prediction (via flDPnn), surface accessibility calculation (via FreeSASA), and UniProt functional annotations; PTM 3D Locator, leveraging the Nightingale/Mol* engine, anchors modification sites onto AlphaFold/Protein Data Bank (PDB) 3D structures through residue mapping via PDBe-SIFTS; and PTM Overview, utilizing the R circlize package, presents a panoramic polar circos plot illustrating modification distribution and inter-group differential regulation. Additionally, three major disease-associated modification databases (PTMD, qPTM, and PhosCancer) are integrated as PTM-Disease Nexus, enabling co-localization comparison between user-defined differential sites and reported disease-related sites. PTMExplorer currently supports eight model organisms, accepts user-uploaded differential analysis results, and provides multi-dimensional annotations and various visualization options (https://www.bioladder.cn/PTMExplorer/). Using a multi-omics dataset from hepatocellular carcinoma (18 patients, 9 modification types) as a case study, we demonstrate the practical utility of PTMExplorer in screening potential biomarkers, revealing multi-modification coordination mechanisms, and distinguishing between absolute and relative quantification patterns.

Protein-cofactor selectivity prediction is important for enzyme annotation, metabolic engineering, and biocatalyst discovery, but it remains challenging because experimentally supported associations are limited and unevenly distributed, and because biologically relevant differences can be subtler than those captured by general protein-ligand interaction models. Here, we present MINT (Multimodal Interaction Network with Teacher supervision), a multimodal framework for cofactor specificity prediction. MINT combines protein sequence features with cofactor sequence and graph representations and is trained with a gradual adaptation strategy that transfers useful information from a pretrained protein-ligand interaction model to the cofactor prediction task. On a fixed balanced held-out test set, MINT achieved the best overall performance among all compared methods (AUC = 0.932), and this ranking was reproduced in an independent family-stratified evaluation at the natural positive rate (pooled AUC = 0.939). Further analyses suggest that the pretrained model provides transferable structural information, while the gradual training scheme helps adapt that information to cofactor specificity. In a case study of the chemically near-identical NAD/NADP pair, MINT recovered 95.0-98.6% of true binders and resolved a single-phosphate-level distinction with direct relevance to engineering enzyme cofactor specificity. These results show that gradual transfer learning is an effective approach to cofactor specificity prediction when annotation is limited.

Amaranthus tricolor is a climate-resilient orphan crop whose betalain pigments contribute to nutritional quality and stress tolerance. However, breeding efforts have traditionally relied on field yield trials due to the limited availability of genomic information and genetic resources. To address this gap, we first used the Illumina and PacBio sequencing platforms to assemble a novel reference genome of A. tricolor, using the Japanese cultivar Bayam. By combining this reference genome with a core collection developed in our previous study, we aimed to identify genomic regions associated with pigmentation-related traits across winter and summer seasonal environments. Betalains are antioxidant phytonutrients that contribute to abiotic stress tolerance, making the regulation of their biosynthesis under heat stress particularly relevant for developing climate-resilient crops such as A. tricolor. As a result, ATR1.0CH03_5131103, which is associated with ATR1.0ch03g000565, was identified under the winter seasonal environment. Meanwhile, transcriptomic profiles in this study revealed that ATR1.0ch03g000565 was differentially expressed under both control and heat stress conditions, suggesting that it may be associated with the regulation of CYP76AD1 expression under optimal conditions. Under the elevated-temperature treatment, transcript levels of CYP76AD1 and 5GT decreased in Am087, coinciding with lower betacyanin-dominated absorbance indices. cDOPA-like homologs were upregulated; however, pigmentation-related absorbance remained reduced. Further molecular experiments, such as CRISPR-Cas9 knockouts or overexpression studies, are necessary to validate the regulatory mechanisms of CYP76AD1 and 5GT under heat stress.

Ribosome profiling is widely used to identify translated small open reading frames (sORFs), but existing prediction models often generalize poorly to newly collected sORF datasets. In addition, many microproteins with strong mass spectrometry (MS) evidence lack support in public Ribo-seq resources, suggesting that Ribo-supported sORF and MS-supported microprotein detection may represent complementary prediction tasks. Here, we developed sORF-Trans2MS, a two-module deep learning framework for predicting Ribo-supported sORFs and MS-supported microproteins. Module I uses RNA-FM representations for upstream, ORF, and downstream regions with a Transformer encoder for Ribo-supported sORF translation prediction. Module II integrates pretrained RNA-FM representations of RNA context with ESM-2 protein representations using multi-scale CNN encoders for predicting translated microproteins supported by MS but not Ribo-seq data. Module I was trained on 9,579 Ribo-supported sORFs and matched background sORFs, while Module II used 14,697 MS-supported (MS++Ribo-) microproteins and matched backgrounds. Module I achieved an AUROC of 0.870 internally and 0.930 on an independent GENCODE dataset. Ablation analysis highlighted upstream RNA context, including a distinct signal around 50 nt upstream of AUG. Module II achieved an AUROC/AUPR of 0.804/0.797 internally and 0.785/0.773 on an independent mass spectrometry dataset. Model interpretation highlighted upstream RNA context and the protein N terminus, while literature-supported microproteins further illustrated the complementary roles of the two modules. Overall, sORF-Trans2MS improves prediction and generalization of Ribo-supported sORFs and extends computational discovery to MS-supported candidates that are not represented in current public Ribo-seq resources.

Biomedical artificial intelligence (AI) increasingly relies on heterogeneous data sources, yet differences in data structure, terminology, evidence quality, and provenance complicate their integration into reliable knowledge resources. Here, we develop an evidence-aware framework for processing and integrating heterogeneous pharmacovigilance data from FDA Adverse Event Reporting System (FAERS) reports, biomedical literature, clinical trials, and electronic health records in Mass General Brigham. The framework combines large language model (LLM)-based information extraction, ontology-driven semantic normalization, cross-source evidence assessment, statistical and machine learning-based prioritization, and ingredient-based adverse drug event (ADE) relationship inference to transform heterogeneous evidence into a structured and evidence-based knowledge resource. The constructed knowledge system contains 11,588 drug nodes, 44,843 ingredient nodes, 3,275 ADE nodes, 993 indication nodes, and more than 2.47 million relationships, with each drug-ADE relationship assigned a confidence score. We further developed a drug-level web interface for accessing the knowledge resource and validated its utility in downstream AI tasks. Specifically, incorporating the developed knowledge resource improved the comprehensiveness, relevance, and overall quality of LLM-based drug-specific ADE synthesis and improved the precision and F1 score of clinical ADE relation extraction. These results demonstrate that AI-assisted processing combined with evidence-aware curation can transform heterogeneous biomedical evidence into reusable, AI-ready knowledge with explicit provenance and evidence strength information. The framework provides a general strategy for integrating heterogeneous biomedical data to support reproducible knowledge construction and downstream biomedical AI applications.