IEEE/ACM Transactions on Computational Biology and Bioinformatics

1Drug--drug interactions between biotech and small-molecule drugs play a critical role in medication safety and therapeutic efficacy. However, most existing computational DDI prediction methods focus primarily on interactions between small-molecule drugs, leaving biotech-small-molecule interactions comparatively underexplored. In this study, we propose B-SMART-Former, an explainable deep learning framework for predicting interaction types between biotech and small-molecule drugs. The proposed framework integrates ChemBERTa embeddings and Morgan molecular fingerprints for small molecules with ProtBERT embeddings for biotech drugs, eliminating the need for similarity-based features while leveraging complementary molecular representations. These multimodal features are processed by a hybrid architecture that combines Transformer-based self-attention, residual convolutional learning, and a multi-layer perceptron classifier to capture both global contextual dependencies and local discriminative patterns. The model is formulated as a multi-class classification task and evaluated using stratified 10-fold cross-validation. To improve model transparency, Integrated Gradients is employed as a post-hoc explainability method to identify the molecular features that contribute most strongly to each prediction. Experimental results demonstrate that B-SMART-Former achieves a micro-averaged AUROC of 0.9978 and an AUPR of 0.9682 while relying solely on intrinsic molecular representations, remaining competitive with similarity-based approaches. The proposed framework offers an effective and explainable solution for biotech-small-molecule DDI prediction and provides a practical foundation for future computational drug interaction studies.

Cervical cancer represents a pressing global health challenge, emphasizing the critical need for accurate and timely diagnostic methods to facilitate effective treatment and improve survival rates. In response to this challenge, the study presents CerViX-Net, an innovative classification framework designed to advance cervical cancer detection through enhanced computational efficiency and diagnostic accuracy. The development of CerViX-Net is motivated by the limitations of traditional diagnostic models, particularly in handling the computational and memory demands of large-scale data, while ensuring precise feature extraction and classification. CerViX-Net employs a hybrid deep learning architecture that combines the capabilities of ResNet50, EfficientNet-B0, and a Modified Vision Transformer (ViT) module. The ResNet50 branch extracts hierarchical features through stacked convolutional and identity blocks. In another path, the modified ViT module transforms image patches via linear projection, augments them with positional and class embeddings, and processes them using Parallel Transformer Encoder layers to model contextual relationships. Concurrently, EfficientNet-B0 utilizes MBConv blocks to extract multi-scale representations. The feature outputs from all three branches are integrated and passed through a classification head consisting of dropout layers and dense layers to ensure robust and accurate predictions. The proposed framework is rigorously evaluated on the Mendeley LBC dataset, achieving exceptional performance metrics with an accuracy of 99.69%, precision of 99.28%, recall of 99.48%, and an F1-score of 99.52%. The robustness of CerViX-Net is further validated on the SIPaKMeD and Herlev Pap Smear datasets, where it demonstrates comparable excellence, underscoring its efficacy and adaptability across diverse cytology datasets. Statistical validation using Friedman's test further reinforces its superiority over competing methods.

Cancer-associated signaling pathways often exhibit abnormal activation under simultaneous dysregulation of multiple molecular components. This study presents a probabilistic temporal Dynamic Bayesian Network (DBN)-based framework for analyzing multi-fault behaviour and intervention response in Growth Factor (GF) and Mitogen-Activated Protein Kinase (MAPK) signaling pathways. Unlike deterministic Boolean propagation, the proposed model represents each pathway component through an activation probability and propagates these probabilities over discrete time steps using soft-logic update rules. One-, two-, three-, and four-fault scenarios were systematically evaluated under a common lowest-burden input vector. The resulting output probabilities were summarized using an encoded pathway-burden score, and known-drug combinations were ranked using efficiency scores relative to no-intervention baselines. Pareto analysis was further used to balance intervention efficiency against drug-vector burden, while a custom dual-target search was performed to identify computational intervention hypotheses beyond predefined drug targets. Results showed that encoded burden increased with fault order in both pathways, with MAPK producing a higher baseline burden than GF. Among known-drug vectors, U0126+LY294002+Temsirolimus consistently emerged as the strongest low-burden candidate, achieving efficiency close to the maximum six-drug vector. Custom dual-target analysis identified ERK1/2+RPS6KB1 in GF and Raf+MEK1 in MAPK as high-impact computational target pairs. Runtime benchmarking showed that batched vectorized NumPy execution substantially improved scalability for higher-order fault simulations. Overall, the framework provides an interpretable and scalable approach for probabilistic pathway-level fault analysis and intervention prioritization.

The rapid growth of biotechnology manufacturing for synthetic DNA and proteins has raised concerns that adversaries could exploit commercial synthesis pipelines to create biological weapons. Without effective safeguards, an attacker could seek regulated genetic sequences from synthesis providers; while synthetic DNA is not itself a pathogen or toxin, access to such sequences can lower barriers to downstream misuse, motivating robust order-time screening. To mitigate this risk, Biosecurity Screening Software (BSS) systems have been developed to flag potentially malicious synthesis orders. Here, we propose one of the first deterministic benchmarks for evaluating the robustness of Biosecurity Screening Software. Our framework enables systematic testing of BSS behaviors and potential on specific nucleic-acid sequences and on targeted regions of malicious genomes. Our framework allows for insights into what is being flagged as malicious in BSSs, leading to potential discussions if specific BSS is fit for a specific manufacturing pipeline. We additionally introduce a dataset of manipulated genomes derived from the HHS and USDA Select Agents and Toxins List. When evaluated on this dataset, SeqScreen flags 42% of the sequences as malicious, while Commec flags 10.2%. Across a range of manipulation strategies, we find that simple manipulations, such as padding sequences by adding a repeated nucleotides at 1.5 times the original length, perform nearly as well as more targeted methods, such as embedding malicious sequences within benign genomic context. Padding-based methods trail embedding-based methods by only 0.75 percentage points in average detection rate. Consistent with prior reports from BSS developers and studies, we observe a sharp drop in detection rate when input sequence length falls below a critical threshold, typically between 50 and 100 base pairs (bp). Under our threat model, this implies that an adversary can bypass most existing safeguards by splitting a target genome into fragments shorter than 50 bp. Fragment-level analysis further reveals that some toxin regions evade detection entirely by SeqScreen, while other malicious genomes remain detectable even when fragmented into 30-50 base-pair segments. We open-source this benchmark to support reproducible evaluation of BSS robustness and to inform the development of next-generation biosecurity screening tools (https://github.com/HenryCWong/DNAS-Bench). For ethical concerns we only open-source the framework while the data is available upon request.

Generating 3D molecules that bind to specific protein targets via generative models has shown great promise in structure-based drug design. Recently, diffusion-based methods have achieved promising results, but their reliance on high sampling steps poses risks of slowing the drug discovery process due to increased time and computational costs. In this work, we propose a novel method named Perturbed Flow Matching (PFM), which significantly reduces sampling steps by leveraging a Flow Matching framework. PFM introduces a unique perturbed conditional probability path design that incorporates pocket binding site information and atom type-coordinate coupled information to enhance molecular generation performance. Experiments on CrossDocked2020 dataset demonstrate that PFM generates molecules with competitive 3D structures and state-of-the-art (SOTA) binding affinities towards the protein targets, achieving an Avg. of -7.12. Additionally, PFM accelerates the generation of valid molecules by a factor of 21.3, while demonstrating potential for further improvement. The code is available at https://github.com/kurisu92725/PFM.

Rare diseases are severely underserved by pharmacological treatments, and computational drug repurposing offers a cost-effective alternative to de novo discovery. We present a reproducible end-to-end pipeline integrating 3,961 rare disease-gene associations from Orphadata with 98,239 gene-drug records from DisGeNET through a multi-stage harmonization pipeline (HGNC symbol standardization and RapidFuzz fuzzy matching), yielding a large-scale gene-bridged rare disease tripartite knowledge graph -- to our knowledge the largest such graph constructed exclusively from Orphadata and DisGeNET-- comprising 15,454 nodes and 35,131 edges spanning 2,249 clinically distinct rare diseases. A Graph Attention Network (GAT) trained on node-type classification as a pretext task achieves macro F1 = 0.651 and ROC-AUC = 0.818 on a stratified held-out test set, with stable performance across five evaluation partitions (SD [&le;] 0.007). Drug candidate retrieval via cosine similarity in the GAT embedding space achieves Hits@10 = 0.400 across 200 evaluated disorders (vs. < 0.001 random baseline), with the clinically validated drug NITISINONE recovered at rank 4 for a tyrosine catabolism pathway disorder without pathway annotations. A deployment-ready interface is publicly available on HuggingFace Spaces.

Since copy number variations (CNVs) in pharmacogenes can cause significant alterations in drug metabolism, their reliable detection is of high importance both for large-scale studies and personalized medicine. Whole-genome sequencing, and specifically long-read sequencing, is the gold standard for CNV detection. Despite increasing availability of these technologies, genotyping arrays are still widely used as cost-effective alternatives in biobank and clinical settings, yet calling CNVs based on array intensity signals is challenging due to low base pair resolution. In this work, we developed a neural network model, nnCNV, to predict deletions in the CYP2C19 pharmacogene region from array intensity signals. We compared our method to the most widely used algorithm, PennCNV, and demonstrated better performance reaching 100% accuracy in the test dataset. Furthermore, we predicted probe-by-probe CYP2C19 deletion coordinates for all Estonian Biobank samples using nnCNV and PennCNV, and validated these predictions using an identity-by-descent (IBD) sharing method, which also demonstrated superior nnCNV performance. For the deletion samples with conflicting PennCNV and nnCNV predictions, we performed PCR analysis for validation, which showed 97% precision for nnCNV compared to 23% for PennCNV. Finally, we assessed the gradient-based feature importance maps and showed that nnCNV utilizes signal intensity information not only from deletion probes, but also from probes in flanking regions. Our results demonstrate that long-range information, which cannot be utilized by hidden Markov models, can improve CNV calling.

Motivation: Graph Neural Networks (GNNs) have gained increasing interest in the biomedical domain, as the integration of prior knowledge and deep neural networks has the potential to enhance insights into molecular processes and disease mechanisms. However, a comprehensive and systematic assessment of model architectures, data modalities, graph structures, and their performance for graph signal classification in the biomedical domain is yet to be performed. In order to close this gap, we conducted a benchmarking study on multiple GNNs on a Protein-Protein Interaction (PPI) network for Kidney Renal Clear Cell Carcinoma and Breast cancer subtype prediction, performing an in-depth investigation of architectures, incorporating skip connections and various data modalities. Results: While none of the GNNs outperforms the structure-agnostic Multi-Layer Perceptron baseline, all of them can handle bimodal data (gene methylation and expression) and offer the ability to gain explainability based on PPIs. We offer practical guidelines for applying GNNs to graph signal processing tasks specifically for cancer classification. Depending on the underlying dataset and PPI structure employed, models on different data modalities outperform others. Overall, we suggest using ChebNet, which tends to outperform the Graph Convolutional Network and the Graph Attention Network in cancer subtype prediction. We recommend using GNN architectures that employ a simple flattening readout layer, as they provide better classification performance and faster training time than those with global average pooling. Additionally, we tested residual connections, but they had only an insignificant impact on classification performance.

Asian rice is one of the best documented crops in terms of genetic diversity. The domestication process, that probably started 9000 years ago in China, remains difficult to infer since the main vertical signal is blurred by horizontal signals related to gene flow among cultivars and wild relatives. Consequently, a large number of hypotheses on the domestication process of rice have been published. Besides, most of the methods used to infer these scenarios do not model all the known biological phenomena at stake. Here, we present a methodological study based on a rich stochastic model, that incorporates introgression events, incomplete lineage sorting, and mutations that happen over time. The global evolutionary scenario is represented by a phylogenetic network. Furthermore, each locus scenario is modeled according to a locus tree through the Multispecies Network Coalescent. More importantly, for inferring the phylogenetic network, we propose a new hybrid approach combining a phylogenetic network method and a machine learning technique. In particular, our hybrid approach, named SO_SCPLOWNARFC_SCPLOW, benefits from advantages of a mathematical phylogenetic method, SO_SCPLOWNAPPC_SCPLOWNO_SCPLOWETC_SCPLOW, and from the potential of a powerful machine learning classifier, i.e. Approximate Bayesian Computation Random Forest (ABC-RF). These two methods are complementary since SO_SCPLOWNAPPC_SCPLOWNO_SCPLOWETC_SCPLOW reconstructs network accurately, whereas ABC-RF is able to handle a large amount of data. The originality is twofold. First, prior distributions required for ABC-RF are calibrated thanks to SO_SCPLOWNAPPC_SCPLOWNO_SCPLOWETC_SCPLOWs estimates. Secondly, ABC-RF relies on summary statistics inspired by phylogenetic network literature. We show, on simulated data, that the SO_SCPLOWNARFC_SCPLOW hybrid approach enjoys very good performances. On rice real data, it infers a scenario with a unique domestication (that of Japonica), followed by three reticulation events involving early Japonica. It highlights two introgression events at the origin of Indica and cAus, and one admixture event responsible for the emergence of cBas. Author summaryToday, in genomics, there is a real need for methods able to infer phylogenetic networks. A phylogenetic network is a directed graph representing events like hybridization, introgression, and horizontal gene transfer. Understanding these complex biological phenomena, essential for crop adaptation, can help breeders when facing challenges like climate change and population growth. Genome-wide diversity analysis thus requires network methods scaling for large data volumes and incorporating fundamental biological phenomena. In this context, we present a new hybrid approach, SO_SCPLOWNARFC_SCPLOW, that benefits from the potential of a powerful machine learning classifier, Approximate Bayesian Computation Random Forest, and from advantages of a mathematical phylogenetic method, SO_SCPLOWNAPPC_SCPLOWNO_SCPLOWETC_SCPLOW. Consequently, SO_SCPLOWNARFC_SCPLOW is able to handle large data-sets thanks to machine learning and is also based on a deep mathematical theory. On simulated data, our hybrid approach performs very well. When applied to real rice genomic data, it supports a scenario with a single domestication event, that of Japonica. The analysis further highlights the role of early Japonica in the origin of both Indica and circumAus. Finally, it identifies an ancient admixture event, involving circumAus in the emergence of circumBasmati. Together, these findings confirm the importance of early rice history along the Himalayan region.

In this work, we present a machine learning model for identifying pathogenic DNA variants. The model was learned from the analysis of normal and pathogenic sequences extracted from the ClinVar database (supported by NCBI). This analysis was based on a conceptual semantic model of DNA sequences converted to peptide sequences (amino acid sequences) governed by a well-defined grammar, which allowed us to apply NLP techniques, specifically Part of Speech tagging (POS tagging). Our predictive model was built by combining two techniques: CRF (from the Markov model family), which performs the sequencing, and BiLSTM (a deep learning model) which captures the past and future content of the sequences. The training space was created with the sequences of 105 genes associated with approximately 27,000 pathogenic variants. The model was evaluated using the metrics precision, P-R and ROC curves, AUC, and confusion matrices. Its performance was also compared against five known methods for predicting pathogenic variants. The results show exceptional performance that exceeds expectations and places this new method at the state of the art for predicting pathogenic DNA sequences.

Heterogeneous biomedical knowledge networks (hetnets) integrate disparate data types, drugs, genes, diseases, and pathways, across independent sources; Hetionet (https://het.io) is a widely used example. A standard approach for assessing connectivity significance is XSwap, which permutes the hetnet P times and fits a gamma-hurdle null model to the degree-weighted path count (DWPC), pooling permuted values across pairs with matching source and target degrees to increase the effective sample size. This permutation approach has been highly successful in practice, but it faces four practical constraints in large graphs: (1) a finite resolution for the smallest reportable p-values, (2) computational cost that grows prohibitive at path lengths L [&ge;] 4 or 5, (3) a variance model (Var {propto} {micro}2) that departs from the configuration-model form (1 +{kappa} ){micro}, and (4) O(P 10m L) runtime. To complement this approach, we present HetNetEX (Heterogeneous Network EXact inference), which computes the null DWPC distribution analytically from degree sequences using the configuration model in O(Ln) time. In simulations at P = 200 across L = 1-4, HetNetEX achieves Spearman{rho} > 0.96 concordance with XSwap rankings while being >10,000x faster and providing analytical p-values without a resolution ceiling. High-degree pairs show larger XSwap sampling error than low-degree pairs, reflecting the finite-sample nature of permutation that analytical computation avoids.

Identification of differentially expressed genes is a crucial step for downstream tasks on gene data such as biomarker discovery, drug target identification. Traditional Methods assume negative binomial distribution on RNA-sequence data and models the DEGs using either generalized linear models or by estimating dispersion and assumption of mean-variance rate. The proposed method uses axiomatic approach by using quantum mechanics principles to project transcript data onto a Hilbert space using a composite kernel. Using the curvature generated by the transcripts on the latent manifold within the Hilbert space, a gravitational search inspired mechanism is used to identify the optimal number of differentially expressed genes by minimizing a representational loss function, and a reduced gene feature space is constructed as the potential differentially expressed genes. The proposed method has been compared with existing empirical methods for validation using proper statistical and biological benchmark analysis.

Standard polygenic risk scores (PRSs) are constructed based on additive genome-wide association study (GWAS) summary statistics. Nonlinear machine learning methods have been increasingly applied to construct PRSs directly from individual-level data, with the aim of improving predictive performance over standard PRSs through their ability to model non-additive genetic effects. However, their superiority across studies has been inconsistent, and the conditions under which they provide meaningful improvements remain unclear. We combined theoretical analysis, simulations and a real-world application to investigate when two widely used nonlinear machine learning methods, random forest and XGBoost, outperform standard PRSs. Theoretical analysis showed that standard PRSs can implicitly capture part of the genetic variance attributable to nonadditive genetic effects through their contributions to marginal SNP effects, thereby losing less information than commonly assumed. Although nonlinear models have a higher theoretical potential, their greater flexibility incurs a bias-variance trade-off that can limit predictive gains at finite sample sizes. Simulations showed that XGBoost outperformed the standard PRS only when the genetic architecture involves a sufficiently large proportion of interaction genetic variance concentrated across relatively few interaction effects and large training samples were available. Random forest consistently underperformed the standard PRS. In an application to ischemic heart disease prediction using UK Biobank data, XGBoost showed no meaningful improvement in predictive performance over the standard PRS, whereas random forest again performed worse. Together, these findings suggest that nonlinear machine learning do not uniformly outperform standard PRSs; rather, their relative performance depends jointly on genetic architecture and training sample size. Our study helps to reconcile the inconsistent results reported across previous studies and provides a framework for identifying settings in which more complex PRS models are likely to be beneficial.

Glioblastoma (GBM) is a highly aggressive brain tumor with an extremely poor 5-year survival rate of 6.9%, largely attributable to the lack of reliable biomarkers. While competing endogenous RNA (ceRNA) and copy number variation (CNV) analyses offer unique biomarker identification potential, current approaches neglect the integration of multiple regulatory mechanisms for biomarker detection. To address this limitation, we applied relational graph convolutional networks (RGCNs) to ceRNA and CNV knowledge graphs through a novel late fusion ensemble architecture. The proposed architecture outperformed baseline models and identified five novel biomarkers, including hsa-miR-196a and hsa-miR-224. Kaplan-Meier survival analysis and Cox regression indicated that the identified genes hold significant prognostic and diagnostic power. The early stratification of the Kaplan-Meier curves indicates the potential these genes hold for patient survival prediction. The results illustrate that a late fusion RGCN ensemble effectively captures complex gene interactions, overcoming limitations of existing models and providing a framework for biomarker discovery. The novel biomarkers serve as prospective targets for future GBM therapeutic development and candidates for non-invasive diagnostic assays.

The leading cause of mortality and morbidity in children under the age of 5 is preterm birth. The timing of birth is influenced by both genetic and environmental factors, but the underlying mechanisms remain poorly understood, making its prediction difficult. In this study, we investigated the potential of using machine learning models to predict preterm birth based on genetic data from the Norwegian Mother, Father and Child Cohort Study (MoBa). We trained and evaluated several classification algorithms on individual-level genetic data from over 15,000 mothers and children. Our results indicate that the predictive capacity of maternal gestational duration-associated loci for preterm birth is limited, with the highest AUC values around 0.57. Additionally, incorporating more SNPs within the associated loci did not improve prediction performance. As expected, the contribution of the maternal genome to preterm birth prediction was found to be larger than that of the fetal genome. Overall, our findings suggest that while genetic testing provides some information about an individual's risk for preterm birth, further research incorporating additional factors is necessary to enhance predictability.

Acute myocardial infarction (AMI) is one of the leading cardiovascular diseases worldwide and remains a major cause of mortality. Early risk prediction can help clinicians identify high risk patients shortly after admission and support timely monitoring and individualized treatment. Previous AMI risk assessment approaches predominantly rely on a single model structure or fixed feature representation, which may limit their ability to capture diverse risk related patterns and reduce predictive performance. To address these challenges, we propose MetaAMI, a random projection based meta-learning framework for AMI outcome prediction. Specifically, patients were selected based on ICD-9 and ICD-10 diagnostic codes for AMI from the Medical Information Mart for Intensive Care IV (MIMIC-IV) v3.1 database. Features were transformed through multiple random projections, with each random projection generating a distinct lower dimensional feature representation. Subsequently, baseline classifiers were trained on each lower dimension representation to predict in-hospital mortality among AMI patients. The predictions were aggregated to construct an integrated feature representation, which was used as input to a meta-learner architecture. By effectively integrating complementary information from diverse baseline models, the meta-learner refined the decision boundary and enhanced overall predictive performance. Survival analysis and SHapley Additive exPlanations (SHAP) analysis were further performed to evaluate clinical utility and interpret the model predictions. Benchmarking results based on MIMIC-IV dataset suggested that our MetaAMI consistently outperformed all the baseline classifiers across seven evaluation metrics including Accuracy, Area Under the Curve (AUC), F1 Score, G-Measure, Jaccard Index, Youden J, and Matthews Correlation Coefficient (MCC). In addition, feature importance analysis showed clinically relevant predictors of in-hospital mortality. In summary, MetaAMI provides an effective and robust solution for machine learning based AMI risk prediction. We anticipate that the application of MetaAMI will have a positive impact on clinical risk stratification and personalized treatment strategies for AMI.

Can plant-derived small RNAs target human mRNA 3UTRs via complementary base pairing and produce experimentally detectable regulatory effects? This question concerns not only the fundamental feasibility of cross-kingdom RNA regulation but also the technological pathway for screening plant-derived active small nucleic acids. Existing miRNA target prediction tools are predominantly designed for endogenous miRNA-mRNA systems, exhibiting notable limitations when applied to cross-species small RNA inputs and small-sample wet-lab experimental adaptation. In this study, we developed a two-layer prediction framework, MetaLulu-AI. The first layer builds upon publicly available human miRNA-mRNA 3UTR interaction data, utilizing XGBoost to learn foundational binding rules on human 3UTRs based on 41 interpretable computational features, including seed region pairing types, local context sequence composition, site positioning, and RNA secondary structures. The second layer is tailored to the experimental system of plant-derived small RNAs and human target genes. It introduces 40 experimental samples using significant changes in endogenous protein expression as the regulatory standard (determined by Western blot or ELISA 48 hours post-transfection of small RNAs via Lipo3000). Using 52-dimensional computational features and the optimal transcript scores from the first layer as inputs, this layer employs TabPFN for experimental label adaptation. The first-layer dataset consists of 38,752 training samples, 5,536 validation samples, and 11,073 testing samples (totaling 55,361), with a positive-to-negative sample ratio of approximately 1:5.4. On the randomly split test set, the model achieved an AUC of 0.9686, a recall of 0.8523, a precision of 0.8080, and an accuracy of 0.9452 (at a decision threshold of 0.4797). Group-based splitting revealed that the model maintains high discriminative power for unseen genes (AUC = 0.9541), though its generalization ability for completely unseen miRNAs decreases (AUC = 0.7390). For the 40 experimental samples in the second layer, the TabPFN model achieved an average AUC of 0.7406 {+/-} 0.092 across ten repeated 70/30 random splits, outperforming the baseline of directly using the first-layer scores (0.3563 {+/-} 0.149); the average AUC in a 5-fold cross-validation was 0.770 {+/-} 0.177. SHAP analysis demonstrated a clear divergence in the discriminative basis of the two models: the first layer relies more heavily on the thermodynamics of the small RNA itself and the quality of canonical seed sites, whereas the second layer focuses more on the local UTR environment and statistical site features. Although the current second-layer results are constrained by sample size and gene coverage, this framework serves as a preliminary observation of the adaptation mechanism for cross-kingdom regulation experiments, and motivating future large-scale validation. Under stricter leave-one-gene-out and leave-one-small-RNA-out evaluation, the adapter exceeded the first-layer score baseline but only matched the majority-class baseline, underscoring that entity-level generalization is not yet established.

BackgroundAdverse drug-drug interactions (DDIs) cause preventable hospitalizations, but exhaustive experimental screening of all drug pairs is infeasible. Many computational predictors rely on SMILES or other molecular representations, limiting their direct applicability to biologics and other non-small-molecule therapeutics. We present a structure-agnostic framework that combines semantic representations derived from Medical Subject Headings (MeSH) with graph-derived topology from a Drug-Target-Protein knowledge graph constructed from DrugBank and UniProt. We further investigate how variation in MeSH annotation depth affects predictive performance. ResultsDrugs are grouped according to their deepest MeSH annotation level (Low, Mid, or Deep), and performance is evaluated across the resulting interaction categories in transductive and inductive settings. The Intermediate ontology scope (Low+Mid) provides the most stable performance, while adding Deep-level terms offers limited and inconsistent benefit. Lightweight topological descriptors are integrated with MeSH features through instance-wise, dimension-specific latent-space gating, using curated reliable-negative pairs for supervision. Fusion improves mean performance over the MeSH-only baseline across all six categories in the transductive setting. Under induction, the clearest gains occur for Low-Low interactions ({Delta}AUROC = 0.056;{Delta} F1 = 0.137) and Low-Mid interactions ({Delta}AUROC = 0.077;{Delta} F1 = 0.114). ConclusionsMeSH annotation depth is associated with systematic variation in DDI prediction performance that aggregate evaluation can obscure. Graph-derived topology is particularly beneficial when ontology annotations are shallow. The framework provides a common, structure-agnostic representation compatible with both small-molecule and biologic therapeutics and supports first-pass DDI prioritization for subsequent expert assessment.

Hybridization is an important evolutionary process, commonly modeled by the network multispecies coalescent. Reconstructing evolutionary histories under this model is notoriously costly, even for level-1 networks where hybridization events are isolated from each other. The widely used methods that combine speed with statistical guarantees rely on quartet concordance factors computed for all subsets of four species, resulting in an o(n4k) bottleneck that severely limits scalability to large numbers of species (n) and genes (k). Among quartet-based methods, NANUQ+ is notable because it decomposes the problem into two steps: first reconstructing a tree of blobs, which compresses each non-treelike part of the network, called a blob, into a single vertex, and second reconstructing the internal structure of each level-1 blob, specifically its circular order and hybrid vertex. Here, we investigate whether level-1 blob reconstruction is difficult once the tree of blobs is known. We present a fast and statistically consistent algorithm, called NetCS, based on two simple primitives: majority voting and merge sort, circumventing the bottleneck of computing all quartet concordance factors. In simulations, NetCS achieved comparable accuracy to NANUQ+ and was dramatically faster, enabling analyses of 200 taxa and 1000 genes in only a few minutes. Both methods attained near-perfect accuracy when given the true tree of blobs; however, their performance degraded in end-to-end pipelines due to errors in tree of blobs reconstruction. Strikingly, even methods that reconstruct level-1 networks directly struggled to accurately predict hybrid ancestry. Our results suggest that reconstructing level-1 blobs is unexpectedly easy once the tree of blobs is known, and that a major challenge for phylogenetic network inference lies in accurate tree of blobs reconstruction.

Modern polygenic risk scores (PRS) exhibit shifts correlated with ancestry, leading to erroneous predictions for non-European individuals when models are trained on predominantly European cohorts. Such shifts arise from, among other factors, (1) algorithmic limitations in the ability of PRS model training to detect causal variants, rather than nearby variants with ancestry-dependent correlations to the causal one, (2) under-representation of alleles with higher prevalence in non-European populations in the association study training, and (3) gene-by-environment interactions where the environment is correlated with genetic ancestry. Current ancestry-adjustment methodologies often discretize individuals into population categories and apply a simple affine mapping to reduce these genetic ancestry biases. However, such approaches provide suboptimal adjustments, particularly for admixed individuals. In this work, we introduce a detailed theoretical characterization of ancestry-dependent biases and propose novel methods based on non-parametric neighborhood techniques that provide more accurate empirical results and admit statistical consistency guarantees. Extensive experiments using the UK Biobank demonstrate the effectiveness of the proposed methods.