Briefings in Bioinformatics

Spatial transcriptomics characterizes tissue-scale gene expression patterns, yet its observations are sparse discrete samples of an underlying continuous molecular field, leading to spatial aliasing and sub-resolution information loss. Existing methods usually formulate this task as spot-level point regression, making it difficult to capture both expression continuity and the regional nature of observation. Here, we propose HiFi-ST, a conditional neural field framework for continuous spatial transcriptomics modeling. HiFi-ST formulates spatial gene expression prediction as continuous expression field learning, models each spot as a regional observation over a finite support domain, approximates local integration through Monte Carlo sampling, and integrates multiscale tissue feature extraction with FiLM-based conditional modulation to improve modeling of complex spatial heterogeneity and consistency with the underlying measurement process. Systematic evaluation on three independent datasets (HER2+, cSCC, and Alex_NatGen) showed that HiFi-ST outperformed mclSTExp, BLEEP, THItoGene, His2ST, and HisToGene on key metrics. On HER2+, HiFi-ST achieved an average PCC improvement of 65.1% and an average MSE reduction of 40.9%; on cSCC, PCC improved by 10.2% and MSE decreased by 51.2%; on Alex_NatGen, PCC improved by 80.0% and MSE decreased by 16.3%. In addition, the learned multiscale tissue representations supported downstream spatial immunoanalysis, including assisted identification of candidate TLS regions. Overall, HiFi-ST provides a unified framework bridging discrete measurements and continuous expression field reconstruction for tumor microenvironment analysis and spatial immune structure characterization.

Discovery of pathway associations and druggability can leverage underutililized dark kinase genes for treating complex diseases (proven for cancer and neurodegeneration), boosted with computational methods. Herein, we employ BERT-based embeddings of proteins and pathways (refined via two-stage transformer and heterogeneous graph transformer) and protein-protein and protein-pathway associations-both positive (curated from databases) and negative (generated using Wasserstein Generative Adversarial Networks with gradient penalty) to train XGBoost and lightGBM classifiers for predicting pathways associated to human dark kinase proteins, with important features unveiled through SHAP analysis. All pathways are clustered and proteins related to same pathway clusters are grouped together (via predicted and positive protein-pathway associations). Selected PCOS-related human dark kinase proteins (with high predicted and existent associations to PCOS pathways) are docked with known PCOS drugs for druggability analysis. Our model attains accuracy, F1-score, specificity, MCC, AUROC and AUPRC of 0.9816, 0.9816, 0.9852, 0.9632, 0.9978 and 0.9982 respectively, supersedes existing work, correctly classifies 97.48% of test data, predicts 62225 pathway associations to above proteins, infers functional similarity of 96 such proteins to human protein(s) and traces nine important positive features. Our model can be used to determine varied functionalities and disease relevance of proteins via predicted pathway associations.

Evaluating protein sequence similarity remains challenging in the protein-sequence twilight zone (20-35% sequence identity), where traditional methods often fail. In this study, we evaluate whether mean-pooled embeddings from four protein language models: ESM-1b, ESM-2, ProtT5, and ProstT5 can estimate pairwise structural similarity without performing sequence alignment. The benchmark dataset includes 20,445 PISCES protein pairs with sequence identity [≤]30%, representing the protein-sequence twilight zone, with TM-align-derived TMmin used as the structural ground truth. Protein embeddings are compared using cosine similarity, Euclidean- and Manhattan-derived similarities, an RBF kernel, and dot product. Among these similarity metrics, cosine similarity performs best across all four models. Moreover, ProstT5 achieves the highest Spearman correlation with TMmin, followed by ESM-2, ProtT5, and ESM-1b, while all four PLMs outperform BLASTP overall. Furthermore, the advantage of PLM embeddings is most pronounced for protein pairs with the lowest sequence identity. ProstT5 also provides the best discrimination between structurally similar and dissimilar protein pairs. Moreover, it offers a favorable balance between similarity performance and the computational requirements of residue-level embedding generation and storage. Overall, these findings support PLM embeddings as an effective alignment-free approach for detecting structural relationships among proteins in the twilight zone.

Deep learning methods, such as AlphaFold and RosettaFold, achieve high accuracy in protein structure prediction. However, predicting the structure of large protein complexes remains challenging due to their large size and intricate multi-chain interactions. Docking-based methods can handle large proteins, but are limited by the huge combinatorial binding space of multichains. Assembly-based approaches offer an alternative, but their accuracy critically relies on the precision of predicted subcomponents. Addressing the challenges, we propose HDOCK-Multimer (HDM), a structure prediction framework of large protein complexes by integrating ab initio docking and combinatorial assembly. HDM can efficiently reduce reliance on subcom-ponent accuracy through docking process, while leveraging the pairwise interactions of subcom-ponents through assembly strategy. HDM is extensively validated on three benchmarks of 35 large heteromeric complexes, 172 large protein complexes, and 7 CASP15 targets, and compared with state-of-the-art methods including MoLPC, CombFold, AlphaFold-Multimer (AFM), and AlphaFold3 (AF3). It is shown that HDOCK-Multimer substantially outperforms the other methods. In addition, HDM also shows ability to predict the stoichiometry and model the complex without stoichiometry input. It is anticipated that HDM will serve as a powerful tool for studying large protein complexes or molecular machines. The HDM package is freely available at https://github.com/huang-laboratory/HDOCK-Multimer/.

Short open reading frames (sORFs) within non-coding RNAs (ncRNAs) have arisen as a hidden layer of gene regulation, encoding small peptides that represent a new class of cancer regulators with diagnostic and therapeutic potential. However, inferring associations between sORFs to specific cancer types remains challenging and requires computational approaches for accurate prediction. Recently, the CoraL framework introduced the first computational approach for predicting cancer-associated peptides, focusing primarily on model architecture while overlooking how feature extraction strategies influence predictive accuracy. We present a systematic evaluation of machine learning models and feature extraction approaches to predict cancer-associated sORFs across 15 cancer types. We benchmarked seven traditional machine learning algorithms combined with three feature extraction methods: k-mer frequency, Word2Vec embeddings, and genomic language model (gLM)-based embeddings. To our knowledge, this is the first study applying gLM-derived embeddings to the prediction of cancer-associated sORFs in ncRNA. Our results show that traditional machine learning models with appropriate feature extraction outperform the CoraL baseline across all cancer types, achieving up to 10% higher accuracy in some of the 15 evaluated datasets. Interestingly, k-mer features consistently outperformed gLM embeddings without fine-tuning, suggesting that local sequence composition may provide more discriminative information for this task and that pre-trained genomic representations may require task-specific adaptation to fully capture these patterns. Additionally, we observed that the way sequences are tokenized, such as the k-mer length, can affect performance: longer fragments (e.g., k=7) sometimes reduced accuracy for Random Forest but had a smaller effect on MLP. Our findings suggest that appropriate feature engineering can provide greater improvements than increasing model complexity.

Microscopic images of cells and tissues are central to disease diagnosis. In computational pathology, multiple instance learning (MIL) has emerged as a key paradigm for analyzing numerous images within a single patient sample. While the representative distribution of cells in a sample is important for diagnosis, existing MIL frameworks largely overlook it. We introduce TopoMIL, a framework that extracts the representative topological structure of the sample and integrates it into the MIL classifier. Three topological representations are assessed, each with distinct advantages and computational costs. We evaluate TopoMIL on four histopathology and cytomorphology datasets, each presenting unique challenges. Integrating the samples topological information into MIL enhances classification across average, max, attention-based, and transformer pooling, yielding AUCROC gains of 3.3%, 4.2%, 5.9%, and 0.5%, respectively, with moderate computational cost. Our work underscores the potential of TopoMIL as a scalable extension to existing morphology-based models in computational pathology.

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.

Accurately predicting the effects of mutations on protein-RNA binding is crucial for elucidating disease mechanisms. Yet, exhaustively exploring the space of all possible variants is prohibitively expensive, motivating computational methods that can quantify mutation-induced changes in binding affinity (aka {Delta}{Delta}G) accurately and efficiently. We present iSCALE, an interpretable and generalizable deep learning method that adopts an implicit Spatial Coupling-Aware Ligand Encoding strategy to predict mutation-induced binding affinity changes. By injecting this implicit multiscale encoding scheme into a bidirectional state space modeling architecture, iSCALE learns a generalizable multiscale coupling pattern that achieves superior performances on not only the protein-RNA binding {Delta}{Delta}G, but also the protein stability {Delta}{Delta}G and protein-protein binding {Delta}{Delta}G predictions. Detailed analyses demonstrate that the model attention scores align well with structural characteristics. In addition, iSCALE shows good discriminative ability when predicting close samples such as complexes of same mutation but with different ligands or the same complex but with different mutation sites. In summary, iSCALE serves as an effective in silico tool for large-scale protein-RNA binding {Delta}{Delta}G prediction, which pushes the border of understanding in mutation-induced pathological outcomes.

BackgroundHighly variable gene (HVG) selection begins almost every single-cell RNA-seq analysis. While ranking formulas have been compared extensively, the integer gene budget at which any ranking must be truncated is typically left to the user and habitually fixed near 2,000. Relying on such a convention carries hidden costs--lists that are too short erase subtle structure, whereas lists that are too long add noise and computational overhead. Moreover, because global rankings measure variance across all cells, markers for rare populations often lose the "variance vote count" to dominant bulk variation, leading to an unfair feature allocation at the hard cutoff. Whether this convention is defensible, and whether the budget and tail can be set from data without disturbing the ranking, has not been examined systematically. ResultsUnder a frozen seurat_v3 ranking, k-sweeps across 18 labeled datasets show that n = 2,000 is ARI-optimal on 1 of 18 datasets and that the best available budget is worth a mean ARI gain of +0.033 over it, establishing cardinality as a real and largely unexploited design axis. We present scFair, a Scanpy-compatible HVG layer that automates list length alone: geometry-aware auto_n sets a base size k from multi-seed density and stability features of an intermediate embedding (trading a modest, intentional compute increase for a safer data-driven default), and a same-rank append step acts as a conservative safeguard against cutoff unfairness by adding a short near-miss tail. The ranking is never recomputed or reweighted. On the 18-dataset panel, the default path improved Leiden-label agreement over HVG@2000 (median {Delta}ARI = +0.016; 13/5; Wilcoxon P = 0.0077) and outperformed the neighborhood-based selector triku at author defaults on 15/18 datasets (median +0.024; P = 0.004), while triku did not improve on HVG@2000. Controls locate the effect: cell-number-only rules do not beat HVG@2000, an FDR-chosen length imposed on the frozen ranking is flat, and a fixed HVG@2200 default is not a general substitute because it cannot produce the short lists that compact matrices call for. ConclusionsA fixed budget near 2,000 HVGs is frequently suboptimal, and list cardinality is a separable design axis that can be automated without changing the ranking formula. Effect sizes are modest, the short-list branch rests on four datasets, and rule thresholds were developed with partial overlap to the evaluation panel.

Large-scale prediction and assessment of clinical patient responses (i.e., RECIST class) to drug combinations remains challenging due to scarce patient-derived data. The existing prediction methods mainly rely on cancer cell line models. However, substantial biological heterogeneity between cancer cell lines and cancer patients within same tissues, as well as the heterogeneity between one tissue and another, often limit the generalizability of these methods in clinical patients. To overcome these limitations, here we present CaMeRe, a Causally-inspired Meta-representation learning framework designed to predict patient-specific clinical Response to drug combinations. In situations where stable causal factors and domain-specific response-modulating factors are unobservable, explicit discrete domain labels are unavailable, and data is scarce, CaMeRe designed a domain-invariant causal representation learning (DICRL) model guided by the invariant information bottleneck theory and causal intervention invariance principle, and also built a meta-learning framework with bi-level domain generalization to optimize DICRL model for achieving multi-domain generalization within and across tissues. By integrating the causal representation learning and meta learning framework, CaMeRe not only exhibited robust multi-domain generalization performance across multiple clinical drug combination response datasets and PDXs drug combination response datasets and generalization scenarios, but also had better interpretability. We applied CaMeRe to predict drug-combination response scores for 3,423 patients across 542,080 drug combinations. The predicted scores were significantly associated with biomarkers of known drug combinations and enabled the prioritization of candidate drug combinations across 11 cancer types, with stronger support from literature and clinical trial evidences than random baselines. We believe that CaMeRe can be a useful tool for predicting large-scale clinical individual drug combination responses and it has broad clinical applications.

Single-cell gene set enrichment analysis is widely used to evaluate the activity of gene sets in individual cells, as measured by single-cell sequencing technologies. However, existing methods often generate ambiguous scores that cannot reliably distinguish cells enriched for a biological signal from background cells. To address this limitation, we developed Cell Set Overlap Analysis (CSOA), a novel method for gene set enrichment analysis that leverages gene pair relationships by quantifying pairwise overlaps between high-expression cell sets constructed for each signature gene. We benchmarked CSOA against sixteen established methods representing five methodological classes: direct scoring, rank-based scoring, model-based scoring, matrix decomposition, and overrepresentation analysis. Our evaluation framework introduces novel metrics tailored for the gene set scoring problem, such as score coverage and silhouette rank alignment. They are used alongside traditional metrics for binary classification, such as the Matthews correlation coefficient and area under the receiver operating characteristic (AUROC). CSOA showed superior accurate annotation of cell types and specific biological processes compared with competing approaches. This advantage was particularly pronounced in the class boundary determination benchmark, where it ranked the first in all evaluated datasets. CSOA also outperformed most of the compared methods in computational efficiency. Notably, CSOAs combination of outstanding performance in the score coverage metric and solid overall performance positions it as a uniquely well-suited method for distinguishing cells enriched for specific biological signals.

Single-cell foundation models have recently emerged as a promising approach for learning general- purpose representations from large-scale transcriptomic data. These models are trained on millions of cells and are designed to transfer their learned representations to a wide range of downstream tasks. However, their practical benefits compared to traditional approaches are still not fully understood. This study evaluates four foundation models, namely scGPT, SCimilarity, UCE, and Transcriptformer, across four downstream tasks: cell type annotation, human data integration, cross-species data integration, and protein expression prediction. Embeddings generated by each model were assessed using multiple public single-cell datasets and compared against conventional machine learning baselines. Performance was measured using task-specific evaluation metrics, including classification, integration, and regression metrics. The results showed that foundation model embeddings did not consistently outperform traditional approaches. In the cell type annotation task, baseline methods achieved the strongest performance across most datasets. For protein expression prediction, however, embeddings from the foundation models generally produced more accurate predictions than the baseline, with SCimilarity achieving the lowest prediction error and Transcriptformer obtaining the highest correlation scores. In the data integration task, all foundation models produced moderate results, while scVI (the baseline) achieved the strongest integration performance. Overall, the results suggest that current single-cell foundation models provide useful representations for some downstream tasks in zero-shot conditions but do not yet offer a universal replacement for task-specific methods. Their effectiveness remains dependent on the application and evaluation setting.

Recent advances in artificial intelligence have accelerated the discovery of bioactive peptides by enabling computational exploration of the vast peptide sequence space. However, existing peptide generation approaches generally rely on either distribution-learning models, which generate biologically realistic sequences but do not consistently optimize functional activity, or optimization-based methods, which maximize prediction confidence while often deviating from the underlying distribution of experimentally validated peptides. To address this limitation, a two-phase generative-evolutionary framework is proposed that integrates distribution learning with evolutionary optimization. In the first phase, Variational Autoencoders (VAE), Autoregressive Transformers (ART), and Token Diffusion Transformers (TDT) are used to generate biologically plausible seed peptides. In the second phase, these peptides were used as initial seed for Hill Climbing optimization procedure that iteratively improves fitness function score. The proposed two-phase framework was evaluated using a dataset of experimentally validated IL-2-inducing peptides. Evaluation using independent IL-2 prediction models showed that Autoregressive Transformer combined with Hill Climbing achieved the best overall performance, achieving the mean IL-2 induction confidence score of 0.96 while reducing KL divergence from 2.26 for standalone Hill Climbing to 0.75. A case study on an independent IL-13 inducing peptide dataset showed similar trends, with ART initialized Hill Climbing achieving the mean IL-13 induction score of 0.99 while reducing KL divergence from 1.76 to 0.59. Overall, the framework provides a generalizable approach for balancing functional optimization and distributional realism and can be applied to peptide discovery and data augmentation in imbalanced biological datasets thereby generating high confidence peptides for wet lab validation. HighlightsO_LIProposed a two-phase framework for bioactive peptide generation with potential to address class imbalance in peptide classification tasks. C_LIO_LIPerformed a systematic comparison of distribution-learning and optimization-based approaches for peptide generation. C_LIO_LICombined distribution-learning models for sequence generation with optimization algorithms for improving peptide functional properties. C_LIO_LIDemonstrated the applicability of the proposed framework across multiple bioactive peptide datasets. C_LI

Vaccine antigen discovery requires prioritizing protein candidates according to both immunogenic potential and recombinant expression feasibility. These properties are typically evaluated using separate computational tools, requiring researchers to integrate heterogeneous outputs through ad hoc workflows. Here, we present BIOINF-farma, a modular platform integrating epitope prediction and developability assessment for rational antigen selection within a unified environment. Candidates can be submitted as amino acid sequences or three-dimensional structures. When experimental structures are unavailable, BIOINF-farma automatically searches for models in AlphaFold DB or performs structure prediction using Boltz-2, ensuring a standardized structural representation for downstream analyses. Antigenicity is quantified by combining structure-based conformational epitope signals (MLCE/REBELOT-BEPPE) and sequence-based linear epitope propensity scores (BepiPred 3.0) into a protein-level Antigenicity Score, with a classification threshold optimized on a manually curated validation dataset. Developability is evaluated through two supervised Random Forest meta-learners that integrate three solubility predictors (DeepSoluE, SoluProt, Protein-Sol) and three thermal stability predictors (TemStaPro, ProLaTherm, BertThermo), whose outputs are combined into an Expression Efficiency Score (EES). By integrating complementary predictive signals, the meta-learning framework achieves greater accuracy and robustness than individual predictors while maintaining performance across a broad range of sequence identities. The Antigenicity Score effectively discriminates antigenic from non-antigenic proteins with a large effect size, whereas EES successfully distinguishes soluble from insoluble outcomes on an independent panel of recombinant proteins expressed in Escherichia coli. BIOINF-farma jointly assesses antigenicity and expression feasibility within a single framework. Its modular architecture facilitates the incorporation of future predictive methods, while its web-based interface makes the full pipeline accessible to users without programming expertise, supporting rapid candidate triage in vaccine research and emerging pathogen responses. Author SummaryVaccine development begins with a critical step: identifying, among the many proteins encoded in a pathogen genome, those most suitable as candidate antigens. A promising candidate must satisfy two requirements that are rarely evaluated together. It must be recognized by the immune system, so that vaccination elicits a protective response; and it must be amenable to recombinant production, since antigens that cannot be obtained in sufficient quantity and quality are of limited practical use. Current computational tools typically address only one of these aspects, and researchers must integrate their outputs manually, through procedures that are time-consuming and prone to inconsistency. We developed BIOINF-farma, an automated platform that brings these two assessments into a single analytical framework. Starting from a protein sequence or an experimental structure, the platform retrieves or predicts a three-dimensional model, evaluates the proteins antigenic potential by combining complementary epitope predictors, and estimates its expression feasibility by integrating multiple solubility and stability predictors through supervised machine learning. A web-based interface makes the full workflow available to experimental immunologists and vaccine developers without requiring computational expertise, supporting rational candidate prioritization in routine vaccine research and during emerging pathogen responses.

MotivationWith rapid advances in sequencing technologies, many heterogeneous omics datasets have been generated, as seen in the Encyclopedia of DNA Elements (ENCODE) and many single-cell multi-omics sequencing projects, bringing substantial challenges to existing integrative methods. In this article, we report a novel multi-omics fusion and analysis software SEMFA which performs general parametric tests for the Mahalanobis Similarity of samples based on the factor scores generated by an Extended version of conventional Multiple Factor Analysis. ResultsOur developed method is effective and robust under both Gaussian and non-Gaussian assumptions. The mean F1 scores are over 0.8 when the column similarity level is 0.9 and the noise level ranges between 0.1 and 0.2, using simulation studies based on ENCODE count data. It was also efficient and effective at handling large-scale single-cell multi-omics data, as demonstrated in colon cancer cases as it unveiled signature network organization patterns of cells for stages III and IV.

Antimicrobial resistance reduces the effectiveness of conventional antibiotics and has become a major global health threat, highlighting the need for new anti-infective agents. Antimicrobial peptides (AMPs), a diverse class of innate immune effectors with broad-spectrum antimicrobial activity, are promising candidates for combating drug-resistant infections. Identifying AMPs by wet-lab experiments, however, remains costly and time-consuming, creating a strong demand for computational identification methods. Our recently developed method, SAMP, captures region-specific residue distributions based on proportionalized split amino acid composition. However, SAMP might ignore key biochemical information and sequence order information. Here we present SAMP V2, a stacking ensemble learning framework based on biochemical and sequence-order information augmented split amino acid composition (BIA-SAAC), which extends SAMP by integrating pseudo-amino acid composition features with biochemical and sequence-order information into split peptide regions. Specifically, each peptide is divided into N-terminal, middle, and C-terminal regions, and pseudo amino acid composition is calculated within each region. Benchmarking tests on six independent test datasets, SAMP V2 outperformed multiple state-of-the-art models, including AMPpred-MFA and iAMP-Attenpred, in terms of accuracy, MCC, G-measure and F1-score. Given its high and robust performance, SAMP V2 could significantly accelerate the discovery of next-generation antimicrobial therapeutics for addressing the global threat of multidrug-resistant pathogens.

Protein language models (pLMs) have enabled strong benchmark performance in biological relation-prediction tasks, but aggregate metrics do not identify which sources of information support that performance. We examined three case studies-MetaESI, DeepGNHV, and SAGEPhos-using frozen pLM full-input baselines, endpoint- or site-restricted controls, clean train-derived prior controls, and a restriction-matched selector control. Frozen pLM-derived inputs coupled to generic downstream learners reached AUROC/AUPRC of 0.827/0.703 for the current MetaESI full-input rerun, 0.922/0.708 for a DeepGNHV two-endpoint baseline, and 0.896/0.893 for SAGEPhos. Restricted controls retained task-dependent signal. Most notably, a self-label-excluding MetaESI endpoint-frequency control reached 0.846/0.676 under the row split, numerically close to the frozen ESM2 full-input reference despite using no sequence embeddings. Clean full-catalog DeepGNHV endpoint priors and SAGEPhos kinase/substrate/site-window priors provided supplementary diagnostics rather than direct architecture-contribution estimates. In a separate fixed frozen-pooling LightGBM experiment, GARD-selected pooling did not show higher observed performance than count-matched random token pooling. Endpoint-cold diagnostics showed performance degradation, while train-label shuffling returned discrimination to approximately chance; hard- or matched-negative and family- or homology-aware evaluations were not available across the case studies. These findings do not diagnose leakage, imply memorization, exclude biological learning, or invalidate the evaluated models. Rather, they show that benchmark utility and performance attribution are distinct: architecture-specific, relation-specific, selector-specific, and generalization claims require controls matched to the interpretation being made.

Background and objectiveGene regulatory networks are formed by complex regulatory relationships between transcription factors and their target genes. A systematic understanding of these regulatory relationships is crucial for deciphering the molecular mechanisms that underlie cell state transitions under physiological and pathological conditions. Single-cell expression data can reveal cell-type-specific transcriptional regulation, and computational methods have recently been developed to infer gene regulatory networks from single-cell transcriptomics and prior regulatory knowledge. However, existing methods could not explore the common and specific information in expression correlations and prior regulatory knowledge, which can adversely affect prediction performance. MethodsWe propose a novel method for inferring gene regulatory networks from single-cell RNA sequencing data. The proposed method consists of dual-channel graph neural networks and a weight-shared common graph neural network, enabling effective fusion of prior regulatory knowledge with gene co-expression patterns. Furthermore, we formulate a new computational framework built upon the proposed algorithm, which integrates differential gene expression profiles and regulatory changes to identify key regulators that distinguish different cell states. ResultsExperimental results demonstrate that our method significantly improves the accuracy of regulatory inference across multiple datasets, outperforming other state-of-the-art approaches. Our method also exhibits robustness to noise and missing data. Analysis of two single-cell expression datasets suggests that the proposed framework could help identify key regulators involved in tumor metastasis and drug resistance. ConclusionThese results indicate that the proposed method could advance the understanding of the biological mechanisms underlying diseases by reconstructing single-cell gene regulatory networks and identifying key regulators across different cell states.

Cysteine and serine proteases act as an immune hub in the plant apoplast to provide robust extracellular immunity during microbial colonisation. Microbial pathogens counteract these immune proteases by inhibiting their activity using small secreted proteins (SSPs). Traditionally, SSPs with protease-inhibitory activity are predicted using sequence-dependent database searches. However, in recent years, fungal SSPs have been shown to exhibit protease-inhibitory functions despite lacking the inhibitor domain that is annotated through sequence similarity searches. Hence, a large number of these novel SSPs with putative protease inhibitor functions are missed during detection and filtered out during sequence similarity searches. This necessitates the development of newer approaches to predict SSPs lacking an annotated inhibitor domain. Machine learning approaches, such as protein language models, have emerged as powerful tools for predicting protein functions. To date, no machine learning models have been developed to predict the protease-inhibitory activities of SSPs lacking an annotated inhibitor domain. Here, we introduce a protease inhibitor prediction pipeline, PINPOINT (Protease INhibitor PredictiOn at plant-pathogen INTerface). The PINPOINT pipeline combines fine-tuned protein language model classifiers, a structure-aware autoencoder, and effector prediction into a multi-level framework for identifying SSPs with predicted protease inhibitor functions. PINPOINT predicts protease inhibitors using SSPs sequences and monomeric structures with pre-computed structures obtained from the AlphaFold Protein Structure Database or predicted using the ESMFold public API. We successfully validated the PINPOINT platform using SSPs from the plant fungal pathogen Macrophomina phaseolina. Notably, the PINPOINT platform robustly predicted several of these SSPs as protease inhibitors including Sequence-unrelated but structurally similar (SUSS) effectors. We further validated the inhibitory potential of these predicted M. phaseolina SSPs using AlphaFold Multimer (AFM) screening against candidate apoplastic soybean cysteine and serine proteases. Additionally, this platform can be used as a pre-filtering step in AFM screening approaches to reduce the number of candidates for discovering novel SSPs with protease inhibitor function for cross-kingdom plant-microbe interaction studies. The PINPOINT platform will accelerate the prediction of novel SSPs including SUSS effectors with protease inhibitor functions in proteomes of any organisms. We made the PINPOINT pipeline accessible to the research community as a web-based notebook environment for interactive computing in Google Colab, available at https://github.com/iitj-mpg-lab/PINPOINT

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.