Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 11 appraisals
mAbs
Prediction of antibody non-specificity using protein language models and biophysical parameters
The development of therapeutic antibodies requires optimizing target binding affinity and pharmacodynamics, while ensuring high developability potential, including minimizing non-specific binding. In this study, we address this problem by predicting antibody non-specificity by two complementary approaches: (1) antibody sequence embeddings by protein language models (PLMs) and (2) a comprehensive set of sequence-based biophysical descriptors. We benchmark the PLM embeddings against interpretable, sequence-derived biophysical descriptors and use fragment-specific models (variable heavy (VH) and variable light (VL) chains, concatenated regions, and individual complementary-determining regions (CDRs) to identify region-level determinants of non-specificity in functional antibodies that bind defined targets. These models were trained on previously published human and mouse antibody data and tested on three public datasets. We show that non-specificity is best predicted from the VH domain and heavy-chain CDRs. These region-level analyses show that heavy-chain features, especially H-CDR3, dominate the predictive signal. The top performing PLM, a VH domain-based Evolutionary Scale Modeling 1 v LogisticReg model, resulted in 10-fold cross-validation accuracy of up to 71%. While predictive accuracy is comparable to classical machine-learning baselines, PLM-based embeddings provide sequence-context representations that yield consistent region-level attribution and provide complementarity to the classical models by enhancing the reliability of predicted non‑specificity scores when used in combination. Our biophysical descriptor-based analysis identified the isoelectric point as a key driver of non-specificity, consistent with previous reports. Our findings highlight the importance of biophysical properties in predicting antibody non-specificity and highlight the potential of PLMs for the development of antibody-based therapeutics. These conclusions are robust to alternative class definitions and are not driven by VH-VL mutational bias. We illustrate the generalizability and practical use of the PLM approach by extending it to therapeutic antibodies and nanobodies, providing a tool for early-stage developability assessment, and we make the models publicly available.
29 May 2026
Read appraisal →Chembiochem : a European journal of chemical biology
Mutant-Initiated Structure-Guided Refinement Enables Second-Generation Compact IscB Genome Editors
Compact RNA-guided nucleases such as IscB represent an attractive foundation for next-generation genome editors, yet their application in mammalian cells has been constrained by suboptimal activity. Here, instead of re-engineering enzymes, we establish a mutant-initiated, structure-guided optimization strategy to generate second-generation high-activity IscB editors. Using AlphaFold3 to model the engineered IscB*-ωRNA-DNA complex, we reveal remodeling of the nucleic-acid-binding interface induced by activity-enhancing substitutions. Guided by this predicted structure, we perform a focused mutational scan and identify V367 as an activity hotspot. Saturation mutagenesis at this position yields a single substitution, V367Y (IscB*-Act), which increases mean editing efficiency by 34% and achieves up to 2.1-fold improvement across endogenous targets in mammalian cells. Importantly, the V367Y substitution is transferable to an IscB-based adenine base editor, elevating A-to-G conversion by 68% on average and up to 4.46-fold at individual loci without altering the intrinsic editing window. Targeted off-target profiling at loci suggests that V367Y does not substantially increase off-target indels or A-to-G conversion. Together, our work demonstrates a practical framework for second-generation refinement of compact genome editors, bridging deep-learning-enabled structural prediction with interpretable protein engineering, and expands the functional potential of miniature IscB systems for both nuclease and base editing applications.
27 May 2026
Read appraisal →Molecular cell
Rapid customization of base editors via machine learning-powered combinatorial mutagenesis
Being able to control the complementarity and hindrance between target DNA and base editor proteins enables precise, bystander-free editing. Here, we combined combinatorial mutagenesis with machine learning to analyze and engineer these interactions at scale. By profiling DNA motif preferences across 160,000 evoAPOBEC1 and 64 million TadA variants in human cells, we used as little as 0.004% of the mutational landscape to make predictions. This identified variants with motif-specific activity and eliminated residual adenine editing in cytosine base editors. In correcting >800 disease-associated mutations, our variants outperformed previous versions in precluding unintended edits at purine motifs, achieving undetectable bystander edits in 50% of cases. Additionally, a pre-trained, structure-based deep learning model predicted functional TadA variants with 63% success across 2026 variants spanning 26 amino acid sites, without experimental data and in a single prediction round. These approaches streamline the re-engineering of base editors for enhanced precision tailored to specific targets.
23 May 2026
Read appraisal →Journal of agricultural and food chemistry
Serum-Free Media in Cellular Agriculture: Current Challenges, Design Strategies, and Future Prospects
Cellular agriculture (CA), an emerging and sustainable agricultural paradigm, offers a promising solution to global challenges in food security and environmental sustainability. However, the large-scale manufacturing of CA is hindered by its dependence on serum-based culture media, which are costly and compositionally variable and raise biosafety and animal welfare concerns. Addressing this bottleneck requires the development of affordable, reliable, and ethically compliant serum-free media (SFM). This perspective elucidates the functional roles of serum components, summarizes recent advances in serum substitutes, and highlights microorganism-derived substitutes as particularly promising because of their low cost, compositional stability, and scalability. Furthermore, we outline the evolution of SFM formulation from empirical and design-of-experiment-based optimization to multiomics-driven formulation and artificial intelligence (AI)-assisted design. Overall, this review provides a focused framework for understanding current challenges, design strategies, and future directions of SFM development for CA.
15 May 2026
Read appraisal →mAbs
Machine learning predictions of IgG1 and IgG4 self-association and high-concentration solution properties
To meet the widespread demand for subcutaneous delivery of antibody therapeutics, candidates with low viscosity, high solubility, and/or low aggregation propensity in concentrated formulations must be identified. Moreover, early identification of candidates with low self-association increases the likelihood of success at later stages of the development process. Here, we experimentally profile the self-association behavior of a panel of clinical-stage antibodies as a function of pH, excipient content, and antibody isotype. We find that acidic formulations (pH 5) with proline (200 mM) are most effective at suppressing self-association for both IgG1 and IgG4 variants. Moreover, our self-association measurements are correlated with antibody viscosity measurements and inversely correlated with antibody recovery after their concentration using membrane filters. Notably, we developed interpretable machine learning-based classifier and regressor models for predicting IgG1 and IgG4 self-association and demonstrated that they identify antibodies with favorable high-concentration properties. These findings are expected to improve the antibody development process by facilitating the identification of drug-like molecules during their discovery and optimization.
13 May 2026
Read appraisal →Science advances
Repertoire-scale antibody structural prediction informs therapeutic design
We present AF3-TurboAb, a scalable framework that makes a repertoire-scale antibody-antigen complex structural decoding routine for antibody engineering. By eliminating preprocessing bottlenecks, AF3-TurboAb enables end-to-end complex modeling in 0.5 minutes per seed on a single GPU while preserving near-experimental interface fidelity, as validated on ~1000 posttraining Protein Data Bank (PDB) benchmarks and 12 experimentally determined cryo-electron microscopy nanobody-antigen structures. Applying this capability to 275,371 immunization-derived antigen-specific nanobodies produced 28,013 high-confidence complex predictions, substantially expanding the structural landscape of antibody recognition. The resulting atlas reveals hundreds of previously unmapped epitopes, extensive coverage of solvent-exposed surfaces, and recurrent affinity hotspots enriched in aromatic and charged residues. Despite wide sequence diversity, we observe structural convergence at shared epitopes and consistent physicochemical and geometric features that complement and extend existing PDB entries. We demonstrate translational utility by (i) designing durable (escape-proof), multiepitope neutralizers against highly evolved viruses, (ii) identifying cross-species and glycoform-specific binders to a cancer checkpoint, and (iii) enabling near-real-time in silico binder triage. The models and metadata will be shared for community use, establishing repertoire-scale structural decoding as a practical design modality that transforms the scale and speed of structure-guided antibody engineering.
27 Apr 2026
Read appraisal →Chemical Society reviews
Machine learning-driven molecular engineering of nucleic acids
Molecular engineering has played a pivotal role in biomedical fields, driving significant advancements in gene therapy, disease diagnosis, and biosensing. However, nucleic acid molecular engineering faces various challenges including vast design spaces, complex structure-function relationships, lengthy application validation cycles, and inefficient optimization processes. Machine learning (ML), with its superior pattern recognition, multidimensional data integration, and automated optimization capabilities, offers a unique opportunity to construct predictive models of sequence-structure-function relationships, thereby enabling a paradigm shift from empirically driven to data-driven approaches. This review systematically surveys recent progress in ML applications across three major domains: nucleic acid structure construction, performance modulation, and application expansion. It also explores core challenges such as data quality, model interpretability, and experimental validation efficiency, along with potential resolution strategies. These insights are poised to propel nucleic acid molecular engineering from static structure prediction toward dynamic behavior simulation, and from single-molecule design to complex system engineering, guiding future directions in hybrid ML-quantum models and expanded applications to non-canonical nucleic acids for transformative innovation in biomedicine, environmental monitoring, and information technology.
20 Apr 2026
Read appraisal →Journal of chemical information and modeling
zERExtractor: An Automated Platform for Enzyme-Catalyzed Reaction Data Extraction from Scientific Literature
The rapid expansion of enzyme reaction literature has created a major bottleneck in database curation, leaving vast amounts of enzyme-substrate-condition relationships unstructured and inaccessible for DL-driven modeling. How to fully utilize the enzymatic reaction data has been an important task for future accurate enzyme activity prediction models. Current deep learning (DL)-based data extraction models heavily rely on large language models (LLMs) without a fidelity check and the ability to continuously evolve. To address these issues, we developed zERExtractor (Zelixir's Enzyme Reaction Data Extractor), an accuracy-oriented and extensible platform for extracting enzyme-catalyzed reaction data from scientific publications. This system offers a unified multimodal information extraction framework (covering molecular reaction diagrams, tables, and texts) to integrate enzymatic reaction descriptors into structured storage. We employ fine-tuned large LLMs together with DL in a human-in-the-loop pipeline that evolves through data fidelity validation by experts and active learning. Also, zERExtractor achieves 89.9% accuracy in table recognition and over 98% accuracy in molecular image recognition on synthetic data sets, outperforming the strongest baseline by more than 2% and consistently maintaining above 95% on realistic benchmarks. zERExtractor bridges the data gap in enzyme reaction data with a scalable framework for accurate multimodal extraction, advancing DL-driven enzyme modeling and enabling future applications in computational enzymology and biotechnology. The platform is publicly accessible online at https://zpaper.zelixir.com/.
14 Apr 2026
Read appraisal →mAbs
Deep learning assessment of nativeness and pairing likelihood for antibody and nanobody design with AbNatiV2.
Most immune-system created antibodies balance good binding and stability with low toxicity and self-reactivity. Quantifying the nativeness of a candidate sequence - its likelihood of belonging to natural immune repertoires - has thus emerged as a valuable strategy for hit selection from synthetic libraries, optimization and humanization, and for guiding de novo design toward developable candidates. We previously introduced AbNatiV, a transformer-based VQ-VAE for nativeness assessment, which proved effective across multiple nanobody engineering tasks. However, AbNatiV1 operated on unpaired sequences, limiting applicability to conventional VH-VL antibodies. Moreover, its performance on nanobody nativeness was constrained by the limited number and diversity of nanobody repertoires available at the time. Here, we sequenced new camelid repertoires, curated additional recent datasets, and present AbNatiV2: an enhanced architecture comprising various models each trained on ≥20 million sequences. AbNatiV2 improves nanobody nativeness classification across held-out and diverse test sets, and more robustly detects nativeness changes upon CDR grafting. We also introduce p-AbNatiV2, a cross-attention model fine-tuned on 3.7 million paired human sequences. p-AbNatiV2 provides residue- and sequence-level humanness for VH/VL pairs and learns pairing-likelihood via noise-contrastive training. On held-out tests, it assigns the native pair a higher score in 74% of cases, substantially outperforming recent pairing models. Together, AbNatiV2 and p-AbNatiV2 extend nativeness assessment and engineering to both nanobodies and conventional antibodies, supporting design decisions at single-residue, Fv-sequence, and paired-domain levels. AbNatiV2 is available as downloadable software and webserver.
8 Apr 2026
Read appraisal →Vaccine
Applied immunoinformatics in modern vaccine design: a comprehensive review of available computational tools
The rapid evolution of computational biology has transformed vaccine design from a largely empirical process into a rational, data-driven discipline. At the center of this transformation lies immunoinformatics, which integrates immunology, molecular biology, and data science to accelerate the identification, evaluation, and optimization of vaccine candidates. By enabling the systematic transition from genomic data to viable immunotherapeutic candidates, these approaches offer an unprecedented capacity to shorten development timelines, reduce costs, and broaden population coverage compared to traditional trial-and-error vaccine pipelines. This review provides a state-of-the-art overview of the currently available immunoinformatic tool that underpins modern vaccine design. From identification of conserved and functionally essential pathogen targets, advances in structural prediction, epitope mapping, safety assessment, and systems-level analyses of host-pathogen interactions, immunoinformatics allows researchers to design vaccines with enhanced success rate. Special emphasis is placed on the shift from purely predictive models toward generative frameworks, where artificial intelligence and deep learning now support not only the evaluation, but also the rational engineering of optimized vaccine candidates. For this review, we systematically examined more than 250 computational tools and algorithms spanning every stage of the vaccine discovery pipeline. From this extensive survey, we distilled and discussed the approaches that currently demonstrate the highest performance and practical usability, thereby providing researchers with a curated overview of some the most reliable resources available.
5 Apr 2026
Read appraisal →Science
Deep generative models design mRNA sequences with enhanced translational capacity and stability
Despite the success of messenger RNA (mRNA) COVID-19 vaccines, extending this modality to more diseases necessitates substantial enhancements. We present GEMORNA, a generative RNA model that uses transformer architectures tailored for mRNA coding sequences (CDSs) and untranslated regions (UTRs) to design mRNAs with enhanced expression and stability. GEMORNA-designed full-length mRNAs exhibited up to a 41-fold increase in firefly luciferase expression compared with an optimized benchmark in vitro. GEMORNA-generated therapeutic mRNAs achieved up to a 15-fold enhancement in human erythropoietin (EPO) expression and substantially elicited antibody titers of COVID vaccine in mice. Additionally, GEMORNA's versatility extends to circular RNA, substantially enhancing circular EPO expression and boosting antitumor cytotoxicity in chimeric antigen receptor T cells. These advancements highlight the vast potential of deep generative artificial intelligence for mRNA therapeutics.
1 Nov 2025
Read appraisal →