Now, a team of researchers from Universidad de Magallanes in Punta Arenas, Chile, the Data Science Institute at Universidad del Desarrollo in Santiago, and PEACCEL in Paris has unveiled MAOMAO (Metadata-Aware Ontology for Multi-source Annotation Organization), an ontology-guided resource designed to bring coherence to the fragmented landscape of peptide toxicity data. Published in Frontiers in Pharmacology as a data report in the Predictive Toxicology section, the resource integrates toxicity information from 56 publicly available databases, literature-derived resources, supplementary datasets, and manually curated repositories into a unified, FAIR-oriented framework that preserves evidence, provenance, and metadata at every step.

The problem MAOMAO addresses is deceptively simple but technically profound. Toxicity annotations for peptides have accumulated across public databases, literature-derived resources, supplementary datasets, and individual experimental studies, but these sources employ heterogeneous terminology, annotation criteria, and metadata standards. A peptide described as haemolytic in one database might appear as hemolytic in another, while cytolytic activity in one source could correspond to cytolysis in a different resource. These inconsistencies complicate integration, reproducibility, and large-scale analysis, and they can introduce annotation ambiguity, conflicting evidence, incomplete metadata, and limited provenance tracking that reduce the reliability of downstream computational reuse.

MAOMAO standardizes toxicity terminology by mapping alternative spellings, synonyms, and source-dependent nomenclature to a unified vocabulary while preserving the original biological meaning. The resource then organizes harmonized annotations within a hierarchical toxicity ontology centered on the root category Toxic, which comprises four primary classes: Cytotoxic, Neurotoxic, Embryotoxic, and Ichthyotoxic. The Cytotoxic branch is further subdivided into Hemolytic, Cytolysis, and Anti-mammalian-cell activity, preserving more specific biological contexts. Hemolytic denotes toxicity involving erythrocyte lysis, whereas Cytolysis captures cell lysis or membrane-disruptive activity without a specified cell type, and anti-mammalian-cell activity denotes damage to mammalian cells or reduced cell viability.

The construction workflow began with structured exploration of the peptide toxicity landscape using scientific search engines, bibliographic repositories, specialized peptide databases, review articles, and citation tracking. Searches combined general terms such as peptide toxicity, toxic peptides, and toxic peptide databases with endpoint-specific queries for hemolytic, cytotoxic, cytolytic, neurotoxic, embryotoxic, ichthyotoxic, and anti-mammalian-cell peptides. Candidate resources were evaluated against predefined eligibility criteria, including relevance to at least one MAOMAO toxicity endpoint, availability of peptide sequences with corresponding categorical toxicity annotations or quantitative toxicity measurements, sufficient provenance information, and the possibility of programmatic or manual retrieval. Resources lacking retrievable sequences or containing only numerical representations, peptide names, or functional annotations without corresponding sequences were excluded.

Retrieved records underwent standardized preprocessing that included sequence validation, format standardization, annotation parsing, identifier normalization, and quality control. The final resource was restricted to peptides containing the 20 canonical amino acids and lengths between 5 and 70 residues. Exact duplicates within each source were removed, while identical sequences reported by different sources were retained to preserve provenance and support evidence integration. Each normalized sequence was assigned a deterministic identifier generated by applying SHA-256 to the UTF-8 encoding of the uppercase, whitespace-free sequence, providing a stable key for linking records across all resource layers. Quantitative HC50, LC50, LD50, and MHC observations were parsed while preserving their reported relation, value, unit, and provenance.

Because the same peptide sequence could be reported with different toxicity annotations across sources, MAOMAO applied an evidence-management framework to classify each peptide-endpoint pair as positive, negative, ambiguous, unlabeled, or no information. Positive states represented direct or hierarchy-supported toxicity evidence, whereas negative states corresponded to direct endpoint-specific non-toxic evidence. Ambiguous states captured conflicting or unresolved annotations, unlabeled states denoted sequences retained in endpoint-specific sources without an explicit class assignment, and no information indicated the absence of evidence for that endpoint. Negative evidence was further classified as strong or weak according to the supporting information available in the original source, with strong negatives explicitly supported by experimental evidence and weak negatives originating from randomly selected negative sets or lacking confirmation of the absence of toxicity annotations.

The final release comprises 71,857 unique peptide sequences across eight toxicity-related endpoints, organized into 574,856 sequence-endpoint combinations together with standardized metadata and provenance records. Of 1,372,190 non-deduplicated source-level records initially collected, 898,637 were retained after source-specific preprocessing, representing a reduction of approximately 34.5 percent. Across the resource, 31,153 states were positive, 91,506 negative, 15,717 ambiguous, and 5,044 unlabeled. The Toxic root category contained 57,080 available peptide-endpoint states, including 13,824 positives, while the Cytotoxic class held 25,454 available states with 7,122 positive. Hemolytic had the highest proportion of ambiguous states at 19.05 percent and was the only endpoint with unlabeled states, representing 14.03 percent of its available annotations. Notably, 7,331 of the 9,421 peptides with at least one positive annotation across the seven non-root endpoints were assigned to multiple toxicity categories, corresponding to 77.82 percent of positive peptides across these endpoints.

MAOMAO is organized into complementary functional layers that separate harmonized biological data, computational representations, benchmark resources, and supporting documentation while preserving interoperability. The Core Layer contains harmonized peptide sequences, toxicity annotations, ontology mappings, evidence classifications, provenance information, and metadata, along with 169 quantitative HC50, LC50, LD50, and MHC measurement records. The Descriptor Layer provides 41 features capturing sequence composition and physicochemical properties, generated using the Roxy package. The Embedding Layer includes 10 protein-language-model embedding matrices and a one-hot representation, all covering the complete set of 71,857 sequences, produced with the Sylphy package. The Benchmark Layer contains 300 endpoint-seed-strategy configurations generated through random and stratified five-fold partitioning of five eligible endpoints using 30 random seeds, corresponding to 1,500 data partitions and, across 11 numerical representations, 3,300 representation-specific configurations and 16,500 fold instances. The Documentation Layer includes ontology definitions, metadata schemas, resource descriptions, versioning records, and licensing information, with files distributed in standard formats including CSV, JSON, and YAML.

To facilitate direct reuse, MAOMAO provides five executable notebooks that operate on the released files rather than reconstructing the resource from original sources. These cover resource access, file validation, navigation of the Core Layer, and linkage of annotations, numerical representations, and benchmark partitions through stable sequence identifiers. Two additional notebooks illustrate downstream machine-learning reuse, including a neurotoxicity classification example that joins a released train-validation-test partition with an existing protein language model representation and evaluates logistic regression, a linear support vector machine, and random forest models using fixed settings, and a quantitative regression example showing how numerical toxicity measurements can be combined with a released sequence representation. The complete, versioned MAOMAO resource is archived on Zenodo, and code, workflows, notebooks, and environment specifications are available on GitHub under the MIT License. The researchers acknowledge that endpoint coverage depends on the availability of retrievable sequence-level evidence across curated sources, resulting in class imbalance and limited representation of some endpoints, particularly Cytolysis, Embryotoxic, and Ichthyotoxic, and that the predefined benchmark partitions rely on random and stratified splitting without homology- or similarity-based control. Future releases may address these limitations through the incorporation of newly available toxicity datasets, expanded endpoint and numerical-property coverage, metadata enrichment, updated numerical representations, and similarity-aware benchmark partitions.

Subject of Research: An ontology-guided FAIR resource for harmonized peptide toxicity data

Article Title: MAOMAO: an ontology-guided FAIR resource for harmonized peptide toxicity data

Article References: Soto-Garcia, N., García-Vinuesa, J., Uribe-Paredes, R., Murgas, L., Oróstica, K., González-Puelma, J., Navarrete, M. A., Cadet, F., & Medina-Ortiz, D. (2026). MAOMAO: an ontology-guided FAIR resource for harmonized peptide toxicity data. Frontiers in Pharmacology, 17, Article 1952924. https://doi.org/10.3389/fphar.2026.1952924

Image Credits: AI Generated

DOI: 10.3389/fphar.2026.1952924

Keywords: MAOMAO, peptide toxicity, FAIR principles, ontology, predictive toxicology, machine learning, therapeutic peptides, data harmonization, protein language models, bioinformatics, ontology-guided, FAIR

The central premise of the collection is that toxicology can no longer operate as a reactive science that merely documents harm after it occurs. Instead, the editors contend, the discipline must integrate risk evaluation and environmental surveillance into proactive, multidisciplinary frameworks. The studies assembled in the special issue span contamination monitoring, remediation, sustainable technological progress, and policy-relevant assessment, reflecting a deliberate effort to bridge laboratory discoveries with real-world environmental management. What emerges is a portrait of a field that increasingly treats pollution not as a series of isolated incidents but as a systems problem demanding chemistry, engineering, data science, and forensic methodology in equal measure.

Among the most striking contributions highlighted in the editorial is research on the thermal pretreatment of water hyacinth, one of the world’s most notorious invasive aquatic plants. Rather than treating the fast-spreading biomass as a disposal burden, the work demonstrates that it can be converted into value-added biofuels, including bioethanol and biomethanol. The approach exemplifies circular economy thinking: an ecological nuisance becomes a feedstock, waste management becomes renewable energy generation, and the economics of removal are partially offset by the value of the fuel produced. For regions where water hyacinth chokes lakes and rivers, threatening fisheries, hydropower intakes, and biodiversity, the prospect of a remediation strategy that pays for itself carries obvious appeal.

The sustainability theme extends beyond biomass into the factory floor. The special issue also features advances in sustainable machining through nanofluid-assisted minimum quantity lubrication, a technique that dramatically reduces the volume of cutting fluid required in metalworking operations. Conventional machining floods cutting zones with lubricants that generate hazardous waste and occupational exposures; by delivering engineered nanoparticles suspended in minute quantities of fluid precisely where they are needed, the process maintains industrial output while slashing environmental impact. It is a reminder, the editors suggest, that green chemistry principles are not confined to environmental laboratories but can reshape heavy industry itself.

Water resources occupy a central place in the collection, reflecting their status as the primary conduit through which many contaminants reach human populations. One study applies geographic information system technologies combined with multi-criteria evaluation to assess groundwater potential across a watershed, providing a quantitative foundation for sustainable water resource planning. By layering environmental variables and weighting them systematically, such approaches allow planners to identify where aquifers are most productive and most vulnerable, informing decisions about extraction, protection zones, and land use before contamination crises develop.

Complementing that work, another study examines how land cover alteration and slope gradient influence the physicochemical properties of soil. The findings offer critical insight into how anthropogenic pressures, such as deforestation and agricultural conversion, interact with geomorphological factors to degrade soil health and alter the dynamics of contaminant transport. Because soils act as both sinks and sources for pollutants, understanding these interactions is essential for predicting how toxins move through landscapes and ultimately into food chains. The research underscores that contaminant risk assessment must account for terrain and land management, not merely chemical concentration.

The special issue also confronts emerging contaminants head-on, with a comprehensive evaluation of lithium in the Anthropocene standing out as particularly timely. Lithium demand has surged with the global transition to batteries and electric vehicles, and the review documents escalating accumulation, bioavailability, and potential health ramifications of the metal in the environment while also surveying remediation strategies. The concern is characteristic of a broader pattern in modern toxicology: technologies celebrated as solutions to one crisis, in this case fossil fuel dependence, can seed the next contamination problem if their life cycles are not managed carefully. Alongside this, the synthesis of multi-walled carbon nanotubes combined with copper-based Cu-BDC metal-organic frameworks for the photocatalytic degradation of methylene blue dye demonstrates how nanostructured materials can break down persistent industrial pollutants in wastewater, turning engineered nanomaterials into instruments of cleanup rather than sources of concern.

Perhaps the most transformative thread running through the collection is the rise of artificial intelligence and data-centric methodologies. One contribution applies explainable deep reinforcement learning to climate forecasting, offering a modeling framework that is not only adaptive but transparent, addressing the long-standing criticism that machine learning predictions arrive as inscrutable black boxes. More consequentially for toxicology itself, AI and machine learning-driven computational models for toxicity prediction signal a decisive shift toward predictive toxicology. Instead of relying solely on slow and expensive animal and cell-based experiments, researchers can screen vast chemical spaces computationally, flagging hazardous compounds before they enter commerce or the environment and accelerating risk assessment at a pace conventional methods cannot match.

In a notably innovative turn, the collection bridges environmental science with criminal investigation through what the editors describe as green forensics. One study presents the effective use of an eco-friendly reagent derived from eggshells to detect latent fingerprints on objects that have been immersed in water, a scenario that defeats many conventional fingerprinting techniques. The work highlights how sustainable, low-cost materials can serve forensic science while simultaneously reducing the toxic chemical burden that traditional reagents impose on technicians and evidence alike. It is a vivid illustration of the editors’ broader argument that green chemistry principles can permeate disciplines far beyond pollution control, linking environmental responsibility with the practical demands of justice.

Taken together, the contributions assembled by Awasthi, Sankhla, and Kumar sketch a multidisciplinary strategy for the future of environmental toxicology, one that integrates environmental chemistry, engineering, data science, and forensic methodologies around the shared goals of pollutant detection, sustainable remediation, risk mitigation, and policy-relevant insight. The editors are candid about the road ahead: laboratory-scale successes must now progress to field validation, scaling, and practical implementation if they are to deliver real environmental safety and resilience. For scholars, policymakers, and practitioners engaged in sustainable environmental management, the collection offers both a status report and a roadmap, arguing that the most effective responses to complex toxicological challenges will come not from any single discipline but from the deliberate fusion of green technology, advanced materials, and intelligent systems working in concert.

Subject of Research: Emerging sustainable technologies, artificial intelligence, and forensic innovations for assessing and mitigating environmental toxicity and human health risks

Article Title: Advancing environmental toxicology through sustainable technologies, intelligent systems, and forensic innovations

Article References: Awasthi, K. K., Sankhla, M. S., & Kumar, R. (2026). Advancing environmental toxicology through sustainable technologies, intelligent systems, and forensic innovations. Environmental Science and Pollution Research, 33(29), 14710-14711. https://doi.org/10.1007/s11356-026-38206-9

Image Credits: AI Generated

DOI: 10.1007/s11356-026-38206-9

Keywords: environmental toxicology, water hyacinth biofuels, circular economy, minimum quantity lubrication, groundwater GIS mapping, lithium contamination, metal-organic frameworks, photocatalytic degradation, predictive toxicology, explainable deep reinforcement learning, green forensics, latent fingerprint detection

The core problem is deceptively simple. When researchers evaluate a toxicity model, they typically shuffle their dataset randomly and hold out a fraction for testing. But chemical datasets are full of close molecular relatives, analogs that differ only by a small substituent yet share nearly identical structures. Under random splitting, a near-twin of a test compound often sits in the training data, and the model effectively memorizes the answer rather than learning generalizable chemistry. ToxBench was designed to measure this inflation directly rather than assume it away.

The benchmark assembles three widely used toxicology datasets: Tox21, covering 7,538 compounds across 12 toxicity endpoints; ClinTox, with 1,379 compounds and 2 tasks focused on clinical toxicity; and SIDER, containing 1,350 compounds and 27 side-effect tasks. All three were processed through a transparent standardization pipeline in which the removal of compounds with conflicting labels is explicitly reported, an unusual level of bookkeeping that makes the benchmark reproducible from end to end.

Four model classes were put through their paces: Random Forest, XGBoost, a multilayer perceptron, and a Graph Neural Network that reads molecules as molecular graphs. Each model was trained under both random and Bemis-Murcko scaffold-based splits, the latter grouping compounds by their shared molecular scaffold so that entire structural families fall on one side of the divide. Every configuration was repeated across five independent random seeds, yielding 120 distinct experimental conditions, a deliberate hedge against the luck-of-the-draw variability that plagues small molecular datasets.

The headline finding is stark. Moving from random to scaffold splitting reduced the area under the receiver operating characteristic curve, or AUROC, by 0.057 to 0.079 points across all four model classes on Tox21, with a mean drop of 0.070. On SIDER, three of the four models lost 0.031 to 0.035 AUROC points. In a field where claimed improvements between competing algorithms are often smaller than that margin, the implication is uncomfortable: a substantial share of the progress reported in predictive toxicology may reflect leakage rather than genuine learning.

Crucially, the authors refused to treat scaffold splitting as a magic fix. Instead of assuming that grouping by scaffold eliminates leakage, they audited the residual structural similarity between training and test sets directly. On Tox21, the fraction of test compounds with a nearest-neighbor Tanimoto similarity above 0.6 to the training set falls from 43.9 percent under random splitting to 12.1 percent under scaffold splitting. That is a dramatic reduction, but it means roughly one test compound in eight still has a close chemical cousin in the training data, and the benchmark quantifies this residue rather than ignoring it.

Not every dataset behaved as expected. ClinTox, the smallest of the three, showed a reversed performance ordering between split types, and its seed-to-seed variance of plus or minus 0.085 to 0.160 AUROC points confirmed that results on this dataset are dominated by sampling noise rather than by the split strategy itself. With extreme class imbalance and only 1,379 compounds, ClinTox serves as a cautionary tale: benchmarks built on small, skewed datasets can produce rankings that are essentially statistical artifacts.

The study also tackled a question that receives far less attention than raw accuracy: whether a model’s predicted probabilities mean what they say. When a toxicity model reports an 80 percent chance of hepatotoxicity, regulators and medicinal chemists need that number to be calibrated, meaning that among compounds assigned that score, roughly 80 percent really are toxic. Post-hoc calibration cut the expected calibration error by 67 to 68 percent on ClinTox, showing that reliable probability estimates are achievable with simple corrections. On Tox21 and SIDER, raw Random Forest predictions were already well calibrated, with expected calibration errors of just 0.018 and 0.057 respectively, and post-hoc methods added nothing. Scaffold splitting, however, consistently worsened calibration across all three datasets, meaning the harder, more honest evaluation regime also produces less trustworthy probabilities.

The benchmark’s third pillar addresses a practical question for anyone deploying these models: when should they be trusted at all? Applicability domain analysis revealed a consistent positive relationship between the Tanimoto similarity of a test compound to its nearest training neighbor and predictive reliability, with low-similarity compounds showing notably reduced AUROC under scaffold splitting. In other words, models are most trustworthy for compounds that resemble their training data, and performance degrades predictably as inputs drift into unfamiliar chemical space. Ensemble-based uncertainty estimates proved useful here too: filtering out predictions the model itself was not confident about improved AUROC by up to 0.025 points on SIDER, offering a simple operational rule for flagging unreliable outputs before they reach a decision-maker.

Together, these analyses turn ToxBench into more than a leaderboard. The authors argue that scaffold splitting, multi-seed evaluation, and applicability domain filtering should become standard practice in toxicity prediction benchmarking, and their leakage audit provides a template for how to verify that a split is genuinely doing its job. For a field whose predictions increasingly inform drug safety decisions, the message is clear: reported accuracy is only as credible as the split that produced it, and knowing when a model is guessing outside its comfort zone may matter as much as how often it is right.

Subject of Research: A leakage-audited multi-task benchmark evaluating machine learning models for predictive toxicology with calibration, uncertainty, and applicability domain analysis

Article Title: ToxBench: a leakage-audited multi-task benchmark for predictive toxicology with calibration, uncertainty, and applicability domain analysis

Article References: Kartic, Seo, Y., Yi, S., & Park, T.-S. (2026). ToxBench: a leakage-audited multi-task benchmark for predictive toxicology with calibration, uncertainty, and applicability domain analysis. BMC Bioinformatics. https://doi.org/10.1186/s12859-026-06621-x

Image Credits: AI Generated

DOI: 10.1186/s12859-026-06621-x

Keywords: predictive toxicology, machine learning, data leakage, scaffold splitting, ToxBench, probability calibration, uncertainty quantification, applicability domain, Tox21, ClinTox, SIDER, graph neural networks