bioRxiv Science⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.64898/2026.09.30.755660

pre-miRBench: a multispecies benchmark and reference model for animal precursor microRNA prediction

Tzimotoudis, D.·Chatzitolios, V. K.·Alexiou, P.·Georgakilas, G.
View original source ↗Export metadata ↓

Abstract

Motivation: Precursor microRNA (pre-miRNA) prediction is used to prioritize genomic hairpins for miRNA annotation. Published predictors are trained and evaluated on different species collections, negative sets and data partitions, making reported gains difficult to compare. Results: We introduce pre-miRBench, a benchmark of 7,056 200-nt windows centered on curated pre-miRNA loci and 70,560 genomic negatives with predicted hairpin structures from 71 animal species, with a fixed 1:10 positive-to-negative ratio in every partition. Four test sets cross whether the species and miRNA family are represented in training: known species/known family, known species/held-out family, held-out species/known family, and held-out species/held-out family. We retrained six published pre-miRNA predictors (DeepMir, deepMiRGene, dnnPreMiR, mirDNN, miRe2e and MuStARD) under the same benchmark splits and evaluated them alongside the pre-miRBench model, an ensemble of three neural networks developed with Agentomics, an autonomous LLM-agent system for biomedical machine learning. The pre-miRBench model achieved the highest mean average precision (AP) across the four test sets (0.9809; dnnPreMiR, 0.9719) and led three tests. The two held-out species were Gallus gallus and Drosophila melanogaster, and the joint species-and-family holdout contained 69 positives and 690 negatives. dnnPreMiR had the highest AP on the joint species-and-family holdout (0.9677 versus 0.9659). The AP difference (pre-miRBench minus dnnPreMiR) was -0.0018, with a paired bootstrap 95% confidence interval of -0.0445 to 0.0341. pre-miRBench establishes a common evaluation for species and miRNA-family holdouts and provides a reproducible reference model for future comparisons. Availability and implementation: Reproducible source code is available at https://github.com/dimostzim/pre-miRBench. Datasets, trained model weights, record-level predictions, evaluation metrics and species-panel metadata for pre-miRBench and the six retrained predictors are available at https://zenodo.org/records/22813044.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Tzimotoudis, D., Chatzitolios, V. K., Alexiou, P., Georgakilas, G.. 2026-10-06. pre-miRBench: a multispecies benchmark and reference model for animal precursor microRNA prediction. https://doi.org/10.64898/2026.09.30.755660

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Deducing splicing events from transcript sets with splicelogic

Long-read RNA sequencing captures a greater proportion of full-length transcripts, enabling more accurate isoform identification, discovery of novel isoforms, and more precise differential transcript usage analysis. However, comparing transcripts, whether between conditions or between sets such as novel and annotated isoforms, yields complex isoform changes that are hard to manipulate, summarize, and visualize. This is compounded by vertical integration of some tools, where downstream analysis depends on the specific output of a particular upstream tool. To address this gap, we have developed splicelogic, an R/Bioconductor package that makes transcript-set comparisons biologically interpretable by turning them into discrete splicing events, such as exon skipping, alternative splice sites, intron retention, and alternative transcription start and end sites. We designed splicelogic to integrate easily with existing RNA-seq workflows and tools. The splicelogic functions are modular, readable, and extensible, making it easy for users to adapt core logic to their own custom scientific questions or novel splicing definitions. By obtaining interpretable splicing events from transcript changes, splicelogic enables downstream analyses, including annotation of RNA-binding protein recognition sites, alongside summary statistics and visualization. The splicelogic package is publicly available and distributed through Bioconductor.

bioinformatics↗
bioRxiv2026

Contrastive Learning Improves Generalization on M2OR Olfactory Binding Dataset

Olfaction-based biosensors stand to have profound impacts in fields such as medical diagnostics, national security, and drug discovery. A promising mode of vapor phase biodetection mimics volatile organic compound-olfactory receptor (VOC-OR) interactions with target-specific protein or peptide probes; however, lack of experimental coverage remains a core bottleneck. Current computational approaches aim to improve prediction of VOC-OR binding to reduce experimental burden, and current machine learning approaches fail to demonstrate a level of generalization that addresses current engineering challenges. Here, using the Molecular to Olfactory Dataset (M2OR) and Insect Olfactory Binding Protein Database (iOBPdb) datasets, data partitioning methods and their performance are evaluated on a neural network and contrastive learning framework on such VOC-OR binding datasets, varying: model training, architecture, and structure of the input data distribution. It was found that holding out certain chemical or proteomic motifs from the training data diminished model performance with a two layer neural network model. The model was able to generalize to state of the art performance (0.88 AUCROC) on every data split by applying a contrastive learning objective defined by shared molecular constituents and a stochastic sampler. This suggests the contrastive objective provides a strong inductive bias for neural networks to predict novel VOC-OR pairs. These findings highlight that model performance on pairwise biological interaction datasets can be inflated through identity leakage from constituent overlap, and emphasize the need for more robust evaluation protocols. Furthermore, we show contrastive regularization mitigates dataset degeneracy through enforcement of compatibility in the models latent geometry that may extend to other binder target-datasets where identity leakage confounds evaluation.

bioinformatics↗
bioRxiv2026

Plate design confounds donor variation and model evaluation in single-cell perturbation screens

Single-cell screens of immune cells from many donors are used to study why individuals respond differently and to benchmark response models. Each donor-perturbation combination typically occupies one well, controls are grouped, and donors share one layout, so technical effects can look biological. Using a 90-cytokine screen, two compound screens, four cohorts and simulations, we show that well effects explain most replicate-control variation in abundant cell types, controls carry a shared offset, and identical control wells differ by hundreds of differentially expressed genes at a standard threshold, about as many as two receptor-negative proteins do. Negative controls, design-aware estimators and perturbation-specific evaluation change the interpretation of four recent analyses. A deep-learning model that scores below a perturbation-agnostic predictor under standard evaluation outperforms a simple baseline on perturbation-specific differences in two of three cell types (significantly in one with stricter controls), but predicts less well the component shared with inert wells.

bioinformatics↗