Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2021.02.04.429840

Multi-task deep learning for concurrent prediction of protein structural properties

zhang, b.·Li, J.·Quan, L.·Lyu, Q.
View original source ↗Export metadata ↓

Abstract

Protein structural properties are diverse and have the characteristics of spatial hierarchy, such as secondary structures, solvent accessibility and backbone angles. Protein tertiary structures are formed in close association with these features. Separate prediction of these structural properties has been improved with the increasing number of samples of protein structures and with advances in machine learning techniques, but concurrent prediction of these tightly related structural features is more useful to understand the overall protein structure and functions. We introduce a multi-task deep learning method for concurrent prediction of protein secondary structures, solvent accessibility and backbone angles ({phi}, {psi}). The new method has main two deep network modules: the first one is designed as a DenseNet architecture a using bidirectional simplified GRU (GRU2) network, and the second module is designed as an updated Google Inception network. The new method is named CRRNN2. CRRNN2 is trained on 14,100 protein sequences and its prediction performance is evaluated by testing on public benchmark datasets: CB513, CASP10, CASP11, CASP12 and TS1199. Compared with state-of-the-art methods, CRRNN2 achieves similar, or better performance on the prediction of 3- and 8-state secondary structures, solvent accessibility and backbone angles ({phi}, {psi}). Online CRRN-N2 applications, datasets and standalone software are available at http://qianglab.scst.suda.edu.cn/crrnn2/.

Explore related subjects

bioinformaticsPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

zhang, b., Li, J., Quan, L., Lyu, Q.. 2021-02-05. Multi-task deep learning for concurrent prediction of protein structural properties. https://doi.org/10.1101/2021.02.04.429840

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

KEEP EXPLORING

Related preprints

bioRxiv2026

StableProt: Structure-Aware Deep Learning for Protein Thermostability (Tm) and Environmental Adaptation (OGT) Prediction

Predicting protein melting temperature (Tm) and organismal optimal growth temperature (OGT) is essential for enzyme engineering, biocatalyst design, and metagenomic bioprospecting, yet computational prediction faces several fundamental bottlenecks: sequence-only representations miss tertiary packing; dual-task coupling induces destructive gradient conflict; natural database skew (>87% mesophiles) drives mesophilic collapse; and existing tools produce uncalibrated point predictions. To address these challenges, we present StableProt, a structure-aware framework that couples amino acid sequences with Foldseek 3Di structural tokens via a frozen SaProt backbone to capture 3D contacts. Disjoint heads condition thermodynamic stability on ecological context without gradient conflict, while targeted 14% mesophilic subsampling expands thermophile representation to eliminate mesophilic collapse. Calibrated ensemble modeling reduces calibration error to 1.92%, providing dependable 95% confidence intervals. Evaluating models across 10{degrees}C temperature intervals reveals severe baseline collapse at thermal extremes, whereas StableProt maintains robust accuracy across regimes. On ProThermDB and zero-shot FireProtDB, StableProt achieves state-of-the-art probabilistic accuracy (CRPS = 4.52{degrees}C and 8.71{degrees}C) while recovering 92.0% of hyperthermophiles ([≥]80{degrees}C), and in prospective validation, its calibrated intervals capture both enzyme stability (75.3% coverage) and host environmental growth temperatures (78.1% coverage). StableProt is freely accessible as an interactive web server at https://stableprot.dixitlab.org/.

bioinformatics↗
bioRxiv2026

RoDPAA: A Robust Dissimilarity-Based Principal Angle Analysis Framework for Multi-View Microbiome Data Integration

Multiview microbiome studies profile the same participants across body sites or molecular layers, but integration is hampered by sparse, compositional data, modest sample sizes and methods that recognize only exact sharing. We present RoDPAA (Robust Dissimilarity-based Principal Angle Analysis), a framework that represents each view through any data-appropriate dissimilarity, such as Bray--Curtis, without log-ratio transformation or likelihood assumptions. RoDPAA aligns view-specific signal subspaces through principal angles, captures complete and partial sharing, and tests by permutation how many components are shared, using only eigendecomposition and little tuning. In Gaussian simulations, RoDPAA matched JIVE and MOFA given true ranks, ran faster and alone recovered the shared dimension in every replicate. In two inflammatory bowel disease (IBD) cohorts with sparse, zero-inflated data, Bray--Curtis-based RoDPAA recovered shared structure that was stable to prevalence filtering, whereas log-ratio-based alternatives were not. Its leading microbiome--metabolome factors, learned without disease labels, were the only ones associated with IBD.

bioinformatics↗
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↗