RNA velocity prediction via neural ordinary differential equation.

RNA velocity is a crucial tool for unraveling the trajectory of cellular responses. Several approaches, including ordinary differential equations and machine learning models, have been proposed to interpret velocity. However, the practicality of these methods is constrained by underlying assumptions. In this study, we introduce SymVelo, a dual-path framework that effectively integrates high- and low-dimensional information. Rigorous benchmarking and extensive studies demonstrate that SymVelo is capable of inferring differentiation trajectories in developing organs, analyzing gene responses to stimulation, and uncovering transcription dynamics. Moreover, the adaptable architecture of SymVelo enables customization to accommodate intricate data and diverse modalities in forthcoming research, thereby providing a promising avenue for advancing our understanding of cellular behavior.

Self-supervised graph representation learning integrates multiple molecular networks and decodes gene-disease relationships.

Leveraging molecular networks to discover disease-relevant modules is a long-standing challenge. With the accumulation of interactomes, there is a pressing need for powerful computational approaches to handle the inevitable noise and context-specific nature of biological networks. Here, we introduce Graphene, a two-step self-supervised representation learning framework tailored to concisely integrate multiple molecular networks and adapted to gene functional analysis via downstream re-training. In practice, we first leverage GNN (graph neural network) pre-training techniques to obtain initial node embeddings followed by re-training Graphene using a graph attention architecture, achieving superior performance over competing methods for pathway gene recovery, disease gene reprioritization, and comorbidity prediction. Graphene successfully recapitulates tissue-specific gene expression across disease spectrum and demonstrates shared heritability of common mental disorders. Graphene can be updated with new interactomes or other omics features. Graphene holds promise to decipher gene function under network context and refine GWAS (genome-wide association study) hits and offers mechanistic insights via decoding diseases from genome to networks to phenotypes.

Segmental duplication as potential biomarkers for non-invasive prenatal testing of aneuploidies.

BACKGROUND: Segmental duplication (SD) regions are distinct targets for aneuploidy detection owing to the virtual elimination of amplification bias. The difficulty of searching SD sequences for assay design has hampered their applications. METHODS: We developed a computational program, ChAPDes, which integrates SD searching, refinement, and design of specific PCR primer/probe sets in a pipeline to remove most of the manual work. The generated primer/probe sets were first tested in a multiplex multicolour melting curve analysis for the detection of five common aneuploidies. The primer/probe sets were then tested in a digital PCR assay for the detection of trisomy 21. Finally, a digital PCR protocol was established to quantify maternal plasma DNA sequences for the non-invasive prenatal detection of fetal trisomy 21. FINDINGS: ChAPDes could output 21,772 candidate primer/probe sets for trisomy 13, 18, 21 and sex chromosome aneuploidies within 2 working days. Clinical evaluation of the multiplex multicolour melting curve analysis involving 463 fetal genomic DNA samples revealed a sensitivity of 100% and specificity of 99.64% in comparison with the reference methods. Using the established digital PCR protocol, we correctly identified two trisomy 21 fetuses and thirteen euploid foetuses from the maternal plasma samples. INTERPRETATION: The combination of ChAPDes with digital PCR detection could facilitate the use of SD as potential biomarkers for the non-invasive prenatal testing of fetal chromosomal aneuploidies. FUNDING: None.

Broad-Spectrum Profiling of Drug Safety via Learning Complex Network.

Drug safety is a severe clinical pharmacology and toxicology problem that has caused immense medical and social burdens every year. Regretfully, a reproducible method to assess drug safety systematically and quantitatively is still missing. In this study, we developed an advanced machine learning model for de novo drug safety assessment by solving the multilayer drug-gene-adverse drug reaction (ADR) interaction network. For the first time, the drug safety was assessed in a broad landscape of 1,156 distinct ADRs. We also designed a parameter ToxicityScore to quantify the overall drug safety. Moreover, we determined association strength for every 3,807,631 gene-ADR interactions, which clues mechanistic exploration of ADRs. For convenience, we deployed the model as a web service ADRAlert-gene at http://www.bio-add.org/ADRAlert/. In summary, this study offers insights into prioritizing safe drug therapy. It helps reduce the attrition rate of new drug discovery by providing a reliable ADR profile in the early preclinical stage.

Karst rocky desertification progress: Soil calcium as a possible driving force.

Karst rocky desertification is a severe irreversible ecosystem failure. The karst ecosystem is so fragile that it is vulnerable to environmental changes, degrading into rocky desertification. Prior studies revealed the potential connections between the soil bacterial community, the edaphic properties and the aboveground vegetation cover in the karst ecosystem. However, how these three elements affect each other and work together in propelling in the karst rocky desertification progress largely remains unexplored. To answer this question, we monitored the bacterial community variations in soils sampled from multiple sites at a successional karst rocky desertification region by sequencing the 16S rRNA V3-V4 regions. Overall, we detected 34 bacterial phyla in the karst soils, of which Proteobacteria, Actinobacteria, and Acidobacteria are the most abundant. Network analysis of the bacterial community- vegetation-edaphic property-vegetation interactions identified 6 bacterial herds that had significant correlation with soil Ca2+ and available phosphorus change during vegetation degradation. Further functional simulation of these bacterial herds unveiled the change of Ca2+ and available phosphorus might disturb the soil carbon and nitrogen metabolism, and thus weakened soil quality. In summary, we hypothesized a calcium-driven bacterial response mechanism in the karst rocky desertification progress.

ADReCS-Target: target profiles for aiding drug safety research and application.

Delivering safe and effective therapeutic treatment to patients is one of the grand challenges in modern medicine. However, drug safety research has been progressing slowly in recent years, compared to other fields such as biotechnologies and precision medicine, due to the mechanistic complexity of adverse drug reactions (ADRs). To fill up this gap, we develop a new database, the Adverse Drug Reaction Classification System-Target Profile (ADReCS-Target, http://bioinf.xmu.edu.cn/ADReCS-Target), which provides comprehensive information about ADRs caused by drug interaction with protein, gene and genetic variation. In total, ADReCS-Target includes 66,573 pairwise relations, among which 1710 are protein-ADR associations, 2613 are genetic variation-ADR associations, and 63,298 are gene-ADR associations. In a case study of exploring the mechanism of rash, we find that HLAs, C1QA and APOA1 are the key gene players and thus can be potential targets (or biomarkers) in monitoring or countermining rashes. In summary, ADReCS-Target can be a useful resource for the biomedical scientific community by serving researchers in the fields of drug development, clinical pharmacology, precision medicine, and from web lab to high-throughput computational platform. Particularly, it helps to identify drug with better ADR profile and design safer drug therapy regimen.