Diverse Omics Data Research Articles

AMIR: a multi-omics data platform for Asteraceae plants genetics and breeding research.

As the largest family of dicotyledon, the Asteraceae family comprises a variety of economically important crops, ornamental plants and numerous medicinal herbs. Advancements in genomics and transcriptomic have revolutionized research in Asteraceae species, generating extensive omics data that necessitate an efficient platform for data integration and analysis. However, existing databases face challenges in mining genes with specific functions and supporting cross-species studies. To address these gaps, we introduce the Asteraceae Multi-omics Information Resource (AMIR; https://yanglab.hzau.edu.cn/AMIR/), a multi-omics hub for the Asteraceae plant community. AMIR integrates diverse omics data from 74 species, encompassing 132 genomes, 4 408 432 genes annotated across seven different perspectives, 3897 transcriptome sequencing samples spanning 131 organs, tissues and stimuli, 42 765 290 unique variants and 15 662 metabolites genes. Leveraging these data, AMIR establishes the first pan-genome, comparative genomics and transcriptome system for the Asteraceae family. Furthermore, AMIR offers user-friendly tools designed to facilitate extensive customized bioinformatics analyses. Two case studies demonstrate AMIR's capability to provide rapid, reproducible and reliable analysis results. In summary, by integrating multi-omics data of Asteraceae species and developing powerful analytical tools, AMIR significantly advances functional genomics research and contributes to breeding practices of Asteraceae.

MultiSC: a deep learning pipeline for analyzing multiomics single-cell data.

Single-cell technologies enable researchers to investigate cell functions at an individual cell level and study cellular processes with higher resolution. Several multi-omics single-cell sequencing techniques have been developed to explore various aspects of cellular behavior. Using NEAT-seq as an example, this method simultaneously obtains three kinds of omics data for each cell: gene expression, chromatin accessibility, and protein expression of transcription factors (TFs). Consequently, NEAT-seq offers a more comprehensive understanding of cellular activities in multiple modalities. However, there is a lack of tools available for effectively integrating the three types of omics data. To address this gap, we propose a novel pipeline called MultiSC for the analysis of MULTIomic Single-Cell data. Our pipeline leverages a multimodal constraint autoencoder (single-cell hierarchical constraint autoencoder) to integrate the multi-omics data during the clustering process and a matrix factorization-based model (scMF) to predict target genes regulated by a TF. Moreover, we utilize multivariate linear regression models to predict gene regulatory networks from the multi-omics data. Additional functionalities, including differential expression, mediation analysis, and causal inference, are also incorporated into the MultiSC pipeline. Extensive experiments were conducted to evaluate the performance of MultiSC. The results demonstrate that our pipeline enables researchers to gain a comprehensive view of cell activities and gene regulatory networks by fully leveraging the potential of multiomics single-cell data. By employing MultiSC, researchers can effectively integrate and analyze diverse omics data types, enhancing their understanding of cellular processes.

Advances in omics data for eosinophilic esophagitis: moving towards multi-omics analyses.

Eosinophilic esophagitis (EoE) is a chronic, allergic inflammatory disease of the esophagus characterized by eosinophil accumulation and has a growing global prevalence. EoE significantly impairs quality of life and poses a substantial burden on healthcare resources. Currently, only two FDA-approved medications exist for EoE, highlighting the need for broader research into its management and prevention. Recent advancements in omics technologies, such as genomics, epigenetics, transcriptomics, proteomics, and others, offer new insights into the genetic and immunologic mechanisms underlying EoE. Genomic studies have identified genetic loci and mutations associated with EoE, revealing predispositions that vary by ancestry and indicating EoE's complex genetic basis. Epigenetic studies have uncovered changes in DNA methylation and chromatin structure that affect gene expression, influencing EoE pathology. Transcriptomic analyses have revealed a distinct gene expression profile in EoE, dominated by genes involved in activated type 2 immunity and epithelial barrier function. Proteomic approaches have furthered the understanding of EoE mechanisms, identifying potential new biomarkers and therapeutic targets. However, challenges in integrating diverse omics data persist, largely due to their complexity and the need for advanced computational methods. Machine learning is emerging as a valuable tool for analyzing extensive and intricate datasets, potentially revealing new aspects of EoE pathogenesis. The integration of multi-omics data through sophisticated computational approaches promises significant advancements in our understanding of EoE, improving diagnostics, and enhancing treatment effectiveness. This review synthesizes current omics research and explores future directions for comprehensively understanding the disease mechanisms in EoE.

MOSGAT: Uniting Specificity-Aware GATs and Cross Modal-Attention to Integrate Multi-Omics Data for Disease Diagnosis.

With the advancement of sequencing methodologies, the acquisition of vast amounts of multi-omics data presents a significant opportunity for comprehending the intricate biological mechanisms underlying diseases and achieving precise diagnosis and treatment for complex disorders. However, as diverse omics data are integrated, extracting sample-specific features within each omics modality and exploring potential correlations among different modalities while avoiding mutual interference becomes a critical challenge in multi-omics data integration research. In the context of this study, we proposed a framework that unites specificity-aware GATs and cross-modal attention to integrate different omics data (MOSGAT). To be specific, we devise Graph Attention Networks (GATs) tailored for each omics modality data to perform feature extraction on samples. Additionally, an adaptive confidence attention weighting technique is incorporated to enhance the confidence in the extracted features. Finally, a cross-modal attention mechanism was devised based on multi-head self-attention, thoroughly uncovering potential correlations between different omics data. Extensive experiments were conducted on four publicly available medical datasets, highlighting the superiority of the proposed framework when compared to state-of-the-art methodologies, particularly in the realm of classification tasks. The experimental results underscore MOSGAT's effectiveness in extracting features and exploring potential inter-omics associations.

Generative machine learning produces kinetic models that accurately characterize intracellular metabolic states

Generating large omics datasets has become routine for gaining insights into cellular processes, yet deciphering these datasets to determine metabolic states remains challenging. Kinetic models can help integrate omics data by explicitly linking metabolite concentrations, metabolic fluxes and enzyme levels. Nevertheless, determining the kinetic parameters that underlie cellular physiology poses notable obstacles to the widespread use of these mathematical representations of metabolism. Here we present RENAISSANCE, a generative machine learning framework for efficiently parameterizing large-scale kinetic models with dynamic properties matching experimental observations. Through seamless integration of diverse omics data and other relevant information, including extracellular medium composition, physicochemical data and expertise of domain specialists, RENAISSANCE accurately characterizes intracellular metabolic states in Escherichia coli. It also estimates missing kinetic parameters and reconciles them with sparse experimental data, substantially reducing parameter uncertainty and improving accuracy. This framework will be valuable for researchers studying metabolic variations involving changes in metabolite and enzyme levels and enzyme activity in health and biotechnology.

ITHindex: An integrated tool for quantifying intra-tumor heterogeneity using omics data in cancers.

e14689 Background: Intra-tumor heterogeneity (ITH) is a hallmark of cancer and plays a significant role in tumor evolution, treatment response, and the development of drug resistance. However, there is currently no standardized metric for assessing ITH in clinical practice. Several recent studies have proposed different algorithms of ITH based on multi-omics data. In this study, we have developed a web-based tool for analyzing tumor heterogeneity using diverse omics data and investigated the correlation between different ITH algorithms using TCGA data. Methods: We collected previously published ITH algorithms based on single-/multi-region genomic, transcriptomic, and proteomic data. We integrated these algorithms into a web server called ITHindex, which utilizes Shiny framework. TCGA data was employed for a comprehensive comparison of five ITH algorithms including MATH, CNH, DEPTH2, Shannon index and DITHER. Results: ITHindex (https://xwen.shinyapps.io/ithindex/) is an open-access online tool that encompasses a total of eight algorithms. Based on the type of input data, these algorithms can be categorized into SNV, cancer cell fraction (CCF), copy number variations segment, bulk or single-cell RNAseq, and multi-region mass spectrometry of protein. According to the calculation principles, these algorithms include those based on Shannon entropy, MAD, tumor clonality, ratio, and distance. To demonstrate the practicality of ITHindex, we employed TCGA data to calculate ITH values using five algorithms. The analysis unveiled that the distribution of the same algorithm differs across various tumor types. When considering the same type of input data, different algorithms exhibited a strong correlation. Furthermore, with the exception of MATH, the other ITH values displayed a negative correlation with overall survival. Conclusions: ITHindex is a user-friendly web-based tool that quantifies intra-tumor heterogeneity, empowering researchers to investigate the role of ITH in oncologic biology.

Research collaboration data platform ensuring general data protection

Translational data is of paramount importance for medical research and clinical innovation. It has the potential to benefit individuals and organizations, however, the protection of personal data must be guaranteed. Collecting diverse omics data and electronic health records (EHR), re-using the minimized data, as well as providing a reliable data transfer between different institutions are mandatory steps for the development of the promising field of big data and artificial intelligence in medical research. This is made possible within the proposed data platform in this research project. The established data platform enables the collaboration between public and commercial organizations by data transfer from various clinical systems into a cloud for supporting multi-site research while ensuring compliant data governance.

SpecLoop predicts cell type-specific chromatin loop via transcription factor cooperation

Cell-type-Specific Chromatin Loops (CSCLs) are crucial for gene regulation and cell fate determination. However, the mechanisms governing their establishment remain elusive. Here, we present SpecLoop, a network regularization-based machine learning framework, to investigate the role of transcription factors (TFs) cooperation in CSCL formation. SpecLoop integrates multi-omics data, including gene expression, chromatin accessibility, sequence, protein-protein interaction, and TF binding motif data, to predict CSCLs and identify TF cooperations. Using high resolution Hi-C data as the gold standard, SpecLoop accurately predicts CSCL in GM12878, IMR90, HeLa–S3, K562, HUVEC, HMEC, and NHEK seven cell types, with the AUROC values ranging from 0.8645 to 0.9852 and AUPR values ranging from 0.8654 to 0.9734. Notably SpecLoop demonstrates improved accuracy in predicting long-distance CSCLs and identifies TF complexes with strong predictive ability. Our study systematically explores the TFs and TF pairs associated with CSCL through effective integration of diverse omics data. SpecLoop is freely available at https://github.com/AMSSwanglab/SpecLoop.

Database Resources of the National Genomics Data Center, China National Center for Bioinformation in 2024.

The National Genomics Data Center (NGDC), which is a part of the China National Center for Bioinformation (CNCB), provides a family of database resources to support the global academic and industrial communities. With the rapid accumulation of multi-omics data at an unprecedented pace, CNCB-NGDC continuously expands and updates core database resources through big data archiving, integrative analysis and value-added curation. Importantly, NGDC collaborates closely with major international databases and initiatives to ensure seamless data exchange and interoperability. Over the past year, significant efforts have been dedicated to integrating diverse omics data, synthesizing expanding knowledge, developing new resources, and upgrading major existing resources. Particularly, several database resources are newly developed for the biodiversity of protists (P10K), bacteria (NTM-DB, MPA) as well as plant (PPGR, SoyOmics, PlantPan) and disease/trait association (CROST, HervD Atlas, HALL, MACdb, BioKA, BioKA, RePoS, PGG.SV, NAFLDkb). All the resources and services are publicly accessible at https://ngdc.cncb.ac.cn.

Genomic and Transcriptomic Approaches to Developing Abiotic Stress-Resilient Crops

In the realm of agriculture, a pressing concern remains the abiotic stresses, such as temperature fluctuation, drought, soil salinity, and heavy metal contamination. These adverse growth conditions hamper crop yields and global food security. In this review, we present a comprehensive examination of the recent advancements in utilizing genomics and transcriptomics, tools to enhance crop resilience against these stress factors. Genomics aids in the identification of genes responsive to stress, unravels regulatory networks, and pinpoints genetic variations linked to stress tolerance. Concurrently, transcriptomics sheds light on the intricate dynamics of gene expression during stress conditions, unearthing novel stress-responsive genes and signaling pathways. This wealth of knowledge shapes the development of stress-tolerant crop varieties, achieved through conventional breeding programs and state-of-the-art genetic engineering and gene editing techniques like CRISPR-Cas9. Moreover, the integration of diverse omics data and functional genomics tools empowers precise manipulation of crop genomes to fortify their stress resilience. In summary, the integration of genomics and transcriptomics holds substantial promise in elucidating the molecular mechanisms behind crop stress tolerance, offering a path towards sustainable agriculture and safeguarding food security amidst shifting environmental challenges.

TCOD: an integrated resource for tropical crops.

Tropical crops are vital for tropical agriculture, with resource scarcity, functional diversity and extensive market demand, providing considerable economic benefits for the world's tropical agriculture-producing countries. The rapid development of sequencing technology has promoted a milestone in tropical crop research, resulting in the generation of massive amount of data, which urgently needs an effective platform for data integration and sharing. However, the existing databases cannot fully satisfy researchers' requirements due to the relatively limited integration level and untimely update. Here, we present the Tropical Crop Omics Database (TCOD, https://ngdc.cncb.ac.cn/tcod), a comprehensive multi-omics data platform for tropical crops. TCOD integrates diverse omics data from 15 species, encompassing 34 chromosome-level de novo assemblies, 1 255 004 genes with functional annotations, 282 436 992 unique variants from 2048 WGS samples, 88 transcriptomic profiles from 1997 RNA-Seq samplesand 13 381 germplasm items. Additionally, TCOD not only employs genes as a bridge to interconnect multi-omics data, enabling cross-species comparisons based on homology relationships, but also offers user-friendly online tools for efficient data mining and visualization. In short, TCOD integrates multi-species, multi-omics data and online tools, which will facilitate the research on genomic selective breeding and trait biology of tropical crops.

Integration of incomplete multi-omics data using Knowledge Distillation and Supervised Variational Autoencoders for disease progression prediction

Objective:The rapid advancement of high-throughput technologies in the biomedical field has resulted in the accumulation of diverse omics data types, such as mRNA expression, DNA methylation, and microRNA expression, for studying various diseases. Integrating these multi-omics datasets enables a comprehensive understanding of the molecular basis of cancer and facilitates accurate prediction of disease progression. Methods:However, conventional approaches face challenges due to the dimensionality curse problem. This paper introduces a novel framework called Knowledge Distillation and Supervised Variational AutoEncoders utilizing View Correlation Discovery Network (KD-SVAE-VCDN) to address the integration of high-dimensional multi-omics data with limited common samples. Through our experimental evaluation, we demonstrate that the proposed KD-SVAE-VCDN architecture accurately predicts the progression of breast and kidney carcinoma by effectively classifying patients as long- or short-term survivors. Furthermore, our approach outperforms other state-of-the-art multi-omics integration models. Results:Our findings highlight the efficacy of the KD-SVAE-VCDN architecture in predicting the disease progression of breast and kidney carcinoma. By enabling the classification of patients based on survival outcomes, our model contributes to personalized and targeted treatments. The favorable performance of our approach in comparison to several existing models suggests its potential to contribute to the advancement of cancer understanding and management. Conclusion:The development of a robust predictive model capable of accurately forecasting disease progression at the time of diagnosis holds immense promise for advancing personalized medicine. By leveraging multi-omics data integration, our proposed KD-SVAE-VCDN framework offers an effective solution to this challenge, paving the way for more precise and tailored treatment strategies for patients with different types of cancer.

Assessing transcriptomic reidentification risks using discriminative sequence models.

Gene expression data provide molecular insights into the functional impact of genetic variation, for example, through expression quantitative trait loci (eQTLs). With an improving understanding of the association between genotypes and gene expression comes a greater concern that gene expression profiles could be matched to genotype profiles of the same individuals in another data set, known as a linking attack. Prior works show such a risk could analyze only a fraction of eQTLs that is independent owing to restrictive model assumptions, leaving the full extent of this risk incompletely understood. To address this challenge, we introduce the discriminative sequence model (DSM), a novel probabilistic framework for predicting a sequence of genotypes based on gene expression data. By modeling the joint distribution over all known eQTLs in a genomic region, DSM improves the power of linking attacks with necessary calibration for linkage disequilibrium and redundant predictive signals. We show greater linking accuracy of DSM compared with existing approaches across a range of attack scenarios and data sets including up to 22,288 individuals, suggesting that DSM helps uncover a substantial additional risk overlooked by previous studies. Our work provides a unified framework for assessing the privacy risks of sharing diverse omics data sets beyond transcriptomics.

Multivariate Analysis of RNA Chemistry Marks Uncovers Epitranscriptomics-Based Biomarker Signature for Adult Diffuse Glioma Diagnostics.

One of the main challenges in cancer management relates to the discovery of reliable biomarkers, which could guide decision-making and predict treatment outcome. In particular, the rise and democratization of high-throughput molecular profiling technologies bolstered the discovery of “biomarker signatures” that could maximize the prediction performance. Such an approach was largely employed from diverse OMICs data (i.e., genomics, transcriptomics, proteomics, metabolomics) but not from epitranscriptomics, which encompasses more than 100 biochemical modifications driving the post-transcriptional fate of RNA: stability, splicing, storage, and translation. We and others have studied chemical marks in isolation and associated them with cancer evolution, adaptation, as well as the response to conventional therapy. In this study, we have designed a unique pipeline combining multiplex analysis of the epitranscriptomic landscape by high-performance liquid chromatography coupled to tandem mass spectrometry with statistical multivariate analysis and machine learning approaches in order to identify biomarker signatures that could guide precision medicine and improve disease diagnosis. We applied this approach to analyze a cohort of adult diffuse glioma patients and demonstrate the existence of an “epitranscriptomics-based signature” that permits glioma grades to be discriminated and predicted with unmet accuracy. This study demonstrates that epitranscriptomics (co)evolves along cancer progression and opens new prospects in the field of omics molecular profiling and personalized medicine.

Network Approaches to Integrate Analyses of Genetics and Metabolomics Data with Applications to Fetal Programming Studies

The integration of genetics and metabolomics data demands careful accounting of complex dependencies, particularly when modelling familial omics data, e.g., to study fetal programming of related maternal–offspring phenotypes. Efforts to identify genetically determined metabotypes using classic genome wide association approaches have proven useful for characterizing complex disease, but conclusions are often limited to a series of variant–metabolite associations. We adapt Bayesian network models to integrate metabotypes with maternal–offspring genetic dependencies and metabolic profile correlations in order to investigate mechanisms underlying maternal–offspring phenotypic associations. Using data from the multiethnic Hyperglycemia and Adverse Pregnancy Outcome (HAPO) study, we demonstrate that the strategic specification of ordered dependencies, pre-filtering of candidate metabotypes, incorporation of metabolite dependencies, and penalized network estimation methods clarify potential mechanisms for fetal programming of newborn adiposity and metabolic outcomes. The exploration of Bayesian network growth over a range of penalty parameters, coupled with interactive plotting, facilitate the interpretation of network edges. These methods are broadly applicable to integration of diverse omics data for related individuals.

Network Approaches for Charting the Transcriptomic and Epigenetic Landscape of the Developmental Origins of Health and Disease.

The early developmental phase is of critical importance for human health and disease later in life. To decipher the molecular mechanisms at play, current biomedical research is increasingly relying on large quantities of diverse omics data. The integration and interpretation of the different datasets pose a critical challenge towards the holistic understanding of the complex biological processes that are involved in early development. In this review, we outline the major transcriptomic and epigenetic processes and the respective datasets that are most relevant for studying the periconceptional period. We cover both basic data processing and analysis steps, as well as more advanced data integration methods. A particular focus is given to network-based methods. Finally, we review the medical applications of such integrative analyses.

Deep latent space fusion for adaptive representation of heterogeneous multi-omics data.

The integration of multi-omics data makes it possible to understand complex biological organisms at the system level. Numerous integration approaches have been developed by assuming a common underlying data space. Due to the noise and heterogeneity of biological data, the performance of these approaches is greatly affected. In this work, we propose a novel deep neural network architecture, named Deep Latent Space Fusion (DLSF), which integrates the multi-omics data by learning consistent manifold in the sample latent space for disease subtypes identification. DLSF is built upon a cycle autoencoder with a shared self-expressive layer, which can naturally and adaptively merge nonlinear features at each omics level into one unified sample manifold and produce adaptive representation of heterogeneous samples at the multi-omics level. We have assessed DLSF on various biological and biomedical datasets to validate its effectiveness. DLSF can efficiently and accurately capture the intrinsic manifold of the sample structures or sample clusters compared with other state-of-the-art methods, and DLSF yielded more significant outcomes for biological significance, survival prognosis and clinical relevance in application of cancer study in The Cancer Genome Atlas. Notably, as a deep case study, we determined a new molecular subtype of kidney renal clear cell carcinoma that may benefit immunotherapy in the viewpoint of multi-omics, and we further found potential subtype-specific biomarkers from multiple omics data, which were validated by independent datasets. In addition, we applied DLSF to identify potential therapeutic agents of different molecular subtypes of chronic lymphocytic leukemia, demonstrating the scalability of DLSF in diverse omics data types and application scenarios.

Relevant and Non-Redundant Feature Selection for Cancer Classification and Subtype Detection.

Simple SummaryHere we introduce a new feature selection algorithm DTA, which selects important, non-redundant, and relevant features from diverse omics data. DTA selects non-redundant features by maximizing the similarity between each patient pair by an approximate k-cover algorithm. We successfully applied this algorithm to three different biological problems: (a) disease to healthy sample classification, (b) multiclass classification of different disease samples, and (c) disease subtypes detection. DTA outperformed other feature selection techniques in the binary classification of healthy and disease samples and multiclass classification of various diseases. It also improved the performance of a subtype detection algorithm by selecting the important features for few cancer types.Biologists seek to identify a small number of significant features that are important, non-redundant, and relevant from diverse omics data. For example, statistical methods such as LIMMA and DEseq distinguish differentially expressed genes between a case and control group from the transcript profile. Researchers also apply various column subset selection algorithms on genomics datasets for a similar purpose. Unfortunately, genes selected by such statistical or machine learning methods are often highly co-regulated, making their performance inconsistent. Here, we introduce a novel feature selection algorithm that selects highly disease-related and non-redundant features from a diverse set of omics datasets. We successfully applied this algorithm to three different biological problems: (a) disease-to-normal sample classification; (b) multiclass classification of different disease samples; and (c) disease subtypes detection. Considering the classification of ROC-AUC, false-positive, and false-negative rates, our algorithm outperformed other gene selection and differential expression (DE) methods for all six types of cancer datasets from TCGA considered here for binary and multiclass classification problems. Moreover, genes picked by our algorithm improved the disease subtyping accuracy for four different cancer types over state-of-the-art methods. Hence, we posit that our proposed feature reduction method can support the community to solve various problems, including the selection of disease-specific biomarkers, precision medicine design, and disease sub-type detection.

Deep learning assisted multi-omics integration for survival and drug-response prediction in breast cancer

BackgroundSurvival and drug response are two highly emphasized clinical outcomes in cancer research that directs the prognosis of a cancer patient. Here, we have proposed a late multi omics integrative framework that robustly quantifies survival and drug response for breast cancer patients with a focus on the relative predictive ability of available omics datatypes. Neighborhood component analysis (NCA), a supervised feature selection algorithm selected relevant features from multi-omics datasets retrieved from The Cancer Genome Atlas (TCGA) and Genomics of Drug Sensitivity in Cancer (GDSC) databases. A Neural network framework, fed with NCA selected features, was used to develop survival and drug response prediction models for breast cancer patients. The drug response framework used regression and unsupervised clustering (K-means) to segregate samples into responders and non-responders based on their predicted IC50 values (Z-score).ResultsThe survival prediction framework was highly effective in categorizing patients into risk subtypes with an accuracy of 94%. Compared to single-omics and early integration approaches, our drug response prediction models performed significantly better and were able to predict IC50 values (Z-score) with a mean square error (MSE) of 1.154 and an overall regression value of 0.92, showing a linear relationship between predicted and actual IC50 values.ConclusionThe proposed omics integration strategy provides an effective way of extracting critical information from diverse omics data types enabling estimation of prognostic indicators. Such integrative models with high predictive power would have a significant impact and utility in precision oncology.

DIVERSE: Bayesian Data IntegratiVE Learning for Precise Drug ResponSE Prediction.

Detecting predictive biomarkers from multi-omics data is important for precision medicine, to improve diagnostics of complex diseases and for better treatments. This needs substantial experimental efforts that are made difficult by the heterogeneity of cell lines and huge cost. An effective solution is to build a computational model over the diverse omics data, including genomic, molecular, and environmental information. However, choosing informative and reliable data sources from among the different types of data is a challenging problem. We propose DIVERSE, a framework of Bayesian importance-weighted tri- and bi-matrix factorization(DIVERSE3 or DIVERSE2) to predict drug responses from data of cell lines, drugs, and gene interactions. DIVERSE integrates the data sources systematically, in a step-wise manner, examining the importance of each added data set in turn. More specifically, we sequentially integrate five different data sets, which have not all been combined in earlier bioinformatic methods for predicting drug responses. Empirical experiments show that DIVERSE clearly outperformed five other methods including three state-of-the-art approaches, under cross-validation, particularly in out-of-matrix prediction, which is closer to the setting of real use cases and more challenging than simpler in-matrix prediction. Additionally, case studies for discovering new drugs further confirmed the performance advantage of DIVERSE.