Deconvolution algorithms mostly rely on single-cell RNA-sequencing (scRNA-seq) data applied onto bulk RNA-sequencing (bulk RNA-seq) to estimate tissues\' cell-type composition, with performance accuracy validated on deposited databases. Adipose tissues\' cellular composition is highly variable, and adipocytes can only be captured by single-nucleus RNA-sequencing (snRNA-seq). Here we report the development of sNucConv, a Scaden deep-learning-based deconvolution tool, trained using 5 hSAT and 7 hVAT snRNA-seq-based data corrected by (i) snRNA-seq/bulk RNA-seq highly correlated genes and (ii) individual cell-type regression models. Applying sNucConv on our bulk RNA-seq data resulted in cell-type proportion estimation of 15 and 13 cell types, with accuracy of R = 0.93 (range: 0.76-0.97) and R = 0.95 (range: 0.92-0.98) for hVAT and hSAT, respectively. This performance level was further validated on an independent set of samples (5 hSAT; 5 hVAT). The resulting model was depot specific, reflecting depot differences in gene expression patterns. Jointly, sNucConv provides proof-of-concept for producing validated deconvolution models for tissues un-amenable to scRNA-seq.

Ab initio computational reconstructions of protein-protein interaction (PPI) networks will provide invaluable insights into cellular systems, enabling the discovery of novel molecular interactions and elucidating biological mechanisms within and between organisms. Leveraging the latest generation protein language models and recurrent neural networks, we present SENSE-PPI, a sequence-based deep learning model that efficiently reconstructs ab initio PPIs, distinguishing partners among tens of thousands of proteins and identifying specific interactions within functionally similar proteins. SENSE-PPI demonstrates high accuracy, limited training requirements, and versatility in cross-species predictions, even with non-model organisms and human-virus interactions. Its performance decreases for phylogenetically more distant model and non-model organisms, but signal alteration is very slow. In this regard, it demonstrates the important role of parameters in protein language models. SENSE-PPI is very fast and can test 10,000 proteins against themselves in a matter of hours, enabling the reconstruction of genome-wide proteomes.

Coronary artery disease (CAD) remains a leading cause of disease burden globally, and there is a persistent need for new therapeutic targets. Instrumental variable (IV) and genetic colocalization analyses can help identify novel therapeutic targets for human disease by nominating causal genes in genome-wide association study (GWAS) loci. We conducted cis-IV analyses for 20,125 genes and 1,746 plasma proteins with CAD using molecular trait quantitative trait loci variant (QTLs) data from three different studies. 19 proteins and 119 genes were significantly associated with CAD risk by IV analyses and demonstrated evidence of genetic colocalization. Notably, our analyses validated well-established targets such as PCSK9 and ANGPTL4 while also identifying HTRA1 and endotrophin (a cleavage product of COL6A3) as proteins whose levels are causally associated with CAD risk. Further experimental studies are needed to confirm the causal role of the genes and proteins identified through our multiomic cis-IV analyses on human disease.

Amyotrophic lateral sclerosis (ALS) is a universally fatal neurodegenerative disease with no cure. Human endogenous retroviruses (HERVs) have been implicated in its pathogenesis but their relevance to ALS is not fully understood. We examined bulk RNA-seq data from almost 2,000 ALS and unaffected control samples derived from the cortex and spinal cord. Using different methods of feature selection, including differential expression analysis and machine learning, we discovered that transcription of HERV-K loci 1q22 and 8p23.1 were significantly upregulated in the spinal cord of individuals with ALS. Additionally, we identified a subset of ALS patients with upregulated HERV-K expression in the cortex and spinal cord. We also found the expression of HERV-K loci 19q11 and 8p23.1 was correlated with protein coding genes previously implicated in ALS and dysregulated in ALS patients in this study. These results clarify the association of HERV-K and ALS and highlight specific genes in the pathobiology of late-stage ALS.

Evaluation of the binding affinities of drugs to proteins is a crucial process for identifying drug pharmacological actions, but it requires three dimensional structures of proteins. Herein, we propose novel computational methods to predict the therapeutic indications and side effects of drug candidate compounds from the binding affinities to human protein structures on a proteome-wide scale. Large-scale docking simulations were performed for 7,582 drugs with 19,135 protein structures revealed by AlphaFold (including experimentally unresolved proteins), and machine learning models on the proteome-wide binding affinity score (PBAS) profiles were constructed. We demonstrated the usefulness of the method for predicting the therapeutic indications for 559 diseases and side effects for 285 toxicities. The method enabled to predict drug indications for which the related protein structures had not been experimentally determined and to successfully extract proteins eliciting the side effects. The proposed method will be useful in various applications in drug discovery.

Cytotoxic T lymphocyte (CTL) and terminal exhausted T lymphocyte (ETL) activities crucially influence immune checkpoint inhibitor (ICI) response. Despite this, the efficacy of ETL and CTL transcriptomic signatures for response prediction remains limited. Investigating this across the TCGA and publicly available single-cell cohorts, we find a strong positive correlation between ETL and CTL expression signatures in most cancers. We hence posited that their limited predictability arises due to their mutually canceling effects on ICI response. Thus, we developed DETACH, a computational method to identify a gene set whose expression pinpoints to a subset of melanoma patients where the CTL and ETL correlation is low. DETACH enhances CTL\'s prediction accuracy, outperforming existing signatures. DETACH signature genes activity also demonstrates a positive correlation with lymphocyte infiltration and the prevalence of reactive T cells in the tumor microenvironment (TME), advancing our understanding of the CTL cell state within the TME.

Accurate detection of pathogens, particularly distinguishing between Gram-positive and Gram-negative bacteria, could improve disease treatment. Host gene expression can capture the immune system\'s response to infections caused by various pathogens. Here, we present a deep neural network model, bvnGPS2, which incorporates the attention mechanism based on a large-scale integrated host transcriptome dataset to precisely identify Gram-positive and Gram-negative bacterial infections as well as viral infections. We performed analysis of 4,949 blood samples across 40 cohorts from 10 countries using our previously designed omics data integration method, iPAGE, to select discriminant gene pairs and train the bvnGPS2. The performance of the model was evaluated on six independent cohorts comprising 374 samples. Overall, our deep neural network model shows robust capability to accurately identify specific infections, paving the way for precise medicine strategies in infection treatment and potentially also for identifying subtypes of other diseases.

Interactions within the tumor microenvironment (TME) significantly influence tumor progression and treatment responses. While single-cell RNA sequencing (scRNA-seq) and spatial genomics facilitate TME exploration, many clinical cohorts are assessed at the bulk tissue level. Integrating scRNA-seq and bulk tissue RNA-seq data through computational deconvolution is essential for obtaining clinically relevant insights. Our method, ProM, enables the examination of major and minor cell types. Through evaluation against existing methods using paired single-cell and bulk RNA sequencing of human urothelial cancer (UC) samples, ProM demonstrates superiority. Application to UC cohorts treated with immune checkpoint inhibitors reveals pre-treatment cellular features associated with poor outcomes, such as elevated SPP1 expression in macrophage/monocytes (MM). Our deconvolution method and paired single-cell and bulk tissue RNA-seq dataset contribute novel insights into TME heterogeneity and resistance to immune checkpoint blockade.

Autopsy rates are declining globally, impacting cause-of-death (CoD) diagnoses and quality control. Postmortem metabolomics was evaluated for CoD screening using 4,282 human cases, encompassing CoD groups: acidosis, drug intoxication, hanging, ischemic heart disease (IHD), and pneumonia. Cases were split 3:1 into training and test sets. High-resolution mass spectrometry data from femoral blood were analyzed via orthogonal-partial least squares discriminant analysis (OPLS-DA) to discriminate CoD groups. OPLS-DA achieved an R2 = 0.52 and Q2 = 0.30, with true-positive prediction rates of 68% and 65% for training and test sets, respectively, across all groups. Specificity-optimized thresholds predicted 56% of test cases with a unique CoD, average 45% sensitivity, and average 96% specificity. Prediction accuracies varied: 98.7% for acidosis, 80.5% for drug intoxication, 81.6% for hanging, 73.1% for IHD, and 93.6% for pneumonia. This study demonstrates the potential of large-scale postmortem metabolomics for CoD screening, offering high specificity and enhancing throughput and decision-making in human death investigations.

Microinjecting yeast cells has been challenging for decades with no significant breakthrough due to the ultra-tough cell wall and low stiffness of the traditional injector tip at the micro-scale. Penetrating this protection wall is the key step for artificially bringing foreign substance into the yeast. In this paper, a yeast cell model was built by using finite element analysis (FEA) method to analyze the penetrating process. The key parameters of the yeast cell wall in the model (the Young\'s modulus, the shear modulus, and the Lame constant) were calibrated according to a general nanoindentation experiment. Then by employing the calibrated model, the injection parameters were optimized to minimize the cell damage (the maximum cell deformation at the critical stress of the cell wall). Key guidelines were suggested for penetrating the cell wall during microinjection.