SAFER: sub-hypergraph attention-based neural network for predicting effective responses to dose combinations.

Background: The potential benefits of drug combination synergy in cancer medicine are significant, yet the risks must be carefully managed due to the possibility of increased toxicity. Although artificial intelligence applications have demonstrated notable success in predicting drug combination synergy, several key challenges persist: (1) Existing models often predict average synergy values across a restricted range of testing dosages, neglecting crucial dose amounts and the mechanisms of action of the drugs involved. (2) Many graph-based models rely on static protein-protein interactions, failing to adapt to dynamic and context-dependent networks. This limitation constrains the applicability of current methods. Results: We introduced SAFER, a Sub-hypergraph Attention-based graph model, addressing these issues by incorporating complex relationships among biological knowledge networks and considering dosing effects on subject-specific networks. SAFER outperformed previous models on the benchmark and the independent test set. The analysis of subgraph attention weight for the lung cancer cell line highlighted JAK-STAT signaling pathway, PRDM12, ZNF781, and CDC5L that have been implicated in lung fibrosis. Conclusions: SAFER presents an interpretable framework designed to identify drug-responsive signals. Tailored for comprehending dose effects on subject-specific molecular contexts, our model uniquely captures dose-level drug combination responses. This capability unlocks previously inaccessible avenues of investigation compared to earlier models. Finally, the SAFER framework can be leveraged by future inquiries to investigate molecular networks that uniquely characterize individual patients.

Molecular pathways enhance drug response prediction using transfer learning from cell lines to tumors and patient-derived xenografts.

Computational models have been successful in predicting drug sensitivity in cancer cell line data, creating an opportunity to guide precision medicine. However, translating these models to tumors remains challenging. We propose a new transfer learning workflow that transfers drug sensitivity predicting models from large-scale cancer cell lines to both tumors and patient derived xenografts based on molecular pathways derived from genomic features. We further compute feature importance to identify pathways most important to drug response prediction. We obtained good performance on tumors (AUROC = 0.77) and patient derived xenografts from triple negative breast cancers (RMSE = 0.11). Using feature importance, we highlight the association between ER-Golgi trafficking pathway in everolimus sensitivity within breast cancer patients and the role of class II histone deacetylases and interlukine-12 in response to drugs for triple-negative breast cancer. Pathway information support transfer of drug response prediction models from cell lines to tumors and can provide biological interpretation underlying the predictions, serving as a steppingstone towards usage in clinical setting.

Tissue-Specific Variations in Transcription Factors Elucidate Complex Immune System Regulation.

Gene expression plays a key role in health and disease. Estimating the genetic components underlying gene expression can thus help understand disease etiology. Polygenic models termed "transcriptome imputation" are used to estimate the genetic component of gene expression, but these models typically consider only the cis regions of the gene. However, these cis-based models miss large variability in expression for multiple genes. Transcription factors (TFs) that regulate gene expression are natural candidates for looking for additional sources of the missing variability. We developed a hypothesis-driven approach to identify second-tier regulation by variability in TFs. Our approach tested two models representing possible mechanisms by which variations in TFs can affect gene expression: variability in the expression of the TF and genetic variants within the TF that may affect the binding affinity of the TF to the TF-binding site. We tested our TF models in whole blood and skeletal muscle tissues and identified TF variability that can partially explain missing gene expression for 1035 genes, 76% of which explains more than the cis-based models. While the discovered regulation patterns were tissue-specific, they were both enriched for immune system functionality, elucidating complex regulation patterns. Our hypothesis-driven approach is useful for identifying tissue-specific genetic regulation patterns involving variations in TF expression or binding.

SynPathy: Predicting Drug Synergy through Drug-Associated Pathways Using Deep Learning.

Drug combination therapy has become a promising therapeutic strategy for cancer treatment. While high-throughput drug combination screening is effective for identifying synergistic drug combinations, measuring all possible combinations is impractical due to the vast space of therapeutic agents and cell lines. In this study, we propose a biologically-motivated deep learning approach to identify pathway-level features from drug and cell lines' molecular data for predicting drug synergy and quantifying the interactions in synergistic drug pairs. This method obtained an MSE of 70.6 ± 6.4, significantly surpassing previous approaches while providing potential candidate pathways to explain the prediction. We further demonstrate that drug combinations tend to be more synergistic when their top contributing pathways are closer to each other on a protein interaction network, suggesting a potential strategy for combination therapy with topologically interacting pathways. Our computational approach can thus be utilized both for prescreening of potential drug combinations and for designing new combinations based on proximity of pathways associated with drug targets and cell lines. IMPLICATIONS: Our computational framework may be translated in the future to clinical scenarios where synergistic drugs are tailored to the patient and additionally, drug development could benefit from designing drugs that target topologically close pathways.

Explainable drug sensitivity prediction through cancer pathway enrichment.

Computational approaches to predict drug sensitivity can promote precision anticancer therapeutics. Generalizable and explainable models are of critical importance for translation to guide personalized treatment and are often overlooked in favor of prediction performance. Here, we propose PathDSP: a pathway-based model for drug sensitivity prediction that integrates chemical structure information with enrichment of cancer signaling pathways across drug-associated genes, gene expression, mutation and copy number variation data to predict drug response on the Genomics of Drug Sensitivity in Cancer dataset. Using a deep neural network, we outperform state-of-the-art deep learning models, while demonstrating good generalizability a separate dataset of the Cancer Cell Line Encyclopedia as well as provide explainable results, demonstrated through case studies that are in line with current knowledge. Additionally, our pathway-based model achieved a good performance when predicting unseen drugs and cells, with potential utility for drug development and for guiding individualized medicine.

Genomic Analysis of Mycobacterium tuberculosis Isolates and Construction of a Beijing Lineage Reference Genome.

Tuberculosis (TB), an infectious disease caused by Mycobacterium tuberculosis, kills over 1 million people worldwide annually. Development of drug resistance (DR) in the pathogen is a major challenge for TB control. We conducted whole-genome analysis of seven Taiwan M. tuberculosis isolates: One drug susceptible (DS) and five DR Beijing lineage isolates and one DR Euro-American lineage isolate. Developing a new method for DR mutation identification and applying it to the next-generation sequencing (NGS) data from the 6 Beijing lineage isolates, we identified 13 known and 6 candidate DR mutations and provided experimental support for 4 of them. We assembled the genomes of one DS and two DR Beijing lineage isolates and the Euro-American lineage isolate using NGS data. Moreover, using both PacBio and NGS sequencing data, we obtained a high-quality assembly of an extensive DR Beijing lineage isolate. Comparative analysis of these five newly assembled genomes and two published complete genomes revealed a large number of genetic changes, including gene gains and losses, indels and translocations, suggesting rapid evolution of M. tuberculosis. We found the MazEF toxin-antitoxin system in all the seven isolates studied and several interesting mutations in MazEF proteins. Finally, we used the four assembled Beijing lineage genomes to construct a high-quality Beijing lineage reference genome that is DS and contains all the genes in the four genomes. It contains 212 genes not found in the standard reference H37Rv, which is Euro-American. It is therefore a better reference than H37Rv for the Beijing lineage, the predominant lineage in Asia.

Genomic and transcriptomic analyses of the medicinal fungus Antrodia cinnamomea for its metabolite biosynthesis and sexual development.

Antrodia cinnamomea, a polyporus mushroom of Taiwan, has long been used as a remedy for cancer, hypertension, and hangover, with an annual market of over $100 million (US) in Taiwan. We obtained a 32.15-Mb genome draft containing 9,254 genes. Genome ontology enrichment and pathway analyses shed light on sexual development and the biosynthesis of sesquiterpenoids, triterpenoids, ergostanes, antroquinonol, and antrocamphin. We identified genes differentially expressed between mycelium and fruiting body and 242 proteins in the mevalonate pathway, terpenoid pathways, cytochrome P450s, and polyketide synthases, which may contribute to the production of medicinal secondary metabolites. Genes of secondary metabolite biosynthetic pathways showed expression enrichment for tissue-specific compounds, including 14-α-demethylase (CYP51F1) in fruiting body for converting lanostane to ergostane triterpenoids, coenzymes Q (COQ) for antroquinonol biosynthesis in mycelium, and polyketide synthase for antrocamphin biosynthesis in fruiting body. Our data will be useful for developing a strategy to increase the production of useful metabolites.