Gene expression based inference of cancer drug sensitivity

Application of artificial intelligence in drug design: A review

Artificial intelligence (AI) is a field of computer science that involves acquiring information, developing rule bases, and mimicking human behaviour. The fundamental concept behind AI is to create intelligent computer systems that can operate with minimal human intervention or without any intervention at all. These rule-based systems are developed using various machine learning and deep learning models, enabling them to solve complex problems. AI is integrated with these models to learn, understand, and analyse provided data. The rapid advancement of Artificial Intelligence (AI) is reshaping numerous industries, with the pharmaceutical sector experiencing a notable transformation. AI is increasingly being employed to automate, optimize, and personalize various facets of the pharmaceutical industry, particularly in pharmacological research. Traditional drug development methods areknown for being time-consuming, expensive, and less efficient, often taking around a decade and costing billions of dollars. The integration of artificial intelligence (AI) techniques addresses these challenges by enabling the examination of compounds with desired properties from a vast pool of input drugs. Furthermore, it plays a crucial role in drug screening by predicting toxicity, bioactivity, ADME properties (absorption, distribution, metabolism, and excretion), physicochemical properties, and more. AI enhances the drug design process by improving the efficiency and accuracy of predicting drug behaviour, interactions, and properties. These approaches further significantly improve the precision of drug discovery processes and decrease clinical trial costs leading to the development of more effective drugs.

scDrug+: predicting drug-responses using single-cell transcriptomics and molecular structure

Predicting drug responses based on individual transcriptomic profiles holds promise for refining prognosis and advancing precision medicine. Although many studies have endeavored to predict the responses of known drugs to novel transcriptomic profiles, research into predicting responses for newly discovered drugs remains sparse. In this study, we introduce scDrug+, a comprehensive pipeline that seamlessly integrates single-cell analysis with drug-response prediction. Importantly, scDrug+ is equipped to predict the response of new drugs by analyzing their molecular structures. The open-source tool is available as a Docker container, ensuring ease of deployment and reproducibility. It can be accessed at https://github.com/ailabstw/scDrugplus.

Exploring and clinical validation of prognostic significance and therapeutic implications of copper homeostasis-related gene dysregulation in acute myeloid leukemia

The patterns and biological functions of copper homeostasis-related genes (CHRGs) in acute myeloid leukemia (AML) remain unclear. We explored the patterns and biological functions of CHRGs in AML. Using independent cohorts, including TCGA-GTEx, GSE114868, GSE37642, and clinical samples, we identified 826 common differentially expressed genes. Specifically, 12 cuproptosis-related genes (e.g., ATP7A, ATP7B) were upregulated, while 17 cuproplasia-associated genes (e.g., ATOX1, ATP7A) were downregulated in AML. We used LASSO-Cox, Kaplan-Meier, and Nomogram analyses to establish prognostic risk models, effectively stratifying patients with AML into high- and low-risk groups. Subgroup analysis revealed that high-risk patients exhibited poorer overall survival and involvement in fatty acid metabolism, apoptosis, and glycolysis. Immune infiltration analysis indicated differences in immune cell composition, with notable increases in B cells, cytotoxic T cells, and memory T cells in the low-risk group, and increased monocytes and neutrophils in the high-risk group. Single-cell sequencing analysis corroborated the expression characteristics of critical CHRGs, such as MAPK1 and ATOX1, associated with the function of T, B, and NK cells. Drug sensitivity analysis suggested potential therapeutic agents targeting copper homeostasis, including Bicalutamide and Sorafenib. PCR validation confirmed the differential expression of 4 cuproptosis-related genes (LIPT1, SLC31A1, GCSH, and PDHA1) and 9 cuproplasia-associated genes (ATOX1, CCS, CP, MAPK1, SOD1, COA6, PDK1, DBH, and PDE3B) in AML cell line. Importantly, these genes serve as potential biomarkers for patient stratification and treatment. In conclusion, we shed light on the expression patterns and biological functions of CHRGs in AML. The developed risk models provided prognostic implications for patient survival, offering valuable information on the regulatory characteristics of CHRGs and potential avenues for personalized treatment in AML.

Trust me if you can: a survey on reliability and interpretability of machine learning approaches for drug sensitivity prediction in cancer

With the ever-increasing number of artificial intelligence (AI) systems, mitigating risks associated with their use has become one of the most urgent scientific and societal issues. To this end, the European Union passed the EU AI Act, proposing solution strategies that can be summarized under the umbrella term trustworthiness. In anti-cancer drug sensitivity prediction, machine learning (ML) methods are developed for application in medical decision support systems, which require an extraordinary level of trustworthiness. This review offers an overview of the ML landscape of methods for anti-cancer drug sensitivity prediction, including a brief introduction to the four major ML realms (supervised, unsupervised, semi-supervised, and reinforcement learning). In particular, we address the question to what extent trustworthiness-related properties, more specifically, interpretability and reliability, have been incorporated into anti-cancer drug sensitivity prediction methods over the previous decade. In total, we analyzed 36 papers with approaches for anti-cancer drug sensitivity prediction. Our results indicate that the need for reliability has hardly been addressed so far. Interpretability, on the other hand, has often been considered for model development. However, the concept is rather used intuitively, lacking clear definitions. Thus, we propose an easily extensible taxonomy for interpretability, unifying all prevalent connotations explicitly or implicitly used within the field.

CanCellVar: A database for single-cell variants map in human cancer

Numerous variants, including both single-nucleotide variants (SNVs) in DNA and A>G RNA edits in mRNA as essential drivers of cellular proliferation and tumorigenesis, are commonly associated with cancer progression and growth. Thus, mining and summarizing single-cell variants will provide a refined and higher-resolution view of cancer and further contribute to precision medicine. Here, we established a database, CanCellVar, which aims to provide and visualize the comprehensive atlas of single-cell variants in tumor microenvironment. The current CanCellVar identified ∼3 million variants (∼1.4 million SNVs and ∼1.4 million A>G RNA edits) involved in 2,754,531 cells of 5 major cell types across 37 cancer types. CanCellVar provides the basic annotation information as well as cellular and molecular function properties of variants. In addition, the clinical relevance of variants can be obtained including tumor grade, treatment, metastasis, and others. Several flexible tools were also developed to aid retrieval and to analyze cell-cell interactions, gene expression, cell-development trajectories, regulation, and molecular structure affected by variants. Collectively, CanCellVar will serve as a valuable resource for investigating the functions and characteristics of single-cell variations and their roles in human tumor evolution and treatment.

Transfer learning of condition-specific perturbation in gene interactions improves drug response prediction

SUMMARY

Drug response is conventionally measured at the cell level, often quantified by metrics like IC50. However, to gain a deeper understanding of drug response, cellular outcomes need to be understood in terms of pathway perturbation. This perspective leads us to recognize a challenge posed by the gap between two widely used large-scale databases, LINCS L1000 and GDSC, measuring drug response at different levels-L1000 captures information at the gene expression level, while GDSC operates at the cell line level. Our study aims to bridge this gap by integrating the two databases through transfer learning, focusing on condition-specific perturbations in gene interactions from L1000 to interpret drug response integrating both gene and cell levels in GDSC. This transfer learning strategy involves pretraining on the transcriptomic-level L1000 dataset, with parameter-frozen fine-tuning to cell line-level drug response. Our novel condition-specific gene-gene attention (CSG2A) mechanism dynamically learns gene interactions specific to input conditions, guided by both data and biological network priors. The CSG2A network, equipped with transfer learning strategy, achieves state-of-the-art performance in cell line-level drug response prediction. In two case studies, well-known mechanisms of drugs are well represented in both the learned gene-gene attention and the predicted transcriptomic profiles. This alignment supports the modeling power in terms of interpretability and biological relevance. Furthermore, our model's unique capacity to capture drug response in terms of both pathway perturbation and cell viability extends predictions to the patient level using TCGA data, demonstrating its expressive power obtained from both gene and cell levels.

AVAILABILITY AND IMPLEMENTATION

The source code for the CSG2A network is available at https://github.com/eugenebang/CSG2A.

Predicting single-cell cellular responses to perturbations using cycle consistency learning

SUMMARY

Phenotype-based drug screening emerges as a powerful approach for identifying compounds that actively interact with cells. Transcriptional and proteomic profiling of cell lines and individual cells provide insights into the cellular state alterations that occur at the molecular level in response to external perturbations, such as drugs or genetic manipulations. In this paper, we propose cycleCDR, a novel deep learning framework to predict cellular response to external perturbations. We leverage the autoencoder to map the unperturbed cellular states to a latent space, in which we postulate the effects of drug perturbations on cellular states follow a linear additive model. Next, we introduce the cycle consistency constraints to ensure that unperturbed cellular state subjected to drug perturbation in the latent space would produces the perturbed cellular state through the decoder. Conversely, removal of perturbations from the perturbed cellular states can restore the unperturbed cellular state. The cycle consistency constraints and linear modeling in the latent space enable to learn transferable representations of external perturbations, so that our model can generalize well to unseen drugs during training stage. We validate our model on four different types of datasets, including bulk transcriptional responses, bulk proteomic responses, and single-cell transcriptional responses to drug/gene perturbations. The experimental results demonstrate that our model consistently outperforms existing state-of-the-art methods, indicating our method is highly versatile and applicable to a wide range of scenarios.

AVAILABILITY AND IMPLEMENTATION

The source code is available at: https://github.com/hliulab/cycleCDR.

Applications of Artificial Intelligence in Prostate Cancer Care: A Path to Enhanced Efficiency and Outcomes

The landscape of prostate cancer care has rapidly evolved. We have transitioned from the use of conventional imaging, radical surgeries, and single-agent androgen deprivation therapy to an era of advanced imaging, precision diagnostics, genomics, and targeted treatment options. Concurrently, the emergence of large language models (LLMs) has dramatically transformed the paradigm for artificial intelligence (AI). This convergence of advancements in prostate cancer management and AI provides a compelling rationale to comprehensively review the current state of AI applications in prostate cancer care. Here, we review the advancements in AI-driven applications across the continuum of the journey of a patient with prostate cancer from early interception to survivorship care. We subsequently discuss the role of AI in prostate cancer drug discovery, clinical trials, and clinical practice guidelines. In the localized disease setting, deep learning models demonstrated impressive performance in detecting and grading prostate cancer using imaging and pathology data. For biochemically recurrent diseases, machine learning approaches are being tested for improved risk stratification and treatment decisions. In advanced prostate cancer, deep learning can potentially improve prognostication and assist in clinical decision making. Furthermore, LLMs are poised to revolutionize information summarization and extraction, clinical trial design and operations, drug development, evidence synthesis, and clinical practice guidelines. Synergistic integration of multimodal data integration and human-AI integration are emerging as a key strategy to unlock the full potential of AI in prostate cancer care.

Learning the cellular activity representation based on gene regulatory networks for prediction of tumor response to drugs

Predicting the response of tumor cells to anti-tumor drugs is critical to realizing cancer precision medicine. Currently, most existing methods ignore the regulatory relationships between genes and thus have unsatisfactory predictive performance. In this paper, we propose to predict anti-tumor drug efficacy via learning the activity representation of tumor cells based on a priori knowledge of gene regulation networks (GRNs). Specifically, the method simulates the cellular biosystem by synthesizing a cell-gene activity network and then infers a new low-dimensional activity representation for tumor cells from the raw high-dimensional expression profile. The simulated cell-gene network mainly comprises known gene regulatory networks collected from multiple resources and fuses tumor cells by linking them to hotspot genes that are over- or under-expressed in them. The resulting activity representation could not only reflect the shallow expression profile (hotspot genes) but also mines in-depth information of gene regulation activity in tumor cells before treatment. Finally, we build deep learning models on the activity representation for predicting drug efficacy in tumor cells. Experimental results on the benchmark GDSC dataset demonstrate the superior performance of the proposed method over SOTA methods with the highest AUC of 0.954 in the efficacy label prediction and the best R2 of 0.834 in the regression of half maximal inhibitory concentration (IC50) values, suggesting the potential value of the proposed method in practice.

Themis: advancing precision oncology through comprehensive molecular subtyping and optimization

Recent advances in tumor molecular subtyping have revolutionized precision oncology, offering novel avenues for patient-specific treatment strategies. However, a comprehensive and independent comparison of these subtyping methodologies remains unexplored. This study introduces 'Themis' (Tumor HEterogeneity analysis on Molecular subtypIng System), an evaluation platform that encapsulates a few representative tumor molecular subtyping methods, including Stemness, Anoikis, Metabolism, and pathway-based classifications, utilizing 38 test datasets curated from The Cancer Genome Atlas (TCGA) and significant studies. Our self-designed quantitative analysis uncovers the relative strengths, limitations, and applicability of each method in different clinical contexts. Crucially, Themis serves as a vital tool in identifying the most appropriate subtyping methods for specific clinical scenarios. It also guides fine-tuning existing subtyping methods to achieve more accurate phenotype-associated results. To demonstrate the practical utility, we apply Themis to a breast cancer dataset, showcasing its efficacy in selecting the most suitable subtyping methods for personalized medicine in various clinical scenarios. This study bridges a crucial gap in cancer research and lays a foundation for future advancements in individualized cancer therapy and patient management.

Promoter hypermethylation as a novel regulator of ANO1 expression and function in prostate cancer bone metastasis

Despite growing evidence implicating the calcium-activated chloride channel anoctamin1 (ANO1) in cancer metastasis, its direct impact on the metastatic potential of prostate cancer and the possible significance of epigenetic alteration in this process are not fully understood. Here, we show that ANO1 is minimally expressed in LNCap and DU145 prostate cancer cell lines with low metastatic potential but overexpressed in high metastatic PC3 prostate cancer cell line. The treatment of LNCap and DU145 cells with DNMT inhibitor 5-aza-2'-deoxycytidine (5-Aza-CdR) potentiates ANO1 expression, suggesting that DNA methylation is one of the mechanisms controlling ANO1 expression. Consistent with this notion, hypermethylation was detected at the CpG island of ANO1 promoter region in LNCap and DU145 cells, and 5-Aza-CdR treatment resulted in a drastic demethylation at promoter CpG methylation sites. Upon 5-Aza-CdR treatment, metastatic indexes, such as cell motility, invasion, and metastasis-related gene expression, were significantly altered in LNCap and DU145 cells. These 5-Aza-CdR-induced metastatic hallmarks were, however, almost completely ablated by stable knockdown of ANO1. These in vitro discoveries were further supported by our in vivo observation that ANO1 expression in xenograft mouse models enhances the metastatic dissemination of prostate cancer cells into tibial bone and the development of osteolytic lesions. Collectively, our results help elucidate the critical role of ANO1 expression in prostate cancer bone metastases, which is epigenetically modulated by promoter CpG methylation.

MMSyn: A New Multimodal Deep Learning Framework for Enhanced Prediction of Synergistic Drug Combinations

Combination therapy is a promising strategy for the successful treatment of cancer. The large number of possible combinations, however, mean that it is laborious and expensive to screen for synergistic drug combinations in vitro. Nevertheless, because of the availability of high-throughput screening data and advances in computational techniques, deep learning (DL) can be a useful tool for the prediction of synergistic drug combinations. In this study, we proposed a multimodal DL framework, MMSyn, for the prediction of synergistic drug combinations. First, features embedded in the drug molecules were extracted: structure, fingerprint, and string encoding. Then, gene expression data, DNA copy number, and pathway activity were used to describe cancer cell lines. Finally, these processed features were integrated using an attention mechanism and an interaction module and then input into a multilayer perceptron to predict drug synergy. Experimental results showed that our method outperformed five state-of-the-art DL methods and three traditional machine learning models for drug combination prediction. We verified that MMSyn achieved superior performance in stratified cross-validation settings using both the drug combination and cell line data. Moreover, we performed a set of ablation experiments to illustrate the effectiveness of each component and the efficacy of our model. In addition, our visual representation and case studies further confirmed the effectiveness of our model. All results showed that MMSyn can be used as a powerful tool for the prediction of synergistic drug combinations.

DNA-based molecular classifiers for the profiling of gene expression signatures

Although gene expression signatures offer tremendous potential in diseases diagnostic and prognostic, but massive gene expression signatures caused challenges for experimental detection and computational analysis in clinical setting. Here, we introduce a universal DNA-based molecular classifier for profiling gene expression signatures and generating immediate diagnostic outcomes. The molecular classifier begins with feature transformation, a modular and programmable strategy was used to capture relative relationships of low-concentration RNAs and convert them to general coding inputs. Then, competitive inhibition of the DNA catalytic reaction enables strict weight assignment for different inputs according to their importance, followed by summation, annihilation and reporting to accurately implement the mathematical model of the classifier. We validated the entire workflow by utilizing miRNA expression levels for the diagnosis of hepatocellular carcinoma (HCC) in clinical samples with an accuracy 85.7%. The results demonstrate the molecular classifier provides a universal solution to explore the correlation between gene expression patterns and disease diagnostics, monitoring, and prognosis, and supports personalized healthcare in primary care.

An integrated framework for prognosis prediction and drug response modeling in colorectal liver metastasis drug discovery

BACKGROUND

Colorectal cancer (CRC) is the third most prevalent cancer globally, and liver metastasis (CRLM) is the primary cause of death. Hence, it is essential to discover novel prognostic biomarkers and therapeutic drugs for CRLM.

METHODS

This study developed two liver metastasis-associated prognostic signatures based on differentially expressed genes (DEGs) in CRLM. Additionally, we employed an interpretable deep learning model utilizing drug sensitivity databases to identify potential therapeutic drugs for high-risk CRLM patients. Subsequently, in vitro and in vivo experiments were performed to verify the efficacy of these compounds.

RESULTS

These two prognostic models exhibited superior performance compared to previously reported ones. Obatoclax, a BCL-2 inhibitor, showed significant differential responses between high and low risk groups classified by prognostic models, and demonstrated remarkable effectiveness in both Transwell assay and CT26 colorectal liver metastasis mouse model.

CONCLUSIONS

This study highlights the significance of developing specialized prognostication approaches and investigating effective therapeutic drugs for patients with CRLM. The application of a deep learning drug response model provides a new drug discovery strategy for translational medicine in precision oncology.

Improving drug response prediction via integrating gene relationships with deep learning

Predicting the drug response of cancer cell lines is crucial for advancing personalized cancer treatment, yet remains challenging due to tumor heterogeneity and individual diversity. In this study, we present a deep learning-based framework named Deep neural network Integrating Prior Knowledge (DIPK) (DIPK), which adopts self-supervised techniques to integrate multiple valuable information, including gene interaction relationships, gene expression profiles and molecular topologies, to enhance prediction accuracy and robustness. We demonstrated the superior performance of DIPK compared to existing methods on both known and novel cells and drugs, underscoring the importance of gene interaction relationships in drug response prediction. In addition, DIPK extends its applicability to single-cell RNA sequencing data, showcasing its capability for single-cell-level response prediction and cell identification. Further, we assess the applicability of DIPK on clinical data. DIPK accurately predicted a higher response to paclitaxel in the pathological complete response (pCR) group compared to the residual disease group, affirming the better response of the pCR group to the chemotherapy compound. We believe that the integration of DIPK into clinical decision-making processes has the potential to enhance individualized treatment strategies for cancer patients.

Complex or not too complex? One size does not fit all in next generation microphysiological systems

In the attempt to overcome the increasingly recognized shortcomings of existing in vitro and in vivo models, researchers have started to implement alternative models, including microphysiological systems. First examples were represented by 2.5D systems, such as microfluidic channels covered by cell monolayers as blood vessel replicates. In recent years, increasingly complex microphysiological systems have been developed, up to multi-organ on chip systems, connecting different 3D tissues in the same device. However, such an increase in model complexity raises several questions about their exploitation and implementation into industrial and clinical applications, ranging from how to improve their reproducibility, robustness, and reliability to how to meaningfully and efficiently analyze the huge amount of heterogeneous datasets emerging from these devices. Considering the multitude of envisaged applications for microphysiological systems, it appears now necessary to tailor their complexity on the intended purpose, being academic or industrial, and possibly combine results deriving from differently complex stages to increase their predictive power.

Uncovering the subtype-specific disease module and the development of drug response prediction models for glioma

The poor prognosis of glioma patients brought attention to the need for effective therapeutic approaches for precision therapy. Here, we deployed algorithms relying on network medicine and artificial intelligence to design the framework for subtype-specific target identification and drug response prediction in glioma. We identified the driver mutations that were differentially expressed in each subtype of lower-grade glioma and glioblastoma multiforme and were linked to cancer-specific processes. Driver mutations that were differentially expressed were also subjected to subtype-specific disease module identification. The drugs from the drug bank database were retrieved to target these disease modules. However, the efficacy of anticancer drugs depends on the molecular profile of the cancer and varies among cancer patients due to intratumor heterogeneity. Hence, we developed a deep-learning-based drug response prediction framework using the experimental drug screening data. Models for 30 drugs that can target the disease module were developed, where drug response measured by IC50 was considered a response and gene expression and mutation data were considered predictor variables. The model construction consists of three steps: feature selection, data integration, and classification. We observed the consistent performance of the models in training, test, and validation datasets. Drug responses were predicted for particular cell lines derived from distinct subtypes of gliomas. We found that subtypes of gliomas respond differently to the drug, highlighting the importance of subtype-specific drug response prediction. Therefore, the development of personalized therapy by integrating network medicine and a deep learning-based approach can lead to cancer-specific treatment and improved patient care.

Cross-layer transmission realized by light-emitting memristor for constructing ultra-deep neural network with transfer learning ability

Deep neural networks have revolutionized several domains, including autonomous driving, cancer detection, and drug design, and are the foundation for massive artificial intelligence models. However, hardware neural network reports still mainly focus on shallow networks (2 to 5 layers). Implementing deep neural networks in hardware is challenging due to the layer-by-layer structure, resulting in long training times, signal interference, and low accuracy due to gradient explosion/vanishing. Here, we utilize negative ultraviolet photoconductive light-emitting memristors with intrinsic parallelism and hardware-software co-design to achieve electrical information's optical cross-layer transmission. We propose a hybrid ultra-deep photoelectric neural network and an ultra-deep super-resolution reconstruction neural network using light-emitting memristors and cross-layer block, expanding the networks to 54 and 135 layers, respectively. Further, two networks enable transfer learning, approaching or surpassing software-designed networks in multi-dataset recognition and high-resolution restoration tasks. These proposed strategies show great potential for high-precision multifunctional hardware neural networks and edge artificial intelligence.

Expression of the checkpoint kinase BUB1 is a predictor of response to cancer therapies

The identification of clinically-relevant biomarkers is of upmost importance for the management of cancer, from diagnosis to treatment choices. We performed a pan-cancer analysis of the mitotic checkpoint budding uninhibited by benzimidazole 1 gene BUB1, in the attempt to ascertain its diagnostic and prognostic values, specifically in the context of drug response. BUB1 was found to be overexpressed in the majority of cancers, and particularly elevated in clinically aggressive molecular subtypes. Its expression was correlated with clinico-phenotypic features, notably tumour staging, size, invasion, hypoxia, and stemness. In terms of prognostic value, the expression of BUB1 bore differential clinical outcomes depending on the treatment administered in TCGA cancer cohorts, suggesting sensitivity or resistance, depending on the expression levels. We also integrated in vitro drug sensitivity data from public projects based on correlation between drug efficacy and BUB1 expression to produce a list of candidate compounds with differential responses according to BUB1 levels. Gene Ontology enrichment analyses revealed that BUB1 overexpression in cancer is associated with biological processes related to mitosis and chromosome segregation machinery, reflecting the mechanisms of action of drugs with a differential effect based on BUB1 expression.

Genomics and Artificial Intelligence: Prostate Cancer

Artificial intelligence (AI) is revolutionizing prostate cancer genomics research. By leveraging machine learning and deep learning algorithms, researchers can rapidly analyze vast genomic datasets to identify patterns and correlations that may be missed by traditional methods. These AI-driven insights can lead to the discovery of novel biomarkers, enhance the accuracy of diagnosis, and predict disease progression and treatment response. As such, AI is becoming an indispensable tool in the pursuit of personalized medicine for prostate cancer.

XGraphCDS: An explainable deep learning model for predicting drug sensitivity from gene pathways and chemical structures

Cancer is a highly complex disease characterized by genetic and phenotypic heterogeneity among individuals. In the era of precision medicine, understanding the genetic basis of these individual differences is crucial for developing new drugs and achieving personalized treatment. Despite the increasing abundance of cancer genomics data, predicting the relationship between cancer samples and drug sensitivity remains challenging. In this study, we developed an explainable graph neural network framework for predicting cancer drug sensitivity (XGraphCDS) based on comparative learning by integrating cancer gene expression information and drug chemical structure knowledge. Specifically, XGraphCDS consists of a unified heterogeneous network and multiple sub-networks, with molecular graphs representing drugs and gene enrichment scores representing cell lines. Experimental results showed that XGraphCDS consistently outperformed most state-of-the-art baselines (R2 = 0.863, AUC = 0.858). We also constructed a separate in vivo prediction model by using transfer learning strategies with in vitro experimental data and achieved good predictive power (AUC = 0.808). Simultaneously, our framework is interpretable, providing insights into resistance mechanisms alongside accurate predictions. The excellent performance of XGraphCDS highlights its immense potential in aiding the development of selective anti-tumor drugs and personalized dosing strategies in the field of precision medicine.

A simple and rapid assay of lysosomal-targeting CDy6 for long-term real-time viability assessments in 2D and 3D in vitro culture models

CDy6, a BODIPY-derived compound, is used to label lysosomes and visualize proliferating cells. However, its effectiveness in long-term, real-time cell viability assays using 2D or 3D cell culture models is unclear. We evaluated the suitability of CDy6 by assessing cell health using human keratinocyte and fibroblast cell lines in both models. Cells were stained with CDy6 or other dyes and fluorescent images were obtained with confocal microscopy. CLV extracts derived from CDy6-stained HaCaT cells were also dissolved with DMSO and analyzed using a spectrometer. Furthermore, we added CDy6-stained collagen hydrogels to CCD-986sk cells, loaded them into a frame construction to establish a 3D dermal layer for long-term culture, and analyzed the status of the CLVs. The CLV method, also measured using a spectrometer, yielded results similar to MTT assay for validating viability. In contrast to calcein AM staining, the CLV method allows for both absorbance measurement and imaging under short-term and long-term culture conditions with less cytotoxicity. In conclusion, the CLV method provides a simple and sensitive tool for assessing the status of live cells in 2D and 3D in vitro cell culture models and can be used as an alternative to animal testing, such as with 3D artificial skin models.

GPDRP: a multimodal framework for drug response prediction with graph transformer

BACKGROUND

In the field of computational personalized medicine, drug response prediction (DRP) is a critical issue. However, existing studies often characterize drugs as strings, a representation that does not align with the natural description of molecules. Additionally, they ignore gene pathway-specific combinatorial implication.

RESULTS

In this study, we propose drug Graph and gene Pathway based Drug response prediction method (GPDRP), a new multimodal deep learning model for predicting drug responses based on drug molecular graphs and gene pathway activity. In GPDRP, drugs are represented by molecular graphs, while cell lines are described by gene pathway activity scores. The model separately learns these two types of data using Graph Neural Networks (GNN) with Graph Transformers and deep neural networks. Predictions are subsequently made through fully connected layers.

CONCLUSIONS

Our results indicate that Graph Transformer-based model delivers superior performance. We apply GPDRP on hundreds of cancer cell lines' bulk RNA-sequencing data, and it outperforms some recently published models. Furthermore, the generalizability and applicability of GPDRP are demonstrated through its predictions on unknown drug-cell line pairs and xenografts. This underscores the interpretability achieved by incorporating gene pathways.

CurveCurator: a recalibrated F-statistic to assess, classify, and explore significance of dose-response curves

Dose-response curves are key metrics in pharmacology and biology to assess phenotypic or molecular actions of bioactive compounds in a quantitative fashion. Yet, it is often unclear whether or not a measured response significantly differs from a curve without regulation, particularly in high-throughput applications or unstable assays. Treating potency and effect size estimates from random and true curves with the same level of confidence can lead to incorrect hypotheses and issues in training machine learning models. Here, we present CurveCurator, an open-source software that provides reliable dose-response characteristics by computing p-values and false discovery rates based on a recalibrated F-statistic and a target-decoy procedure that considers dataset-specific effect size distributions. The application of CurveCurator to three large-scale datasets enables a systematic drug mode of action analysis and demonstrates its scalable utility across several application areas, facilitated by a performant, interactive dashboard for fast data exploration.

DELFOS-drug efficacy leveraging forked and specialized networks-benchmarking scRNA-seq data in multi-omics-based prediction of cancer sensitivity

MOTIVATION

Cancer is currently one of the most notorious diseases, with over 1 million deaths in the European Union alone in 2022. As each tumor can be composed of diverse cell types with distinct genotypes, cancer cells can acquire resistance to different compounds. Moreover, anticancer drugs can display severe side effects, compromising patient well-being. Therefore, novel strategies for identifying the optimal set of compounds to treat each tumor have become an important research topic in recent decades.

RESULTS

To address this challenge, we developed a novel drug response prediction algorithm called Drug Efficacy Leveraging Forked and Specialized networks (DELFOS). Our model learns from multi-omics data from over 65 cancer cell lines, as well as structural data from over 200 compounds, for the prediction of drug sensitivity. We also evaluated the benefits of incorporating single-cell expression data to predict drug response. DELFOS was validated using datasets with unseen cell lines or drugs and compared with other state-of-the-art algorithms, achieving a high prediction performance on several correlation and error metrics. Overall, DELFOS can effectively leverage multi-omics data for the prediction of drug responses in thousands of drug-cell line pairs.

AVAILABILITY AND IMPLEMENTATION

The DELFOS pipeline and associated data are available at github.com/MoreiraLAB/delfos.

Preclinical Efficacy of LP-184, a Tumor Site Activated Synthetic Lethal Therapeutic, in Glioblastoma

PURPOSE

Glioblastoma (GBM) is the most common brain malignancy with median survival <2 years. Standard-of-care temozolomide has marginal efficacy in approximately 70% of patients due to MGMT expression. LP-184 is an acylfulvene-derived prodrug activated by the oxidoreductase PTGR1 that alkylates at N3-adenine, not reported to be repaired by MGMT. This article examines LP-184 efficacy against preclinical GBM models and identifies molecular predictors of LP-184 efficacy in clinical GBM.

EXPERIMENTAL DESIGN

LP-184 effects on GBM cell viability and DNA damage were determined using cell lines, primary PDX-derived cells and patient-derived neurospheres. GBM cell sensitivities to LP-184 relative to temozolomide and MGMT expression were examined. Pharmacokinetics and CNS bioavailability were evaluated in mice with GBM xenografts. LP-184 effects on GBM xenograft growth and animal survival were determined. Machine learning, bioinformatic tools, and clinical databases identified molecular predictors of GBM cells and tumors to LP-184 responsiveness.

RESULTS

LP-184 inhibited viability of multiple GBM cell isolates including temozolomide-resistant and MGMT-expressing cells at IC50 = approximately 22-310 nmol/L. Pharmacokinetics showed favorable AUCbrain/plasma and AUCtumor/plasma ratios of 0.11 (brain Cmax = 839 nmol/L) and 0.2 (tumor Cmax = 2,530 nmol/L), respectively. LP-184 induced regression of GBM xenografts and prolonged survival of mice bearing orthotopic xenografts. Bioinformatic analyses identified PTGR1 elevation in clinical GBM subtypes and associated LP-184 sensitivity with EGFR signaling, low nucleotide excision repair (NER), and low ERCC3 expression. Spironolactone, which induces ERCC3 degradation, decreased LP-184 IC50 3 to 6 fold and enhanced GBM xenograft antitumor responses.

CONCLUSIONS

These results establish LP-184 as a promising chemotherapeutic for GBM with enhanced efficacy in intrinsic or spironolactone-induced TC-NER-deficient tumors.

MSDRP: a deep learning model based on multisource data for predicting drug response

MOTIVATION

Cancer heterogeneity drastically affects cancer therapeutic outcomes. Predicting drug response in vitro is expected to help formulate personalized therapy regimens. In recent years, several computational models based on machine learning and deep learning have been proposed to predict drug response in vitro. However, most of these methods capture drug features based on a single drug description (e.g. drug structure), without considering the relationships between drugs and biological entities (e.g. target, diseases, and side effects). Moreover, most of these methods collect features separately for drugs and cell lines but fail to consider the pairwise interactions between drugs and cell lines.

RESULTS

In this paper, we propose a deep learning framework, named MSDRP for drug response prediction. MSDRP uses an interaction module to capture interactions between drugs and cell lines, and integrates multiple associations/interactions between drugs and biological entities through similarity network fusion algorithms, outperforming some state-of-the-art models in all performance measures for all experiments. The experimental results of de novo test and independent test demonstrate the excellent performance of our model for new drugs. Furthermore, several case studies illustrate the rationality for using feature vectors derived from drug similarity matrices from multisource data to represent drugs and the interpretability of our model.

AVAILABILITY AND IMPLEMENTATION

The codes of MSDRP are available at https://github.com/xyzhang-10/MSDRP.

Deep learning of 2D-Restructured gene expression representations for improved low-sample therapeutic response prediction

Clinical outcome prediction is important for stratified therapeutics. Machine learning (ML) and deep learning (DL) methods facilitate therapeutic response prediction from transcriptomic profiles of cells and clinical samples. Clinical transcriptomic DL is challenged by the low-sample sizes (34-286 subjects), high-dimensionality (up to 21,653 genes) and unordered nature of clinical transcriptomic data. The established methods rely on ML algorithms at accuracy levels of 0.6-0.8 AUC/ACC values. Low-sample DL algorithms are needed for enhanced prediction capability. Here, an unsupervised manifold-guided algorithm was employed for restructuring transcriptomic data into ordered image-like 2D-representations, followed by efficient DL of these 2D-representations with deep ConvNets. Our DL models significantly outperformed the state-of-the-art (SOTA) ML models on 82% of 17 low-sample benchmark datasets (53% with >0.05 AUC/ACC improvement). They are more robust than the SOTA models in cross-cohort prediction tasks, and in identifying robust biomarkers and response-dependent variational patterns consistent with experimental indications.

A subcomponent-guided deep learning method for interpretable cancer drug response prediction

Accurate prediction of cancer drug response (CDR) is a longstanding challenge in modern oncology that underpins personalized treatment. Current computational methods implement CDR prediction by modeling responses between entire drugs and cell lines, without the consideration that response outcomes may primarily attribute to a few finer-level 'subcomponents', such as privileged substructures of the drug or gene signatures of the cancer cell, thus producing predictions that are hard to explain. Herein, we present SubCDR, a subcomponent-guided deep learning method for interpretable CDR prediction, to recognize the most relevant subcomponents driving response outcomes. Technically, SubCDR is built upon a line of deep neural networks that enables a set of functional subcomponents to be extracted from each drug and cell line profile, and breaks the CDR prediction down to identifying pairwise interactions between subcomponents. Such a subcomponent interaction form can offer a traceable path to explicitly indicate which subcomponents contribute more to the response outcome. We verify the superiority of SubCDR over state-of-the-art CDR prediction methods through extensive computational experiments on the GDSC dataset. Crucially, we found many predicted cases that demonstrate the strength of SubCDR in finding the key subcomponents driving responses and exploiting these subcomponents to discover new therapeutic drugs. These results suggest that SubCDR will be highly useful for biomedical researchers, particularly in anti-cancer drug design.

Evolution-Informed Strategies for Combating Drug Resistance in Cancer

The ever-changing nature of cancer poses the most difficult challenge oncologists face today. Cancer's remarkable adaptability has inspired many to work toward understanding the evolutionary dynamics that underlie this disease in hopes of learning new ways to fight it. Eco-evolutionary dynamics of a tumor are not accounted for in most standard treatment regimens, but exploiting them would help us combat treatment-resistant effectively. Here, we outline several notable efforts to exploit these dynamics and circumvent drug resistance in cancer.

Enzalutamide-induced signatures revealed by epigenetic plasticity using single-cell multi-omics sequencing in prostate cancer

Prostate cancer is morphologically and molecularly heterogeneous, which poses obstacles for early diagnosis and treatment. Advancements in understanding the heterogeneity of prostate cancer will help navigate through these challenges and ultimately benefit patients. In this study, we integrated single-cell sequencing for transposase-accessible chromatin and whole transcriptome in prostate cancer cell lines, aiming to decode the epigenetic plasticity upon enzalutamide (ENZ) treatment. By comparing the cell populations representing early-treatment response or resistance to the initial tumor cells, we identified seven signature gene sets; they present consistent trends of chromatin closing co-occurred with down-regulated genes during early response and chromatin opening with up-regulated genes upon maintaining drug resistance. In the molecular signatures, we found genes ZNF337, MAPK15, and ESRRG are favorable in progression-free prognosis during early response, while genes CCDC150, CCDC18, and POC1A marked poor prognosis underpinning the pre-existing drug resistance in The Cancer Genome Atlas prostate adenocarcinoma cohort. Ultimately, drug-target analyses nominated combinatory drug candidates to either enhance early-treatment response or potentially overcome ENZ resistance. Together, our integrative, single-cell multi-omics approach in pre-clinical models is effective in identifying informative signatures from complex molecular events, illustrating diverse drug responses in prostate cancer, and invoking novel combinatory drug strategies to inform clinical decision making.

Advances of Artificial Intelligence in Anti-Cancer Drug Design: A Review of the Past Decade

Anti-cancer drug design has been acknowledged as a complicated, expensive, time-consuming, and challenging task. How to reduce the research costs and speed up the development process of anti-cancer drug designs has become a challenging and urgent question for the pharmaceutical industry. Computer-aided drug design methods have played a major role in the development of cancer treatments for over three decades. Recently, artificial intelligence has emerged as a powerful and promising technology for faster, cheaper, and more effective anti-cancer drug designs. This study is a narrative review that reviews a wide range of applications of artificial intelligence-based methods in anti-cancer drug design. We further clarify the fundamental principles of these methods, along with their advantages and disadvantages. Furthermore, we collate a large number of databases, including the omics database, the epigenomics database, the chemical compound database, and drug databases. Other researchers can consider them and adapt them to their own requirements.

Artificial Intelligence-Assisted Transcriptomic Analysis to Advance Cancer Immunotherapy

The emergence of immunotherapy has dramatically changed the cancer treatment paradigm and generated tremendous promise in precision medicine. However, cancer immunotherapy is greatly limited by its low response rates and immune-related adverse events. Transcriptomics technology is a promising tool for deciphering the molecular underpinnings of immunotherapy response and therapeutic toxicity. In particular, applying single-cell RNA-seq (scRNA-seq) has deepened our understanding of tumor heterogeneity and the microenvironment, providing powerful help for developing new immunotherapy strategies. Artificial intelligence (AI) technology in transcriptome analysis meets the need for efficient handling and robust results. Specifically, it further extends the application scope of transcriptomic technologies in cancer research. AI-assisted transcriptomic analysis has performed well in exploring the underlying mechanisms of drug resistance and immunotherapy toxicity and predicting therapeutic response, with profound significance in cancer treatment. In this review, we summarized emerging AI-assisted transcriptomic technologies. We then highlighted new insights into cancer immunotherapy based on AI-assisted transcriptomic analysis, focusing on tumor heterogeneity, the tumor microenvironment, immune-related adverse event pathogenesis, drug resistance, and new target discovery. This review summarizes solid evidence for immunotherapy research, which might help the cancer research community overcome the challenges faced by immunotherapy.

Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

A systematic assessment of deep learning methods for drug response prediction: from in vitro to clinical applications

Drug response prediction is an important problem in personalized cancer therapy. Among various newly developed models, significant improvement in prediction performance has been reported using deep learning methods. However, systematic comparisons of deep learning methods, especially of the transferability from preclinical models to clinical cohorts, are currently lacking. To provide a more rigorous assessment, the performance of six representative deep learning methods for drug response prediction using nine evaluation metrics, including the overall prediction accuracy, predictability of each drug, potential associated factors and transferability to clinical cohorts, in multiple application scenarios was benchmarked. Most methods show promising prediction within cell line datasets, and TGSA, with its lower time cost and better performance, is recommended. Although the performance metrics decrease when applying models trained on cell lines to patients, a certain amount of power to distinguish clinical response on some drugs can be maintained using CRDNN and TGSA. With these assessments, we provide a guidance for researchers to choose appropriate methods, as well as insights into future directions for the development of more effective methods in clinical scenarios.

Upregulation of Neuroinflammatory Protein Biomarkers in Acute Rhegmatogenous Retinal Detachments

The purpose of this study is to characterize the inflammatory cytokine profile in rhegmatogenous retinal detachments (RRDs) compared to surgical controls. Vitreous humor was collected from patients undergoing vitrectomy for RRD and noninflammatory vitreoretinal diseases. A quantitative immunoassay was used to measure the levels of 36 cytokine markers. Linear regression analysis with the duration of detachment as the predictor and log-transformed cytokine levels as the outcome was conducted for normally distributed cytokines as determined by the Shapiro-Wilk test. The analysis was adjusted for age, sex, and race. The Kruskal-Wallis test was used for cytokines not normally distributed. Twenty-seven RRD cases and thirteen control cases were studied. Between all RRDs and controls, fibroblast growth factor 2 (FGF2) (p = 0.0029), inducible protein-10(IP-10) (p = 0.0021), monocyte chemoattractant protein-1 (MCP-1) (p = 0.0040), interleukin (IL)-16 (p = 0.018), IL-8 (p = 0.0148), IL-6 (p = 0.0071), eotaxin (p = 0.0323), macrophage inflammatory protein (MIP)-1 alpha (p = 0.0149), MIP-1 beta (p = 0.0032), and the thymus and activation regulated cytokine (TARC) (p = 0.0121) were elevated in RRD cases. Between acute RRDs (n = 16) and controls, FGF2 (p = 0.0001), IP10 (p = 0.0027), MCP-1 (p = 0.0015), MIP-1β (p = 0.0004), IL-8 (p = 0.0146), and IL-6 (p = 0.0031) were elevated. Determining alterations in inflammatory cytokine profiles may aid in understanding their impact on RRD development, clinical course, and complications before and after surgical repair.

A bile acid-related prognostic signature in hepatocellular carcinoma

Due to the high mortality of hepatocellular carcinoma (HCC), its prognostic models are urgently needed. Bile acid (BA) metabolic disturbance participates in hepatocarcinogenesis. We aim to develop a BA-related gene signature for HCC patients. Research data of HCC were obtained from The Cancer Genome Atlas (TCGA) and International Cancer Genome Consortium (ICGC) online databases. After least absolute shrinkage and selection operator (LASSO) regression analysis, we developed a BA-related prognostic signature in TCGA cohort based on differentially expressed prognostic BA-related genes. Then, the predictive performance of the signature was evaluated and verified in TCGA and ICGC cohort respectively. We obtained the risk score of each HCC patient according to the model. The differences of immune status and drug sensitivity were compared in patients that were stratified based on risk score. The protein and mRNA levels of the modeling genes were validated in the Human Protein Atlas database and our cell lines, respectively. In TCGA cohort, we selected 4 BA-related genes to construct the first BA-related prognostic signature. The risk signature exhibited good discrimination and predictive ability, which was verified in ICGC cohort. Patients were classified into high- and low-risk groups according to their median scores. The occurrence of death increased with increasing risk score. Low-risk patients owned favorable overall survival. High-risk patients possessed high immune checkpoint expression and low IC50 values for sorafenib, cisplatin and doxorubicin. Real-time quantitative PCR and immunohistochemical results validate expression of modeling genes in the signature. We constructed the first BA-related gene signature, which might help to identify HCC patients with poor prognosis and guide individualized treatment.

Hepatitis B virus pathogenesis relevant immunosignals uncovering amino acids utilization related risk factors guide artificial intelligence-based precision medicine

Background: Although immune microenvironment-related chemokines, extracellular matrix (ECM), and intrahepatic immune cells are reported to be highly involved in hepatitis B virus (HBV)-related diseases, their roles in diagnosis, prognosis, and drug sensitivity evaluation remain unclear. Here, we aimed to study their clinical use to provide a basis for precision medicine in hepatocellular carcinoma (HCC) via the amalgamation of artificial intelligence. Methods: High-throughput liver transcriptomes from Gene Expression Omnibus (GEO), NODE (https://www.bio.sino.org/node), the Cancer Genome Atlas (TCGA), and our in-house hepatocellular carcinoma patients were collected in this study. Core immunosignals that participated in the entire diseases course of hepatitis B were explored using the "Gene set variation analysis" R package. Using ROC curve analysis, the impact of core immunosignals and amino acid utilization related gene on hepatocellular carcinoma patient's clinical outcome were calculated. The utility of core immunosignals as a classifier for hepatocellular carcinoma tumor tissue was evaluated using explainable machine-learning methods. A novel deep residual neural network model based on immunosignals was constructed for the long-term overall survival (LS) analysis. In vivo drug sensitivity was calculated by the "oncoPredict" R package. Results: We identified nine genes comprising chemokines and ECM related to hepatitis B virus-induced inflammation and fibrosis as CLST signals. Moreover, CLST was co-enriched with activated CD4+ T cells bearing harmful factors (aCD4) during all stages of hepatitis B virus pathogenesis, which was also verified by our hepatocellular carcinoma data. Unexpectedly, we found that hepatitis B virus-hepatocellular carcinoma patients in the CLST^highaCD4^high subgroup had the shortest overall survival (OS) and were characterized by a risk gene signature associated with amino acids utilization. Importantly, characteristic genes specific to CLST/aCD4 showed promising clinical relevance in identifying patients with early-stage hepatocellular carcinoma via explainable machine learning. In addition, the 5-year long-term overall survival of hepatocellular carcinoma patients can be effectively classified by CLST/aCD4 based GeneSet-ResNet model. Subgroups defined by CLST and aCD4 were significantly involved in the sensitivity of hepatitis B virus-hepatocellular carcinoma patients to chemotherapy treatments. Conclusion: CLST and aCD4 are hepatitis B virus pathogenesis-relevant immunosignals that are highly involved in hepatitis B virus-induced inflammation, fibrosis, and hepatocellular carcinoma. Gene set variation analysis derived immunogenomic signatures enabled efficient diagnostic and prognostic model construction. The clinical application of CLST and aCD4 as indicators would be beneficial for the precision management of hepatocellular carcinoma.