Genomic data integration by WON-PARAFAC identifies interpretable factors for predicting drug-sensitivity in vivo

A comparative analysis of computational drug repurposing approaches: proposing a novel tensor-matrix-tensor factorization method

Efficient drug discovery relies on drug repurposing, an important and open research field. This work presents a novel factorization method and a practical comparison of different approaches for drug repurposing. First, we propose a novel tensor-matrix-tensor (TMT) formulation as a new data array method with a gradient-based factorization procedure. Additionally, this paper examines and contrasts four computational drug repurposing approaches-factorization-based methods, machine learning methods, deep learning methods, and graph neural networks-to fulfill the second purpose. We test the strategies on two datasets and assess each approach's performance, drawbacks, problems, and benefits based on results. The results demonstrate that deep learning techniques work better than other strategies and that their results might be more reliable. Ultimately, graph neural methods need to be in an inductive manner to have a reliable prediction.

Microbiome-based classification models for fresh produce safety and quality evaluation

Small sample sizes and loss of sequencing reads during the microbiome data preprocessing can limit the statistical power of differentiating fresh produce phenotypes and prevent the detection of important bacterial species associated with produce contamination or quality reduction. Here, we explored a machine learning-based k-mer hash analysis strategy to identify DNA signatures predictive of produce safety (PS) and produce quality (PQ) and compared it against the amplicon sequence variant (ASV) strategy that uses a typical denoising step and ASV-based taxonomy strategy. Random forest-based classifiers for PS and PQ using 7-mer hash data sets had significantly higher classification accuracy than those using the ASV data sets. We also demonstrated that the proposed combination of integrating multiple data sets and leveraging a 7-mer hash strategy leads to better classification performance for PS and PQ compared to the ASV method but presents lower PS classification accuracy compared to the feature-selected ASV-based taxonomy strategy. Due to the current limitation of generating taxonomy using the 7-mer hash strategy, the ASV-based taxonomy strategy with remarkably less computing time and memory usage is more efficient for PS and PQ classification and applicable for important taxa identification. Results generated from this study lay the foundation for future studies that wish and need to incorporate and/or compare different microbiome sequencing data sets for the application of machine learning in the area of microbial safety and quality of food.

IMPORTANCE

Identification of generalizable indicators for produce safety (PS) and produce quality (PQ) improves the detection of produce contamination and quality decline. However, effective sequencing read loss during microbiome data preprocessing and the limited sample size of individual studies restrain statistical power to identify important features contributing to differentiating PS and PQ phenotypes. We applied machine learning-based models using individual and integrated k-mer hash and amplicon sequence variant (ASV) data sets for PS and PQ classification and evaluated their classification performance and found that random forest (RF)-based models using integrated 7-mer hash data sets achieved significantly higher PS and PQ classification accuracy. Due to the limitation of taxonomic analysis for the 7-mer hash, we also developed RF-based models using feature-selected ASV-based taxonomic data sets, which performed better PS classification than those using the integrated 7-mer hash data set. The RF feature selection method identified 480 PS indicators and 263 PQ indicators with a positive contribution to the PS and PQ classification.

Dynamic modeling of the cellular senescence gene regulatory network

Cellular senescence is a cell fate that prominently impacts physiological and pathophysiological processes. Diverse cellular stresses induce it, and dramatic gene expression changes accompany it. However, determining the interactions comprising the gene regulatory network (GRN) governing senescence remains challenging. Recent advances in signal processing techniques provide opportunities to reconstruct GRNs. Here, we describe a GRN for senescence integrating time-series transcriptome and transcription factor depletion datasets. Specifically, we infer a set of differential equations using the "Sparse Identification of Nonlinear Dynamics" (SINDy) algorithm, discriminate genes with potential hidden regulators, validate the inferred GRN for time-points not included in the training data, and comprehensively benchmark our approach. Our work is a proof of concept for a data-driven GRN reconstruction method, consolidating an iterative, powerful mathematical platform for senescence modeling that can be used to test hypotheses in silico and has the potential for future discoveries of clinical impact.

Opportunities and challenges in interpretable deep learning for drug sensitivity prediction of cancer cells

In precision oncology, therapy stratification is done based on the patients' tumor molecular profile. Modeling and prediction of the drug response for a given tumor molecular type will further improve therapeutic decision-making for cancer patients. Indeed, deep learning methods hold great potential for drug sensitivity prediction, but a major problem is that these models are black box algorithms and do not clarify the mechanisms of action. This puts a limitation on their clinical implementation. To address this concern, many recent studies attempt to overcome these issues by developing interpretable deep learning methods that facilitate the understanding of the logic behind the drug response prediction. In this review, we discuss strengths and limitations of recent approaches, and suggest future directions that could guide further improvement of interpretable deep learning in drug sensitivity prediction in cancer research.

Nanoparticle delivery of miR-21-3p sensitizes melanoma to anti-PD-1 immunotherapy by promoting ferroptosis

Background

Although anti-programmed cell death protein 1 (PD-1) immunotherapy is greatly effective in melanoma treatment, low response rate and treatment resistance significantly hinder its efficacy. Tumor cell ferroptosis triggered by interferon (IFN)-γ that is derived from tumor-infiltrating CD8⁺ T cells greatly contributes to the effect of immunotherapy. However, the molecular mechanism underlying IFN-γ-mediated ferroptosis and related potentially promising therapeutic strategy warrant further clarification. MicroRNAs (miRNAs) participate in ferroptosis execution and can be delivered systemically by multiple carriers, which have manifested obvious therapeutic effects on cancer.

Methods

MiRNAs expression profile in IFN-γ-driven ferroptosis was obtained by RNA sequencing. Biochemical assays were used to clarify the role of miR-21-3p in IFN-γ-driven ferroptosis and the underlying mechanism. MiR-21-3p-loaded gold nanoparticles were constructed and systemically applied to analyze the role of miR-21-3p in anti-PD-1 immunotherapy in preclinical transplanted tumor model.

Results

MiRNAs expression profile of melanoma cells in IFN-γ-driven ferroptosis was first obtained. Then, upregulated miR-21-3p was proved to facilitate IFN-γ-mediated ferroptosis by potentiating lipid peroxidation. miR-21-3p increased the ferroptosis sensitivity by directly targeting thioredoxin reductase 1 (TXNRD1) to enhance lipid reactive oxygen species (ROS) generation. Furthermore, miR-21-3p overexpression in tumor synergized with anti-PD-1 antibody by promoting tumor cell ferroptosis. More importantly, miR-21-3p-loaded gold nanoparticles were constructed, and the systemic delivery of them increased the efficacy of anti-PD-1 antibody without prominent side effects in preclinical mice model. Ultimately, ATF3 was found to promote miR-21-3p transcription in IFN-γ-driven ferroptosis.

Conclusions

MiR-21–3 p upregulation contributes to IFN-γ-driven ferroptosis and synergizes with anti-PD-1 antibody. Nanoparticle delivery of miR-21–3 p is a promising therapeutic approach to increase immunotherapy efficacy without obvious systemic side effects.

Machine learning approach informs biology of cancer drug response

Background

The mechanism of action for most cancer drugs is not clear. Large-scale pharmacogenomic cancer cell line datasets offer a rich resource to obtain this knowledge. Here, we present an analysis strategy for revealing biological pathways that contribute to drug response using publicly available pharmacogenomic cancer cell line datasets.

Methods

We present a custom machine-learning based approach for identifying biological pathways involved in cancer drug response. We test the utility of our approach with a pan-cancer analysis of ML210, an inhibitor of GPX4, and a melanoma-focused analysis of inhibitors of BRAF^V600. We apply our approach to reveal determinants of drug resistance to microtubule inhibitors.

Results

Our method implicated lipid metabolism and Rac1/cytoskeleton signaling in the context of ML210 and BRAF inhibitor response, respectively. These findings are consistent with current knowledge of how these drugs work. For microtubule inhibitors, our approach implicated Notch and Akt signaling as pathways that associated with response.

Conclusions

Our results demonstrate the utility of combining informed feature selection and machine learning algorithms in understanding cancer drug response.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04720-z.

Dynamic Meta-data Network Sparse PCA for Cancer Subtype Biomarker Screening

Previous research shows that each type of cancer can be divided into multiple subtypes, which is one of the key reasons that make cancer difficult to cure. Under these circumstances, finding a new target gene of cancer subtypes has great significance on developing new anti-cancer drugs and personalized treatment. Due to the fact that gene expression data sets of cancer are usually high-dimensional and with high noise and have multiple potential subtypes’ information, many sparse principal component analysis (sparse PCA) methods have been used to identify cancer subtype biomarkers and subtype clusters. However, the existing sparse PCA methods have not used the known cancer subtype information as prior knowledge, and their results are greatly affected by the quality of the samples. Therefore, we propose the Dynamic Metadata Edge-group Sparse PCA (DM-ESPCA) model, which combines the idea of meta-learning to solve the problem of sample quality and uses the known cancer subtype information as prior knowledge to capture some gene modules with better biological interpretations. The experiment results on the three biological data sets showed that the DM-ESPCA model can find potential target gene probes with richer biological information to the cancer subtypes. Moreover, the results of clustering and machine learning classification models based on the target genes screened by the DM-ESPCA model can be improved by up to 22–23% of accuracies compared with the existing sparse PCA methods. We also proved that the result of the DM-ESPCA model is better than those of the four classic supervised machine learning models in the task of classification of cancer subtypes.

Few-shot learning creates predictive models of drug response that translate from high-throughput screens to individual patients

Cell-line screens create expansive datasets for learning predictive markers of drug response, but these models do not readily translate to the clinic with its diverse contexts and limited data. In the present study, we apply a recently developed technique, few-shot machine learning, to train a versatile neural network model in cell lines that can be tuned to new contexts using few additional samples. The model quickly adapts when switching among different tissue types and in moving from cell-line models to clinical contexts, including patient-derived tumor cells and patient-derived xenografts. It can also be interpreted to identify the molecular features most important to a drug response, highlighting critical roles for RB1 and SMAD4 in the response to CDK inhibition and RNF8 and CHD4 in the response to ATM inhibition. The few-shot learning framework provides a bridge from the many samples surveyed in high-throughput screens (n-of-many) to the distinctive contexts of individual patients (n-of-one).

Application of Artificial Intelligence Technology in Oncology: Towards the Establishment of Precision Medicine

In recent years, advances in artificial intelligence (AI) technology have led to the rapid clinical implementation of devices with AI technology in the medical field. More than 60 AI-equipped medical devices have already been approved by the Food and Drug Administration (FDA) in the United States, and the active introduction of AI technology is considered to be an inevitable trend in the future of medicine. In the field of oncology, clinical applications of medical devices using AI technology are already underway, mainly in radiology, and AI technology is expected to be positioned as an important core technology. In particular, "precision medicine," a medical treatment that selects the most appropriate treatment for each patient based on a vast amount of medical data such as genome information, has become a worldwide trend; AI technology is expected to be utilized in the process of extracting truly useful information from a large amount of medical data and applying it to diagnosis and treatment. In this review, we would like to introduce the history of AI technology and the current state of medical AI, especially in the oncology field, as well as discuss the possibilities and challenges of AI technology in the medical field.

Integrative analysis of genomic amplification-dependent expression and loss-of-function screen identifies ASAP1 as a driver gene in triple-negative breast cancer progression

The genetically heterogeneous triple-negative breast cancer (TNBC) continues to be an intractable disease, due to lack of effective targeted therapies. Gene amplification is a major event in tumorigenesis. Genes with amplification-dependent expression are being explored as therapeutic targets for cancer treatment. In this study, we have applied Analytical Multi-scale Identification of Recurring Events analysis and transcript quantification in the TNBC genome across 222 TNBC tumors and identified 138 candidate genes with positive correlation in copy number gain (CNG) and gene expression. siRNA-based loss-of-function screen of the candidate genes has validated EGFR, MYC, ASAP1, IRF2BP2, and CCT5 genes as drivers promoting proliferation in different TNBC cells. MYC, ASAP1, IRF2BP2, and CCT5 display frequent CNG and concurrent expression over 2173 breast cancer tumors (cBioPortal dataset). More frequently are MYC and ASAP1 amplified in TNBC tumors (>30%, n = 320). In particular, high expression of ASAP1, the ADP-ribosylation factor GTPase-activating protein, is significantly related to poor metastatic relapse-free survival of TNBC patients (n = 257, bc-GenExMiner). Furthermore, we have revealed that silencing of ASAP1 modulates numerous cytokine and apoptosis signaling components, such as IL1B, TRAF1, AIFM2, and MAP3K11 that are clinically relevant to survival outcomes of TNBC patients. ASAP1 has been reported to promote invasion and metastasis in various cancer cells. Our findings that ASAP1 is an amplification-dependent TNBC driver gene promoting TNBC cell proliferation, functioning upstream apoptosis components, and correlating to clinical outcomes of TNBC patients, support ASAP1 as a potential actionable target for TNBC treatment.