Genomic signatures for paclitaxel and gemcitabine resistance in breast cancer derived by machine learning

Combined KRAS-MAPK pathway inhibitors and HER2-directed drug conjugate is efficacious in pancreatic cancer

Targeting the mitogen-activated protein kinase (MAPK) cascade in pancreatic ductal adenocarcinoma (PDAC) remains clinically unsuccessful. We aim to develop a MAPK inhibitor-based therapeutic combination with strong preclinical efficacy. Utilizing a reverse-phase protein array, we observe rapid phospho-activation of human epidermal growth factor receptor 2 (HER2) in PDAC cells upon pharmacological MAPK inhibition. Mechanistically, MAPK inhibitors lead to swift proteasomal degradation of dual-specificity phosphatase 6 (DUSP6). The carboxy terminus of HER2, containing a TEY motif also present in extracellular signal-regulated kinase 1/2 (ERK1/2), facilitates binding with DUSP6, enhancing its phosphatase activity to dephosphorylate HER2. In the presence of MAPK inhibitors, DUSP6 dissociates from the protective effect of the RING E3 ligase tripartite motif containing 21, resulting in its degradation. In PDAC patient-derived xenograft (PDX) models, combining ERK and HER inhibitors slows tumour growth and requires cytotoxic chemotherapy to achieve tumour regression. Alternatively, MAPK inhibitors with trastuzumab deruxtecan, an anti-HER2 antibody conjugated with cytotoxic chemotherapy, lead to sustained tumour regression in most tested PDXs without causing noticeable toxicity. Additionally, KRAS inhibitors also activate HER2, supporting testing the combination of KRAS inhibitors and trastuzumab deruxtecan in PDAC. This study identifies a rational and promising therapeutic combination for clinical testing in PDAC patients.

Large-Scale Machine Learning Analysis Reveals DNA Methylation and Gene Expression Response Signatures for Gemcitabine-Treated Pancreatic Cancer

Background: Gemcitabine is a first-line chemotherapy for pancreatic adenocarcinoma (PAAD), but many PAAD patients do not respond to gemcitabine-containing treatments. Being able to predict such nonresponders would hence permit the undelayed administration of more promising treatments while sparing gemcitabine life-threatening side effects for those patients. Unfortunately, the few predictors of PAAD patient response to this drug are weak, none of them exploiting yet the power of machine learning (ML). Methods: Here, we applied ML to predict the response of PAAD patients to gemcitabine from the molecular profiles of their tumors. More concretely, we collected diverse molecular profiles of PAAD patient tumors along with the corresponding clinical data (gemcitabine responses and clinical features) from the Genomic Data Commons resource. From systematically combining 8 tumor profiles with 16 classification algorithms, each of the resulting 128 ML models was evaluated by multiple 10-fold cross-validations. Results: Only 7 of these 128 models were predictive, which underlines the importance of carrying out such a large-scale analysis to avoid missing the most predictive models. These were here random forest using 4 selected mRNAs [0.44 Matthews correlation coefficient (MCC), 0.785 receiver operating characteristic-area under the curve (ROC-AUC)] and XGBoost combining 12 DNA methylation probes (0.32 MCC, 0.697 ROC-AUC). By contrast, the hENT1 marker obtained much worse random-level performance (practically 0 MCC, 0.5 ROC-AUC). Despite not being trained to predict prognosis (overall and progression-free survival), these ML models were also able to anticipate this patient outcome. Conclusions: We release these promising ML models so that they can be evaluated prospectively on other gemcitabine-treated PAAD patients.

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.

Computational Advancements in Cancer Combination Therapy Prediction

Given the high attrition rate of de novo drug discovery and limited efficacy of single-agent therapies in cancer treatment, combination therapy prediction through in silico drug repurposing has risen as a time- and cost-effective alternative for identifying novel and potentially efficacious therapies for cancer. The purpose of this review is to provide an introduction to computational methods for cancer combination therapy prediction and to summarize recent studies that implement each of these methods. A systematic search of the PubMed database was performed, focusing on studies published within the past 10 years. Our search included reviews and articles of ongoing and retrospective studies. We prioritized articles with findings that suggest considerations for improving combination therapy prediction methods over providing a meta-analysis of all currently available cancer combination therapy prediction methods. Computational methods used for drug combination therapy prediction in cancer research include networks, regression-based machine learning, classifier machine learning models, and deep learning approaches. Each method class has its own advantages and disadvantages, so careful consideration is needed to determine the most suitable class when designing a combination therapy prediction method. Future directions to improve current combination therapy prediction technology include incorporation of disease pathobiology, drug characteristics, patient multiomics data, and drug-drug interactions to determine maximally efficacious and tolerable drug regimens for cancer. As computational methods improve in their capability to integrate patient, drug, and disease data, more comprehensive models can be developed to more accurately predict safe and efficacious combination drug therapies for cancer and other complex diseases.

Gynecologic and Breast Cancers: What's New in Chemoresistance and Chemosensitivity Tests?

Gynecological and breast cancers affect women's health worldwide. Although chemotherapy is one of the principal treatments for cancer, it also has limitations owing to toxicity and tumor resistance to the drugs used. Thus, individualized treatment based on personal tumor characteristics is essential for improving therapeutic outcomes and patient survival. Chemoresistance and chemosensitivity tests can be useful for predicting tumor response and guiding chemotherapy choices. This methodology has already been applied to breast, ovarian, cervical, and endometrial cancers, identifying successfully which drugs cause resistance and sensitivity responses for each individual person, influencing their progression-free survival and overall response. In addition, more recent techniques, such as organoids and patient-derived xenografts, can also recapitulate patients' tumor characteristics and contribute to chemo response evaluation. Therefore, this review compiles information on chemoresistance and chemosensitivity tests performed in gynecologic and breast cancers and their main results for women's health improvement.

Combination of Polymeric Micelle Formulation of TGFβ Receptor Inhibitors and Paclitaxel Produce Consistent Response Across Different Mouse Models of TNBC

Triple-negative breast cancer (TNBC) is notoriously difficult to treat due to the lack of targetable receptors and sometimes poor response to chemotherapy. The transforming growth factor-beta (TGFβ) family of proteins and their receptors (TGFR) are highly expressed in TNBC and implicated in chemotherapy-induced cancer stemness. Here we evaluated combination treatments using experimental TGFR inhibitors (TGFβi), SB525334 (SB), and LY2109761 (LY) with Paclitaxel (PTX) chemotherapy. These TGFβi target TGFR-I (SB) or both TGFR-I&II (LY). Due to the poor water solubility of these drugs, we incorporated each of them in poly(2-oxazoline) (POx) high-capacity polymeric micelles (SB-POx and LY-POx). We assessed their anti-cancer effect as single agents and in combination with micellar Paclitaxel (PTX-POx) using multiple immunocompetent TNBC mouse models that mimic human subtypes (4T1, T11-Apobec and T11-UV). While either TGFβi or PTX showed a differential effect in each model as single agents, the combinations were consistently effective against all three models. Genetic profiling of the tumors revealed differences in the expression levels of genes associated with TGFβ, EMT, TLR-4, and Bcl2 signaling, alluding to the susceptibility to specific gene signatures to the treatment. Taken together, our study suggests that TGFβi and PTX combination therapy using high-capacity POx micelle delivery provides a robust anti-tumor response in multiple TNBC subtype mouse models.

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

The rapid development of artificial intelligence (AI) technologies in the context of the vast amount of collectable data obtained from high-throughput sequencing has led to an unprecedented understanding of cancer and accelerated the advent of a new era of clinical oncology with a tone of precision treatment and personalized medicine. However, the gains achieved by a variety of AI models in clinical oncology practice are far from what one would expect, and in particular, there are still many uncertainties in the selection of clinical treatment options that pose significant challenges to the application of AI in clinical oncology. In this review, we summarize emerging approaches, relevant datasets and open-source software of AI and show how to integrate them to address problems from clinical oncology and cancer research. We focus on the principles and procedures for identifying different antitumor strategies with the assistance of AI, including targeted cancer therapy, conventional cancer therapy, and cancer immunotherapy. In addition, we also highlight the current challenges and directions of AI in clinical oncology translation. Overall, we hope this article will provide researchers and clinicians with a deeper understanding of the role and implications of AI in precision cancer therapy, and help AI move more quickly into accepted cancer guidelines.

Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications

Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.

FGF1 protects FGFR1-overexpressing cancer cells against drugs targeting tubulin polymerization by activating AKT via two independent mechanisms

Cancer drug resistance is a common, unpredictable phenomenon that develops in many types of tumors, resulting in the poor efficacy of current anticancer therapies. One of the most common, and yet the most complex causes of drug resistance is a mechanism related to dysregulation of tumor cell signaling. Abnormal signal transduction in a cancer cell is often stimulated by growth factors and their receptors, including fibroblast growth factors (FGFs) and FGF receptors (FGFRs). Here, we investigated the effect of FGF1 and FGFR1 activity on the action of drugs that disrupt tubulin polymerization (taltobulin, paclitaxel, vincristine) in FGFR1-positive cell lines, U2OS stably transfected with FGFR1 (U2OSR1) and DMS114 cells. We observed that U2OSR1 cells exhibited reduced sensitivity to the tubulin-targeting drugs, compared to U2OS cells expressing a negligible level of FGFRs. This effect was dependent on receptor activation, as inhibition of FGFR1 by a specific small-molecule inhibitor (PD173074) increased the cells’ sensitivity to these drugs. Expression of functional FGFR1 in U2OS cells resulted in increased AKT phosphorylation, with no change in total AKT level. U2OSR1 cells also exhibited an elevated MDR1 and blocking MDR1 activity with cyclosporin A increased the toxicity of paclitaxel and vincristine, but not taltobulin. Analysis of tubulin polymerization pattern using fluorescence microscopy revealed that FGF1 in U2OSR1 cells partially reverses the drug-altered phenotype in paclitaxel- and vincristine-treated cells, but not in taltobulin-treated cells. Furthermore, we showed that FGF1, through activation of FGFR1, reduces caspase 3/7 activity and PARP cleavage, preventing apoptosis induced by tubulin-targeting drugs. Next, using specific kinase inhibitors, we investigated which signaling pathways are responsible for the FGF1-mediated reduction of taltobulin cytotoxicity. We found that AKT kinase is a key factor in FGF1-induced cell protection against taltobulin in U2OSR1 and DMS114 cells. Interestingly, only direct inhibition of AKT or dual-inhibition of PI3K and mTOR abolished this effect for cells treated with taltobulin. This suggests that both canonical (PI3K-dependent) and alternative (PI3K-independent) AKT-activating pathways may regulate FGF1/FGFR1-driven cancer cell survival. Our findings may contribute to the development of more effective therapies and may facilitate the prevention of drug resistance in FGFR1-positive cancer cells.

Systematic Analysis of Genetic and Pathway Determinants of Eribulin Sensitivity across 100 Human Cancer Cell Lines from the Cancer Cell Line Encyclopedia (CCLE)

Eribulin, a natural product-based microtubule targeting agent with cytotoxic and noncytotoxic mechanisms, is FDA approved for certain patients with advanced breast cancer and liposarcoma. To investigate the feasibility of developing drug-specific predictive biomarkers, we quantified antiproliferative activities of eribulin versus paclitaxel and vinorelbine against 100 human cancer cell lines from the Cancer Cell Line Encyclopedia, and correlated results with publicly available databases to identify genes and pathways associated with eribulin response, either uniquely or shared with paclitaxel or vinorelbine. Mean expression ratios of 11,985 genes between the most and least sensitive cell line quartiles were sorted by p-values and drug overlaps, yielding 52, 29 and 80 genes uniquely associated with eribulin, paclitaxel and vinorelbine, respectively. Further restriction to minimum 2-fold ratios followed by reintroducing data from the middle two quartiles identified 9 and 13 drug-specific unique fingerprint genes for eribulin and vinorelbine, respectively; surprisingly, no gene met all criteria for paclitaxel. Interactome and Reactome pathway analyses showed that unique fingerprint genes of both drugs were primarily associated with cellular signaling, not microtubule-related pathways, although considerable differences existed in individual pathways identified. Finally, four-gene (C5ORF38, DAAM1, IRX2, CD70) and five-gene (EPHA2, NGEF, SEPTIN10, TRIP10, VSIG10) multivariate regression models for eribulin and vinorelbine showed high statistical correlation with drug-specific responses across the 100 cell lines and accurately calculated predicted mean IC50s for the most and least sensitive cell line quartiles as surrogates for responders and nonresponders, respectively. Collectively, these results provide a foundation for developing drug-specific predictive biomarkers for eribulin and vinorelbine.

Precise prediction of multiple anticancer drug efficacy using multi target regression and support vector regression analysis

BACKGROUND AND OBJECTIVES

The prediction of multiple drug efficacies using machine learning prediction techniques based on clinical and molecular attributes of tumors is a new approach in the field of precision medicine of oncology. The selection of suitable and effective therapeutic drugs among the potential drugs is performed computationally considering the tumor features. In this study, we developed and validated machine learning models to predict the efficacy of five anti-cancer drugs according to the clinical and molecular attributes of 30 oral squamous cell carcinoma (OSCC) cohorts. This sounds a bit odd - consider: Ranking of the drugs was achieved using their apoptotic priming.

METHODS

We developed multiple drug efficacy prediction models based on three types of tumor characteristics by applying machine learning methods, including multi-target regression (MTR) and support vector regression (SVR). The prediction accuracy of existing machine learning methods was enhanced by introducing novel pre-processing techniques to develop Enhanced MTR (E_MTR), Enhanced Log-based MTR (EL_MTR), Enhanced Multi-target SVR (EM_SVR), and Enhanced Log-based Multi-target SVR (ELM_SVR). As a unique capability, ELM_SVR and EL_MTR rank the drugs based on their predicted efficacy. All the drug efficacy prediction models were built using OSCC real samples and theoretical samples. The best model was selected was based on dataset size and evaluation metrics, such as error terms, residuals and parameter tuning, and cross-validated (CV) using 30 real samples and 340 theoretical samples.

RESULTS

When 30 real tumor samples were used for the train-test and CV methods, MTR models predicted the efficacy with less error than SVR models. Comparatively, using 340 theoretical samples for the train-test and CV methods, though MTR improved the performance, SVR predicted the efficacy with zero error. We found that, for small samples, the proposed MTR provided a 0.01 difference between actual apoptotic priming and predicted priming of five drugs. For large samples, the predicted values by the proposed SVR had a difference of 0.00001. The error terms (Actual vs. Predicted) also reveal that the enhanced log model is suitable when MTR is applied. Meanwhile, the enhanced model is suitable for SVR learning for multiple drug efficacy prediction. It was found that the predicted ranks of the drugs based on the multi-targeted efficacy prediction exactly match the actual rankings.

CONCLUSION

We developed efficient statistical and machine learning models using MTR and SVR analysis for anticancer drug efficacy, which will be useful in the field of precision medicine to choose the most suitable drugs in personalized manner. The performance results of the proposed enhanced ranking techniques are described as follows: i) EL_MTR is the best to predict multiple anticancer drug efficacies and improve the accuracy of ranking drugs, irrespective of sample size; and ii) ELM_SVR performs better than other MTR models with a large sample size and precise ranking process.

Interpretable Machine Learning Models to Predict the Resistance of Breast Cancer Patients to Doxorubicin from Their microRNA Profiles

Doxorubicin is a common treatment for breast cancer. However, not all patients respond to this drug, which sometimes causes life-threatening side effects. Accurately anticipating doxorubicin-resistant patients would therefore permit to spare them this risk while considering alternative treatments without delay. Stratifying patients based on molecular markers in their pretreatment tumors is a promising approach to advance toward this ambitious goal, but single-gene gene markers such as HER2 expression have not shown to be sufficiently predictive. The recent availability of matched doxorubicin-response and diverse molecular profiles across breast cancer patients permits now analysis at a much larger scale. 16 machine learning algorithms and 8 molecular profiles are systematically evaluated on the same cohort of patients. Only 2 of the 128 resulting models are substantially predictive, showing that they can be easily missed by a standard-scale analysis. The best model is classification and regression tree (CART) nonlinearly combining 4 selected miRNA isoforms to predict doxorubicin response (median Matthew correlation coefficient (MCC) and area under the curve (AUC) of 0.56 and 0.80, respectively). By contrast, HER2 expression is significantly less predictive (median MCC and AUC of 0.14 and 0.57, respectively). As the predictive accuracy of this CART model increases with larger training sets, its update with future data should result in even better accuracy.

Codelivery of Gemcitabine and MUC1 Inhibitor Using PEG-PCL Nanoparticles for Breast Cancer Therapy

In breast cancer therapy, Gemcitabine (Gem) is an antineoplastic antimetabolite with greater anticancer efficacy and tolerability. However, effectiveness of Gem is limited by its off-target effects. The synergistic potential of MUC1 (mucin 1) inhibitors and Gem-loaded polymeric nanoparticles (NPs) was discussed in this work in order to reduce dose-related toxicities and enhance the therapeutic efficacy. The double emulsion solvent evaporation method was used to prepare poly(ethylene glycol) methyl ether-block-poly-caprolactone (PEG-PCL)-loaded Gem and MUC 1 inhibitor NPs. The average size of Gem and MUC 1 inhibitor-loaded NPs was 128 nm, with a spherical shape. Twin-loaded NPs containing Gem and the MUC1 inhibitor decreased IC₅₀ and behaved synergistically. Furthermore, in vitro mechanistic studies, that is, loss of MMP, clonogenic assay, Annexin V FITC assay, and Western blotting to confirm apoptosis with simultaneous induction of autophagy using acridine orange (AO) staining were performed in this study. Furthermore, the investigated NPs upon combination exhibited greater loss of MMP and decreased clonogenic potential with simultaneous induction of autophagy in MCF-7 cells. Annexin V FITC clearly showed the percentage of apoptosis while Western blotting protein expression analysis revealed an increase in caspase-3 activity with simultaneous decrease in Bcl-2 protein expression, a hallmark of apoptosis. The effectiveness of the Ehrlich ascites solid (EAT) mice treated with Gem-MUC1 inhibitor NPs was higher than that of the animals treated alone. Overall, the combined administration of Gem and MUC1 inhibitor-loaded NPs was found to be more efficacious than Gem and MUC1 inhibitor delivered separately.

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.

Application of Artificial Intelligence in Discovery and Development of Anticancer and Antidiabetic Therapeutic Agents

Spectacular developments in molecular and cellular biology have led to important discoveries in cancer research. Despite cancer is one of the major causes of morbidity and mortality globally, diabetes is one of the most leading sources of group of disorders. Artificial intelligence (AI) has been considered the fourth industrial revolution machine. The most major hurdles in drug discovery and development are the time and expenditures required to sustain the drug research pipeline. Large amounts of data can be explored and generated by AI, which can then be converted into useful knowledge. Because of this, the world's largest drug companies have already begun to use AI in their drug development research. In the present era, AI has a huge amount of potential for the rapid discovery and development of new anticancer drugs. Clinical studies, electronic medical records, high-resolution medical imaging, and genomic assessments are just a few of the tools that could aid drug development. Large data sets are available to researchers in the pharmaceutical and medical fields, which can be analyzed by advanced AI systems. This review looked at how computational biology and AI technologies may be utilized in cancer precision drug development by combining knowledge of cancer medicines, drug resistance, and structural biology. This review also highlighted a realistic assessment of the potential for AI in understanding and managing diabetes.

Machine learning in medical applications: A review of state-of-the-art methods

Applications of machine learning (ML) methods have been used extensively to solve various complex challenges in recent years in various application areas, such as medical, financial, environmental, marketing, security, and industrial applications. ML methods are characterized by their ability to examine many data and discover exciting relationships, provide interpretation, and identify patterns. ML can help enhance the reliability, performance, predictability, and accuracy of diagnostic systems for many diseases. This survey provides a comprehensive review of the use of ML in the medical field highlighting standard technologies and how they affect medical diagnosis. Five major medical applications are deeply discussed, focusing on adapting the ML models to solve the problems in cancer, medical chemistry, brain, medical imaging, and wearable sensors. Finally, this survey provides valuable references and guidance for researchers, practitioners, and decision-makers framing future research and development directions.

Advancements in Oncology with Artificial Intelligence—A Review Article

Simple Summary

With the advancement of artificial intelligence, including machine learning, the field of oncology has seen promising results in cancer detection and classification, epigenetics, drug discovery, and prognostication. In this review, we describe what artificial intelligence is and its function, as well as comprehensively summarize its evolution and role in breast, colorectal, and central nervous system cancers. Understanding the origin and current accomplishments might be essential to improve the quality, accuracy, generalizability, cost-effectiveness, and reliability of artificial intelligence models that can be used in worldwide clinical practice. Students and researchers in the medical field will benefit from a deeper understanding of how to use integrative AI in oncology for innovation and research.

Abstract

Well-trained machine learning (ML) and artificial intelligence (AI) systems can provide clinicians with therapeutic assistance, potentially increasing efficiency and improving efficacy. ML has demonstrated high accuracy in oncology-related diagnostic imaging, including screening mammography interpretation, colon polyp detection, glioma classification, and grading. By utilizing ML techniques, the manual steps of detecting and segmenting lesions are greatly reduced. ML-based tumor imaging analysis is independent of the experience level of evaluating physicians, and the results are expected to be more standardized and accurate. One of the biggest challenges is its generalizability worldwide. The current detection and screening methods for colon polyps and breast cancer have a vast amount of data, so they are ideal areas for studying the global standardization of artificial intelligence. Central nervous system cancers are rare and have poor prognoses based on current management standards. ML offers the prospect of unraveling undiscovered features from routinely acquired neuroimaging for improving treatment planning, prognostication, monitoring, and response assessment of CNS tumors such as gliomas. By studying AI in such rare cancer types, standard management methods may be improved by augmenting personalized/precision medicine. This review aims to provide clinicians and medical researchers with a basic understanding of how ML works and its role in oncology, especially in breast cancer, colorectal cancer, and primary and metastatic brain cancer. Understanding AI basics, current achievements, and future challenges are crucial in advancing the use of AI in oncology.

Predictive and Prognostic Significance of mRNA Expression and DNA Copies Aberrations of ERCC1, RRM1, TOP1, TOP2A, TUBB3, TYMS, and GSTP1 Genes in Patients with Breast Cancer

Increasingly, many researchers are focusing on the sensitivity in breast tumors (BC) to certain chemotherapy drugs and have personalized their research based on the assessment of this sensitivity. One such personalized approach is to assess the chemotherapy’s gene expression, as well as aberrations in the number of DNA copies—deletions and amplifications with the ability to have a significant effect on the gene’s activity. Thus, the aim of this work was to study the predictive and prognostic significance of the expression and chromosomal aberrations of eight chemosensitivity genes in breast cancer patients. Material and methods. The study involved 97 patients with luminal B breast cancer IIB–IIIB stages. DNA and RNA were isolated from samples of tumor tissue before and after treatment. Microarray analysis was performed for all samples on high-density microarrays (DNA chips) of Affymetrix (USA) CytoScanTM HD Array and Clariom™ S Assay, human. Detection of expression level of seven chemosensitivity genes—RRM1, ERCC1, TOP1, TOP2a, TUBB3, TYMS, and GSTP1—was performed using PCR real-time (RT-qPCR). Results. The expression of the RRM1 (AC scheme), TOP2α, TYMS, and TUBB3 genes in patients with an objective response to treatment (complete and partial regression) is higher than in patients with stabilization and progression (p < 0.05). According to our results, the presence of a high level of GSTP1 in a tumor biopsy is associated with the low efficiency of the NAC CP scheme (p = 0.05). The presence of RRM1 deletion is associated with complete and partial regression, as for the TOP1 and TUBB3 genes (p < 0.05). Higher rates of metastatic survival are associated with a high level of expression and amplification of the GSTP1 gene (log-rank test p = 0.02 and p = 0.05). Conclusion. Thus, a complex assessment of the chemotherapy’s gene expression is important not only for understanding the heterogeneity and molecular biology of breast cancer but also to obtain a more accurate disease prognosis.

Big Data to Knowledge: Application of Machine Learning to Predictive Modeling of Therapeutic Response in Cancer

Background

In recent years, the availability of high throughput technologies, establishment of large molecular patient data repositories, and advancement in computing power and storage have allowed elucidation of complex mechanisms implicated in therapeutic response in cancer patients. The breadth and depth of such data, alongside experimental noise and missing values, requires a sophisticated human-machine interaction that would allow effective learning from complex data and accurate forecasting of future outcomes, ideally embedded in the core of machine learning design.

Objective

In this review, we will discuss machine learning techniques utilized for modeling of treatment response in cancer, including Random Forests, support vector machines, neural networks, and linear and logistic regression. We will overview their mathematical foundations and discuss their limitations and alternative approaches in light of their application to therapeutic response modeling in cancer.

Conclusion

We hypothesize that the increase in the number of patient profiles and potential temporal monitoring of patient data will define even more complex techniques, such as deep learning and causal analysis, as central players in therapeutic response modeling.

FGF/FGFR-Dependent Molecular Mechanisms Underlying Anti-Cancer Drug Resistance

Simple Summary

Deregulation of the FGF/FGFR axis is associated with many types of cancer and contributes to the development of chemoresistance, limiting the effectiveness of current treatment strategies. There are several mechanisms involved in this phenomenon, including cross-talks with other signaling pathways, avoidance of apoptosis, stimulation of angiogenesis, and initiation of EMT. Here, we provide an overview of current research and approaches focusing on targeting components of the FGFR/FGF signaling module to overcome drug resistance during anti-cancer therapy.

Abstract

Increased expression of both FGF proteins and their receptors observed in many cancers is often associated with the development of chemoresistance, limiting the effectiveness of currently used anti-cancer therapies. Malfunctioning of the FGF/FGFR axis in cancer cells generates a number of molecular mechanisms that may affect the sensitivity of tumors to the applied drugs. Of key importance is the deregulation of cell signaling, which can lead to increased cell proliferation, survival, and motility, and ultimately to malignancy. Signaling pathways activated by FGFRs inhibit apoptosis, reducing the cytotoxic effect of some anti-cancer drugs. FGFRs-dependent signaling may also initiate angiogenesis and EMT, which facilitates metastasis and also correlates with drug resistance. Therefore, treatment strategies based on FGF/FGFR inhibition (using receptor inhibitors, ligand traps, monoclonal antibodies, or microRNAs) appear to be extremely promising. However, this approach may lead to further development of resistance through acquisition of specific mutations, metabolism switching, and molecular cross-talks. This review brings together information on the mechanisms underlying the involvement of the FGF/FGFR axis in the generation of drug resistance in cancer and highlights the need for further research to overcome this serious problem with novel therapeutic strategies.

Pathway-extended gene expression signatures integrate novel biomarkers that improve predictions of patient responses to kinase inhibitors

Cancer chemotherapy responses have been related to multiple pharmacogenetic biomarkers, often for the same drug. This study utilizes machine learning to derive multi‐gene expression signatures that predict individual patient responses to specific tyrosine kinase inhibitors, including erlotinib, gefitinib, sorafenib, sunitinib, lapatinib and imatinib. Support vector machine (SVM) learning was used to train mathematical models that distinguished sensitivity from resistance to these drugs using a novel systems biology‐based approach. This began with expression of genes previously implicated in specific drug responses, then expanded to evaluate genes whose products were related through biochemical pathways and interactions. Optimal pathway‐extended SVMs predicted responses in patients at accuracies of 70% (imatinib), 71% (lapatinib), 83% (sunitinib), 83% (erlotinib), 88% (sorafenib) and 91% (gefitinib). These best performing pathway‐extended models demonstrated improved balance predicting both sensitive and resistant patient categories, with many of these genes having a known role in cancer aetiology. Ensemble machine learning‐based averaging of multiple pathway‐extended models derived for an individual drug increased accuracy to >70% for erlotinib, gefitinib, lapatinib and sorafenib. Through incorporation of novel cancer biomarkers, machine learning‐based pathway‐extended signatures display strong efficacy predicting both sensitive and resistant patient responses to chemotherapy.

Improved radiation expression profiling in blood by sequential application of sensitive and specific gene signatures

PURPOSE

Combinations of expressed genes can discriminate radiation-exposed from normal control blood samples by machine learning (ML) based signatures (with 8-20% misclassification rates). These signatures can quantify therapeutically relevant as well as accidental radiation exposures. The prodromal symptoms of acute radiation syndrome (ARS) overlap those present in influenza and dengue fever infections. Surprisingly, these human radiation signatures misclassified gene expression profiles of virally infected samples as false positive exposures. The present study investigates these and other confounders, and then mitigates their impact on signature accuracy.

METHODS

This study investigated recall by previous and novel radiation signatures independently derived from multiple Gene Expression Omnibus datasets on common and rare non-neoplastic blood disorders and blood-borne infections (thromboembolism, S. aureus bacteremia, malaria, sickle cell disease, polycythemia vera, and aplastic anemia). Normalized expression levels of signature genes are used as input to ML-based classifiers to predict radiation exposure in other hematological conditions.

RESULTS

Except for aplastic anemia, these blood-borne disorders modify the normal baseline expression values of genes present in radiation signatures, leading to false-positive misclassification of radiation exposures in 8-54% of individuals. Shared changes, predominantly in DNA damage response and apoptosis-related gene transcripts in radiation and confounding hematological conditions, compromise the utility of these signatures for radiation assessment. These confounding conditions (sickle cell disease, thrombosis, S. aureus bacteremia, malaria) induce neutrophil extracellular traps, initiated by chromatin decondensation, DNA damage response and fragmentation followed by programmed cell death or extrusion of DNA fragments. Riboviral infections (e.g. influenza or dengue fever) have been proposed to bind and deplete host RNA binding proteins, inducing R-loops in chromatin. R-loops that collide with incoming replication forks can result in incompletely repaired DNA damage, inducing apoptosis and releasing mature virus. To mitigate the effects of confounders, we evaluated predicted radiation-positive samples with novel gene expression signatures derived from radiation-responsive transcripts encoding secreted blood plasma proteins whose expression levels are unperturbed by these conditions.

CONCLUSIONS

This approach identifies and eliminates misclassified samples with underlying hematological or infectious conditions, leaving only samples with true radiation exposures. Diagnostic accuracy is significantly improved by selecting genes that maximize both sensitivity and specificity in the appropriate tissue using combinations of the best signatures for each of these classes of signatures.

Post-Hypoxic Cells Promote Metastatic Recurrence after Chemotherapy Treatment in TNBC

Simple Summary

Intratumoral hypoxia is a negative prognostic factor in breast cancer progression and recurrence. By implementing a hypoxia fate-mapping system, we followed cells that experience intratumoral hypoxia in vivo and determined that these cells have an increased ability to metastasize compared to cells that were never exposed to hypoxia. In this work, we investigate whether cells that experienced intratumoral hypoxia are also resistant to chemotherapy. By utilizing both in vivo and ex vivo models, we conclude that metastatic cells found in the lung and liver, that were exposed to hypoxia in the primary tumor, are less sensitive to doxorubicin and paclitaxel and drive recurrence after treatment. Our studies also suggest that chemoresistance is associated with a cancer stem cell-like phenotype that is maintained in post-hypoxic cells.

Abstract

Hypoxia occurs in 90% of solid tumors and is associated with treatment failure, relapse, and mortality. HIF-1α signaling promotes resistance to chemotherapy in cancer cell lines and murine models via multiple mechanisms including the enrichment of breast cancer stem cells (BCSCs). In this work, we utilize a hypoxia fate-mapping system to determine whether triple-negative breast cancer (TNBC) cells that experience hypoxia in the primary tumor are resistant to chemotherapy at sites of metastasis. Using two orthotopic mouse models of TNBC, we demonstrate that cells that experience intratumoral hypoxia and metastasize to the lung and liver have decreased sensitivity to doxorubicin and paclitaxel but not cisplatin or 5-FU. Resistance to therapy leads to metastatic recurrence caused by post-hypoxic cells. We further determined that the post-hypoxic cells that metastasize are enriched in pathways related to cancer stem cell gene expression. Overall, our results show that even when hypoxic cancer cells are reoxygenated in the bloodstream they retain a hypoxia-induced cancer stem cell-like phenotype that persists and promotes resistance and eventually recurrence.

Breast cancer resistance to chemotherapy: When should we suspect it and how can we prevent it?

Chemotherapy is an essential treatment for breast cancer, inducing cancer cell death. However, chemoresistance is a problem that limits the effectiveness of chemotherapy. Many factors influence chemoresistance, including drug inactivation, changes in drug targets, overexpression of ABC transporters, epithelial-to-mesenchymal transitions, apoptotic dysregulation, and cancer stem cells. The effectiveness of chemotherapy can be assessed clinically and pathologically. Clinical response evaluation is based on physical examination or imaging (mammography, ultrasonography, computed tomography scan, or magnetic resonance imaging) and includes tumor size changes after chemotherapy. Pathological response evaluation is a method based on tumor residues in histopathological preparations. We should be suspicious of chemoresistance if there are no significant changes clinically according to the Response Evaluation Criteria in Solid Tumors and World Health Organization criteria or pathological changes according to the Miller and Payne criteria, especially after 2–3 cycles of chemotherapy treatments. Chemoresistance is mostly detected after the administration of chemotherapy drugs. No reliable parameters or biomarkers can predict chemotherapy responses appropriately and effectively. Well-known parameters such as cancer type, grade, subtype, estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, Ki-67, and MDR-1/P-gP have been used for selecting chemotherapy regimens. Some new methods for predicting chemoresistance include chemosensitivity and chemoresistance assays, multigene expressions, and positron emission tomography assays. The latest approaches are based on evaluation of molecular processes and the metabolic activity of cancer cells. Some methods for preventing chemoresistance include using the right regimen, using some combination of chemotherapy methods, conducting adequate monitoring, and using drugs that could prevent the emergence of multidrug resistance.

•

Chemotherapy is an essential treatment in the management of breast cancer.

•

Chemotherapy is carried out based on the selection of regimens for the specific individual and tumor characteristics.

•

Combination therapy, monitoring, and evaluation are used to prevent chemoresistance.

Identification of Key Genes and Pathways Associated With Paclitaxel Resistance in Esophageal Squamous Cell Carcinoma Based on Bioinformatics Analysis

Esophageal squamous cell carcinoma (ESCC) ranks as the fourth leading cause of cancer-related death in China. Although paclitaxel has been shown to be effective in treating ESCC, the prolonged use of this chemical will lead to paclitaxel resistance. In order to uncover genes and pathways driving paclitaxel resistance in the progression of ESCC, bioinformatics analyses were performed based on The Cancer Genome Atlas (TCGA) database and the Gene Expression Omnibus (GEO) database including GSE86099 and GSE161533. Differential expression analysis was performed in TCGA data and two GEO datasets to obtain differentially expressed genes (DEGs). Based on GSE161533, weighted gene co-expression network analysis (WGCNA) was conducted to identify the key modules associated with ESCC tumor status. The DEGs common to the two GEO datasets and the genes in the key modules were intersected to obtain the paclitaxel resistance-specific or non-paclitaxel resistance-specific genes, which were subjected to subsequent least absolute shrinkage and selection operator (LASSO) feature selection, whereby paclitaxel resistance-specific or non-paclitaxel resistance-specific key genes were selected. Ten machine learning models were used to validate the biological significance of these key genes; the potential therapeutic drugs for paclitaxel resistance-specific genes were also predicted. As a result, we identified 24 paclitaxel resistance-specific genes and 18 non-paclitaxel resistance-specific genes. The ESCC machine classifiers based on the key genes achieved a relatively high AUC value in the cross-validation and in an independent test set, GSE164158. A total of 207 drugs (such as bevacizumab) were predicted to be alternative therapeutics for ESCC patients with paclitaxel resistance. These results might shed light on the in-depth research of paclitaxel resistance in the context of ESCC progression.

Artificial intelligence and inflammatory bowel disease

With the development of artificial intelligence (AI) and its gradual application in the medical field, AI has brought new ideas to the medical development. The research and application of AI in inflammatory l bowel disease (IBD), which includes ulcerative colitis (UC) and Crohn's disease (CD), are increasing. Selecting appropriate models and methods through machine learning can help diagnose, treat, and predict the prognosis of IBD. In recent years, AI combined with endoscopy has made an appearance in the diagnosis of IBD and achieved satisfactory results. At the same time, AI plays an important role in the process of disease prediction and treatment evaluation for patients with IBD. However, we should also be aware that there are still some problems with AI. This paper gives a brief review of the practical application value of AI in IBD.

An in vivo genome-wide shRNA screen identifies BCL6 as a targetable biomarker of paclitaxel resistance in breast cancer

Paclitaxel is a common breast cancer drug; however, some tumors are resistant. The identification of biomarkers for paclitaxel resistance or sensitivity would enable the development of strategies to improve treatment efficacy. A genome-wide in vivo shRNA screen was performed on paclitaxel-treated mice with MDA-MB-231 tumors to identify genes associated with paclitaxel sensitivity or resistance. Gene expression of the top screen hits was associated with tumor response (resistance or sensitivity) among patients who received neoadjuvant chemotherapy containing paclitaxel. We focused our validation on screen hit B-cell lymphoma 6 (BCL6), which is a therapeutic target in cancer but for which no effects on drug response have been reported. Knockdown of BCL6 resulted in increased tumor regression in mice treated with paclitaxel. Similarly, inhibiting BCL6 using a small molecule inhibitor enhanced paclitaxel treatment efficacy both in vitro and in vivo in breast cancer models. Mechanism studies revealed that reduced BCL6 enhances the efficacy of paclitaxel by inducing sustained G1/S arrest, concurrent with increased apoptosis and expression of target gene cyclin-dependent kinase inhibitor 1A. In summary, the genome-wide shRNA knockdown screen has identified BCL6 as a potential targetable resistance biomarker of paclitaxel response in breast cancer.

Integration and interplay of machine learning and bioinformatics approach to identify genetic interaction related to ovarian cancer chemoresistance

Although chemotherapy is the first-line treatment for ovarian cancer (OCa) patients, chemoresistance (CR) decreases their progression-free survival. This paper investigates the genetic interaction (GI) related to OCa-CR. To decrease the complexity of establishing gene networks, individual signature genes related to OCa-CR are identified using a gradient boosting decision tree algorithm. Additionally, the genetic interaction coefficient (GIC) is proposed to measure the correlation of two signature genes quantitatively and explain their joint influence on OCa-CR. Gene pair that possesses high GIC is identified as signature pair. A total of 24 signature gene pairs are selected that include 10 individual signature genes and the influence of signature gene pairs on OCa-CR is explored. Finally, a signature gene pair-based prediction of OCa-CR is identified. The area under curve (AUC) is a widely used performance measure for machine learning prediction. The AUC of signature gene pair reaches 0.9658, whereas the AUC of individual signature gene-based prediction is 0.6823 only. The identified signature gene pairs not only build an efficient GI network of OCa-CR but also provide an interesting way for OCa-CR prediction. This improvement shows that our proposed method is a useful tool to investigate GI related to OCa-CR.

NLRP3 augmented resistance to gemcitabine in triple-negative breast cancer cells via EMT/IL-1β/Wnt/β-catenin signaling pathway

Background: Gemcitabine is widely used in the treatment of breast cancer (BC). However, the resistance to drugs remains a tough concern. The study explored the potential mechanism concerning gemcitabine resistance in triple-negative BC (TNBC) in vitro. Methods: TNBC cells (TNBCC) and gemcitabine-resistance cell lines (GRC) were used. We investigated the sensitivity to gemcitabine responsive to regulation of Nod-like receptor protein 3 (NLRP3) expression in TNBCC in different gemcitabine concentrations. RT-PCR checked NLRP3 mRNA expression and MTT assessed the cell cytotoxicity. Gemcitabine resistance was studied in GRC exposed to 0, 1, 3, 5 nm gemcitabine after GRC were treated with NLRP3 agonist Nigericin sodium salt (NSS) or antagonist CY-09. Epithelial-to-mesenchymal transition (EMT) biomarkers were evaluated via RT-PCR and inflammasome IL-1β, β-catenin content and GSK-3β activity were measured by ELISA methods. Last, we inactivated the signaling and examined the NLRP3, EMT mRNA expression by RT-PCR, IL-1β, β-catenin content and GSK-3β activity by ELISA and cell cytotoxicity through MTT. Results: NLRP3 up-regulation improved cell survival and reduced sensitivity to gemcitabine (P<0.05). NLRP3 had higher expression in GRC than TNBCC. GRC cell viability dropped as the gemcitabine concentration increased. NLRP3 up-regulation added to resistance to gemcitabine in GRC (P<0.05). NLRP3 agonist might induce EMT process, activate wnt/β-catenin signaling and IL-1β, while inactivation of wnt/β-catenin signaling could result in the inhibition of NLRP3, IL-1β and EMT as well as cell viability in GRC (P<0.05). Conclusion: NLRP3 could enhance resistance to gemcitabine via IL-1β/EMT/Wnt/β-catenin signaling, which suggested that NLRP3 antagonist CY-09 might be incorporated into gemcitabine treatment for TNBC.

The BIRC Family Genes Expression in Patients with Triple Negative Breast Cancer

The BIRC (baculoviral IAP repeat-containing; BIRC) family genes encode for Inhibitor of Apoptosis (IAP) proteins. The dysregulation of the expression levels of the genes in question in cancer tissue as compared to normal tissue suggests that the apoptosis process in cancer cells was disturbed, which may be associated with the development and chemoresistance of triple negative breast cancer (TNBC). In our study, we determined the expression level of eight genes from the BIRC family using the Real-Time PCR method in patients with TNBC and compared the obtained results with clinical data. Additionally, using bioinformatics tools (Ualcan and The Breast Cancer Gene-Expression Miner v4.5 (bc-GenExMiner v4.5)), we compared our data with the data in the Cancer Genome Atlas (TCGA) database. We observed diverse expression pattern among the studied genes in breast cancer tissue. Comparing the expression level of the studied genes with the clinical data, we found that in patients diagnosed with breast cancer under the age of 50, the expression levels of all studied genes were higher compared to patients diagnosed after the age of 50. We observed that in patients with invasion of neoplastic cells into lymphatic vessels and fat tissue, the expression levels of BIRC family genes were lower compared to patients in whom these features were not noted. Statistically significant differences in gene expression were also noted in patients classified into three groups depending on the basis of the Scarff-Bloom and Richardson (SBR) Grading System.

Molecular modeling approaches to address drug-metabolizing enzymes (DMEs) mediated chemoresistance: a review

Resistance against clinically approved anticancer drugs is the main roadblock in cancer treatment. Drug metabolizing enzymes (DMEs) that are capable of metabolizing a variety of xenobiotic get overexpressed in malignant cells, therefore, catalyzing drug inactivation. As evident from the literature reports, the levels of DMEs increase in cancer cells that ultimately lead to drug inactivation followed by drug resistance. To puzzle out this issue, several strategies inclusive of analog designing, prodrug designing, and inhibitor designing have been forged. On that front, the implementation of computational tools can be considered a fascinating approach to address the problem of chemoresistance. Various research groups have adopted different molecular modeling tools for the investigation of DMEs mediated toxicity problems. However, the utilization of these in-silico tools in maneuvering the DME mediated chemoresistance is least considered and yet to be explored. These tools can be employed in the designing of such chemotherapeutic agents that are devoid of the resistance problem. The current review canvasses various molecular modeling approaches that can be implemented to address this issue. Special focus was laid on the development of specific inhibitors of DMEs. Additionally, the strategies to bypass the DMEs mediated drug metabolism were also contemplated in this report that includes analogs and pro-drugs designing. Different strategies discussed in the review will be beneficial in designing novel chemotherapeutic agents that depreciate the resistance problem.

Regulation of breast cancer metastasis signaling by miRNAs

Despite the decline in death rate from breast cancer and recent advances in targeted therapies and combinations for the treatment of metastatic disease, metastatic breast cancer remains the second leading cause of cancer-associated death in U.S. women. The invasion-metastasis cascade involves a number of steps and multitudes of proteins and signaling molecules. The pathways include invasion, intravasation, circulation, extravasation, infiltration into a distant site to form a metastatic niche, and micrometastasis formation in a new environment. Each of these processes is regulated by changes in gene expression. Noncoding RNAs including microRNAs (miRNAs) are involved in breast cancer tumorigenesis, progression, and metastasis by post-transcriptional regulation of target gene expression. miRNAs can stimulate oncogenesis (oncomiRs), inhibit tumor growth (tumor suppressors or miRsupps), and regulate gene targets in metastasis (metastamiRs). The goal of this review is to summarize some of the key miRNAs that regulate genes and pathways involved in metastatic breast cancer with an emphasis on estrogen receptor α (ERα+) breast cancer. We reviewed the identity, regulation, human breast tumor expression, and reported prognostic significance of miRNAs that have been documented to directly target key genes in pathways, including epithelial-to-mesenchymal transition (EMT) contributing to the metastatic cascade. We critically evaluated the evidence for metastamiRs and their targets and miRNA regulation of metastasis suppressor genes in breast cancer progression and metastasis. It is clear that our understanding of miRNA regulation of targets in metastasis is incomplete.

Highly expressed SLCO1B3 inhibits the occurrence and development of breast cancer and can be used as a clinical indicator of prognosis

The role of organic anion transporting polypeptide 1B3 (SLCO1B3) in breast cancer is still controversial. The clinical immunohistochemical results showed that a greater proportion of patients with negative lymph nodes, AJCC stage I, and histological grade 1 (P < 0.05) was positively correlated with stronger expression of SLCO1B3, and DFS and OS were also increased significantly in these patients (P = 0.041, P = 0.001). Further subgroup analysis showed that DFS and OS were significantly enhanced with the increased expression of SLCO1B3 in the ER positive subgroup. The cellular function assay showed that the ability of cell proliferation, migration and invasion was significantly enhanced after knockdown of SLCO1B3 expression in breast cancer cell lines. In contrast, the ability of cell proliferation, migration and invasion was significantly reduced after overexpress the SLCO1B3 in breast cancer cell lines (P < 0.05). Overexpression or knockdown of SLCO1B3 had no effect on the apoptotic ability of breast cancer cells. High level of SLCO1B3 expression can inhibit the proliferation, invasion and migration of breast cancer cells, leading to better prognosis of patients. The role of SLCO1B3 in breast cancer may be related to estrogen. SLCO1B3 will become a potential biomarker for breast cancer diagnosis and prognosis assessment.

Two-step multi-omics modelling of drug sensitivity in cancer cell lines to identify driving mechanisms

Drug sensitivity prediction models for human cancer cell lines constitute important tools in identifying potential computational biomarkers for responsiveness in a pre-clinical setting. Integrating information derived from a range of heterogeneous data is crucial, but remains non-trivial, as differences in data structures may hinder fitting algorithms from assigning adequate weights to complementary information that is contained in distinct omics data. In order to counteract this effect that tends to lead to just one data type dominating supposedly multi-omics models, we developed a novel tool that enables users to train single-omics models separately in a first step and to integrate them into a multi-omics model in a second step. Extensive ablation studies are performed in order to facilitate an in-depth evaluation of the respective contributions of singular data types and of combinations thereof, effectively identifying redundancies and interdependencies between them. Moreover, the integration of the single-omics models is realized by a range of distinct classification algorithms, thus allowing for a performance comparison. Sets of molecular events and tissue types found to be related to significant shifts in drug sensitivity are returned to facilitate a comprehensive and straightforward analysis of potential computational biomarkers for drug responsiveness. Our two-step approach yields sets of actual multi-omics pan-cancer classification models that are highly predictive for a majority of drugs in the GDSC data base. In the context of targeted drugs with particular modes of action, its predictive performances compare favourably to those of classification models that incorporate multi-omics data in a simple one-step approach. Additionally, case studies demonstrate that it succeeds both in correctly identifying known key biomarkers for sensitivity towards specific drug compounds as well as in providing sets of potential candidates for additional computational biomarkers.

Engineering in Medicine To Address the Challenge of Cancer Drug Resistance: From Micro- and Nanotechnologies to Computational and Mathematical Modeling

Drug resistance has profoundly limited the success of cancer treatment, driving relapse, metastasis, and mortality. Nearly all anticancer drugs and even novel immunotherapies, which recalibrate the immune system for tumor recognition and destruction, have succumbed to resistance development. Engineers have emerged across mechanical, physical, chemical, mathematical, and biological disciplines to address the challenge of drug resistance using a combination of interdisciplinary tools and skill sets. This review explores the developing, complex, and under-recognized role of engineering in medicine to address the multitude of challenges in cancer drug resistance. Looking through the "lens" of intrinsic, extrinsic, and drug-induced resistance (also referred to as "tolerance"), we will discuss three specific areas where active innovation is driving novel treatment paradigms: (1) nanotechnology, which has revolutionized drug delivery in desmoplastic tissues, harnessing physiochemical characteristics to destroy tumors through photothermal therapy and rationally designed nanostructures to circumvent cancer immunotherapy failures, (2) bioengineered tumor models, which have benefitted from microfluidics and mechanical engineering, creating a paradigm shift in physiologically relevant environments to predict clinical refractoriness and enabling platforms for screening drug combinations to thwart resistance at the individual patient level, and (3) computational and mathematical modeling, which blends in silico simulations with molecular and evolutionary principles to map mutational patterns and model interactions between cells that promote resistance. On the basis that engineering in medicine has resulted in discoveries in resistance biology and successfully translated to clinical strategies that improve outcomes, we suggest the proliferation of multidisciplinary science that embraces engineering.

Estimating partial-body ionizing radiation exposure by automated cytogenetic biodosimetry

PURPOSE

Inhomogeneous exposures to ionizing radiation can be detected and quantified with the dicentric chromosome assay (DCA) of metaphase cells. Complete automation of interpretation of the DCA for whole-body irradiation has significantly improved throughput without compromising accuracy, however, low levels of residual false positive dicentric chromosomes (DCs) have confounded its application for partial-body exposure determination.

MATERIALS AND METHODS

We describe a method of estimating and correcting for false positive DCs in digitally processed images of metaphase cells. Nearly all DCs detected in unirradiated calibration samples are introduced by digital image processing. DC frequencies of irradiated calibration samples and those exposed to unknown radiation levels are corrected subtracting this false positive fraction from each. In partial-body exposures, the fraction of cells exposed, and radiation dose can be quantified after applying this modification of the contaminated Poisson method.

RESULTS

Dose estimates of three partially irradiated samples diverged 0.2-2.5 Gy from physical doses and irradiated cell fractions deviated by 2.3%-15.8% from the known levels. Synthetic partial-body samples comprised of unirradiated and 3 Gy samples from 4 laboratories were correctly discriminated as inhomogeneous by multiple criteria. Root mean squared errors of these dose estimates ranged from 0.52 to 1.14 Gy² and from 8.1 to 33.3%² for the fraction of cells irradiated.

CONCLUSIONS

Automated DCA can differentiate whole- from partial-body radiation exposures and provides timely quantification of estimated whole-body equivalent dose.

Analysis of H3K4me3 and H3K27me3 bivalent promotors in HER2+ breast cancer cell lines reveals variations depending on estrogen receptor status and significantly correlates with gene expression

BACKGROUND

The role of histone modifications is poorly characterized in breast cancer, especially within the major subtypes. While epigenetic modifications may enhance the adaptability of a cell to both therapy and the surrounding environment, the mechanisms by which this is accomplished remains unclear. In this study we focus on the HER2 subtype and investigate two histone trimethylations that occur on the histone 3; the trimethylation located at lysine 4 (H3K4me3) found in active promoters and the trimethylation located at lysine 27 (H3K27me3) that correlates with gene repression. A bivalency state is the result of the co-presence of these two marks at the same promoter.

METHODS

In this study we investigated the relationship between these histone modifications in promoter regions and their proximal gene expression in HER2+ breast cancer cell lines. In addition, we assessed these patterns with respect to the presence or absence of the estrogen receptor (ER). To do this, we utilized ChIP-seq and matching RNA-seq from publicly available data for the AU565, SKBR3, MB361 and UACC812 cell lines. In order to visualize these relationships, we used KEGG pathway enrichment analysis, and Kaplan-Meyer plots.

RESULTS

We found that the correlation between the three types of promoter trimethylation statuses (H3K4me3, H3K27me3 or both) and the expression of the proximal genes was highly significant overall, while roughly a third of all genes are regulated by this phenomenon. We also show that there are several pathways related to cancer progression and invasion that are associated with the bivalent status of the gene promoters, and that there are specific differences between ER+ and ER- HER2+ breast cancer cell lines. These specific differences that are differentially trimethylated are also shown to be differentially expressed in patient samples. One of these genes, HIF1AN, significantly correlates with patient outcome.

CONCLUSIONS

This study highlights the importance of looking at epigenetic markings at a subtype specific level by characterizing the relationship between the bivalent promoters and gene expression. This provides a deeper insight into a mechanism that could lead to future targets for treatment and prognosis, along with oncogenesis and response to therapy of HER2+ breast cancer patients.

FORESEE: a tool for the systematic comparison of translational drug response modeling pipelines

Summary

Translational models that utilize omics data generated in in vitro studies to predict the drug efficacy of anti-cancer compounds in patients are highly distinct, which complicates the benchmarking process for new computational approaches. In reaction to this, we introduce the uniFied translatiOnal dRug rESponsE prEdiction platform FORESEE, an open-source R-package. FORESEE not only provides a uniform data format for public cell line and patient datasets, but also establishes a standardized environment for drug response prediction pipelines, incorporating various state-of-the-art pre-processing methods, model training algorithms and validation techniques. The modular implementation of individual elements of the pipeline facilitates a straightforward development of combinatorial models, which can be used to re-evaluate and improve already existing pipelines as well as to develop new ones.

Availability and implementation

FORESEE is licensed under GNU General Public License v3.0 and available at https://github.com/JRC-COMBINE/FORESEE and https://doi.org/10.17605/OSF.IO/RF6QK, and provides vignettes for documentation and application both online and in the Supplementary Files 2 and 3.

Supplementary information

Supplementary data are available at Bioinformatics online.

High-throughput, microscope-based sorting to dissect cellular heterogeneity

Microscopy is a powerful tool for characterizing complex cellular phenotypes, but linking these phenotypes to genotype or RNA expression at scale remains challenging. Here, we present Visual Cell Sorting, a method that physically separates hundreds of thousands of live cells based on their visual phenotype. Automated imaging and phenotypic analysis directs selective illumination of Dendra2, a photoconvertible fluorescent protein expressed in live cells; these photoactivated cells are then isolated using fluorescence-activated cell sorting. First, we use Visual Cell Sorting to assess hundreds of nuclear localization sequence variants in a pooled format, identifying variants that improve nuclear localization and enabling annotation of nuclear localization sequences in thousands of human proteins. Second, we recover cells that retain normal nuclear morphologies after paclitaxel treatment, and then derive their single-cell transcriptomes to identify pathways associated with paclitaxel resistance in cancers. Unlike alternative methods, Visual Cell Sorting depends on inexpensive reagents and commercially available hardware. As such, it can be readily deployed to uncover the relationships between visual cellular phenotypes and internal states, including genotypes and gene expression programs.

Artificial intelligence in drug combination therapy

Currently, the development of medicines for complex diseases requires the development of combination drug therapies. It is necessary because in many cases, one drug cannot target all necessary points of intervention. For example, in cancer therapy, a physician often meets a patient having a genomic profile including more than five molecular aberrations. Drug combination therapy has been an area of interest for a while, for example the classical work of Loewe devoted to the synergism of drugs was published in 1928-and it is still used in calculations for optimal drug combinations. More recently, over the past several years, there has been an explosion in the available information related to the properties of drugs and the biomedical parameters of patients. For the drugs, hundreds of 2D and 3D molecular descriptors for medicines are now available, while for patients, large data sets related to genetic/proteomic and metabolomics profiles of the patients are now available, as well as the more traditional data relating to the histology, history of treatments, pretreatment state of the organism, etc. Moreover, during disease progression, the genetic profile can change. Thus, the ability to optimize drug combinations for each patient is rapidly moving beyond the comprehension and capabilities of an individual physician. This is the reason, that biomedical informatics methods have been developed and one of the more promising directions in this field is the application of artificial intelligence (AI). In this review, we discuss several AI methods that have been successfully implemented in several instances of combination drug therapy from HIV, hypertension, infectious diseases to cancer. The data clearly show that the combination of rule-based expert systems with machine learning algorithms may be promising direction in this field.

Drug uptake-based chemoresistance in breast cancer treatment

Breast cancer is the most prevalent type of tumor and the second leading cause of death due to cancer among women. Although screening methods, diagnosis and therapeutic options have improved in the last decade, chemoresistance remains an important challenge. There is evidence relating breast cancer resistance with signaling pathways involving hormone and growth receptors, survival, apoptosis and the activation of efflux pumps. However, the resistance mechanisms linked to drug uptake are poorly understood, despite it often being observed that the drug content is lower in resistant cancer cells and that the entry of the drug into these cells is a limiting process for the subsequent therapeutic effect.In this review, we provide an overview of drug uptake-based resistance mechanisms developed by cancer cells in the four main types of chemotherapy used in breast cancer: anthracyclines, taxanes, oxazaphosphorines and platinum-based drugs. The contribution of tumor microenvironment to reduced drug-uptake and multidrug resistance is also analyzed. As a developing field, nanomedicine-based approaches provide promising opportunities to improve drug specific targeting, cell interaction and uptake into cancer cells. The endocytic-mediated pathways attributed to the different types of nanoformulations as well as the contribution of nanotherapeutics to overcoming chemoresistance affecting drug uptake in breast cancer will be described. New approaches focusing on drug uptake mechanisms could improve breast cancer chemotherapy, obtaining better dose-response outcomes and reducing toxic side effects.

The Emerging Role of the SLCO1B3 Protein in Cancer Resistance

Currently, chemotherapy is one of the mainstays of oncologic therapies. But the efficacy of chemotherapy is often limited by drug resistance and severe side effects. Consequently, it is becoming increasingly important to investigate the underlying mechanism and overcome the problem of anticancer chemotherapy resistance. The solute carrier organic anion transporter family member 1B3 (SLCO1B3), a functional transporter normally expressed in the liver, transports a variety of endogenous and exogenous compounds, including hormones and their conjugates as well as some anticancer drugs. The extrahepatic expression of SLCO1B3 has been detected in different cancer cell lines and cancer tissues. Recently, accumulating data indicates that the abnormal expression and function of SLCO1B3 are involved in resistance to anticancer drugs, such as taxanes, camptothecin and its analogs, SN-38, and Androgen Deprivation Therapy (ADT) in breast, prostate, lung, hepatic, and colorectal cancer, respectively. Thus, more investigations have been implemented to identify the potential SLCO1B3-related mechanisms of cancer drug resistance. In this review, we focus on the emerging roles of SLCO1B3 protein in the development of cancer chemotherapy resistance and briefly discuss the mechanisms of resistance. Elucidating the function of SLCO1B3 in chemoresistance may bring out novel therapeutic strategies for cancer treatment.

Thymoquinone Enhances Paclitaxel Anti-Breast Cancer Activity via Inhibiting Tumor-Associated Stem Cells Despite Apparent Mathematical Antagonism

Thymoquinone (TQ) has shown substantial evidence for its anticancer effects. Using human breast cancer cells, we evaluated the chemomodulatory effect of TQ on paclitaxel (PTX). TQ showed weak cytotoxic properties against MCF-7 and T47D breast cancer cells with IC₅₀ values of 64.93 ± 14 µM and 165 ± 2 µM, respectively. Combining TQ with PTX showed apparent antagonism, increasing the IC₅₀ values of PTX from 0.2 ± 0.07 µM to 0.7 ± 0.01 µM and from 0.1 ± 0.01 µM to 0.15 ± 0.02 µM in MCF-7 and T47D cells, respectively. Combination index analysis showed antagonism in both cell lines with CI values of 4.6 and 1.6, respectively. However, resistance fractions to PTX within MCF-7 and T47D cells (42.3 ± 1.4% and 41.9 ± 1.1%, respectively) were completely depleted by combination with TQ. TQ minimally affected the cell cycle, with moderate accumulation of cells in the S-phase. However, a significant increase in Pre-G phase cells was observed due to PTX alone and PTX combination with TQ. To dissect this increase in the Pre-G phase, apoptosis, necrosis, and autophagy were assessed by flowcytometry. TQ significantly increased the percent of apoptotic/necrotic cell death in T47D cells after combination with paclitaxel. On the other hand, TQ significantly induced autophagy in MCF-7 cells. Furthermore, TQ was found to significantly decrease breast cancer-associated stem cell clone (CD44+/CD24-cell) in both MCF-7 and T47D cells. This was mirrored by the downregulation of TWIST-1 gene and overexpression of SNAIL-1 and SNAIL-2 genes. TQ therefore possesses potential chemomodulatory effects to PTX when studied in breast cancer cells via enhancing PTX induced cell death including autophagy. In addition, TQ depletes breast cancer-associated stem cells and sensitizes breast cancer cells to PTX killing effects.