Precision combination therapies based on recurrent oncogenic co-alterations

The clinical application of artificial intelligence in cancer precision treatment

BACKGROUND

Artificial intelligence has made significant contributions to oncology through the availability of high-dimensional datasets and advances in computing and deep learning. Cancer precision medicine aims to optimize therapeutic outcomes and reduce side effects for individual cancer patients. However, a comprehensive review describing the impact of artificial intelligence on cancer precision medicine is lacking.

OBSERVATIONS

By collecting and integrating large volumes of data and applying it to clinical tasks across various algorithms and models, artificial intelligence plays a significant role in cancer precision medicine. Here, we describe the general principles of artificial intelligence, including machine learning and deep learning. We further summarize the latest developments in artificial intelligence applications in cancer precision medicine. In tumor precision treatment, artificial intelligence plays a crucial role in individualizing both conventional and emerging therapies. In specific fields, including target prediction, targeted drug generation, immunotherapy response prediction, neoantigen prediction, and identification of long non-coding RNA, artificial intelligence offers promising perspectives. Finally, we outline the current challenges and ethical issues in the field.

CONCLUSIONS

Recent clinical studies demonstrate that artificial intelligence is involved in cancer precision medicine and has the potential to benefit cancer healthcare, particularly by optimizing conventional therapies, emerging targeted therapies, and individual immunotherapies. This review aims to provide valuable resources to clinicians and researchers and encourage further investigation in this field.

Coacervation for biomedical applications: innovations involving nucleic acids

Gene therapies, drug delivery systems, vaccines, and many other therapeutics, although seeing breakthroughs over the past few decades, still suffer from poor stability, biocompatibility, and targeting. Coacervation, a liquid-liquid phase separation phenomenon, is a pivotal technique increasingly employed to enhance the effectiveness of therapeutics. Through coacervation strategies, many current challenges in therapeutic formulations can be addressed due to the tunable nature of this technique. However, much remains to be explored to enhance these strategies further and scale them from the benchtop to industrial applications. In this review, we highlight the underlying mechanisms of coacervation, elucidating how factors such as pH, ionic strength, temperature, chirality, and charge patterning influence the formation of coacervates and the encapsulation of active ingredients. We then present a perspective on current strategies harnessing these systems, specifically for nucleic acid-based therapeutics. These include peptide-, protein-, and polymer-based approaches, nanocarriers, and hybrid methods, each offering unique advantages and challenges. Nucleic acid-based therapeutics are crucial for designing rapid responses to diseases, particularly in pandemics. While these exciting systems offer many advantages, they also present limitations and challenges which are explored in this work. Exploring coacervation in the biomedical frontier opens new avenues for innovative nucleic acid-based treatments, marking a significant stride towards advanced therapeutic solutions.

Combination of MDM2 and Targeted Kinase Inhibitors Results in Prolonged Tumor Control in Lung Adenocarcinomas With Oncogenic Tyrosine Kinase Drivers and MDM2 Amplification

PURPOSE

MDM2, a negative regulator of the TP53 tumor suppressor, is oncogenic when amplified. MDM2 amplification (MDM2amp) is mutually exclusive with TP53 mutation and is seen in 6% of patients with lung adenocarcinoma (LUAD), with significant enrichment in subsets with receptor tyrosine kinase (RTK) driver alterations. Recent studies have shown synergistic activity of MDM2 and MEK inhibition in patient-derived LUAD models with MDM2amp and RTK driver alterations. However, the combination of MDM2 and RTK inhibitors in LUAD has not been studied.

METHODS

We evaluated the combination of MDM2 and RTK inhibition in patient-derived models of LUAD.

RESULTS

In a RET-fusion LUAD patient-derived model with MDM2amp, MDM2 inhibition with either milademetan or AMG232 combined with selpercatinib resulted in long-term in vivo tumor control markedly superior to either agent alone. Similarly, in an EGFR-mutated model with MDM2amp, combining either milademetan or AMG232 with osimertinib resulted in long-term in vivo tumor control, which was strikingly superior to either agent alone.

CONCLUSION

These preclinical in vivo data provide a rationale for further clinical development of this combinatorial targeted therapy approach.

Transfer learning predicts species-specific drug interactions in emerging pathogens

Machine learning (ML) algorithms are necessary to efficiently identify potent drug combinations within a large candidate space to combat drug resistance. However, existing ML approaches cannot be applied to emerging and under-studied pathogens with limited training data. To address this, we developed a transfer learning and crowdsourcing framework (TACTIC) to train ML models on data from multiple bacteria. TACTIC was built using 2,965 drug interactions from 12 bacterial strains and outperformed traditional ML models in predicting drug interaction outcomes for species that lack training data. Top TACTIC model features revealed genetic and metabolic factors that influence cross-species and species-specific drug interaction outcomes. Upon analyzing ~600,000 predicted drug interactions across 9 metabolic environments and 18 bacterial strains, we identified a small set of drug interactions that are selectively synergistic against Gram-negative (e.g., A. baumannii) and non-tuberculous mycobacteria (NTM) pathogens. We experimentally validated synergistic drug combinations containing clarithromycin, ampicillin, and mecillinam against M. abscessus, an emerging pathogen with growing levels of antibiotic resistance. Lastly, we leveraged TACTIC to propose selectively synergistic drug combinations to treat bacterial eye infections (endophthalmitis).

Reliable anti-cancer drug sensitivity prediction and prioritization

The application of machine learning (ML) to solve real-world problems does not only bear great potential but also high risk. One fundamental challenge in risk mitigation is to ensure the reliability of the ML predictions, i.e., the model error should be minimized, and the prediction uncertainty should be estimated. Especially for medical applications, the importance of reliable predictions can not be understated. Here, we address this challenge for anti-cancer drug sensitivity prediction and prioritization. To this end, we present a novel drug sensitivity prediction and prioritization approach guaranteeing user-specified certainty levels. The developed conformal prediction approach is applicable to classification, regression, and simultaneous regression and classification. Additionally, we propose a novel drug sensitivity measure that is based on clinically relevant drug concentrations and enables a straightforward prioritization of drugs for a given cancer sample.

Genetic interactions reveal distinct biological and therapeutic implications in breast cancer

Co-occurrence and mutual exclusivity of genomic alterations may reflect the existence of genetic interactions, potentially shaping distinct biological phenotypes and impacting therapeutic response in breast cancer. However, our understanding of them remains limited. Herein, we investigate a large-scale multi-omics cohort (n = 873) and a real-world clinical sequencing cohort (n = 4,405) including several clinical trials with detailed treatment outcomes and perform functional validation in patient-derived organoids, tumor fragments, and in vivo models. Through this comprehensive approach, we construct a network comprising co-alterations and mutually exclusive events and characterize their therapeutic potential and underlying biological basis. Notably, we identify associations between TP53mut-AURKAamp and endocrine therapy resistance, germline BRCA1mut-MYCamp and improved sensitivity to PARP inhibitors, and TP53mut-MYBamp and immunotherapy resistance. Furthermore, we reveal that precision treatment strategies informed by co-alterations hold promise to improve patient outcomes. Our study highlights the significance of genetic interactions in guiding genome-informed treatment decisions beyond single driver alterations.

Model informed precision medicine of Chinese herbal medicines formulas-A multi-scale mechanistic intelligent model

Recent trends suggest that Chinese herbal medicine formulas (CHM formulas) are promising treatments for complex diseases. To characterize the precise syndromes, precise diseases and precise targets of the precise targets between complex diseases and CHM formulas, we developed an artificial intelligence-based quantitative predictive algorithm (DeepTCM). DeepTCM has gone through multilevel model calibration and validation against a comprehensive set of herb and disease data so that it accurately captures the complex cellular signaling, molecular and theoretical levels of traditional Chinese medicine (TCM). As an example, our model simulated the optimal CHM formulas for the treatment of coronary heart disease (CHD) with depression, and through model sensitivity analysis, we calculated the balanced scoring of the formulas. Furthermore, we constructed a biological knowledge graph representing interactions by associating herb-target and gene-disease interactions. Finally, we experimentally confirmed the therapeutic effect and pharmacological mechanism of a novel model-predicted intervention in humans and mice. This novel multiscale model opened up a new avenue to combine "disease syndrome" and "macro micro" system modeling to facilitate translational research in CHM formulas.

Informing immunotherapy with multi-omics driven machine learning

Progress in sequencing technologies and clinical experiments has revolutionized immunotherapy on solid and hematologic malignancies. However, the benefits of immunotherapy are limited to specific patient subsets, posing challenges for broader application. To improve its effectiveness, identifying biomarkers that can predict patient response is crucial. Machine learning (ML) play a pivotal role in harnessing multi-omic cancer datasets and unlocking new insights into immunotherapy. This review provides an overview of cutting-edge ML models applied in omics data for immunotherapy analysis, including immunotherapy response prediction and immunotherapy-relevant tumor microenvironment identification. We elucidate how ML leverages diverse data types to identify significant biomarkers, enhance our understanding of immunotherapy mechanisms, and optimize decision-making process. Additionally, we discuss current limitations and challenges of ML in this rapidly evolving field. Finally, we outline future directions aimed at overcoming these barriers and improving the efficiency of ML in immunotherapy research.

Predictive Value of Machine Learning for Platinum Chemotherapy Responses in Ovarian Cancer: Systematic Review and Meta-Analysis

BACKGROUND

Machine learning is a potentially effective method for predicting the response to platinum-based treatment for ovarian cancer. However, the predictive performance of various machine learning methods and variables is still a matter of controversy and debate.

OBJECTIVE

This study aims to systematically review relevant literature on the predictive value of machine learning for platinum-based chemotherapy responses in patients with ovarian cancer.

METHODS

Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we systematically searched the PubMed, Embase, Web of Science, and Cochrane databases for relevant studies on predictive models for platinum-based therapies for the treatment of ovarian cancer published before April 26, 2023. The Prediction Model Risk of Bias Assessment tool was used to evaluate the risk of bias in the included articles. Concordance index (C-index), sensitivity, and specificity were used to evaluate the performance of the prediction models to investigate the predictive value of machine learning for platinum chemotherapy responses in patients with ovarian cancer.

RESULTS

A total of 1749 articles were examined, and 19 of them involving 39 models were eligible for this study. The most commonly used modeling methods were logistic regression (16/39, 41%), Extreme Gradient Boosting (4/39, 10%), and support vector machine (4/39, 10%). The training cohort reported C-index in 39 predictive models, with a pooled value of 0.806; the validation cohort reported C-index in 12 predictive models, with a pooled value of 0.831. Support vector machine performed well in both the training and validation cohorts, with a C-index of 0.942 and 0.879, respectively. The pooled sensitivity was 0.890, and the pooled specificity was 0.790 in the training cohort.

CONCLUSIONS

Machine learning can effectively predict how patients with ovarian cancer respond to platinum-based chemotherapy and may provide a reference for the development or updating of subsequent scoring systems.

Personalized tumor combination therapy optimization using the single-cell transcriptome

BACKGROUND

The precise characterization of individual tumors and immune microenvironments using transcriptome sequencing has provided a great opportunity for successful personalized cancer treatment. However, the cancer treatment response is often characterized by in vitro assays or bulk transcriptomes that neglect the heterogeneity of malignant tumors in vivo and the immune microenvironment, motivating the need to use single-cell transcriptomes for personalized cancer treatment.

METHODS

Here, we present comboSC, a computational proof-of-concept study to explore the feasibility of personalized cancer combination therapy optimization using single-cell transcriptomes. ComboSC provides a workable solution to stratify individual patient samples based on quantitative evaluation of their personalized immune microenvironment with single-cell RNA sequencing and maximize the translational potential of in vitro cellular response to unify the identification of synergistic drug/small molecule combinations or small molecules that can be paired with immune checkpoint inhibitors to boost immunotherapy from a large collection of small molecules and drugs, and finally prioritize them for personalized clinical use based on bipartition graph optimization.

RESULTS

We apply comboSC to publicly available 119 single-cell transcriptome data from a comprehensive set of 119 tumor samples from 15 cancer types and validate the predicted drug combination with literature evidence, mining clinical trial data, perturbation of patient-derived cell line data, and finally in-vivo samples.

CONCLUSIONS

Overall, comboSC provides a feasible and one-stop computational prototype and a proof-of-concept study to predict potential drug combinations for further experimental validation and clinical usage using the single-cell transcriptome, which will facilitate and accelerate personalized tumor treatment by reducing screening time from a large drug combination space and saving valuable treatment time for individual patients. A user-friendly web server of comboSC for both clinical and research users is available at www.combosc.top . The source code is also available on GitHub at https://github.com/bm2-lab/comboSC .

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.

Recurrent composite markers of cell types and states

Determining concise sets of genomic markers that identify cell types and states within tissue ecosystems remains challenging. To address this challenge, we developed Recurrent Composite Markers for Biological Identities with Neighborhood Enrichment (RECOMBINE). Validations of RECOMBINE with simulation and transcriptomics data in bulk, single-cell and spatial resolutions demonstrated the method's ability for unbiased selection of composite markers that characterize biological subpopulations. RECOMBINE captured markers of mouse visual cortex from single-cell RNA sequencing data and provided a gene panel for targeted spatial transcriptomics profiling. RECOMBINE identified composite markers of CD8 T cell states including GZMK ⁺ HAVCR2 ^- effector memory cells associated with anti-PD1 therapy response. The method outperformed differential gene expression analysis in characterizing a rare cell subpopulation within mouse intestine. Using RECOMBINE, we uncovered hierarchical gene programs of inter- and intra-tumoral heterogeneity in breast and skin tumors. In conclusion, RECOMBINE offers a data-driven approach for unbiased selection of composite markers, resulting in improved interpretation, discovery, and validation of cell types and states.

Advances and Prospects in the Treatment of Pancreatic Cancer

Pancreatic cancer is a highly malignant and incurable disease, characterized by its aggressive nature and high fatality rate. The most common type is pancreatic ductal adenocarcinoma (PDAC), which has poor prognosis and high mortality rate. Current treatments for pancreatic cancer mainly encompass surgery, chemotherapy, radiotherapy, targeted therapy, and combination regimens. However, despite efforts to improve prognosis, and the 5-year survival rate for pancreatic cancer remains very low. Therefore, it's urgent to explore novel therapeutic approaches. With the rapid development of therapeutic strategies in recent years, new ideas have been provided for treating pancreatic cancer. This review expositions the advancements in nano drug delivery system, molecular targeted drugs, and photo-thermal treatment combined with nanotechnology for pancreatic cancer. It comprehensively analyzes the prospects of combined drug delivery strategies for treating pancreatic cancer, aiming at a deeper understanding of the existing drugs and therapeutic approaches, promoting the development of new therapeutic drugs, and attempting to enhance the therapeutic effect for patients with this disease.

Mapping the functional interactions at the tumor-immune checkpoint interface

The interactions between tumor intrinsic processes and immune checkpoints can mediate immune evasion by cancer cells and responses to immunotherapy. It is, however, challenging to identify functional interactions due to the prohibitively complex molecular landscape of the tumor-immune interfaces. We address this challenge with a statistical analysis framework, immuno-oncology gene interaction maps (ImogiMap). ImogiMap quantifies and statistically validates tumor-immune checkpoint interactions based on their co-associations with immune-associated phenotypes. The outcome is a catalog of tumor-immune checkpoint interaction maps for diverse immune-associated phenotypes. Applications of ImogiMap recapitulate the interaction of SERPINB9 and immune checkpoints with interferon gamma (IFNγ) expression. Our analyses suggest that CD86-CD70 and CD274-CD70 immunoregulatory interactions are significantly associated with IFNγ expression in uterine corpus endometrial carcinoma and basal-like breast cancer, respectively. The open-source ImogiMap software and user-friendly web application will enable future applications of ImogiMap. Such applications may guide the discovery of previously unknown tumor-immune interactions and immunotherapy targets.

Breast cancer sub-types display heterogeneity in gene amplification and mRNA expression of the anti-apoptotic members of BCL2 family

BACKGROUND

Progress in therapies and improved outcomes in recent decades have followed a better understanding of breast cancers pathogenesis and their heterogeneity but new treatments are needed especially for metastatic disease which remains incurable. Inhibition of apoptosis is a hallmark characteristic of cancer and can be targeted for therapy.

METHODS

The five anti-apoptotic members of the BCL2 family are at the core of apoptosis execution and are involved in apoptosis evasion of transformed cells. Genetic lesions as well as mRNA regulation of these members in breast cancer and its sub-types and implications for survival outcomes were investigated using data from various publicly available databases.

RESULTS

Genes encoding for anti-apoptotic BCL2 proteins are rarely mutated in breast cancer and copy number alterations are observed only in MCL1 gene which is amplified in a minority of breast cancer ranging from 1.6% to 18.7% in breast cancers. Over-expression of BCL2, BCL-X and MCL1 is observed in luminal A cancers, while cases of luminal B and basal breast cancers display mRNA up-regulation of BCL-X and MCL1, respectively. Basal cancers possess also more frequently than other sub-sets MCL1 amplifications. Survival outcomes are not significantly different in cancers with higher expression of anti-apoptotic BCL2 mRNAs.

CONCLUSION

Therapeutic targeting of the apoptotic process in breast cancer sub-types will be improved by a detailed understanding of the core players in the process, including anti-apoptotic BCL2 family proteins. A sub-set of breast cancers harbor amplifications of MCL1 and dysregulations of expression of most family members that could affect the sensitivity to their inhibition by altering the cell's apoptotic threshold.

Charting co-mutation patterns associated with actionable drivers in intrahepatic cholangiocarcinoma

BACKGROUND & AIMS

In recent years, intrahepatic cholangiocarcinoma (iCCA) has evolved as a "role model" for precision oncology in gastrointestinal cancers. However, its rarity, paired with its genomic heterogeneity, challenges the development and evolution of targeted therapies. Interrogating large datasets drives better understanding of the characteristics of molecular subgroups of rare cancers and enables the identification of genomic patterns that remain unrecognized in smaller cohorts.

METHODS

We performed a retrospective analysis of 6,130 patients diagnosed with iCCA from the FoundationCORE database who received diagnostic panel sequencing on the FoundationOne platform. Short variants/fusion-rearrangements and copy number alterations in >300 tumor-associated genes were evaluated, and the tumor mutational burden (TMB) as well as the microsatellite instability (MSI) status were available for the majority of the cohort.

RESULTS

We provide a highly representative cartography of the genomic landscape of iCCA and outline the co-mutational spectra of seven therapeutically relevant oncogenic driver genes: IDH1/2, FGFR2, ERBB2, BRAF, MDM2, BRCA1/2, MET and KRAS^G12C. We observed a negative selection of RTK/RAS/ERK pathway co-alterations, and an enrichment of epigenetic modifiers such as ARID1A and BAP1 in patients with IDH1/2 and FGFR2 alterations. RNF43 as well as KMT2D occurred with high frequency in MSI^high and TMB^high tumors.

CONCLUSION

Detailed knowledge of the most prevalent genomic constellations is key to the development of effective treatment strategies for iCCA. Our study provides a valuable resource that could be used to assess the feasibility of clinical trials and subgroup analyses, spurs the development of translationally relevant preclinical models, and serves as a knowledge base to predict potential mechanisms of resistance to targeted therapies in genomically defined subgroups.

IMPACT AND IMPLICATIONS

Due to the high frequency of targetable alterations, molecular diagnostics is recommended in patients with biliary tract cancers, and especially in those with iCCA. The identification of an actionable lesion, however, does not guarantee therapeutic success, and the co-mutational spectrum may act as a critical modifier of drug response. Using a large dataset of comprehensive panel sequencing results from 6,130 patients with iCCA, we provide a detailed analysis of the co-mutational spectrum of the most frequent druggable genetic alterations, which is meant to serve as a reference to establish genetically relevant preclinical models, develop hypothesis-driven combination therapies and identify recurrent genetic profiles.

Simultaneous regression and classification for drug sensitivity prediction using an advanced random forest method

Machine learning methods trained on cancer cell line panels are intensively studied for the prediction of optimal anti-cancer therapies. While classification approaches distinguish effective from ineffective drugs, regression approaches aim to quantify the degree of drug effectiveness. However, the high specificity of most anti-cancer drugs induces a skewed distribution of drug response values in favor of the more drug-resistant cell lines, negatively affecting the classification performance (class imbalance) and regression performance (regression imbalance) for the sensitive cell lines. Here, we present a novel approach called SimultAneoUs Regression and classificatiON Random Forests (SAURON-RF) based on the idea of performing a joint regression and classification analysis. We demonstrate that SAURON-RF improves the classification and regression performance for the sensitive cell lines at the expense of a moderate loss for the resistant ones. Furthermore, our results show that simultaneous classification and regression can be superior to regression or classification alone.

REFLECTions on Combination Therapies Empowered by Data Sharing

SUMMARY

Li and colleagues present REFLECT, a computational approach to precision oncology that nominates effective drug combinations by utilizing a diverse compendium of publicly available preclinical and clinical genomic, transcriptomic, and proteomic data. The preliminary validation of the REFLECT system in preclinical and clinical trial settings showcases potential for clinical implementation, although challenges remain. See related article by Li et al., p. 1542 (4).

Oxidative Damage in Sporadic Colorectal Cancer: Molecular Mapping of Base Excision Repair Glycosylases MUTYH and hOGG1 in Colorectal Cancer Patients

Oxidative stress, oxidative DNA damage and resulting mutations play a role in colorectal carcinogenesis. Impaired equilibrium between DNA damage formation, antioxidant status, and DNA repair capacity is responsible for the accumulation of genetic mutations and genomic instability. The lesion-specific DNA glycosylases, e.g., hOGG1 and MUTYH, initiate the repair of oxidative DNA damage. Hereditary syndromes (MUTYH-associated polyposis, NTHL1-associated tumor syndrome) with germline mutations causing a loss-of-function in base excision repair glycosylases, serve as straight forward evidence on the role of oxidative DNA damage and its repair. Altered or inhibited function of above glycosylases result in an accumulation of oxidative DNA damage and contribute to the adenoma-adenocarcinoma transition. Oxidative DNA damage, unless repaired, often gives rise G:C > T:A mutations in tumor suppressor genes and proto-oncogenes with subsequent occurrence of chromosomal copy-neutral loss of heterozygosity. For instance, G>T transversions in position c.34 of a KRAS gene serves as a pre-screening tool for MUTYH-associated polyposis diagnosis. Since sporadic colorectal cancer represents more complex and heterogenous disease, the situation is more complicated. In the present study we focused on the roles of base excision repair glycosylases (hOGG1, MUTYH) in colorectal cancer patients by investigating tumor and adjacent mucosa tissues. Although we found downregulation of both glycosylases and significantly lower expression of hOGG1 in tumor tissues, accompanied with G>T mutations in KRAS gene, oxidative DNA damage and its repair cannot solely explain the onset of sporadic colorectal cancer. In this respect, other factors (especially microenvironment) per se or in combination with oxidative DNA damage warrant further attention. Base excision repair characteristics determined in colorectal cancer tissues and their association with disease prognosis have been discussed as well.