📋 Browse Articles

Tumor metastases account for nearly 90% of cancer-related fatalities. To tackle this issue, chemotherapeutic agents that induce immunogenic cell death (ICD) are being investigated as promising candidates for metastatic cancer treatment. Herein, the chemical synthesis and biological evaluation of a novel Ga(III) complex with Schiff bases, [Ga((E)-1-((quinolin-8-ylimino)methyl)naphthalen-2-olato)₂][Cl], for potential use in combined chemotherapy and immunotherapy are reported. This compound exhibited broad cytotoxicity against human breast cancer, pancreatic cancer, cervical cancer cell lines, and the noncancerous human fibroblast cell line. Mechanistic investigations revealed that the compound triggers apoptosis and ICD hallmarks, such as translocation of calreticulin, phosphorylation of eIF2α, migration of high mobility group protein 1, and release of adenosine triphosphate. Deeper biological assessment using multicellular tumor spheroids of cervical cancer cell lines, a solid tumor model, demonstrated successful eradication at micromolar concentrations. This study presents one of the few reported Ga(III) complexes capable of inducing immunogenic cell death. Show less

Abstract Cancer cells rely heavily on de novo pyrimidine synthesis. Inhibiting pyrimidine metabolism directly suppresses tumor growth and fosters immune activation within the tumor microenvironment. Dihydroorotate dehydrogenase (DHODH) is a key enzyme in the de novo pyrimidine synthesis pathway. Inhibiting DHODH can reverse immune suppression and trigger a mild innate immune response. However, the impact of DHODH inhibition on natural killer (NK) cells remains to be explored. In this study, we found that DHODH inhibition promoted NK cell infiltration into tumors efficiently. Mechanistically, DHODH suppression induced mitochondrial oxidative stress, leading to mitochondrial DNA (mtDNA) release into the cytoplasm through voltage-dependent anion channel (VDAC) oligomerization and caspase-3 activation. This subsequently activated the stimulator of interferon gene (STING) pathway, triggered ferroptosis, and induced gasdermin E (GSDME) mediated pyroptosis in cancer cells. These changes collectively facilitated NK cell recruitment. Furthermore, infiltrated NK cells enhanced GSDME-dependent pyroptosis in tumor cells through granzyme release, establishing a positive feedback loop that amplified anti-tumor immunity. Additionally, we developed EA6, a novel DHODH inhibitor that is more effective at promoting NK cell infiltration. In summary, this study reveals that targeting pyrimidine metabolism activates a novel mechanism involving pyroptosis-ferroptosis crosstalk and STING pathway activation to enhance NK cell-mediated immunity. These finding opens new avenues for enhancing the efficacy of targeted nucleotide metabolism in cancer therapy. Show less

AuL4 triggers necroptosis and paraptosis in A549 cells. TLDR: AuL4 emerged as the most active compound, exhibited potent anticancer activity, triggering mitochondrial membrane depolarization and inducing necroptosis and paraptosis in human lung adenocarcinoma cells-a mechanism distinct from conventional apoptosis-inducing gold complexes. Show less

AbstractA series of xylose‐based ligands was obtained using a convenient approach, in a few steps from D‐xylose. The complexation properties of these ligands towards Au3+ cations have been studied through different methods (multinuclear NMR, mass spectrometry, elemental analysis). The biological properties (antibacterial and anti‐tumoral) of all the isolated xyloside Au(III) complexes were investigated in vitro. The xyloside Au(III) complexes gave the highest activities against E. coli (vs P. aeruginosa, S. aureus and S. epidermidis). The study also revealed that the nature of the sugar may play an important role in determining the selectivity of the antibacterial effect. Preliminary anti‐tumoral evaluations showed that one complex containing a polyamine chain, exhibited interesting anti‐proliferative activities on breast tumor cell lines MDA‐MB‐231 and BT‐20. The anti‐migratory effect of this complex also showed an average 35 % reduction in cell migration on the same two cancer cell lines. Show less

High-Grade Serous Ovarian Cancer (HGSOC) is the most common and lethal subtype of ovarian cancer, known for its high aggressiveness and extensive genomic alterations. Typically diagnosed at an advanced stage, HGSOC presents formidable challenges in drug therapy. The limited efficacy of standard treatments, development of chemoresistance, scarcity of targeted therapies, and significant tumor heterogeneity render this disease incurable with current treatment options, highlighting the urgent need for novel therapeutic approaches to improve patient outcomes. In this study we report a straightforward and stereoselective synthetic route to novel Pd(II)-vinyl and -butadienyl complexes bearing a wide range of monodentate and bidentate ligands. Most of the synthesized complexes exhibited good to excellent in vitro anticancer activity against ovarian cancer cells. Particularly promising is the water-soluble complex bearing two PTA (1,3,5-triaza-7-phosphaadamantane) ligands and the Pd(II)-butadienyl fragment. This compound combines excellent cytotoxicity towards cancer cells with substantial inactivity towards non-cancerous ones. This derivative was selected for further studies on ex vivo tumor organoids and in vivo mouse models, which demonstrate its remarkable efficacy with surprisingly low collateral toxicity even at high dosages. Moreover, this class of compounds appears to operate through a ferroptotic mechanism, thus representing the first such example for an organopalladium compound. Show less

Chemotherapy for cancer frequently uses platinum-based medications, including oxaliplatin, carboplatin, and cisplatin; however, due to their high systemic toxicity, lack of selectivity, drug resistance, and other side effects, platinum-based medications have very limited clinical application. As a first-line medication in antitumor therapy, oxaliplatin must be administered to minimize side effects while achieving anticancer objectives. A new CDC7 inhibitor called XL413 has demonstrated promising antitumor therapeutic effects in a variety of malignant tumors and may have anticancer properties. This offers a fresh viewpoint on how to lessen oxaliplatin resistance and, specifically, increase the potency of already prescribed anticancer therapies. In this paper, the current developments in anticancer therapy are discussed, along with the many mechanisms of oxaliplatin's antitumor effects, clinical treatment challenges, and related approaches. We conducted more research on oxaliplatin resistance that arose during chemotherapy and searched for ways to lessen it in order to enhance its chemotherapeutic performance. Ultimately, we studied how distinct resistance routes relate to one another. Meanwhile, XL413, a novel CDC7 inhibitor, offers a perspective on the possibilities for developing treatment approaches for this innovation point. The search terms "Oxaliplatin, XL413, drug resistance, cancer treatment," etc., were applied in the X-MOL and PubMed databases for this review's literature search. Boolean logic was then employed to maximize the search approach. These databases can offer thorough research data and cover a broad range of biological publications. Excluded publications were works of low relevance, duplicates, or those with insufficient information. The mechanism of oxaliplatin's anticancer effect, oxaliplatin resistance and its amelioration, and the role of XL413 in oxaliplatin treatment were the main topics of the 140 publications that were ultimately included for analysis. Show less

One of the major challenges in precision oncology is the identification of pathogenic, actionable variants and the selection of personalized treatments. We present Onkopus, a variant interpretation framework based on a modular architecture, for interpreting and prioritizing genetic alterations in cancer patients. A multitude of tools and databases are integrated into Onkopus to provide a comprehensive overview about the consequences of a variant, each with its own semantic, including pathogenicity predictions, allele frequency, biochemical and protein features, Show less

Background: Adverse drug reactions (ADRs) are harmful side effects of medications. Social media provides real-time, patient-generated data, though its unstructured format presents challenges. Natural language processing and transfer learning offer promising solutions. Objective: This study aimed to evaluate whether transformer-based models fine-tuned on a general ADR dataset can effectively classify ADRs from tweets related to glucagon-like peptide-1 (GLP-1) receptor agonists and to benchmark their performance against state-ofthe-art large language models (LLMs). Show less

Liquid-liquid phase separation (LLPS)-driven coacervate droplets, formed by the self-assembly of phase-separating molecules, have emerged as a new platform for the intracellular delivery of macromolecular therapeutics such as antibodies, plasmids, and mRNA. Their appeal lies in their high loading capacity, low cytotoxicity, and high cellular uptake efficiency. Beyond traditional polymer and protein systems, recent advances have demonstrated that low-molecular-weight compounds, including peptides and small molecules, can also form functional coacervates. In this perspective, we will discuss and elucidate the possible mechanisms underlying coacervate cellular uptake and highlight their applications in macromolecular delivery and disease therapy. We also provide our perspective on future research directions and translational opportunities. By critically evaluating these aspects, we aim to bridge fundamental insights with translational potential while providing a promising strategy in disease treatment. Show less

AbstractNew, asymmetric quinizarin‐Au(I)‐NHC complexes were designed, isolated, and fully characterised including by single crystal X‐ray crystallography. Cytotoxicity studies showed effective growth inhibition in HeLa cervical cancer cells with IC50 values ranging from 2.4 μM to 5.3 μM. The successful cellular uptake was evidenced by X‐ray fluorescence imaging on cryo‐preserved whole HeLa cells and the sub‐cellular localisation was monitored by live‐cell fluorescence microscopy. Notably, complex 2 b showed circumvention of acquired anthracycline resistance in K562 leukaemia cells as well as synergistic activity with doxorubicin against both wild‐type and anthracycline‐resistant Nalm‐6 leukaemia cells. Interestingly, sub‐cellular localisation towards mitochondria proved to be more important than the compounds’ overall cytotoxicity for potent antiproliferative activity and to achieve effective resistance circumvention. Show less

Mitochondria are the energy production centers in cells and have unique genetic information. Due to the irreplaceable function of mitochondria, mitochondrial dysfunction often leads to pathological changes. Mitochondrial dysfunction induces an imbalance between oxidation and antioxidation, mitochondrial DNA (mtDNA) damage, mitochondrial dynamics dysregulation, and changes in mitophagy. It results in oxidative stress due to excessive reactive oxygen species (ROS) generation, which contributes to cell damage and death. Mitochondrial dysfunction can also trigger inflammation through the activation of damage-associated molecular patterns (DAMPs), inflammasomes and inflammatory cells. Besides, mitochondrial alterations in the functional regulation, energy metabolism and genetic stability accompany the aging process, and there has been a lot of evidence suggesting that oxidative stress and inflammation, both of which are associated with mitochondrial dysfunction, are predisposing factors of aging. Therefore, this review hypothesizes that mitochondria serve as central hubs regulating oxidative stress, inflammation, and aging, and their dysfunction contributes to various diseases, including cancers, cardiovascular diseases, neurodegenerative disorders, metabolic diseases, sepsis, ocular pathologies, liver diseases, and autoimmune conditions. Moreover, we outline therapies aimed at various mitochondrial dysfunctions, highlighting their performance in animal models and human trials. Additionally, we focus on the limitations of mitochondrial therapy in clinical applications, and discuss potential future research directions for mitochondrial therapy. Show less

Abstract Neuroblastoma, a transcriptionally driven pediatric malignancy, exhibits a remarkable clinical and biological heterogeneity. Two major subtypes, the adrenergic and mesenchymal, are differentially governed by a subset of transcription factors that comprise the core regulatory circuit (CRC). The former subtype is often associated with MYCN amplification and is particularly aggressive and therapy-resistant, underscoring the need for novel targets. Here, we identify the multifunctional non-POU domain-containing octamer-binding (NONO) protein as a guardian of individual CRC genes, thereby contributing to survival of neuroblastoma cells with different MYCN copy numbers. Intracellular oxidation in response to auranofin, an inhibitor of thioredoxin reductase 1, rapidly down-regulated the amounts of NONO mRNA and protein in MYCN -amplified Kelly cell line. Conversely, NONO knockdown with RNA interference (siNONO) also triggered intracellular oxidation. These effects were less pronounced in the SK-N-AS cell line carrying a single MYCN copy, as well as in non-malignant HS5 fibroblasts. In Kelly cells, siNONO attenuated auranofin-induced activation of CRC genes HAND2 and PHOX2B . In line with preferential effects on NONO abundance, the Kelly cells were more sensitive than single MYCN copy counterparts to combinations of a sublethal concentration of auranofin with siNONO. Importantly, MYCN -amplified cells demonstrated a significantly suppressed clonogenic survival 14 days after transient exposure to these combinations compared with each agent alone; HS5 fibroblasts were largely spared. Our findings 1) establish NONO as a redox sensor, a non-trivial role for transcriptional proteins, and 2) justify the strategy of therapeutic targeting of MYCN -amplified tumors vulnerable to oxidative stress. Key points NONO, a master regulator of the core regulatory circuit (CRC) in MYCN -amplified neuroblastoma, is rapidly down-regulated by auranofin-induced intracellular oxidation. NONO knockdown synergizes with auranofin in triggering individual CRC gene deregulation and lethal oxidative stress preferentially in MYCN -amplified cells. Show less

Here, we shed physico-chemical light on major kinase signal transduction cascades in cell proliferation in the Ras network, MAPK and PI3K/AKT/mTOR. The cascades respond to external stimuli. The kinases are allosterically activated and relay the signal, leading to cell growth and division. The pathways are crosslinked, with the output of one pathway influencing the other. The effectiveness of their allosteric signaling relay stems from coordinated speed and precision. These qualities are essential for cell life-yet exactly how they are obtained and regulated has challenged the community over four decades. Here, we define their nature by their kinases' repertoires, substrate specificities and breadth, activation and autoinhibition mechanisms, catalytic rates, interactions, and their dilution state. The cascades are lodged in a dense molecular condensate phase at the membrane adjoining RTK clusters, where their assemblies promote specific, productive signaling. Aiming to shed further physico-chemical light, we ask (i) how starting the cascades with a single substrate and ending with hundreds is still labeled specific; (ii) what we can learn from their different number of mutations; and (iii) why B-Raf unique side-to-side inverse dimerization slows ERK activation and signaling. We point to the (iv) chemical mechanics of the distributions of rates of the crucial MAPK cascade: slower at the top and rapid at the bottom. Finally, the cascades provide inspiration for pharmacological perspectives. Collectively, our updated physico-chemical outlook provides the molecular basis of targeting protein kinases in cancer and spans mechanisms and scales, from conformational landscapes to membraneless organelles, cells and systems levels. Show less

BACKGROUND: Drug repositioning is a pivotal strategy in pharmaceutical research, offering accelerated and cost-effective therapeutic discovery. However, biomedical information relevant to drug repositioning is often complex, dispersed, and underutilized due to limitations in traditional extraction methods, such as reliance on annotated data and poor generalizability. Large language models (LLMs) show promise but face challenges such as hallucinations and interpretability issues. OBJECTIVE: This study proposed long chain-of-thought for drug repositioning knowledge extraction (LCoDR-KE), a lightweight and domain-specific framework to enhance LLMs' accuracy and adaptability in extracting structured biomedical knowledge for drug repositioning. METHODS: A domain-specific schema defined 11 entities (eg, drug, disease) and 18 relationships (eg, treats, is biomarker of). Following the established schema architecture, we constructed automatic annotation based on 10,000 PubMed abstracts via chain-of-thought prompt engineering. A total of 1000 expert-validated abstracts were curated into a drug repositioning corpus, a high-quality specialized corpus, while the remaining entries were allocated for model training purposes. Then, the proposed LCoDR-KE framework combined supervised fine-tuning of the Qwen2.5-7B-Instruct model with reinforcement learning and dual-reward mechanisms. Performance was evaluated against state-of-the-art models (eg, conditional random fields, Bidirectional Encoder Representations From Transformers, BioBERT, Qwen2.5, DeepSeek-R1, OpenBioLLM-70B, and model variants) using precision, recall, and F1-score. In addition, the convergence of the training method was assessed by analyzing performance progression across iteration steps. RESULTS: LCoDR-KE achieved an entity F1 of 81.46% (eg, drug 95.83%, disease 90.52%) and triplet F1 of 69.04%, outperforming traditional models and rivaling larger LLMs (DeepSeek-R1: entity F1=84.64%, triplet F1=69.02%). Ablation studies confirmed the contributions of supervised fine-tuning (8.61% and 20.70% F1 drop if removed) and reinforcement learning (6.09% and 14.09% F1 drop if removed). The training process demonstrated stable convergence, validated through iterative performance monitoring. Qualitative analysis of the model's chain-of-thought outputs showed that LCoDR-KE performed structured and schema-aware reasoning by validating entity types, rejecting incompatible relations, enforcing constraints, and generating compliant JSON. Error analysis revealed 4 main types of mistakes and challenges for further improvement. CONCLUSIONS: LCoDR-KE enhances LLMs' domain-specific adaptability for drug repositioning by offering an open-source drug repositioning corpus and a long chain-of-thought framework based on a lightweight LLM model. This framework supports drug discovery and knowledge reasoning while providing scalable, interpretable solutions applicable to broader biomedical knowledge extraction tasks. Show less

Computational metabolomics will be established in drug discovery and research on complex biological networks. This field of research enhances the detection of metabolic biomarkers and the prediction of molecular interactions by combining multiscale analysis with in silico and molecular docking methods. These include nuclear magnetic resonance, mass spectrometry, and innovative bioinformatics, which enable the accurate generation and characterization of metabolomes. Molecular docking is a crucial tool for simulating the interaction between ligands and receptors, thereby facilitating the identification of potential therapeutics. It also discusses the potential of metabolomics to inform drug modes of action, from pharmacokinetics to forecasting toxicity, thereby streamlining drug development pipelines. We highlight applications in anticancer, antimicrobial, and antiviral drug discovery and explain how these computational models can accelerate target validation and enhance the accuracy of therapeutic strategies. In addition, this review addresses the current challenges and future directions for computational techniques in conjunction with experimental data to advance personalized medicine. In conclusion, this review aims to highlight the prospective approaches of computational metabolomics and molecular docking that identify evolutionary adaptive metabolisms of multiscale biological systems through their synergistic utilization to overcome the key hurdles involved in both drug discovery and metabolomic research. Show less

LitSense 2.0 (https://www.ncbi.nlm.nih.gov/research/litsense2/) is an advanced biomedical search system enhanced with dense vector semantic retrieval, designed for accessing literature on sentence and paragraph levels. It provides unified access to 38 million PubMed abstracts and 6.6 Show less

The convergence of artificial intelligence (AI) and genomics is redefining cancer drug discovery by facilitating the development of personalized and effective therapies. This review examines the transformative role of AI technologies, including deep learning and advanced data analytics, in accelerating key stages of the drug discovery process: target identification, drug design, clinical trial optimization, and drug response prediction. Cutting-edge tools such as DrugnomeAI and PandaOmics have made substantial contributions to therapeutic target identification, while AI's predictive capabilities are driving personalized treatment strategies. Additionally, advancements like AlphaFold highlight AI's capacity to address intricate challenges in drug development. However, the field faces significant challenges, including the management of large-scale genomic datasets and ethical concerns surrounding AI deployment in healthcare. This review underscores the promise of data-centric AI approaches and emphasizes the necessity of continued innovation and interdisciplinary collaboration. Together, AI and genomics are charting a path toward more precise, efficient, and transformative cancer therapeutics. Show less

Claudin (CLDN) proteins are extensively studied due to their critical role in maintaining tissue barriers and cell polarity. However, significant gaps remain in understanding the functional mechanisms of their sequence motifs and the molecular mechanisms of their interactions with other tight junction proteins. This review systematically examines the multifunctional properties of the CLDN protein family from the perspectives of sequence and structure. During evolution, CLDN family members have developed highly conserved structural features, particularly key conserved sites within the first extracellular loop (ECL1) and the C-terminal PDZ-binding domain, which play a central role in regulating the barrier function of tight junctions, ion selectivity, and protein-protein interactions. Furthermore, the distribution pattern of acidic and basic amino acids in ECL1 has been shown to directly determine ion selectivity and paracellular permeability. Meanwhile, the assembly and functional stability of tight junctions are precisely regulated by the C-terminal PDZ-binding domain through its interactions with the ZO protein family. Additionally, the study further elucidates how CLDN proteins modulate critical signaling pathways governing cellular proliferation, survival, and permeability, thereby participating in diverse physiological and pathological processes. These insights have deepened the understanding of the functional diversity of CLDN proteins and provided a new theoretical basis for developing disease diagnostic markers and designing targeted treatment strategies based on CLDN proteins. Show less

Tumour cells undergo profound changes in their metabolism, but targeting these metabolic pathways requires understanding of the impact on immune cells as well as cancer cells. This Review discusses how metabolic pathways in cancer and immune cells shape the tumour microenvironment and describes metabolic modulators and dietary nutrients developed to improve the anticancer immune response. Show less

Background/ObjectivesNew computational methods, based on statistical, machine learning, and deep learning techniques using drug-related entities (e.g., genes, protein bindings, etc.), help reduce the costs of in-vitro experiments through drug-drug interaction prediction (DDIp). This review examines recent advances in DDIp. It presents an in-depth review of the state-of-the-art studies relating to semi-supervised, supervised, self-supervised learning, and other techniques such as graph-based learning and matrix factorization methods for predicting DDIs. All possible interactions between drugs are not known, and accurately predicting interactions is even more difficult due to the complex nature of drug-drug interactions (DDI).MethodsOf the 49 papers published in Web of Science in the last 6 years, 24 papers were considered relevant based on information presented in their titles and abstracts. The included articles focus specifically on predicting DDIs using a type of machine learning algorithm. Excluded articles focused on drug discovery, drug repurposing, molecular representation, or the extraction of biomedical interactions. The methodology, results limitations, and future research directions were studied for each paper. Common challenges, limitations, and future research directions were analyzed.Results and conclusionThe main limitations are class imbalance, poor performance on new drugs, limited explainability, and the need for additional data sources. Show less

BACKGROUND: Globally, the onset and progression of multiple human diseases are associated with mitochondrial dysfunction and dysregulation of Ca2+ uptake dynamics mediated by the mitochondrial calcium uniporter (MCU) complex, which plays a key role in mitochondrial dysfunction. Despite relevant studies, the underlying pathophysiological mechanisms have not yet been fully elucidated. AIM OF REVIEW: This article provides an in-depth analysis of the current research status of the MCU complex, focusing on its molecular composition, regulatory mechanisms, and association with diseases. In addition, we conducted an in-depth analysis of the regulatory effects of agonists, inhibitors, and traditional Chinese medicine (TCM) monomers on the MCU complex and their application prospects in disease treatment. From the perspective of medicinal chemistry, we conducted an in-depth analysis of the structure-activity relationship between these small molecules and MCU and deduced potential pharmacophores and binding pockets. Simultaneously, key structural domains of the MCU complex in Homo sapiens were identified. We also studied the functional expression of the MCU complex in Drosophila, Zebrafish, and Caenorhabditis elegans. These analyses provide a basis for exploring potential treatment strategies targeting the MCU complex and provide strong support for the development of future precision medicine and treatments. KEY SCIENTIFIC CONCEPTS OF REVIEW: The MCU complex exhibits varying behavior across different tissues and plays various roles in metabolic functions. It consists of six MCU subunits, an essential MCU regulator (EMRE), and solute carrier 25A23 (SLC25A23). They regulate processes, such as mitochondrial Ca2+ (mCa2+) uptake, mitochondrial adenosine triphosphate (ATP) production, calcium dynamics, oxidative stress (OS), and cell death. Regulation makes it a potential target for treating diseases, especially cardiovascular diseases, neurodegenerative diseases, inflammatory diseases, metabolic diseases, and tumors. Show less

In this Review, Emerling and colleagues summarize the roles of phosphatidylinositol 4-kinases (PI4Ks) and phosphatidylinositol phosphate kinases (PIPKs) in cancer. They highlight the altered expression of these kinases in tumours and discuss ongoing efforts in developing therapies targeting these lesser-studied phosphoinositide kinase families. Show less

Abstract Cells use the covalent attachment of Ubiquitin (Ub) chains to mark proteins for degradation, alter their cellular localization or drive their association. Protein fate is encoded in the distinct poly-Ub linkages, exploiting the vast combinatorial space of linear and branched Ub modifications. AlphaFold has emerged as a powerful tool to predict the structure of protein-protein complexes. However, standard AlphaFold does not consider linkages between individual protein chains, limiting its applicability to Ub chains. The near complete conservation of the ubiquitin sequence and the large number of binding partners suppresses coevolutionary signals, further challenging the prediction of poly-Ub complex structures. We address this challenge, first, by introducing correlated cysteine mutations to induce linkage-specific proximity of Ubs in complex with interacting proteins. Second, we introduce short covalent linker groups in AlphaFold 3 calculations that mimic the isopeptide bonds between linked lysines and Ub C-terminal carboxylates. These two approaches enable the robust structural modeling of complexes involving poly-Ub chains with AlphaFold. The linker approach is general and can be used for other covalent inter-chain connections and to enforce distance restraints for integrative structural modeling. Show less

AbstractTaxanes and platinum molecules, specifically paclitaxel and carboplatin, are widely used anticancer drugs that induce cell death and serve as first‐line chemotherapy for various cancer types. Despite the efficient effect of both drugs on cancer cell proliferation, many tumours have innate resistance against paclitaxel and carboplatin, which leads to inefficient treatment and poor survival rates. Haploid human embryonic stem cells (hESCs) are a novel and robust platform for genetic screening. To gain a comprehensive view of genes that affect or regulate paclitaxel and carboplatin resistance, genome‐wide loss‐of‐function screens in haploid hESCs were performed. Both paclitaxel and carboplatin screens have yielded selected plausible gene lists and pathways relevant to resistance prediction. The effects of mutations in selected genes on the resistance to the drugs were demonstrated. Based on the results, an algorithm that can predict resistance to paclitaxel or carboplatin was developed. Applying the algorithm to the DNA mutation profile of patients' tumours enabled the separation of sensitive versus resistant patients, thus, providing a prediction tool. As the anticancer drugs arsenal can offer alternatives in case of resistance to either paclitaxel or carboplatin, an early prediction can provide a significant advantage and should improve treatment. The algorithm assists this unmet need and helps predict whether a patient will respond to the treatment and may have an immediate clinically actionable application. Show less