Cancer Drug Design Research Articles

Artificial Intelligence–Driven Computational Approaches in the Development of Anticancer Drugs

The integration of AI has revolutionized cancer drug development, transforming the landscape of drug discovery through sophisticated computational techniques. AI-powered models and algorithms have enhanced computer-aided drug design (CADD), offering unprecedented precision in identifying potential anticancer compounds. Traditionally, cancer drug design has been a complex, resource-intensive process, but AI introduces new opportunities to accelerate discovery, reduce costs, and optimize efficiency. This manuscript delves into the transformative applications of AI-driven methodologies in predicting and developing anticancer drugs, critically evaluating their potential to reshape the future of cancer therapeutics while addressing their challenges and limitations.

Topological coindices and QSPR analysis for some potential drugs used in lung cancer treatment via CoM and CoNM-polynomials

Topological indices are used to convert a chemical structure into a real number, usually to study the physicochemical and biological properties of molecules. The groundwork is prepared for the interpretation of the obtained data by processing with Quantitative Structure Property/Activity Relationship (QSPR/QSAR). In this study, the drugs lorlatinib, gefitinib, sotorasib, pralsetinib, crizotinib, adagrasib, alectinib, brigatinib, dacomitinib and entrectinib, which are potential to be used in the treatment of lung cancer, are discussed. Topological coindices are calculated with the help of CoM and CoNM polynomials obtained with the graph structures of these drugs. The relationship between topological coindices and physicochemical properties such as evaporation enthalpy, flash point, molar refraction, polarisation, surface tension, molar volume are investigated by QSPR analysis. At this stage, linear, logarithmic and quadratic regression methods have been used. The results show that the values of these topological indices are highly correlated with certain physicochemical properties of the used some drugs in the treatment of lung cancer. In addition, using comparative analysis, the actual values and the values calculated with the help of topological indices have been examined in terms of predictive ability. The findings of this search demonstrate topological indices’ potential as tools for cancer drug discovery and design.

Novel Computational Methods for Cancer Drug Design.

Cancer is a complex and debilitating disease that is one of the leading causes of death in the modern world. Computational methods have contributed to the successful design and development of several drugs. The recent advances in computational methodology, coupled with the avalanche of data being acquired through high throughput genomics, proteomics, and metabolomics, are likely to increase the contribution of computational methods toward the development of more effective treatments for cancer. Recent advances in the application of neural networks for the prediction of the native conformation of proteins have provided structural information regarding the complete human proteome. In addition, advances in machine learning and network pharmacology have provided novel methods for target identification and for the utilization of biological, pharmacological, and clinical databases for the design and development of drugs. This is a review of the key advances in computational methods that have the potential for application in the design and development of drugs for cancer.

Cancer drug sensitivity prediction from routine histology images

Drug sensitivity prediction models can aid in personalising cancer therapy, biomarker discovery, and drug design. Such models require survival data from randomised controlled trials which can be time consuming and expensive. In this proof-of-concept study, we demonstrate for the first time that deep learning can link histological patterns in whole slide images (WSIs) of Haematoxylin & Eosin (H&E) stained breast cancer sections with drug sensitivities inferred from cell lines. We employ patient-wise drug sensitivities imputed from gene expression-based mapping of drug effects on cancer cell lines to train a deep learning model that predicts patients’ sensitivity to multiple drugs from WSIs. We show that it is possible to use routine WSIs to predict the drug sensitivity profile of a cancer patient for a number of approved and experimental drugs. We also show that the proposed approach can identify cellular and histological patterns associated with drug sensitivity profiles of cancer patients.

Computer aided drug design for breast cancer

Computer aided drug design for breast cancer

Unrevealing the multitargeted potency of 3-1-BCMIYPPA against lung cancer structural maintenance and suppression proteins through pharmacokinetics, QM-DFT, and multiscale MD simulation studies.

Lung cancer, a relentless and challenging disease, demands unwavering attention in drug design research. Single-target drugs have yielded limited success, unable to effectively address this malignancy's profound heterogeneity and often developed resistance. Consequently, the clarion call for lung cancer drug design echoes louder than ever, and multitargeted drug design emerges as an imperative approach in this landscape, which is done by concurrently targeting multiple proteins and pathways and offering a beacon of hope. This study is focused on the multitargeted drug designing approach by identifying drug candidates against human cyclin-dependent kinase-2, SRC-2 domains of C-ABL, epidermal growth factor and receptor extracellular domains, and insulin-like growth factor-1 receptor kinase. We performed the multitargeted molecular docking studies of Drug Bank compounds using HTVS, SP and XP algorithms and poses filter with MM\GBSA against all proteins and identified DB02504, namely [3-(1-Benzyl-3-Carbamoylmethyl-2-Methyl-1h-Indol-5-Yloxy)-Propyl-]-Phosphonic Acid (3-1-BCMIYPPA) as multitargeted lead with docking and MM\GBSA score range from -8.242 to -6.274 and -28.2 and -44.29 Kcal/mol, respectively. Further, the QikProp-based pharmacokinetic computations and QM-based DFT showed acceptance results against standard values, and interaction fingerprinting reveals that THR, MET, GLY, VAL, LEU, GLU and ASP were among the most interacting residues. The NPT ensemble-based 100ns MD simulation in a neutralised state with an SPC water model has also shown a stable performance and produced deviation and fluctuations <2Å with huge interactions, making it a promising multitargeted drug candidate-however, experimental studies are suggested.

Characteristic Binding Landscape of Estrogen Receptor-α36 Protein Enhances Promising Cancer Drug Design.

Breast cancer (BC) remains the most common cancer among women worldwide, and estrogen receptor-α expression is a critical diagnostic factor for BC. Estrogen receptor (ER-α36) is a dominant-negative effector of ER-α66-mediated estrogen-responsive gene pathways. ER-α36 is a novel target that mediates the non-genomic estrogen signaling pathway. However, the crystallized structure of ER-α36 remains unavailable for molecular studies. ER-positive and triple-negative BC tumors aggressively resist the FDA-approved drugs; therefore, highly potent structure-based inhibitors with preeminent benefits over toxicity will preferably replace the current BC treatment. Broussoflanol B (BFB), a B. papyrifera bark compound, exhibits potent growth inhibitory activity in ER-negative BC cells by inducing cell cycle arrest. For the first time, we unravel the comparative dynamic events of the enzymes' structures and the binding mechanisms of BFB when bound to the ER-α36 and ER-α66 ligand-binding domain using an all-atom molecular dynamics simulations approach and MM/PBSA-binding-free energy calculations. The dynamic findings have revealed that ER-α36 and ER-α66 LBD undergo timescale "coiling", opening and closing conformations favoring the high-affinity BFB-bound ER-α36 (ΔG = -52.57 kcal/mol) compared to the BFB-bound ER-α66 (ΔG = -42.41 kcal/mol). Moreover, the unbound (1.260 Å) and bound ER-α36 (1.182 Å) exhibit the highest flexibilities and atomistic motions relative to the ER-α66 systems. The RMSF (Å) of the unbound ER-α36 and ER-α66 exhibit lesser stabilities than the BFB-bound systems, resulting in higher structural flexibilities and atomistic motions than the bound variants. These findings present a model that describes the mechanisms by which the BFB compound induces downregulation-accompanied cell cycle arrest at the Gap0 and Gap1 phases.

Homology Modeling and Structure Based Drug Design for Human Gastric Cancer

Abstract: This research article delves into the multifaceted world of structural biology and bioinformatics, exploring a diverse array of tools and resources employed to decipher the intricacies of proteins and their implications in health and disease. The paper navigates through various computational tools and databases used for sequence analysis, structural analysis, mutation site detection, and molecular docking, shedding light on their individual contributions in unraveling the secrets of proteins. COBALT serves as the initial compass, guiding researchers in the alignment of protein sequences, identifying conserved domains, and elucidating structural features in proteins. The exploration continues, with a focus on tools such as RasMol, PyMol, and Pharmit. This research article explores a range of bioinformatics tools and databases crucial for elucidating the complex world of proteins and their involvement in diseases like gastric cancer. It begins by highlighting the pivotal role of the Catalogue of Somatic Mutations in Cancer (COSMIC) in mutation site detection, providing a comprehensive repository of somatic mutations in cancer. The Kyoto Encyclopedia of Genes and Genomes (KEGG) complements this with a wealth of biological data and pathways. Shifting the focus to protein stability and dynamics, the article introduces DynaMUT, a computational tool employing molecular dynamics simulations to predict mutation impacts on protein behavior. Lastly, SwissDock takes the stage for drug discovery, facilitating the prediction and analysis of interactions between small molecules and target proteins. Collectively, these tools and databases offer an interdisciplinary lens through which researchers unravel protein intricacies and their relevance in diseases, exemplifying the indispensable role of structural biology and bioinformatics in advancing biological understanding.

Computational Methods for Inferring and Reconstructing Gene Regulatory Networks

Gene regulatory network (GRN) describes dynamic and complex gene interactions that determine the functions of cells. Ergo, understanding of GRNs has played a great role in cancer treatment, drug design, and gene research. However, the GRN study suffers from a lack of experiment measurement data and the complexity of the model. Computational approaches have evolved in recent years to promote the study of GRN. In this review, we summarized popular Computational approaches for GRN reconstruction. We started with traditional bioinformatic methods, such as Bayesian networks and mutual information methods. Later, we introduced how today's hot technology in the computer field - machine learning benefited GRN research. Tree-based approaches and other machine-learning methods are elaborated on in this section. We discussed not only the advantages and progression brought by various methods but also the drawbacks and limitations, such as the accuracy and robustness of GRN reconstruction. We expect to inspire readers for improved GRN study approaches via our introduction to this field.

Growing wiser with age: Results from the ACCELERATE Fostering Age Inclusive Research Group clinical trial survey.

e13596 Background: Adolescent and Young Adult (AYA) cancer patients are disproportionately excluded from clinical trials because of trial age limits that prevent access across the paediatric and adult oncology divide. Working under ACCELERATE, the international collaborative working to improve paediatric cancer drug design and regulation, the Fostering Age Inclusive Research (FAIR) group's aim is to reduce this inequality in access. Here, we report an international survey of AYA oncology professionals, and identify key barriers to age-inclusive participation in clinical trials. Methods: An online survey was created by ACCELERATE-FAIR trials working group members, and subsequently distributed to academic and industry professionals involved in AYA oncology through international networks including the ACCELERATE multi-stakeholder platform, ITCC, and cancer-specific research groups. Demographic factors were recorded, and participants were asked to consider whether listed potential barriers to AYA inclusion are ‘thought’ (presumed/expected) or ‘real’ in practice. Responses were recorded using in-built survey software. Results: The 124 respondents were from Europe (75%), America (22%; North America, Brazil), Algeria, India and Australia. 66 respondents (53%) had participated in opening an ‘adult’ phase I/II which permitted inclusion of adolescents ( &lt; 18 years old), and 63 (51%) had opened a ‘paediatric’ phase I/II trial that included adult cancer patients. Key ‘thought’ barriers to AYA inclusion in early phase (I/II) adult oncology trials largely mirrored ‘real’ barriers, such as “Limited incidence of the disease in adolescents (ages 12 to 17)” and “Trials approved in certain institutions or countries only for 18 years old and above”. A key ‘real’ barrier to the inclusion of AYA patients was “Reluctance from medical oncologists”, identified by 21 responders. Important disparities in the ‘thought’ and ‘real’ barriers to AYA enrolment were also highlighted; “No appropriate adult oncology network” was identified by 2 respondents as a ‘thought’ barrier, and by 13 as a ‘real’ barrier. Importantly, only 35% of respondents were aware of the FDA’s guidance on the inclusion of 12-17 year old patients in adult early-phase trials. Conclusions: This international drug development multi-stakeholder survey highlighted key barriers to clinical trial access in AYA oncology. Whilst more than half of respondents reported being involved in trials which were AYA inclusive, there were clear disparities in understanding the ‘thought’ and ‘real’ barriers to trial entry. Key issues included a lack of medical oncologists responding to this survey. Whilst the issues surrounding AYA inclusion in clinical trials remain, we illustrate key goals for future improvement such as improving understanding around FDA guidance in this area and collaborating further with medical oncologists.

Pharmacophore-based Identification of Potential Mutant Isocitrate Dehydrogenases I/2 Inhibitors: An Explorative Avenue in Cancer Drug Design.

Heterozygous mutations in the cytoplasmic and mitochondrial isoforms of isocitrate dehydrogenase enzymes 1 and 2 subtypes have been extensively exploited as viable druggable targets, as they decrease the affinity of isocitrate and higher affinity of D-2-hydroxyglutarate, an oncometabolite. Vorasidenib (AG-881) has recently been reported as a promising dual inhibitor of mutant isocitrate dehydrogenase 1 and 2 with the ability to penetrate the blood-brain barrier towards the treatment of low-grade glioma. In order to combat drug resistance and toxicity levels, this compelled us to further investigate this substance as a basis for the creation of potential selective inhibitors of mutant isocitrate dehydrogenases 1 and 2. By employing a wide range of computational techniques, binding moieties of AG-881 that contributed towards its selective binding to isocitrate dehydrogenase enzymes 1 and 2 were identified and subsequently used to generate pharmacophore models for the screening of potential inhibitor drugs that were further assessed by their pharmacokinetics and physicochemical properties. AG-881 was identified as the most favorable candidate for isocitrate dehydrogenase enzyme 1, exhibiting a binding free energy of -28.69 kcal/mol. ZINC93978407 was the most favorable candidatefor isocitrate dehydrogenase enzyme 2, displaying a strong binding free energy of -27.10 kcal/mol. ZINC9449923 and ZINC93978407 towards isocitrate dehydrogenase enzyme 1 and 2 showed good protein structural stability with a low radius of gyration values relative to AG-881. We investigated that ZINC9449923 of isocitrate dehydrogenase enzyme 1 and ZINC 93978407 of isocitrate dehydrogenase enzyme 2 could serve as promising candidates for the treatment of lower-grade glioma as they cross the blood-brain barrier, and present with lower toxicity levels relative to AG-881.

Abstract 135: Elucidating tumor evolution in pediatric cancers using stochastic models and mutation accumulation experiments

Abstract Ontology-based approaches have been utilized for identifying cancer genes. However, among the thousands of mutations in pediatric cancer genes, accurate prediction of driver genes is one of the biggest challenges. A binary logistic regression model was developed to distinguish pediatric and non-pediatric cancer genes. To build the predictive model, Gene Ontology (GO) enrichment analysis was performed, followed by the PANTHER overrepresentation test, using PANTHER GO-slim, PANTHER, Reactome pathways, and three sets of specific variables, the lists of pediatric cancer genes found in the germline, relapsed, and chemotherapy-resistant cells, respectively. This statistical model was pediatric cancer-specific, confirming known driver genes across cancers. In addition, mathematical models were developed using stochastic differential equation approaches and computational simulations to extend our understanding of the evolutionary dynamics during pediatric tumorigenesis. Moreover, our stochastic models in childhood cancers were validated by mutation accumulation experiments using E. coli strains carrying a mutation in replication restart genes. Finally, this study that elucidates tumor evolution in pediatric cancers could have profound implications for cancer therapy and drug design. Citation Format: Ana Beatriz Massei, Jasmin Jovel Platero, Kyungchan Hong, Sofia Zeledon, Taha Afzal, Hyunjeong Cha, Seung-Hwan Kim. Elucidating tumor evolution in pediatric cancers using stochastic models and mutation accumulation experiments [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 135.

Classification of GTP-dependent K-Ras4B active and inactive conformational states.

Classifying reliably active and inactive molecular conformations of wildtype (WT) and mutated oncogenic proteins is a key, ongoing challenge in molecular cancer studies. Here, we probe the GTP-bound K-Ras4B conformational dynamics using long-time atomistic molecular dynamics (MD) simulations. We extract and analyze the detailed underlying free energy landscape of WT K-Ras4B. We use two key reaction coordinates, labeled d1 and d2 (i.e., distances coordinating the Pβ atom of the GTP ligand with two key residues, T35 and G60), shown to correlate closely with activities of WT and mutated K-Ras4B. However, our new K-Ras4B conformational kinetics study reveals a more complex network of equilibrium Markovian states. We show that a new reaction coordinate is required to account for the orientation of acidic K-Ras4B sidechains such as D38 with respect to the interface with binding effector RAF1 and rationalize the activation/inactivation propensities and the corresponding molecular binding mechanisms. We use this understanding to unveil how a relatively conservative mutation (i.e., D33E, in the switch I region) can lead to significantly different activation propensities compared with WT K-Ras4B. Our study sheds new light on the ability of residues near the K-Ras4B-RAF1 interface to modulate the network of salt bridges at the binding interface with the RAF1 downstream effector and, thus, to influence the underlying GTP-dependent activation/inactivation mechanism. Altogether, our hybrid MD-docking modeling approach enables the development of new in silico methods for quantitative assessment of activation propensity changes (e.g., due to mutations or local binding environment). It also unveils the underlying molecular mechanisms and facilitates the rational design of new cancer drugs.

Sericultural By-Products: The Potential for Alternative Therapy in Cancer Drug Design

Major progress has been made in cancer research; however, cancer remains one of the most important health-related burdens. Sericulture importance is no longer limited to the textile industry, but its by-products, such as silk fibroin or mulberry, exhibit great impact in the cancer research area. Fibroin, the pivotal compound that is found in silk, owns superior biocompatibility and biodegradability, representing one of the most important biomaterials. Numerous studies have reported its successful use as a drug delivery system, and it is currently used to develop three-dimensional tumor models that lead to a better understanding of cancer biology and play a great role in the development of novel antitumoral strategies. Moreover, sericin's cytotoxic effect on various tumoral cell lines has been reported, but also, it has been used as a nanocarrier for target therapeutic agents. On the other hand, mulberry compounds include various bioactive elements that are well known for their antitumoral activities, such as polyphenols or anthocyanins. In this review, the latest progress of using sericultural by-products in cancer therapy is discussed by highlighting their notable impact in developing novel effective drug strategies.

A Review on Nanotechnology in Cancer Diagnosis and Therapy: it’s Application

Cancer is a leading cause of death and poor quality of life globally. Even though several strategies are devised to reduce deaths, reduce chronic pain and improve the quality of life, there remains a shortfall in the adequacies of these cancer therapies. Among the cardinal steps towards ensuring optimal cancer treatment are early detection of cancer cells and drug application with high specificity to reduce toxicities. Due to increased systemic toxicities and refractoriness with conventional cancer diagnostic and therapeutic tools, other strategies including nanotechnology are being employed to improve diagnosis and mitigate disease severity. Over the years, immunotherapeutic agents based on nanotechnology have been used for several cancer types to reduce the invasiveness of cancerous cells while sparing healthy cells at the target site. Nanomaterials including carbon nanotubes, polymeric micelles and liposomes have been used in cancer drug design where they have shown considerable pharmacokinetic and pharmacodynamic benefits in cancer diagnosis and treatment. In this review, we outline the commonly used nanomaterials which are employed in cancer diagnosis and therapy. We have highlighted the suitability of these nanomaterials for cancer management based on their physicochemical and biological properties. We further reviewed the challenges that are associated with the various nanomaterials which limit their uses and hamper their translatability into the clinical setting in certain cancer types. Keywords: Nanomaterials, Nanotechnology, Cancer, Diagnosis, Treatment.

Systems Drug Design for Muscle Invasive Bladder Cancer and Advanced Bladder Cancer by Genome-Wide Microarray Data and Deep Learning Method with Drug Design Specifications.

Bladder cancer is the 10th most common cancer worldwide. Due to the lack of understanding of the oncogenic mechanisms between muscle-invasive bladder cancer (MIBC) and advanced bladder cancer (ABC) and the limitations of current treatments, novel therapeutic approaches are urgently needed. In this study, we utilized the systems biology method via genome-wide microarray data to explore the oncogenic mechanisms of MIBC and ABC to identify their respective drug targets for systems drug discovery. First, we constructed the candidate genome-wide genetic and epigenetic networks (GWGEN) through big data mining. Second, we applied the system identification and system order detection method to delete false positives in candidate GWGENs to obtain the real GWGENs of MIBC and ABC from their genome-wide microarray data. Third, we extracted the core GWGENs from the real GWGENs by selecting the significant proteins, genes and epigenetics via the principal network projection (PNP) method. Finally, we obtained the core signaling pathways from the corresponding core GWGEN through the annotations of the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway to investigate the carcinogenic mechanisms of MIBC and ABC. Based on the carcinogenic mechanisms, we selected the significant drug targets NFKB1, LEF1 and MYC for MIBC, and LEF1, MYC, NOTCH1 and FOXO1 for ABC. To design molecular drug combinations for MIBC and ABC, we employed a deep neural network (DNN)-based drug-target interaction (DTI) model with drug specifications. The DNN-based DTI model was trained by drug-target interaction databases to predict the candidate drugs for MIBC and ABC, respectively. Subsequently, the drug design specifications based on regulation ability, sensitivity and toxicity were employed as filter criteria for screening the potential drug combinations of Embelin and Obatoclax for MIBC, and Obatoclax, Entinostat and Imiquimod for ABC from their candidate drugs. In conclusion, we not only investigated the oncogenic mechanisms of MIBC and ABC, but also provided promising therapeutic options for MIBC and ABC, respectively.

Therapeutic and Diagnostic Analysis of Cadmium Sulfide Quantum Dots Conjugated with Cysteine, Anticancer Drug and Folate

Background: Nanotechnology is evolving in the field of cancer drug design and cancer therapy. The ultrafine nanoparticles that have a size range of 1-10nm are called Quantum Dots. The ability to fluorescence has deemed quantum dots as suitable candidate for diagnostic imaging. Upon proper structural arrangement these quantum dots can be engineered to detect specifically cancer cells and deliver anticancer agents to the targeted site for cancer cell apoptosis. Aim: Cadmium sulfide (CdS) nanoparticles conjugated with cysteine were prepared by wet method under high temperature and pressure Methods: Folic acid receptor has shown overexpression in multiple types of cancers therefore the binding of folate to the composite ensures that only the cancer cells are targeted and normal cells remain unaffected. HeLa cells were opted to check the composite activity. Results: Composite showed 23% cell death in the first 2 hours of delivery. FTIR analysis confirmed conjugation of CdS with cysteine and further conjugation of dacarbazine and folate to cysteine. The molecules of folic acid attached to cysteine could be measured to be 2.545× 1018 molecules which were attached to 0.996× 〖10〗^22 molecules of cysteine that were attached 1.66 x〖 10〗^(20 ) molecules of CdS. Similarly, 2.3103 × 1019 of doxorubicin were attached to 0.996× 〖10〗^22 molecules of of cysteine attached to 1.66 x〖 10〗^(20 ) molecules of CdS. Furthermore, the cytotoxic nature of Cadmium Sulfide also gives an advantage two way cancer cell death. Conclusion: Quantum dots attached to specific ligands that bind to cancer antigens, antibodies, proteins, Receptors etc. can be used for effective diagnosis of cancer. They can act as probe and detect thousands of molecules simultaneously by using only a small quantity of nanoComposite. Keywords: Cadmium sulfide, Cancer, Quantum dots, Dacarbazine

Ornithine aminotransferase and carbamoyl phosphate synthetase 1 involved in ammonia metabolism serve as novel targets for early stages of gastric cancer.

ObjectiveThe sensitivity and specificity of current biomarkers for gastric cancer were insufficient. The aim of the present study was to screen novel biomarkers and determine the diagnostic values of ornithine aminotransferase (OAT) and carbamoyl phosphate synthetase 1 (CPS1) for detecting gastric cancer.MethodsWith stable isotope tags, we labelled an initial discovery group of four paired gastric cancer tissue samples and identified with LC‐ESI‐MS/MS. A validation group of 159 gastric cancer samples and 30 healthy controls were used to validate the candidate targets. GSEA was used to explore the pathways activated in gastric cancer.ResultsFour hundred and thirty one proteins were found differentially expressed in gastric cancer tissues. Of these proteins, OAT and CPS1 were found over‐expressed in gastric cancer patients, with sensitivity of 70.4% (95% CI: 63.3%–77.6%) and specificity of 80.5% (95% CI: 74.3%–86.7%) for ornithine aminotransferase, and with sensitivity of 68.6% (95% CI: 61.3%–75.8%) and specificity of 73% (95% CI: 66%–79.9%) for carbamoyl phosphate synthetase 1. The co‐expression of OAT and CPS1 in gastric cancer tissues has a sensitivity of 81% (95% CI: 73.2%–88.8%) and specificity of 89% (95% CI: 83%–95%). Furthermore, both OAT and CPS1 were overexpressed in patients with local invasion T3 and T4 stages than those in patients with T1 and T2 stages. The co‐expression of OAT and CPS1 was strongly correlated with histological grade I 68% (95% CI: 58.7%–77.3%) and TNM stage I/II 52% (95% CI: 42%–62%). The areas under ROC curves were up to 0.758 for the co‐expression of OAT and CPS1 in gastric cancer. GSEA results showed that two gene sets and 30 gene sets were activated in OAT high‐ and CPS1 high‐expression patients with gastric cancer, respectively.ConclusionsThe present findings indicated a tight correlation between the co‐expression of OAT and CPS1 and the histological grade, local invasion, and TNM stages of gastric cancer. Therefore, OAT and CPS1 might be predictors for gastric cancer invasion and potential targets for anticancer drug design for gastric cancer.

Optimization Method of an Antibreast Cancer Drug Candidate Based on Machine Learning.

Breast cancer is a common but serious and even lethal disease. Fortunately, compared with other cancers, breast cancer treatments currently are relatively well developed. The use of specific drugs is typically essential in the majority of breast cancer treatment strategies. Given the aforementioned factors, it is important to continue researching effective antibreast cancer drug design. Machine learning-based computer-aided drug design is currently a common practice in both drug industries and academic institutes. According to the characteristics of breast cancer, we selected multiple candidate compounds; based on the corresponding molecular descriptors, biological activities, and pharmacokinetic properties, a dataset of inhibition potency and pharmacokinetic properties paired with multiple features of compounds was constructed. On this basis, the random forest method was utilized to choose greater-influenced feature embeddings; thus, 224 main operating variables were selected for further analysis; we then employed the efficient MobileNetV3 deep neural network as the backbone to establish the prediction models for the inhibition potency and pharmacokinetic properties of the compounds. After data preprocessing, the weights are obtained by training on the refined dataset. Finally, we define an optimization problem to discover compounds with the best properties. The problem is solved using the genetic algorithm with the acquired prediction model, and the solution value for the corresponding operating variables with the best clinical properties in theory is then obtained. Analysis demonstrates that our approach could be used to aid the screening process of antibreast cancer drug candidates.

Activity prediction of anti-cancer drug candidate ER&amp;lt;bold&amp;gt;&amp;alpha;&amp;lt;/bold&amp;gt; inhibitor

Breast cancer is the most common malignancy which threats the women's health worldwide. Studies have revealed that the estrogen receptor alpha subtype (ERα) plays an important role in breast development and is considered as an important target for breast cancer treatment. Compounds that can antagonize ERα activity may be candidates for breast cancer treatment. A quantitative structure-activity relationship prediction model is proposed to predict the bioactivity of compounds that can be applied to anti-breast cancer drugs under small samples and multi-characteristic conditions. First, the descriptive statistics and multicollinearity diagnosis are performed on the information of 729 molecular descriptors of 1 974 compounds, and the random forest method is used to screen 20 significant variables with variable importance measure that is greater than 0.01. Then, a CNN-based two-dimensional feature matrix is constructed, and a Bayesian hyperparametric optimization (BHO) method is used to perform hyperparametric optimization of the Bi-LSTM model. Finally, the prediction effect of model is analyzed and evaluated. The results show that compared with the GBDT integrated learning method, the prediction effect of Mul-BHO-Bi-LSTM integrated machine learning prediction model is better, and the model error indexes MSE, NRMSE, error mean, and error std are less than 0.15, and the correlated indicators <italic>R</italic>² and <italic>r</italic> are above 0.99, indicating that the integrated machine learning predictionmodel of Mul-BHO-Bi-LSTM has the good robustness and generalization, and the model can provide a method for the screening and design of anti-breast cancer drugs.