Identification of human flap endonuclease 1 (FEN1) inhibitors using a machine learning based consensus virtual screening

Metacaspase (Pf MCA-1) as antimalarial drug target: An in silico approach and their biological validation

AIMS

Acquired drug resistance of Plasmodium is a global issue for the treatment of malaria. There are various proteases in the genome of Plasmodium falciparum (P. falciparum) including metacaspase-1 (PfMCA-1) that are essential and are being considered as an attractive drug target. It is aimed to identify novel therapeutics against malaria and their action on PfMCA-1 along with other apoptotic pathway events.

MAIN METHODS

High throughput virtual screening of 55,000 compounds derived from Maybridge library was performed against PfMCA-1. Based on the docking score, sixteen compounds were selected for in vitro antimalarial screening against drug sensitive and resistant strains of P. falciparum using SYBR green-based assay. Subsequently, three lead molecules were selected and subjected to the evaluation of cytotoxicity, caspase like protease activity, mitochondrial membrane potential, ROS generation and DNA fragmentation via TUNEL assay.

KEY FINDINGS

The in silico and in vitro approaches have brought forward some Maybridge library compounds with antiplasmodial activity most likely by enhancing the metacaspase activity. The compound CD11095 has shown better antimalarial efficacy, and KM06591 depicted higher caspase mediated killing, elevated TUNEL positive cells and moderate ROS generation. Mitochondrial membrane depolarization was augmented by RJC0069. Exposure of P. falciparum to CD11095, KM06591 and RJC0069 has ended up in parasite growth arrest via multiple mechanisms.

SIGNIFICANCE

It is proposed that the Maybridge molecules CD11095, KM06591 and RJC0069 have antimalarial activity. Their mechanism of action was found to be by enhancing the metacaspases-like protease activity, mitochondrial depolarization and DNA fragmentation which stipulates significant insights towards promising candidates for drug development.

Identification of Drug Compounds for Capsular Contracture Based on Text Mining and Deep Learning

BACKGROUND

Capsular contracture is a common and unpredictable complication after breast implant placement. Currently, the pathogenesis of capsular contracture is unclear, and the effectiveness of nonsurgical treatment is still doubtful. The authors' study aimed to investigate new drug therapies for capsular contracture by using computational methods.

METHODS

Genes related to capsular contracture were identified by text mining and GeneCodis. Then, the candidate key genes were selected through protein-protein interaction analysis in Search Tool for the Retrieval of Interacting Genes/Proteins and Cytoscape. Drugs targeting the candidate genes with relation to capsular contracture were screened out in Pharmaprojects. Based on the drug-target interaction analysis by DeepPurpose, candidate drugs with highest predicted binding affinity were obtained eventually.

RESULTS

The authors' study identified 55 genes related to capsular contracture. Gene set enrichment analysis and protein-protein interaction analysis generated eight candidate genes. One hundred drugs targeting the candidate genes were selected. The seven candidate drugs with the highest predicted binding affinity were determined by DeepPurpose, including tumor necrosis factor alpha antagonist, estrogen receptor agonist, insulin-like growth factor 1 receptor, tyrosine kinase inhibitor, and matrix metallopeptidase 1 inhibitor.

CONCLUSION

Text mining and DeepPurpose can be used as a promising tool for drug discovery in exploring nonsurgical treatment to capsular contracture.

CLINICAL QUESTION/LEVEL OF EVIDENCE

Therapeutic, V.

Machine learning-based predictive modeling, virtual screening and biological evaluation studies for identification of potential inhibitors of MMP-13

Matrix Metalloproteinase-13 (MMP-13) is a collagenase that regulates the homeostasis of the extracellular matrix (ECM) and basement membrane, as well as the breakdown of type II collagen. Recent research studies on the molecular and cellular mechanisms of cartilage degradation suggest that MMP-13 overexpression triggers osteoarthritis and is considered a promising target for osteoarthritis treatment. The present work employs machine learning-based virtual screening and structure-based rational drug design approaches to identify potential inhibitors of MMP-13 with diverse chemical scaffolds. The twelve top-scoring screened compounds were subjected to biological evaluation to validate the robustness and predictive modeling of ML-based Virtual Screening. It was observed that eight compounds exhibited approximately 44%-60% inhibition at 0.1 µM concentration, and the IC50 lies in the range of 1.9-2.3 µM against MMP-13. Interestingly, two of the compounds, DP01473 and RH01617, showed potent dose-dependent inhibitory activity. Compound DP01473 inhibited MMP-13 by 44%, 50%, and 70%, while compound RH01617 inhibited MMP-13 by 54%, 55%, and 57% at 0.1 μM, 1 μM, and 10 μM concentrations, respectively, and can be further optimized for the design and development of more potent MMP-13 inhibitors.Communicated by Ramaswamy H. Sarma.

Machine learning study: from the toxicity studies to tetrahydrocannabinol effects on Parkinson's disease

Aim: Investigating molecules having toxicity and chemical similarity to find hit molecules. Methods: The machine learning (ML) model was developed to predict the arylhydrocarbon receptor (AHR) activity of anti-Parkinson's and US FDA-approved drugs. The ML algorithm was a support vector machine, and the dataset was Tox21. Results: The ML model predicted apomorphine in anti-Parkinson's drugs and 73 molecules in FDA-approved drugs as active. The authors were curious if there is any molecule like apomorphine in these 73 molecules. A fingerprint similarity analysis of these molecules was conducted and found tetrahydrocannabinol (THC). Molecular docking studies of THC for dopamine receptor 1 (affinity = -8.2 kcal/mol) were performed. Conclusion: THC may affect dopamine receptors directly and could be useful for Parkinson's disease.

Lighting-up aptamer transcriptional amplification for highly sensitive and label-free FEN1 detection

Specific and sensitive detection of flap endonuclease 1 (FEN1), an enzyme biomarker involved in DNA replications and several metabolic pathways, is of high values for the diagnosis of various cancers. In this work, a fluorescence strategy based on transcriptional amplification of lighting-up aptamers for label-free, low background and sensitive monitoring of FEN1 is developed. FEN1 cleaves the 5' flap of the DNA complex probe with double flaps to form a notched dsDNA, which is ligated by T4 DNA ligase to yield fully complementary dsDNA. Subsequently, T7 RNA polymerase binds the promoter region to initiate cyclic transcriptional generation of many RNA aptamers that associate with the malachite green dye to yield highly amplified fluorescence for detecting FEN1 with detection limit as low as 0.22 pM in a selective way. In addition, the method can achieve diluted serum monitoring of low concentrations of FEN1, exhibiting its potential for the diagnosis of early-stage cancers.

Artificial intelligence in virtual screening: models versus experiments

A typical drug discovery project involves identifying active compounds with significant binding potential for selected disease-specific targets. Experimental high-throughput screening (HTS) is a traditional approach to drug discovery, but is expensive and time-consuming when dealing with huge chemical libraries with billions of compounds. The search space can be narrowed down with the use of reliable computational screening approaches. In this review, we focus on various machine-learning (ML) and deep-learning (DL)-based scoring functions developed for solving classification and ranking problems in drug discovery. We highlight studies in which ML and DL models were successfully deployed to identify lead compounds for which the experimental validations are available from bioassay studies.

Identification of a Chlorogenic Ester as a Monoamine Oxidase (MAO-B) Inhibitor by Integrating "Traditional and Machine Learning" Virtual Screening and In Vitro as well as In Vivo Validation: A Lead against Neurodegenerative Disorders?

Parkinson's disease (PD) is the furthermost motor disorder of adult-onset dementia connected to memory and other cognitive abilities. Monoamine oxidases (MAOs) have gained significant attention in recent years owing to their possible therapeutic use against PD. Expression of MAO-B has been found to be elevated in PD patients for increased uptake of dopamine, producing hydrogen peroxide and finally causing neuronal injury. In this work, two new compounds have been identified as leads against MAO-B, and one of those compounds has been validated in vitro and in vivo. From the Protein Data Bank, MAO-B protein structures complexed with selegiline, 6-hydroxy-N-propargyl-1(R)-aminoindan, or a chromen derivative have been selected as templates for shape-based virtual screening (SB-VS) against the Traditional Chinese Medicinal (TCM) natural database. In parallel, using machine learning, a molecular-descriptor-based support vector model (SVM) was prepared and screened. For this purpose, naïve Bayesian, logistic regression, and random forest strategies were employed with the best specific molecular descriptor, which yielded a model with an overall accuracy (Q) of 0.81. Two common hit compounds lead-1 and lead-2 resulting from both shape and SVM screenings were analyzed through molecular docking and molecular dynamics (MD) simulation (200 ns). Also, from trajectory analysis such as molecular mechanics generalized Born surface area (MMGB/SA) and the residual interaction network (RIN) analyzer, both leads were found to bind at the active site with a favorable correlated motion, including domain movements. Lead-2, which is a chlorogenic ester, was synthesized and found to have no cytotoxic effect up to 50 μg/mL on Neuro-2A cells. The significant reactive oxygen species (ROS) scavenging activity by lead-2 could be correlated to its neuroprotective efficacy. Its capacity to inhibit human MAO-B through a competitive mode could be observed. An experimental zebra fish model confirms the neuroprotection by lead-2 by assessing the locomotor activities under malathion influence and treatment of lead-2. Also, histopathology analysis revealed that lead-2 could slow down degeneration in the brain. The present study emphasizes that integrating machine learning in parallel with traditional virtual screening may be useful to identify effective lead compounds for a given target.

Fragment- and structure-based drug discovery for developing therapeutic agents targeting the DNA Damage Response

Cancer will directly affect the lives of over one-third of the population. The DNA Damage Response (DDR) is an intricate system involving damage recognition, cell cycle regulation, DNA repair, and ultimately cell fate determination, playing a central role in cancer etiology and therapy. Two primary therapeutic approaches involving DDR targeting include: combinatorial treatments employing anticancer genotoxic agents; and synthetic lethality, exploiting a sporadic DDR defect as a mechanism for cancer-specific therapy. Whereas, many DDR proteins have proven "undruggable", Fragment- and Structure-Based Drug Discovery (FBDD, SBDD) have advanced therapeutic agent identification and development. FBDD has led to 4 (with ∼50 more drugs under preclinical and clinical development), while SBDD is estimated to have contributed to the development of >200, FDA-approved medicines. Protein X-ray crystallography-based fragment library screening, especially for elusive or "undruggable" targets, allows for simultaneous generation of hits plus details of protein-ligand interactions and binding sites (orthosteric or allosteric) that inform chemical tractability, downstream biology, and intellectual property. Using a novel high-throughput crystallography-based fragment library screening platform, we screened five diverse proteins, yielding hit rates of ∼2-8% and crystal structures from ∼1.8 to 3.2 Å. We consider current FBDD/SBDD methods and some exemplary results of efforts to design inhibitors against the DDR nucleases meiotic recombination 11 (MRE11, a.k.a., MRE11A), apurinic/apyrimidinic endonuclease 1 (APE1, a.k.a., APEX1), and flap endonuclease 1 (FEN1).

Pathway-Based Drug-Repurposing Schemes in Cancer: The Role of Translational Bioinformatics

Cancer is a set of complex pathologies that has been recognized as a major public health problem worldwide for decades. A myriad of therapeutic strategies is indeed available. However, the wide variability in tumor physiology, response to therapy, added to multi-drug resistance poses enormous challenges in clinical oncology. The last years have witnessed a fast-paced development of novel experimental and translational approaches to therapeutics, that supplemented with computational and theoretical advances are opening promising avenues to cope with cancer defiances. At the core of these advances, there is a strong conceptual shift from gene-centric emphasis on driver mutations in specific oncogenes and tumor suppressors-let us call that the silver bullet approach to cancer therapeutics-to a systemic, semi-mechanistic approach based on pathway perturbations and global molecular and physiological regulatory patterns-we will call this the shrapnel approach. The silver bullet approach is still the best one to follow when clonal mutations in driver genes are present in the patient, and when there are targeted therapies to tackle those. Unfortunately, due to the heterogeneous nature of tumors this is not the common case. The wide molecular variability in the mutational level often is reduced to a much smaller set of pathway-based dysfunctions as evidenced by the well-known hallmarks of cancer. In such cases "shrapnel gunshots" may become more effective than "silver bullets". Here, we will briefly present both approaches and will abound on the discussion on the state of the art of pathway-based therapeutic designs from a translational bioinformatics and computational oncology perspective. Further development of these approaches depends on building collaborative, multidisciplinary teams to resort to the expertise of clinical oncologists, oncological surgeons, and molecular oncologists, but also of cancer cell biologists and pharmacologists, as well as bioinformaticians, computational biologists and data scientists. These teams will be capable of engaging on a cycle of analyzing high-throughput experiments, mining databases, researching on clinical data, validating the findings, and improving clinical outcomes for the benefits of the oncological patients.

PubChem in 2021: new data content and improved web interfaces

PubChem (https://pubchem.ncbi.nlm.nih.gov) is a popular chemical information resource that serves the scientific community as well as the general public, with millions of unique users per month. In the past two years, PubChem made substantial improvements. Data from more than 100 new data sources were added to PubChem, including chemical-literature links from Thieme Chemistry, chemical and physical property links from SpringerMaterials, and patent links from the World Intellectual Properties Organization (WIPO). PubChem's homepage and individual record pages were updated to help users find desired information faster. This update involved a data model change for the data objects used by these pages as well as by programmatic users. Several new services were introduced, including the PubChem Periodic Table and Element pages, Pathway pages, and Knowledge panels. Additionally, in response to the coronavirus disease 2019 (COVID-19) outbreak, PubChem created a special data collection that contains PubChem data related to COVID-19 and the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2).

Machine and deep learning approaches for cancer drug repurposing

Knowledge of the underpinnings of cancer initiation, progression and metastasis has increased exponentially in recent years. Advanced "omics" coupled with machine learning and artificial intelligence (deep learning) methods have helped elucidate targets and pathways critical to those processes that may be amenable to pharmacologic modulation. However, the current anti-cancer therapeutic armamentarium continues to lag behind. As the cost of developing a new drug remains prohibitively expensive, repurposing of existing approved and investigational drugs is sought after given known safety profiles and reduction in the cost barrier. Notably, successes in oncologic drug repurposing have been infrequent. Computational in-silico strategies have been developed to aid in modeling biological processes to find new disease-relevant targets and discovering novel drug-target and drug-phenotype associations. Machine and deep learning methods have especially enabled leaps in those successes. This review will discuss these methods as they pertain to cancer biology as well as immunomodulation for drug repurposing opportunities in oncologic diseases.

Prediction of Compound Bioactivities Using Heat-Diffusion Equation

Machine learning is expected to improve low throughput and high assay cost in cell-based phenotypic screening. However, it is still a challenge to apply machine learning to achieving sufficiently complex phenotypic screening due to imbalanced datasets, non-linear prediction, and unpredictability of new chemotypes. Here, we developed a prediction model based on the heat-diffusion equation (PM-HDE) to address this issue. The algorithm was verified as feasible for virtual compound screening using biotest data of 946 assay systems registered with PubChem. PM-HDE was then applied to actual screening. Based on supervised learning of the data of about 50,000 compounds from biological phenotypic screening with motor neurons derived from ALS-patient-induced pluripotent stem cells, virtual screening of >1.6 million compounds was implemented. We confirmed that PM-HDE enriched the hit compounds and identified new chemotypes. This prediction model could overcome the inflexibility in machine learning, and our approach could provide a novel platform for drug discovery.

•

Prediction model based on heat-diffusion equation (PM-HDE) was constructed

•

PM-HDE succeeded in increasing the hit ratio and identifying potent compounds

•

PM-HDE discovered new chemotypes in compound evaluation with an ALS-patient iPSC panel

•

PM-HDE could represent an algorithm for future drug discovery with AI

There remain many intractable diseases with no treatment available, including amyotrophic lateral sclerosis (ALS), for which the development of a cure is crucial. However, compound screening for drug development demands time, energy, and cost, and therefore artificial intelligence (AI) is expected to improve the efficiency of drug discovery. We built a novel machine-learning algorithm to predict hit compounds in compound screening using the heat-diffusion equation (HDE). This prediction model harbors the potential to solve issues that have been challenging for conventional machine learning and to exhibit accurate performance leading to the discovery of new drugs. In fact, the HDE model predicted hits with new chemotypes among millions of compounds for ALS therapeutics using a panel of large numbers of ALS patient-derived induced pluripotent stem cell models (ALS-patient iPSC panel). This algorithm could contribute to the acceleration and development of future drug discoveries using AI.

Cross-Species Complementation of Nonessential Yeast Genes Establishes Platforms for Testing Inhibitors of Human Proteins

Cross-species complementation can be used to generate humanized yeast, which is a valuable resource with which to model and study human biology. Humanized yeast can be used as an in vivo platform to screen for chemical inhibition of human protein drug targets. To this end, we report the systematic complementation of nonessential yeast genes implicated in chromosome instability (CIN) with their human homologs. We identified 20 human-yeast complementation pairs that are replaceable in 44 assays that test rescue of chemical sensitivity and/or CIN defects. We selected a human-yeast pair (hFEN1/yRAD27), which is frequently overexpressed in cancer and is an anticancer therapeutic target, to perform in vivo inhibitor assays using a humanized yeast cell-based platform. In agreement with published in vitro assays, we demonstrate that HU-based PTPD is a species-specific hFEN1 inhibitor. In contrast, another reported hFEN1 inhibitor, the arylstibonic acid derivative NSC-13755, was determined to have off-target effects resulting in a synthetic lethal phenotype with yRAD27-deficient strains. Our study expands the list of human-yeast complementation pairs to nonessential genes by defining novel cell-based assays that can be utilized as a broad resource to study human drug targets.

Upregulation of FEN1 Is Associated with the Tumor Progression and Prognosis of Hepatocellular Carcinoma

Background

Studies show that patients with hepatocellular carcinoma (HCC) have poor prognosis, particularly when patients are diagnosed at late stages of the disease development. The flap endonuclease 1 (FEN1) gene is overexpressed in multiple malignant tumors and may promote tumor aggressiveness. However, its expression profile and functional roles in HCC are still unclear. Here, we evaluated the molecular mechanisms of FEN1 in HCC.

Methods

The expression of FEN1 in HCC was evaluated using HCC mRNA expression data from TCGA and GEO databases. The expression of FEN1 was also confirmed by immunohistochemistry (IHC) using a tissue microarray (TMA) cohort with a total of 396 HCC patients. Kaplan-Meier analysis and univariate and multivariate Cox regression analyses were used to determine the correlation between FEN1 expression and survival rate of HCC patients. The molecular mechanism and biological functions of FEN1 in HCC were predicted using functional and pathway enrichment analysis in vitro experiments.

Results

FEN1 was overexpressed in multiple HCC cohorts at both mRNA and protein levels. The receiver operating characteristic (ROC) curve showed that FEN1 can serve as a diagnostic predictor of HCC. Meanwhile, patients with high FEN1 expression levels showed lower overall survival (OS) and relapse-free survival (RFS) rates than those with low FEN1 expression. More importantly, we found that FEN1 elevation was an independent prognostic factor for OS and RFS in HCC patients based on univariate and multivariate analyses, indicating that FEN1 might be a potential prognostic marker in HCC. Furthermore, knocking down FEN1 resulted in suppressed cell proliferation and migration in vitro. This could have been due to regulation expressions of c-Myc, survivin, and cyclin D1 genes, indicating that FEN1 may function as an oncogene through its role in the cell cycle and DNA replication pathway.

Conclusion

Our study indicated that high FEN1 expression might function as a biomarker for diagnosis and prognosis. In addition, the study confirms that FEN1 is an oncogene in HCC progression.

Advances with support vector machines for novel drug discovery

INTRODUCTION

Novel drug discovery remains an enormous challenge, with various computer-aided drug design (CADD) approaches having been widely employed for this purpose. CADD, specifically the commonly used support vector machines (SVMs), can employ machine learning techniques. SVMs and their variations offer numerous drug discovery applications, which range from the classification of substances (as active or inactive) to the construction of regression models and the ranking/virtual screening of databased compounds. Areas covered: Herein, the authors consider some of the applications of SVMs in medicinal chemistry, illustrating their main advantages and disadvantages, as well as trends in their utilization, via the available published literature. The aim of this review is to provide an up-to-date review of the recent applications of SVMs in drug discovery as described by the literature, thereby highlighting their strengths, weaknesses, and future challenges. Expert opinion: Techniques based on SVMs are considered as powerful approaches in early drug discovery. The ability of SVMs to classify active or inactive compounds has enabled the prioritization of substances for virtual screening. Indeed, one of the main advantages of SVMs is related to their potential in the analysis of nonlinear problems. However, despite successes in employing SVMs, the challenges of improving accuracy remain.

Versatile Types of DNA-Based Nanobiosensors for Specific Detection of Cancer Biomarker FEN1 in Living Cells and Cell-Free Systems

Flap structure-specific endonuclease 1 (FEN1) is overexpressed in various types of human cancer cells and has been recognized as a promising biomarker for cancer diagnosis in the recent years. In order to specifically detect the abundance and activity of this cancer-overexpressed enzyme, different types of DNA-based nanodevices were created during our investigations. It is shown in our studies that these newly designed biosensors are highly sensitive and specific for FEN1 in living cells as well as in cell-free systems. It is expected that these nanoprobes could be useful for monitoring FEN1 activity in human cancer cells, and also for cell-based screening of FEN1 inhibitors as new anticancer drugs.

Machine Learning-based Virtual Screening and Its Applications to Alzheimer's Drug Discovery: A Review

BACKGROUND

Virtual Screening (VS) has emerged as an important tool in the drug development process, as it conducts efficient in silico searches over millions of compounds, ultimately increasing yields of potential drug leads. As a subset of Artificial Intelligence (AI), Machine Learning (ML) is a powerful way of conducting VS for drug leads. ML for VS generally involves assembling a filtered training set of compounds, comprised of known actives and inactives. After training the model, it is validated and, if sufficiently accurate, used on previously unseen databases to screen for novel compounds with desired drug target binding activity.

OBJECTIVE

The study aims to review ML-based methods used for VS and applications to Alzheimer's Disease (AD) drug discovery.

METHODS

To update the current knowledge on ML for VS, we review thorough backgrounds, explanations, and VS applications of the following ML techniques: Naïve Bayes (NB), k-Nearest Neighbors (kNN), Support Vector Machines (SVM), Random Forests (RF), and Artificial Neural Networks (ANN).

RESULTS

All techniques have found success in VS, but the future of VS is likely to lean more largely toward the use of neural networks - and more specifically, Convolutional Neural Networks (CNN), which are a subset of ANN that utilize convolution. We additionally conceptualize a work flow for conducting ML-based VS for potential therapeutics for AD, a complex neurodegenerative disease with no known cure and prevention. This both serves as an example of how to apply the concepts introduced earlier in the review and as a potential workflow for future implementation.

CONCLUSION

Different ML techniques are powerful tools for VS, and they have advantages and disadvantages albeit. ML-based VS can be applied to AD drug development.