RKRajnish Kumar

Rajnish Kumar

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Rajnish Kumar has a total of 101 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Identification of Potential Necroptosis Inhibitors using Pharmacophore Model: An In-silico Approach

    by Manisha Pritam, Somenath Dutta, Rajnish Kumar

    Background:: Necrosis, a form of uncontrolled cell death, can be triggered by a variety of stressors, including infection, injury, toxins, and ischemia. Such necrotic events, particularly when induced by pathogenic infections, can lead to severe health complications. The mixed lineage kinase domain-like pseudokinase (MLKL) has been identified as a crucial drug target for mitigating necrosis. Objective:: The objective of this study is to identify potential MLKL inhibitors that act against necroptosis via a pharmacophore model and virtual screening. Methods:: In this study, we developed a ligand-based pharmacophore model to facilitate the identification of inhibitors that target MLKL. Comprehensive ADMET analysis, virtual screening, and molecular docking were employed to identify potential therapeutic candidates. Subsequently, molecular dynamics (MD) simulations and free energy calculation of a leading candidate were conducted using GROMACS and gmxMMPBSA tool to assess the stability of the MLKL-inhibitor complex. Results:: Our investigations identified 26 potential MLKL binders, with three compounds emerging as frontrunners on the basis of their favorable pharmacokinetic profiles, including high/low gastrointestinal absorption, optimal bioavailability, solubility, and non-hepatotoxicity. The MD simulations further corroborated the structural stability of the MLKL-drug complex. Conclusion:: The integrated computational approach adopted here could serve as a model for accelerating the discovery of drug candidates in other therapeutic areas as well. These findings necessitate further experimental validation before progressing to clinical trials.


  • Open Access

    Investigating molecular features that influence blood − brain barrier permeability of compounds

    by Deeksha Saxena, Anju Sharma, Mohammed Haris Siddiqui, Rajnish Kumar

    Introduction: The blood–brain barrier (BBB) is a semipermeable border that is responsible for maintaining central nervous system (CNS) homeostasis in the brain. Screening compounds based on their BBB permeability is an important consideration for CNS-acting drug development. Several studies have attempted to link physicochemical properties to specific BBB permeability; however, there is no widely accepted rule that can determine how and to what extent molecular properties affect the BBB permeability of compounds. To understand the complex phenomenon of BBB permeability, we explored the vast molecular space of the compounds to determine whether some features could differentiate the compounds based on their BBB permeability. Materials and Methods: A dataset of 1951 compounds containing 1246 BBB-permeable and 705 BBB-nonpermeable molecules was used in the study. Each compound encoded 499 molecular features. Feature selection was performed using feature selection algorithms, feature-to-feature, and feature-to-permeability correlation analysis. The findings of the feature selection algorithms were merged to select the best set of 53 features. Results: The descriptive analysis of the molecular features suggests that nCXr (number of X on ring C[sp3]) feature values for BBB nonpermeable compounds are zero for all considered compounds except for compounds with PubChem ID 71260, Flurithromycin. In addition, the majority of compounds were found to have nCrq (number of ring quaternary C[sp3]) feature values of zero for BBB nonpermeable compounds. For BBB-permeable compounds, MACCS fingerprints 8 feature values for all 1951 compounds were found to be zero except for the compound with PubChem ID 146291, Dezinamide. Conclusion: The descriptive and nonparametric tests confirm that molecular feature distributions are significantly different for BBB permeable and BBB nonpermeable compounds. The following core competencies are addressed in this article: Medical knowledge.


  • Open Access

    CoVSeverity-Net: an efficient deep learning model for COVID-19 severity estimation from Chest X-Ray images

    by Sagar Deep Deb, Rajib Kumar Jha, Rajnish Kumar, Prem S. Tripathi, Yash Talera, Manish Kumar

    Purpose COVID-19 is not going anywhere and is slowly becoming a part of our life. The World Health Organization declared it a pandemic in 2020, and it has affected all of us in many ways. Several deep learning techniques have been developed to detect COVID-19 from Chest X-Ray images. COVID-19 infection severity scoring can aid in establishing the optimum course of treatment and care for a positive patient, as all COVID-19 positive patients do not require special medical attention. Still, very few works are reported to estimate the severity of the disease from the Chest X-Ray images. The unavailability of the large-scale dataset might be a reason. Methods We aim to propose CoVSeverity-Net, a deep learning-based architecture for predicting the severity of COVID-19 from Chest X-ray images. CoVSeverity-Net is trained on a public COVID-19 dataset, curated by experienced radiologists for severity estimation. For that, a large publicly available dataset is collected and divided into three levels of severity, namely Mild, Moderate, and Severe. Results An accuracy of 85.71% is reported. Conducting 5-fold cross-validation, we have obtained an accuracy of 87.82 ± 6.25%. Similarly, conducting 10-fold cross-validation we obtained accuracy of 91.26 ± 3.42. The results were better when compared with other state-of-the-art architectures. Conclusion We strongly believe that this study has a high chance of reducing the workload of overworked front-line radiologists, speeding up patient diagnosis and treatment, and easing pandemic control. Future work would be to train a novel deep learning-based architecture on a larger dataset for severity estimation.


  • Epigenetic Modifications by Estrogen and Androgen in Alzheimer’s Disease

    by Rajnish Kumar, Faiza Fatima, Garima Yadav, Simran Singh, Subhagata Haldar, Athanasios Alexiou, Ghulam Md Ashraf

    For the development and maintenance of neuron networks in the brain, epigenetic mechanisms are necessary, as indicated by recent findings. This includes some of the high-order brain processes, such as behavior and cognitive functions. Epigenetic mechanisms could influence the pathophysiology or etiology of some neuronal diseases, altering disease susceptibility and therapy responses. Recent studies support epigenetic dysfunctions in neurodegenerative and psychiatric conditions, such as Alzheimer's disease (AD). These dysfunctions in epigenetic mechanisms also play crucial roles in the transgenerational effects of the environment on the brain and subsequently in the inheritance of pathologies. The possible role of gonadal steroids in the etiology and progression of neurodegenerative diseases, including Alzheimer’s disease, has become the subject of a growing body of research over the last 20 years. Recent scientific findings suggest that epigenetic changes, driven by estrogen and androgens, play a vital role in brain functioning. Therefore, exploring the role of estrogen and androgen-based epigenetic changes in the brain is critical for the deeper understanding of AD. This review highlights the epigenetic modifications caused by these two gonadal steroids and the possible therapeutic strategies for AD.


  • Decoding Seven Basic Odors by Investigating Pharmacophores and Molecular Features of Odorants

    by Anju Sharma, Rajnish Kumar, Pritish Kumar Varadwaj

    Background: The odors we perceive are primarily the result of a mixture of odorants. There can be one or multiple odors associated with an odorant. Several studies have attempted to link odorant physicochemical properties to specific olfactory perception; however, no universal rule that can determine how and to what extent molecular properties affect odor perception exists. Objective: This study aims to identify important and common features of odorants with seven basic odors (floral, fruity, minty, nutty, pungent, sweet, woody) to comprehend the complex topic of odors better. Methods: We adopted an in-silico approach to study key and common odorants features with seven fundamental odors (floral, fruity, minty, nutty, pungent, sweet, and woody). A dataset of 1136 odorants having one of the odors was built and studied. Results: A set of nineteen structural features has been proposed to identify seven fundamental odors rapidly. The findings also indicated associations between odors, and specific molecular features associated with each group of odorants and shared spatial distribution of odor features. Conclusion: This study revealed olfactory associations, unique chemical properties linked with each set of odorants, and a common spatial distribution of odor features for considered odors.


  • Recent Applications of Artificial Intelligence in Early Cancer Detection

    by Nausheen Khanam, Rajnish Kumar

    Cancer is a deadly disease that is often caused by the accumulation of various genetic mutations and pathological alterations. The death rate can only be reduced when it is detected in the early stages, because cancer treatment when the tumor has not metastasized in many regions of the body is more effective. However, early cancer detection is fraught with difficulties. Advances in artificial intelligence (AI) have developed a new scope for efficient and early detection of such a fatal disease. AI algorithms have a remarkable ability to perform well on a variety of tasks that are presented or fed to the system. Numerous studies have produced machine learning and deep learning-assisted cancer prediction models to detect cancer from previously accessible data with better accuracy, sensitivity, and specificity. It has been observed that the accuracy of prediction models in classifying fed data as benign, malignant, or normal is improved by implementing efficient image processing techniques and data segmentation augmentation methodologies, along with advanced algorithms. In this review, recent AI-based models for the diagnosis of the most prevalent cancers in the breast, lung, brain, and skin have been analysed. Available AI techniques, data preparation, modeling processes, and performance assessments have been included in the review.


  • Recent Applications of Artificial Intelligence in the Detection of Gastrointestinal, Hepatic and Pancreatic Diseases

    by Rajnish Kumar, Farhat Ullah Khan, Anju Sharma, Izzatdin B.A. Aziz, Nitesh Kumar Poddar

    : There has been substantial progress in artificial intelligence (AI) algorithms and their medical sciences applications in the last two decades. AI-assisted programs have already been established for remote health monitoring using sensors and smartphones. A variety of AI-based prediction models are available for gastrointestinal, inflammatory, non-malignant diseases, and bowel bleeding using wireless capsule endoscopy, hepatitis-associated fibrosis using electronic medical records, and pancreatic carcinoma utilizing endoscopic ultrasounds. AI-based models may be of immense help for healthcare professionals in the identification, analysis, and decision support using endoscopic images to establish prognosis and risk assessment of patients’ treatment employing multiple factors. Enough randomized clinical trials are warranted to establish the efficacy of AI-algorithms assisted and non-AI-based treatments before approval of such techniques from medical regulatory authorities. In this article, available AI approaches and AI-based prediction models for detecting gastrointestinal, hepatic, and pancreatic diseases are reviewed. The limitations of AI techniques in such diseases’ prognosis, risk assessment, and decision support are discussed.


  • Development of Machine Learning Based Blood-brain Barrier Permeability Prediction Models Using Physicochemical Properties, MACCS and Substructure Fingerprints

    by Deeksha Saxena, Anju Sharma, Mohammed Haris Siddiqui, Rajnish Kumar

    Background: Blood-Brain Barrier (BBB) protects the central nervous system from systemic circulation and maintains the homeostasis of the brain. BBB permeability is one of the essential characteristics of drugs acting on the central nervous system to indicate if the drug could reach the brain or not. The available laboratory methods for the prediction of BBB permeability are accurate but expensive and time-consuming. Therefore, many attempts have been made over the years to predict the BBB permeability of compounds using computational approaches. The accuracy of the prediction models with external dataset has always been an issue with the prediction models. Objective: To develop Machine learning-based BBB permeability prediction model using physicochemical properties and molecular fingerprints Methods: Support vector machine (SVM), k-nearest neighbor (kNN), Random forest (RF), and Naïve Bayes (NB) algorithms were applied on a large dataset of 1978 compounds using 1917 feature vectors containing physicochemical properties, MACCS fingerprints, and substructure fingerprints to predict the BBB permeability. Results and Discussion: The comparative analysis of performance metrics of developed models suggested that SVM with the radial basis function kernel performed better than the kNN, RF, and NB algorithms. The BBB permeability prediction model's accuracy with the SVM was 96.77%. The prediction performance of the model developed in this study was found better than the existing machine learning-based BBB permeability prediction models. Conclusion: The prediction model developed in this study could be useful for screening compounds based on their BBB permeability at the preliminary stages of drug design and development.


  • Deep Learning in Disease Diagnosis: Models and Datasets

    by Deeksha Saxena, Mohammed Haris Siddiqui, Rajnish Kumar

    Background: Deep learning (DL) is an Artificial neural network-driven framework with multiple levels of representation for which non-linear modules combined in such a way that the levels of representation can be enhanced from lower to a much abstract level. Though DL is used widely in almost every field, it has largely brought a breakthrough in biological sciences as it is used in disease diagnosis and clinical trials. DL can be clubbed with machine learning, but at times both are used individually as well. DL seems to be a better platform than machine learning as the former does not require an intermediate feature extraction and works well with larger datasets. DL is one of the most discussed fields among scientists and researchers these days for diagnosing and solving various biological problems. However, deep learning models need some improvisation and experimental validations to be more productive. Objective: To review the available DL models and datasets that are used in disease diagnosis. Methods: Available DL models and their applications in disease diagnosis were reviewed discussed and tabulated. Types of datasets and some of the popular disease-related data sources for DL were highlighted. Results: We have analyzed the frequently used DL methods, data types, and discussed some of the recent deep learning models used for solving different biological problems. Conclusion: The review presents useful insights about DL methods, data types, and selection of DL models for the disease diagnosis.