Computational Biology and Chemistry最新文献

{"title":"Incremental learning for acute lymphoblastic leukemia classification based on hybrid deep learning using blood smear image","authors":"Smritilekha Das,&nbsp;K. Padmanaban","doi":"10.1016/j.compbiolchem.2025.108456","DOIUrl":"10.1016/j.compbiolchem.2025.108456","url":null,"abstract":"<div><div>The prevalent type of blood cancer is called leukemia, which is caused by the irregular production of immature malignant cells in the bone marrow. This dangerous condition weakens the immune system, making the body susceptible to infections, and can lead to death if not treated quickly. Thus, immediate treatments are necessary to detect leukemia at the initial stage to control abnormal cell growth. Leukemia detection from microscopic images of blood smears of malignant leukemia cells is a time-consuming and tedious task. Thus, a Tangent Sand Cat Swarm Optimization-Long Short-Term Memory-LeNet (TSCO-L-LeNet) with incremental learning is designed for the precise classification of acute lymphoblastic leukemia. The proposed model offers cheaper, faster and safer diagnosis service as the use of blood smear images reduces the diagnosis time and improves accuracy. Here, the input image is pre-processed using the adaptive median filter and the Scribble2label is used to segment the image. Later, the augmentation of segmented image is performed and the feature extraction process is employed to extract the necessary features from the augmented image. Finally, the L-LeNet with incremental learning is executed for acute lymphoblastic leukemia classification from the extracted features, where the TSCO approach is used to train the weights of L-LeNet. The experimental results show that TSCO-L-LeNet achieved maximum performance of 0.987 for accuracy, 0.977 for True Negative Rate (TNR), 0.967 for recall, 0.033 for False Negative rate, 0.023 for False Positive rate, and 0.979 for precision.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108456"},"PeriodicalIF":2.6,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823821","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Black seed (Nigella sativa) extract enhances early and late apoptosis through activation of caspase-3 mediated regulatory pathway in LC540 cells: A network pharmacological and molecular docking approach","authors":"Sanjay Gopi ,&nbsp;S. Madesh ,&nbsp;Karthikeyan Ramamurthy ,&nbsp;Mikhlid H. Almutairi ,&nbsp;Bader O. Almutairi ,&nbsp;S. Karthick Raja Namasivayam ,&nbsp;Jesu Arockiaraj","doi":"10.1016/j.compbiolchem.2025.108455","DOIUrl":"10.1016/j.compbiolchem.2025.108455","url":null,"abstract":"<div><div>Testicular cancer continues to rise in incidence globally, and conventional chemotherapy is often associated with severe side effects that significantly impact patient’s quality of life. Identifying safer alternative therapies is becoming crucial day by day which leads to focus on naturally available phytocompounds with high bioactivity. Over the period of time, <em>Nigella sativa</em> (<em>N. sativa</em>) has garnered attention due to the presence of its rich bioactive compounds with antioxidant and anticancer properties, providing potential therapeutic benefits with minimal side effects. Since we used a network pharmacological based <em>in-silico</em> approach combined with <em>in-vitro</em> and <em>in-vivo</em> efficacy testing of <em>N. sativa</em> against testicular cancer. Molecular docking studies showed significant interactions between <em>N. sativa</em> phytochemicals and critical proteins involved in testicular and other cancer related pathways. Biochemical assays revealed decreased ROS levels with enhanced antioxidant enzyme activities such as SOD, CAT, GSH and reduced LDH levels. AO/PI staining further corroborated the enhanced apoptosis and necrosis rates in treated cells. m-RNA analysis demonstrated notable expression of inflammatory and apoptotic genes such as <em>casp-3</em> and key testicular markers such as <em>oct4, sox2</em> and other pro inflammatory cytokines. Histomorphological analysis of zebrafish testis showed decreased morphological alterations. With solid evidence of its anticancer effects through multiple biological mechanisms, including apoptosis induction, oxidative stress reduction, and oncogene suppression, these findings warrant further exploration of <em>N. sativa</em> as part of integrative cancer therapies to improve outcomes for patients with testicular cancer.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108455"},"PeriodicalIF":2.6,"publicationDate":"2025-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Insights from computational studies about structural determinants of steroidal inhibitors in 5-alpha-reductase type II","authors":"Elkin Sanabria-Chanaga ,&nbsp;Edwin L. Bonilla-Rozo","doi":"10.1016/j.compbiolchem.2025.108446","DOIUrl":"10.1016/j.compbiolchem.2025.108446","url":null,"abstract":"<div><div>5-alpha-reductase type II (5αR2) is an important protein involved in the reduction of testosterone to dihydrotestosterone, a product that promotes prostate growth and can lead to conditions such as prostate cancer and benign prostatic hyperplasia. This study presents a computational analysis of steroidal compounds with close structural relationships but notable differences in their biological activity. A set of molecules with reported half-maximal inhibitory concentrations, obtained under consistent conditions, was selected, and molecular docking and molecular dynamics simulations were performed. Considering the covalent inhibition mechanism of this protein, key atomic distances, root mean square deviations, and binding free energy were investigated to explain the significant differences in biological activity. The data suggest that the key to inhibitory capacity lies in the conformation that optimally facilitates bond formation between the NADPH cofactor and the α,β-unsaturated system of the inhibitors within the 5αR2 pocket. Considering that the protein pocket is rich in hydrophobic residues, introducing an atom such as fluorine, which increases the hydrophobicity of the ligand, may alter the favorable conformation within the pocket. This, in turn, could compromise the ability of the ligand to form a covalent bond with NADPH. Given the covalent nature of the inhibition mechanism, stability within the catalytic site plays a secondary role. Understanding these structural features is crucial for designing new potential 5αR2 inhibitors, particularly steroidal compounds, that aim to leverage a covalent mechanism of inhibition.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108446"},"PeriodicalIF":2.6,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PLM-IL4: Enhancing IL-4-inducing peptide prediction with protein language model","authors":"Ruiqi Liu ,&nbsp;Shankai Yan ,&nbsp;Zilong Zhang ,&nbsp;Junlin Xu ,&nbsp;Yajie Meng ,&nbsp;Qingchen Zhang ,&nbsp;Leyi Wei ,&nbsp;Quan Zou ,&nbsp;Feifei Cui","doi":"10.1016/j.compbiolchem.2025.108448","DOIUrl":"10.1016/j.compbiolchem.2025.108448","url":null,"abstract":"<div><div>Despite progress in developing antiviral drugs and vaccines, infections continue to be a significant challenge. Interleukin-4 (IL-4) is crucial for regulating immune responses and mediating allergic reactions. This research aims to improve the predictive accuracy of IL-4-inducing peptides by tackling data imbalance and enhancing feature extraction. Specifically, we introduce a new approach that utilizes SMOTE and ENN for balancing the dataset and applies a 30-layer ESM-2 model for extracting deep features. The extracted features are subsequently processed through a Gated Recurrent Unit (GRU) model, which is optimized through hyperparameter tuning. Our method achieves notable improvements, with an AUC of 0.98 and an accuracy of 93.1 %, highlighting its potential to support future immunotherapy and vaccine development efforts. The PLM-IL4 web server is freely accessible at <span><span>http://www.bioai-lab.com/PLM-IL4</span><svg><path></path></svg></span>, and the datasets used in this research are also available for download from the website.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108448"},"PeriodicalIF":2.6,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143799944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accelerating drug discovery targeting dihydroorotate dehydrogenase using machine learning and generative AI approaches","authors":"Gayathri Krishnamurthy Ganga","doi":"10.1016/j.compbiolchem.2025.108443","DOIUrl":"10.1016/j.compbiolchem.2025.108443","url":null,"abstract":"<div><div>Dihydroorotate dehydrogenase (DHODH) is a key enzyme in pyrimidine biosynthesis, making it an attractive drug target for cancer, autoimmune diseases, and infections. Traditional DHODH inhibitor discovery is slow and costly. Our study integrated machine learning (ML) and generative artificial intelligence (AI) to accelerate this process, enhancing efficiency and reducing costs. We employed Random Forest (RF), XGBoost (XGB), and Logistic Regression (LR) to predict pIC50 values, with RF achieving the highest accuracy (93 % test accuracy, 81 % on unseen molecules), demonstrating superior generalization. Using a Graph Convolutional Network-based Variational Autoencoder (GCN-VAE), we generated 59 unique drug-like molecules, five with pIC50 &gt; 7, expanding the chemical space beyond conventional screening.</div><div>Docking studies confirmed strong binding affinities, with the most promising newly generated molecule showing a binding energy of –11.1 kcal/mol and an inhibition constant (Ki) of 269.8 nM. Key interactions with residues such as ALA59, PHE36, TYR38, GLN47, and ARG36 further validated stability and inhibitory potential. This AI-driven workflow accelerates DHODH inhibitor discovery by significantly reducing screening time, enhancing molecular diversity, and improving predictive accuracy. Our approach presents a scalable, cost-effective strategy for developing novel therapeutics, offering a transformative shift in drug discovery.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108443"},"PeriodicalIF":2.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploring spirocyclic isoquinoline-piperidine compounds in tuberculosis therapy: ADMET profiling, docking, DFT, MD simulations, and MMGBSA analysis","authors":"Sri Mounika Bellapukonda ,&nbsp;Siva Singothu ,&nbsp;Anuradha Singampalli ,&nbsp;Rani Bandela ,&nbsp;Pardeep Kumar ,&nbsp;Venkata Madhavi Yaddanapudi ,&nbsp;Vasundhra Bhandari ,&nbsp;Srinivas Nanduri ,&nbsp;Mohamed Enneiymy ,&nbsp;Mohamed F. AlAjm ,&nbsp;Ali oubella","doi":"10.1016/j.compbiolchem.2025.108447","DOIUrl":"10.1016/j.compbiolchem.2025.108447","url":null,"abstract":"<div><div>Tuberculosis remains a global health challenge due to drug-resistant strains. MmpL3 inhibitors have emerged as promising anti-tubercular agents, and their clinical development has been hindered by poor microsomal stability. This study computationally designed and screened 40 spirocyclic analogs, and compared them with ICA38 and SQ109. In silico analyses, including docking, MD simulations, and DFT calculations, were conducted to assess their potential as anti-tubercular agents, highlighting promising candidates for further development. Docking studies using Glide software identified C21 (3,4- dichloro derivative) and C20 (5-chloro derivative) as promising candidates, exhibiting binding scores of −9.79 kcal/mol and −9.64 kcal/mol, respectively. Both compounds interacted with the active site residue Asp645 via hydrogen bonding and also formed a hydrophobic interaction. DFT results revealed that C21 displayed the balanced chemical reactivity, characterized by high dipole moment (3.63D), an optimal energy gap (0.18752 eV), softness and hardness (η = 0.09376 eV, σ = 10.666 eV⁻¹), high electron affinity (0.02305 eV), high electronegativity (0.11681 eV) and high ionization potential (0.21057 cV). On the other hand, C20 exhibited similar electronic properties with marginal differences than C21. MD simulations showed C21 and C20's stability (RMSD 2.4 Å and 2.2 Å, RMSF &lt;2.5 Å), indicating improved Arg344-Leu354 stability. Additionally, C21 and C20 maintained Asp645 interactions (91 %, 97 %) and showed strong binding with free energy values (MMGBSA: −72.23, −66.50 kcal/mol). These findings highlight the efficiency of the compounds C21 and C20 with strong binding affinity, favorable stability, and optimal electronic properties, making them promising candidates for further development of next-generation MmpL3 inhibitors.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108447"},"PeriodicalIF":2.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143792775","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Pinpointing potent hits for cancer immunotherapy targeting the TIGIT/PVR pathway using the XGBoost model, centroid-based virtual screening, and MD simulation","authors":"Xudong Lü ,&nbsp;Chenyu Wang ,&nbsp;Mengjia Tang ,&nbsp;Jing Li ,&nbsp;Zhiyong Xia ,&nbsp;Shuai Fan ,&nbsp;Yuanyuan Jin ,&nbsp;Zhaoyong Yang","doi":"10.1016/j.compbiolchem.2025.108450","DOIUrl":"10.1016/j.compbiolchem.2025.108450","url":null,"abstract":"<div><div>T cell immunoreceptor with immunoglobulin and ITIM domain (TIGIT) is one of the most promising targets for cancer immunotherapy. The combination of TIGIT and poliovirus receptor (PVR), which is highly expressed on the tumor surface, inhibits the killing of tumor cells by immune cells. Although antibody blocking the PVR/TIGIT immune checkpoint has shown encouraging anti-tumor effects, small molecules targeting TIGIT to block PVR/TIGIT have not yet been studied. In this study, diverse computational approaches were employed to identify potential inhibitors of this therapeutic targets. First, virtual alanine scanning was used to identify hotspot residues of TIGIT that were effective inhibitory sites. Second, the Extreme Gradient Boosting (XGBoost) classification model and the RO4 rule were used to initially exclude negative compounds. Then, centroid-based virtual screening was used in combination with absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction to identify the four most promising candidate molecules. Molecular dynamics simulation trajectory analysis showed stable dynamic behavior of the candidate molecules and proteins. Molecular mechanics and Poisson-Boltzmann surface area (MMPBSA) calculations showed that MCULE-5939418698 had the lowest binding free energy (-39.79 kcal/mol). Binding-conformation and energy-decomposition analyses indicated significant involvement of residues L47, Q53, V54 and N58 in inhibitor binding. Principal component analysis and free energy landscape analysis further demonstrated that the binding of MCULE-4861917955 made the system thermodynamically more favorable. Thus, we screened potential inhibitors targeting TIGIT and provide a fresh pipeline for future drug screening research.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108450"},"PeriodicalIF":2.6,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Metagenomics studies in aquaculture systems: Big data analysis, bioinformatics, machine learning and quantum computing","authors":"Orkid Coskuner-Weber ,&nbsp;Semih Alpsoy ,&nbsp;Ozgur Yolcu ,&nbsp;Egehan Teber ,&nbsp;Ario de Marco ,&nbsp;Spase Shumka","doi":"10.1016/j.compbiolchem.2025.108444","DOIUrl":"10.1016/j.compbiolchem.2025.108444","url":null,"abstract":"<div><div>The burgeoning field of aquaculture has become a pivotal contributor to global food security and economic growth, presently surpassing capture fisheries in aquatic animal production as evidenced by recent statistics. However, the dense fish populations inherent in aquaculture systems exacerbate abiotic stressors and promote pathogenic spread, posing a risk to sustainability and yield. This study delves into the transformative potential of metagenomics, a method that directly retrieves genetic material from environmental samples, in elucidating microbial dynamics within aquaculture ecosystems. Our findings affirm that metagenomics, bolstered by tools in big data analytics, bioinformatics, and machine learning, can significantly enhance the precision of microbial assessment and pathogen detection. Furthermore, we explore quantum computing’s emergent role, which promises unparalleled efficiency in data processing and model construction, poised to address the limitations of conventional computational techniques. Distinct from metabarcoding, metagenomics offers an expansive, unbiased profile of microbial biodiversity, revolutionizing our capacity to monitor, predict, and manage aquaculture systems with high accuracy and adaptability. Despite the challenges of computational demands and variability in data standardization, this study advocates for continued technological integration, thereby fostering resilient and sustainable aquaculture practices in a climate of escalating global food requirements.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"118 ","pages":"Article 108444"},"PeriodicalIF":2.6,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143776323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to ‘Decoding the Link between microbial secondary metabolites and colorectal cancer’ [Comput. Biol. Chem. 115 (2025) 1–7/108372]","authors":"Shengqin Wang ,&nbsp;Mingjiang Wu","doi":"10.1016/j.compbiolchem.2025.108445","DOIUrl":"10.1016/j.compbiolchem.2025.108445","url":null,"abstract":"","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"117 ","pages":"Article 108445"},"PeriodicalIF":2.6,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143756478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"pACPs-DNN: Predicting anticancer peptides using novel peptide transformation into evolutionary and structure matrix-based images with self-attention deep learning model","authors":"Shahid ,&nbsp;Maqsood Hayat ,&nbsp;Ali Raza ,&nbsp;Shahid Akbar ,&nbsp;Wajdi Alghamdi ,&nbsp;Nadeem Iqbal ,&nbsp;Quan Zou","doi":"10.1016/j.compbiolchem.2025.108441","DOIUrl":"10.1016/j.compbiolchem.2025.108441","url":null,"abstract":"<div><div>Globally, cancer remains a major health challenge due to its high mortality rates. Traditional experimental approaches and therapies are resource-intensive and often cause significant side effects. Anticancer peptides (ACPs) have emerged as alternative therapeutic agents owing to their selectivity, safety, and potential to mitigate drug resistance. In this paper, we propose pACPs-DNN, a novel attention mechanism-based deep learning model developed for the accurate prediction of ACPs and non-ACPs. The pACPs-DNN model transforms input peptides into image representations using residue-wise energy contact matrix (RECM), substitution Matrix Representation (SMR), and Position Specific Scoring Matrix (PSSM) embeddings, followed by local binary pattern (LBP)-based decomposition to capture enhanced structural and local semantic features. These transformations generate novel feature sets, including RECM_LBP, LBP_SMR, and LBP_PSSM. Subsequently, a two-tier feature selection approach is employed to identify a high-ranking optimal feature set, which is then used to train an attention-based deep neural network. The proposed pACPs-DNN model achieves an impressive training accuracy of 96.91 % and an AUC of 0.98. To evaluate its generalization capability, the model was validated on independent datasets, demonstrating significant improvements of 5 % and 3.5 % in accuracy over existing models on the Ind-I and Ind-II datasets, respectively. The demonstrated efficacy and robustness of pACPs-DNN highlight its potential as a valuable tool for advancing drug discovery and academic research in cancer-related therapeutic development.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"117 ","pages":"Article 108441"},"PeriodicalIF":2.6,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739969","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}