Recep Adiyaman
bioinformatics

Issue #35: PepScorer::RMSD: An Improved Machine Learning Scoring Function for Protein-Peptide Docking.

January 29, 2026 Daily Intelligence
Protein Design Daily

Building something in Protein Design?

I love collaborating on new architectural challenges. Let's build together.

LinkedIn Connect Direct Message

šŸ§¬ Protein Design Digest

Curated protein signals by Recep Adiyaman

Join 1,000+ researchers. Unsubscribe anytime.

šŸš€ Today’s Top Signal

PepScorer::RMSD: An Improved Machine Learning Scoring Function for Protein-Peptide Docking.

šŸ§¬ Abstract

Over the past two decades, pharmaceutical peptides have emerged as a powerful alternative to traditional small molecules, offering high potency, specificity, and low toxicity. However, most computational drug discovery tools remain optimized for small molecules and need to be entirely adapted to peptide-based compounds. Molecular docking algorithms, commonly employed to rank drug candidates in early-stage drug discovery, often fail to accurately predict peptide binding poses due to their high conformational flexibility and scoring functions not being tailored to peptides. To address these limitations, we present PepScorer::RMSD, a novel machine learning-based scoring function specifically designed for pose selection and enhancement of docking power (DP) in virtual screening campaigns targeting peptide libraries. The model predicts the root-mean-squared deviation (RMSD) of a peptide pose relative to its native conformation using a curated dataset of protein-peptide complexes (3-10 amino acids). PepScorer::RMSD outperformed conventional, ML-based, and peptide-specific scoring functions, achieving a Pearson correlation of 0.70, a mean absolute error of 1.77 ƅ, and top-1 DP values of 92% on the evaluation set and 81% on an external test set. Our PLANTS-based workflow was benchmarked against AlphaFold-Multimer predictions, confirming its robustness for virtual screening. PepScorer::RMSD and the curated dataset are freely available in Zenodo.

Why it matters: Expands the searchable sequence space for novel folds and high-affinity binders.

ā­ Additional Signals

Decrypting potential mechanisms linking ochratoxin A to hepatocellular carcinoma: an integrated approach combining toxicology, machine learning, molecular docking, and molecular dynamics simulation.

Background Ochratoxin A (OTA), a common food-borne mycotoxin, is a potential human carcinogen, yet the specific molecular mechanisms linking it to hepatocellular carcinoma (HCC) remain unclear. Methods We integrated network toxicology to predict OTA targets and intersected them with HCC transcriptomic data to identify key candidate genes. Functional enrichment analysis was then conducted. Multiple machine learning algorithms were applied to screen and validate core genes. Furthermore, molecular docking and molecular dynamics (MD) simulations were employed to evaluate the binding stability between OTA and key target proteins. Results A total of 50 key genes were identified as potential targets for potential OTA-associated hepatocarcinogenesis. Enrichment analysis revealed their significant involvement in critical processes such as xenobiotic metabolism and oxidative stress response. Machine learning analysis prioritized eight core genes (AURKA, GABARAPL1, CA2, PARP1, LMNA, SLC27A5, EPHX2, and GSTP1), and a combined diagnostic model demonstrated outstanding performance (AUC = 0.986). Structural analyses via molecular docking and MD simulations confirmed stable binding interactions between OTA and these core targets. Conclusions This integrated computational study identifies a set of candidate genes through which OTA may potentially interact with HCC-associated molecular networks. The robust binding predicted between OTA and the core targets provides a structural basis for these interactions. These findings offer a prioritized list of targets and a theoretical framework for subsequent experimental validation and investigation into OTA’s toxicological role in HCC.

Artificial Intelligence Driven Virtual Screening and Molecular Docking Approaches Identified LIFR, BTG2, EPHX2, and PAK3 as Targets and BI-2536, AP-24534, and AZ-628 as Repurposed Drugs for PDAC.

Pancreatic ductal adenocarcinoma (PDAC) is one of the most aggressive and lethal tumors worldwide, with limited effective treatments. Globally, the incidence of pancreatic cancer is expected to rise to 18.6 per 100,000 by 2050, with an average annual growth rate of 1.1%, implying that PDAC would represent a considerable public health burden. Identifying prognostic markers is critical for making therapy decisions and improving patient outcomes. In this study, the microarray gene expression data of PDAC were analyzed using artificial intelligence (AI) algorithms and molecular docking to identify the differentially expressed genes (DEGs) and drug repurposing. The GSE183795 dataset used in this study was obtained from the National Centre for Biotechnology Information. Further, the data were analyzed using GEO2R tools, and genes were selected based on logFC values>2. Then, these genes were ranked using AI algorithms such as support vector machine (SVM), logistic regression, random forest, extreme gradient boosting (XGB), and one-dimensional convolutional neural network to identify the DEGs. The performance of the models was evaluated using stratified 10-fold cross-validation and different classification metrics. A drug library was prepared using DepMap corresponding to the identified DEGs, and subsequently, molecular docking and pharmacokinetics analysis were performed. The result of the logFC>2 listed 107 upregulated genes in PDAC. It was observed that SVM and XGB show the average 10-fold accuracy, sensitivity, specificity, precision, and F-score of 79.25%, 78.37%, 78.37%, 79.33% and 78.35% respectively. Our results revealed that LIFR, BTG2, EPHX2, and PAK3 are within the top three and commonly ranked by AI models. Further, we identified three drugs, such as BI-2536, Ponatinib (AP-24534), and AZ-628, which show the best efficacy based on the binding energies by molecular docking analysis. The pharmacokinetics study strengthened our results that the identified drugs can be used as a therapeutic for PDAC as they obey Lipinski’s rule. In conclusion, identified genes can act as prognostic markers, and drugs could be used as potential therapeutics for PDAC.

Study on the Mechanism of Ku Diding in the Treatment of Diabetes based on Network Pharmacology, Molecular Docking Technology, and Molecular Dynamics.

Introduction To explore how Ku Diding (KDD) works in managing Diabetes Mellitus (DM), researchers utilized network pharmacology, molecular docking, and molecular dynamics methodologies. Methods Key active components of KDD were identified using the Traditional Chinese Medicine Systematic Pharmacology Database and Analysis Platform (TCMSP). Data for diabetesrelated targets were retrieved from the Human Genetic Comprehensive Databases (Genecards) and the Online Mendelian Inheritance in Man (OMIM) database. The intersection of these targets was analyzed to determine potential therapeutic targets for diabetes treatment. Proteinprotein interaction networks (PPI) were constructed using the STRING database and Cytoscape software, followed by Gene Ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis. Molecular docking between the components and key targets was performed using the AutoDock Vina platform. Results This study identified that Dihydrosanguinarine, (S)-Scoulerine, among others, are the main active ingredients of KDD for treating DM, showing high affinity for critical targets like PTGS2 and PRKACA, through multiple pathways including vascular regulation, neuromodulation, metabolic regulation, and endocrine regulation. The molecular docking results showed that there are interactions between the active ingredients and the key targets, with the majority of the effective components exhibiting a stronger binding affinity than Metformin. Among them, (S)-Scoulerine and Dihydrosanguinarine demonstrated high docking affinity with the key target proteins PTGS2 and PRKACA. Discussion DM is closely linked to oxidative stress, chronic inflammation, and insulin signaling dysregulation. This study reveals that KDD exerts anti-diabetic effects via a multi-target network involving proteins such as PRKACA, PTGS2, ESR1, FOS, and DRD2. These targets are associated with glucose metabolism, inflammation, oxidative stress, and neural regulation. Modulation of these pathways likely enhances insulin sensitivity, lowers blood glucose, suppresses inflammation, and protects against oxidative damage. GO and KEGG analyses further indicate involvement in MAPK signaling, synaptic transmission, and vascular regulation, forming a multidimensional “metabolism-inflammation-neural” regulatory network. Compared to Metformin, most KDD-derived compounds showed stronger binding, highlighting their therapeutic potential. Molecular dynamics simulations support the stability of the observed binding conformations, suggesting their potential as therapeutic targets. These findings underscore KDD’s ability to simultaneously target multiple pathological mechanisms, offering a holistic treatment strategy for DM. Conclusion This study provides preliminary evidence that KDD is characterized by a multicomponent, multi-target, and multi-pathway approach in the treatment of diabetes mellitus (DM), thereby establishing a scientific foundation for further in-depth exploration of KDD’s molecular mechanisms.

šŸ§Ŗ AI & Research News

šŸ¢ Industry Insight & Applications

āš” Quick Reads

Investigating the impact of aspartame on Alzheimer’s disease through network toxicology and molecular docking.

Introduction Alzheimer’s disease (AD) is a prevalent neurodegenerative disorder, and the relationship between its pathogenesis and environmental factors has garnered increasing scholarly interest. Aspartame, a widely utilized artificial sweetener, has potential neurotoxic effects that remain incompletely understood. This study employs network toxicology and molecular docking to speculate on the potential molecular mechanisms by which aspartame is involved in the pathological process of AD. Methods By integrating data from multiple databases, including ChEMBL, SwissTargetPrediction, OMIM, and GeneCards, we obtained the shared targets of aspartame and AD. A protein-protein interaction (PPI) network was constructed using the STRING database and Cytoscape software to discern the core targets. Subsequently, Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed via the DAVID database, and molecular docking validation of the core targets was conducted using AutoDock Vina. Results In this study, a total of 298 targets associated with aspartame and 2,042 targets related to AD were identified. Seventy-five common targets were discovered, with BCL2, PPARG, TNF, IL1Ī², MAPK3, ESR1, and CASP3 were hypothesized as key core targets. GO functional analysis indicated that these targets are predominantly involved in biological processes such as protein metabolism, neuroinflammation, apoptosis, and oxidative stress. Furthermore, KEGG pathway analysis revealed significant enrichment in pathways TNF signaling, MAPK signaling, and PI3K-Akt signaling, among others. Molecular docking studies have shown that aspartame has A certain binding affinity with some core targets. Discussion It is speculated that aspartame may be involved in the key pathological processes of AD through multi-target and multi-pathway mechanisms, including neuroinflammation, apoptosis and amyloid-beta (AĪ²) metabolism. This computational study speculates that aspartame, as an environmental exposure factor, is involved in the potential molecular mechanism of AD pathogenesis, thereby providing a theoretical basis for evaluating its neurotoxicity. Further experimental studies are needed in the future to confirm its biological effects.

Integrative molecular simulations reveal NeuroAid II mechanisms in ischemic stroke through network pharmacology, molecular dynamics, and pharmacophore modeling.

Ischemic stroke remains a major health challenge with limited treatment options. NeuroAid II (MLC901), a multi-herbal remedy, has shown clinical promise in post-stroke recovery, though its molecular mechanisms are unclear. This study employed an integrative computational approach, including network pharmacology, molecular docking, molecular dynamics (MD) simulations, molecular mechanics/Poisson-Boltzmann surface area (MM/PBSA) free energy calculations, and pharmacophore modeling, to investigate NeuroAid II’s neuroprotective mechanisms. Active compounds were screened for drug-likeness and matched to ischemic stroke-related targets via target prediction and protein-protein interaction analysis. Top ligands were docked to key targets, followed by 100 ns MD simulations and binding energy estimation. Network analysis identified MMP2 and SRC as critical targets. Docking and MD results showed baicalin, DCP-sterol, and DMCG formed stable, specific interactions with both proteins. DCP-sterol showed the strongest binding affinity to MMP2 (- 31.06 kcal/mol) and SRC (- 17.10 kcal/mol), outperforming standard inhibitors. DMCG and baicalin also displayed favorable binding to MMP2 (- 12.17 and - 13.54 kcal/mol, respectively) and SRC (- 16.19 and - 10.60 kcal/mol, respectively). Pharmacophore models revealed conserved hydrogen bonding (Ala86 in MMP2; Ala393/Ala296 in SRC) and key hydrophobic features. These findings provide molecular insights into NeuroAid II’s multitarget effects and highlight promising lead compounds for further validation.

Molecular Investigation of Product Nkabinde in HIV Therapy: A Network Pharmacology and Molecular Docking Approach.

HIV/AIDS continues to pose a significant global public health concern, with Sub-Saharan Africa having the highest number of people living with HIV (PLHIV). Traditional medicines have been increasingly essential in treating and managing PLHIV. Product Nkabinde (PN), a polyherbal formulation derived from traditional medicinal plants, has recently demonstrated significant potential in the treatment of HIV. This study aims to elucidate the molecular mechanisms underlying the therapeutic effects of phytochemicals identified from PN in HIV treatment, utilizing network pharmacology and molecular docking. The intersecting (common) genes of the 27 phytochemicals of PN and HIV were computed on a Venn diagram, while the protein-protein interaction (PPI) network of the intersecting genes was plotted using STRING. The hub (10) genes were computed and analyzed for Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment pathways using ShinyGO. Molecular docking and protein-ligand interaction analysis of the 27 phytochemicals with each of the 10 hub genes were performed using the Maestro Schrodinger suite. The KEGG analysis reveals an important network with lower False Discovery Rate (FDR) values and higher fold enrichment. The pathway enrichments reveal that the 10 hub genes regulated by PN focus on immune regulation, metabolic modulation, viral comorbidity, carcinogenesis, and inflammation. GO analysis further reveals that PN plays key roles in transcription regulation, such as miRNA, responses to hormones and endogenous stimuli, oxidative stress regulation, and apoptotic signalling, kinase binding, protein kinase binding, transcription factor binding, and ubiquitin ligase binding enriched pathways. Consequently, molecular docking unveils complexes with higher binding energies, such as rutin-HSP90AA1 (-10.578), catechin-JUN (-9.512), quercetin-3-O-arabinoside-AKT1 (-9.874), rutin-EGFR (-8.127), aloin-ESR1 (-8.585), and quercetin-3-0-Ī²-D-(6’-galloyl)-glucopyranoside-BCL2 (-7.021 kcal/mol). Overall, the results reveal pathways associated with HIV pathology and possible anti-HIV mechanisms of PN. Therefore, further in silico, in vitro, and in vivo validations are required to substantiate these findings.

Discontinued BACE1 Inhibitors in Phase II/III Clinical Trials and AM-6494 (Preclinical) Towards Alzheimer’s Disease Therapy: Repurposing Through Network Pharmacology and Molecular Docking Approach.

Background : Ī²-site amyloid precursor protein cleaving enzyme 1 (BACE1) inhibitors demonstrated amyloid-lowering efficacy but failed in phase II/III clinical trials due to adverse effects and limited disease-modifying outcomes. This study employed an integrated network pharmacology and molecular docking approach to quantitatively elucidate the multitarget mechanisms of 4 (phase II/III) discontinued BACE1 inhibitors (Verubecestat, Lanabecestat, Elenbecestat, and Umibecestat) and the preclinical compound AM-6494 in Alzheimer’s disease (AD). Methods : Drug-associated targets were intersected with AD-related genes to construct a protein-protein interaction (PPI) network, followed by topological analysis to identify hub proteins. Gene Ontology (GO) and KEGG pathway enrichment analyses were performed using statistically significant thresholds ( p Results : Network analysis identified 10 hub proteins (CASP3, STAT3, BCL2, AKT1, MTOR, BCL2L1, HSP90AA1, HSP90AB1, TNF, and MDM2). GO enrichment highlighted key biological processes, including the negative regulation of autophagy, regulation of apoptotic signalling, protein folding, and inflammatory responses. KEGG pathway analysis revealed significant enrichment in the PI3K-AKT-MTOR signalling, apoptosis, and TNF signalling pathways. Molecular docking demonstrated strong multitarget binding, with binding affinities ranging from approximately -6.6 to -11.4 kcal/mol across the hub proteins. Umibecestat exhibited the strongest binding toward AKT1 (-11.4 kcal/mol), HSP90AB1 (-9.5 kcal/mol), STAT3 (-8.9 kcal/mol), HSP90AA1 (-8.5 kcal/mol), and MTOR (-8.3 kcal/mol), while Lanabecestat showed high affinity for AKT1 (-10.6 kcal/mol), HSP90AA1 (-9.9 kcal/mol), BCL2L1 (-9.2 kcal/mol), and CASP3 (-8.5 kcal/mol), respectively. These interactions were stabilized by conserved hydrogen bonding, hydrophobic contacts, and Ļ€-alkyl interactions within key regulatory domains of the target proteins, supporting their multitarget engagement beyond BACE1 inhibition. Conclusions : This study demonstrates that clinically failed BACE1 inhibitors engage multiple non-structural regulatory proteins that are central to AD pathogenesis, particularly those governing autophagy, apoptosis, proteostasis, and neuroinflammation. The identified ligand-hub protein complexes provide a mechanistic rationale for repurposing and optimization strategies targeting network-level dysregulation in Alzheimer’s disease, warranting further in silico refinement and experimental validation.

Study on the Molecular Mechanism of Interaction Between Perfluoroalkyl Acids and PPAR by Molecular Docking.

Per- and polyfluoroalkyl substances (PFASs), as a class of “permanent chemicals” with high environmental persistence and bioaccumulation, have attracted much attention. In this study, we focused on the molecular mechanism of the interaction between perfluoroalkyl acids (PFAAs) and peroxisome proliferator-activated receptor Ī“ (PPARĪ“). Using molecular docking, binding free energy calculation, and structural analysis, we systematically investigated the binding modes, key amino acid residues, and binding energies of 20 structurally diverse PFAAs with PPARĪ“. The results showed that the binding energies of PFAAs with PPARĪ“ were significantly affected by the molecular weight, the number of hydrogen bond donors, and the melting point of PFAAs. PFAAs with smaller molecular weights and fewer hydrogen bond donors showed stronger binding affinity. The binding sites were concentrated in high-frequency amino acid residues such as TRP-256, ASN-269, and GLY-270, and the interaction forces were dominated by hydrogen and halogen bonds. PFAAs with branched structure of larger molecular weight (e.g., 3m-PFOA, binding energy of -2.92 kcalĀ·mol -1 ; 3,3m 2 -PFOA, binding energy of -2.45 kcalĀ·mol -1 ) had weaker binding energies than their straight-chain counterparts due to spatial site-blocking effect. In addition, validation group experiments further confirmed the regulation law of binding strength by physicochemical properties. In order to verify the binding stability of the key complexes predicted by molecular docking, and to investigate the dynamic behavior under the conditions of solvation and protein flexibility, molecular dynamics simulations were conducted on PFBA, PFOA, 3,3m 2 -PFOA, and PFHxA. The results confirmed the dynamic stability of the binding of the high-affinity ligands selected through docking to PPARĪ“. Moreover, the influence of molecular weight and branched structure on the binding strength was quantitatively verified from the perspectives of energy and RMSD trajectories. The present study revealed the molecular mechanism of PFAAs interfering with metabolic homeostasis through the PPARĪ“ pathway, providing a theoretical basis for assessing its ecological and health risks.

Baricitinib in chronic kidney disease: an exploratory analysis integrating network toxicology, molecular docking and pharmacovigilance.

Background Chronic kidney disease (CKD) presents a major global health challenge due to ineffective therapies against progressive renal fibrosis. Baricitinib, a selective JAK1/JAK2 inhibitor, has anti-inflammatory and anti-fibrotic potential, yet its mechanistic basis and safety implications in CKD require further exploration. Methods An integrated strategy was employed, combining network toxicology across multiple databases, protein-protein interaction network analysis and molecular docking. Real-world safety was evaluated by analyzing adverse event (AE) reports from FDA Adverse Event Reporting System (FAERS) (2018-2024), capturing safety data across all approved indications for baricitinib by calculating reporting odds ratios (RORs) and proportional reporting ratios (PRRs). Results Predictive toxicology indicated potential respiratory and acute toxicity risks. Network analysis identified 229 shared targets; core hubs (AKT1, SRC, STAT3, EGFR, ESR1) showed high-affinity docking, suggesting potentially stronger theoretical binding affinity than JAK1. Pathway enrichment suggested potential suppression of JAK-STAT/MAPK and TGF-Ī²/Smad3 pathways. FAERS analysis of 6,006 reports from its broader clinical use showed significantly elevated RORs for infections and thromboembolic events, alongside the absence of a disproportionate signal for renal AEs. This finding aligns with the mechanistic profile derived from intersecting baricitinib’s predicted targets with CKD-related genes, highlighting the need to systematically evaluate renal safety in prospective CKD trials. Conclusion Baricitinib has computational and mechanistic potential to modulate key pathways in CKD. Pharmacovigilance data confirm risks of infection and thrombosis but show no disproportionate renal safety signal. These exploratory findings generate a testable hypothesis for its use in CKD, underscoring the necessity of prospective, renal-function-stratified trials.

Anticancer Activity of Picolinamide and Sulfur Chelated Pt(II) Complexes Against Breast Cancer: In Vitro Interaction Studies Through Molecular Docking With Bio-Receptors.

Herein, picolinamide (pica) and sulfur chelated Pt(II) complexes were focused to investigate for their bioactivity and cytotoxic property. For better anticancer activity and less toxicity of Pt(II) complex, l-cysteine (L-cys) and N-acetyl-l-cysteine (N-acetyl-l-cys) were used to synthesize Pt(II) complexes. Complex Pt(pica)(OH2)22, C-2 was obtained on hydrolysis of [Pt(pica)Cl2], C-1. The complex [Pt(pica)(l-cys)]+; C-3 and [Pt(pica)(N-ac-l-cys)]; C-4 were synthesized from C-2 with thiols l-cys and N-ac-l-cys, respectively. The binding activity of Pt(II) complexes with DNA and BSA were performed for their binding mode and binding constants. The binding modes of the Pt(II) complexes were executed by electronic and fluorescence spectroscopic methods. Synchronous and 3D fluorescence spectroscopic investigations were performed to observe the insight interaction and conformational change of BSA, when interacts with the complex. The drug likeness property was conducted by PASS prediction and ADMET software programs. Molecular docking of the complexes was carried out with DNA, HSA, and HER-2 cancer protein. The cytotoxic activity of the complexes was tested on breast cancer cell lines; MCF-7, MDA MB-231 and normal human embryonic kidney HEK293T cells. Necrotic cell death mechanism was confirmed by Annexin-V-FITC/PI assay by flow cytometric method and the production of reactive oxygen species (ROS) was assessed through DCFDA assay.

Exploring Antibiotic Degradation Mechanisms: Molecular Docking Analysis of Beta-Lactamase Enzymes from Pseudomonas songnenensis.

This study investigates the potential of Pseudomonas songnenensis (P. songnenensis) in degrading Ī²-lactam antibiotics through enzymatic hydrolysis by Ī²-lactamase (Ī²-Lase). Faecal soil samples were collected from ten poultry farms in Tamil Nadu, India, between June and July 2023. Each housing 10,000-50,000 birds and is routinely administered antibiotics. Among the bacterial isolates obtained, strain 18 showed the highest degradation activity. Molecular docking analysis revealed stable enzyme-antibiotic interactions, with Amoxicillin showing the strongest binding affinity due to multiple hydrogen bonds. The Ī²-Lase enzyme effectively hydrolyses the Ī²-lactam ring, breaking the amide bond and rendering antibiotics inactive. This stepwise degradation mechanism contributes to reducing antibiotic persistence in the environment and offers insights into microbial-driven bioremediation strategies. The findings highlight the novelty of using P. songnenensis for antibiotic degradation and emphasise its potential application in mitigating antibiotic pollution in livestock farming and food production systems.

šŸ’” Pipeline Tip

Verify FASTA headers for special characters that break Rosetta pipelines.

šŸ› ļø Resources

Deep learning is not a magic wand, but a powerful lens for structural biology. ā€” Recep Adiyaman

BS HF DK