Skip to main content
recep.adiyaman
Vision About Experience Education Skills Publications Tools Newsletter Updates Podcasts Blog Contact CV Subscribe
All Issues
Older Newer
Daily Signal May 21, 2026 · 10 min read

Issue #113: High-Affinity Protein Binder Design via Flow Matching and In Silico Maturation

Protein Design Digest #113: Exploring the mechanism of saffron in treating viral myocarditis using n…

Share X LinkedIn
Protein Design Daily

Building something in Protein Design?

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

LinkedIn Email

Subscribe to Protein Design Digest

Daily curated signals from arXiv, PubMed, and BioRxiv.

Signal of the Day

High-Affinity Protein Binder Design via Flow Matching and In Silico Maturation

The de novo design of high-affinity protein binders remains a central challenge in protein engineering and therapeutic discovery. While deep generative models have advanced backbone generation and interface design, achieving picomolar or nanomolar binding affinities typically demands extensive experimental screening or iterative in vitro maturation. A general computational approach for the direct production of high-affinity binders has remained elusive. Here, we introduce an integrated framework that synergizes PPIFlow, a flow-matching-based generative model, with a novel in silico maturation strategy. PPIFlow employs a pairformer architecture to explicitly reason over pair-wise geometric and chemical interactions, modeling protein backbone rigid-body transformations as continuous flows. To bridge the affinity gap, we implement a dedicated in silico affinity maturation stage that combines interface rotamer enrichment with partial flow refinement to optimize energetic packing. This pipeline is further accelerated by AF3Score, a score-only adaptation of AlphaFold3 that enables high-fidelity and computationally efficient candidate prioritization. Across a diverse set of therapeutic targets, this synergistic approach consistently produces picomolar and nanomolar affinity binders without experimental affinity maturation. Notably, the framework proves highly effective for the de novo design of single-domain antibodies (VHHs), producing sub-nanomolar binders across multiple targets. These results establish that coupling robust backbone generation with focused in silico maturation renders the purely computational design of high-affinity binders feasible.

Why this matters:

Also Worth Reading

Unraveling the anti-neuroinflammatory mechanisms of Cervus cucumis polypeptide injection in Alzheimer’s disease: insights from network pharmacology, molecular docking, molecular dynamics simulation, and experimental validation.

Objective Alzheimer’s disease (AD) is a progressive neurodegenerative disorder with increasing global prevalence, in which neuroinflammation serves as a critical pathological driver exacerbating cognitive decline. While current therapies offer limited symptomatic relief, multi-target strategies are urgently needed. Cervus cucumis polypeptide injection (CCPI), a traditional Chinese medicine (TCM) formulation, has demonstrated anti-inflammatory properties; however, its mechanisms of action against AD remain unclear. This study aimed to elucidate the anti-AD potential mechanisms of CCPI using an integrated approach combining network pharmacology, molecular docking, molecular dynamics (MD) simulation, and experimental validation. Methods Active components and corresponding targets of CCPI were retrieved from the TCMSP database, while AD-related targets were collected from Genecards, OMIM, and DrugBank. Potential therapeutic targets were identified by intersecting drug and disease targets, followed by protein-protein interaction (PPI) network construction, Gene Ontology (GO), and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. Molecular docking and MD simulations were performed to evaluate interactions between potential active components and key targets. In vitro experiments were conducted on Aβ 25-35 -induced BV2 microglial cells to assess cell viability (CCK-8 assay), inflammatory cytokine levels (ELISA), and protein expression (Western blot) related to the neuroinflammation pathway and microglial polarization. Results A total of 28 active components and 50 common targets of CCPI for AD treatment were identified. Linoleic acid (LA) was determined to be a potential active component, with IL-6 as the key target based on PPI network topology. Molecular docking and MD simulation confirmed a stable binding affinity between LA and IL-6. KEGG analysis revealed significant enrichment in the HIF-1 signaling pathway, particularly the IL-6/STAT3/VEGF signaling pathway. In vitro , CCPI treatment significantly enhanced cell viability and attenuated the pro-inflammatory response, as evidenced by reduced levels of IL-6, IL-1β, and TNF-α, decreased the expression of the pro-inflammatory marker iNOS. Concurrently, it elevated the expression of the anti-inflammatory/repair-associated marker CD206. Western blot analysis further verified that CCPI suppressed IL-6/STAT3 activation while upregulating VEGF expression. Additionally, LA alone significantly reduced IL-6 levels and STAT3 phosphorylation, decreased the expression of iNOS, and increased the expression of CD206, with therapeutic efficacy comparable to CCPI. Conclusion CCPI exerts neuroprotective effects in AD models by regulating the IL-6/STAT3/VEGF pathway, downregulating the expression of the inflammation-related iNOS protein, upregulating the expression of the CD206 protein associated with anti-inflammatory and reparative functions, remodeling the functional state of microglia, inhibiting their pro-inflammatory responses, and enhancing their reparative functions. Its potential active component, LA, likely mediates this effect by stably binding to and inhibiting IL-6, thus suppressing the downstream STAT3 phosphorylation that drives inflammatory activation.

A multimodal approach integrating spectroscopy, deep learning guided molecular docking, and molecular dynamics simulation for predictive assessment of pioglitazone to albumin binding for formulation development.

Binding affinity is a critical parameter that can influence the state of the drug in vivo and help to define the formulation strategy. The current study implements a multimodal approach to analyse the binding affinity between human serum albumin (HSA) and pioglitazone. Ultraviolet (UV) absorbance and fluorescence spectrometry analyses were performed on different combinations of HSA and pioglitazone complexes, and the absorbance and fluorescence intensities were mapped to calculate the binding constant. DynamicBind, a distinct deep-learning artificial intelligence tool, was implemented to perform in silico docking studies using a non-conventional approach. Furthermore, molecular dynamics simulation was also performed to generate root mean square deviation, radius of gyration, and root mean square fluctuation values, followed by principal component analysis, probability distribution function, and free energy landscape analysis. The simulation output was analysed to interpret the binding affinity and associated conformation of the protein-active pharmaceutical ingredient (API) complex. The binding constant calculated through UV analysis was 1.1 × 10 4 M -1 . Fluorescence spectroscopic analysis derived a value of 1.7 × 10 5 M -1 . At the same time, DynamicBind predicted the cLDDT score for the top predicted model to be 0.634, and a binding affinity value of greater than 5, indicating a relatively moderate binding between pioglitazone and HSA. The results from molecular dynamics simulations further complemented our earlier observations, indicating non-covalent binding interactions and a stable protein-API complex, which is desirable for developing a formulation using HSA as a carrier polymer. This orthogonal approach also provided critical information on the fate of the API and possible considerations that needed to be made during the design of the formulation process, highlighting the need for similar approaches that could provide multifaceted advantages and help in optimising R&D costs and timelines.

Antiparasitic activity and molecular docking of canthin-6-one derivatives from LED- modulated Eurycoma longifolia roots against Blastocystis ST3 and ST7.

Eurycoma longifolia (tongkat ali) is a widely recognized medicinal plant in Southeast Asia, valued for its bioactive alkaloids and quassinoids. Building on previous findings that light-emitting diode (LED) modulation enhances the antiproliferative activity of E. longifolia hairy root cultures (ELHRCs) crude extracts, this study aimed to isolate the specific active constituents, characterize their subtype-specific efficacy, and perform in silico analysis to evaluate potential interaction with proteases against Blastocystis ST3 and ST7. Through chromatographic purification and spectroscopic analysis (NMR, FT-IR, and GC-MS), two compounds canthin-6-one (1) and 9-methoxycanthin-6-one (2) were isolated from ELHRCs grown under various LED spectra for 10 weeks. Quantitative analysis revealed that compound 1 was specifically isolated from Red LED treatments. In contrast, compound 2 was successfully isolated across all treatments, with the highest yield (1.00%) obtained under Mint Green LED illumination. In vitro assays demonstrated that both compounds exhibited dose-dependent inhibitory activity. Using nonlinear sigmoidal dose-response modelling, the values for compound 2 were determined to be 0.0427 mg/mL (ST3) and 0.0433 mg/mL (ST7), while compound 1 exhibited values of 0.0482 mg/mL (ST3) and 0.0603 mg/mL (ST7). Molecular docking studies targeting a cysteine protease surrogate revealed binding affinities of - 6.9 kcal/mol and - 7.3 kcal/mol for compounds 1 and 2, respectively. Although the standard drug metronidazole exhibited higher potency in vitro, these results indicate that LED-stimulated ELHRCs are a viable source for the production of canthin-6-one alkaloids with promising antiparasitic potential.

Research & AI Updates

From the Industry

Quick Reads

Essential oil of ocimum gratissimum as a natural fungicide against pathogenic fungi of fruit crops and molecular docking studies.

Fungal diseases in fruit crops compromise productivity even when synthetic fungicides are applied. Read more →

Dual-channel graph learning reveals similarity and complementarity in protein-protein interaction networks.

Protein-protein interactions (PPIs) are governed by two fundamental interfacial mechanisms: similarity-driven, often involving symmetric structural motifs, and complementarity-driven, arising from geometric and physicochemical matching between binding surfaces. Read more →

It is Not Always Crystal Clear: In-Pocket Analysis for Understanding Binding Site Microenvironment Properties

Structural biology enabled key advances in biochemistry, drug discovery, and AI-driven three-dimensional structure modelling. Read more →

Novel molecular design via a scaffold-aware transformer with multi-scale attention mechanisms.

Recent advancements in artificial intelligence have demonstrated enhanced potential in accelerating drug discovery by exploring vast chemical spaces and predicting molecular properties. Read more →

High-Affinity Protein Binder Design via Flow Matching and In Silico Maturation

The de novo design of high-affinity protein binders remains a central challenge in protein engineering and therapeutic discovery. Read more →

A multi-dimensional computational screening strategy for rapid identification of active components from traditional chinese medicine: Validation and application in Liangdi decoction against endometriosis.

Aims This study aims to develop and validate a Multi-Dimensional Computational Screening (MDCS) strategy to identify bioactive components by jointly considering target affinity, exposure potential, and safety, using Liangdi decoction (LDD) as a case study. Read more →

Fast Adversarial Generation of Molecular Dynamics Trajectories with Kinetic Fidelity

Molecular dynamics (MD) simulations yield atomic-level insights into molecular motion but struggle to reach the long timescales needed for rare events due to prohibitive computational costs. Read more →

Absolute Binding Free Energy Calculations between the SARS-CoV-2 Main Protease and 130 Drug Leads Using Implicit Ligand Theory.

Absolute binding free energy (ΔG) calculations can rank structurally diverse compounds, which could be useful for early-stage drug discovery. Read more →

Pipeline Tip

Use Snakemake for reproducible end-to-end protein design workflows.

Resources & Tools

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

BS HF DK