Recep Adiyaman
Vision About Experience Education Skills Publications Tools Newsletter Updates Podcasts Blog Contact CV Subscribe
All Issues
Older Newer
Weekly Digest February 13, 2026 · 21 min read

Weekly Digest: Feb 09 - Feb 13, 2026

A curated summary of the top protein engineering and structure prediction signals from Feb 09 - Feb 13, 2026.

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.

🧬 Weekly Recap

Feb 09 - Feb 13, 2026

Missed a day? Here are the top research signals and tools from Monday to Friday, summarized in one place.

🏆 Top Signals of the Week

🗓️ Monday, Feb 09

From Atoms to Cells: AI-Based Structure Prediction Fueling Molecular Dynamics Simulations in Computational Structural Biology.

🧬 Abstract

The simulation of biological systems has undergone a revolutionary transformation, progressing from modeling single proteins to entire cellular environments. This leap forward is driven by the convergence of molecular dynamics (MD) simulations and artificial intelligence (AI)-powered structure prediction. Traditionally, MD simulations provided atomic-level insights into protein function and interactions, yet their accuracy relied on experimentally determined structures. AI-based models, such as AlphaFold, now enable the rapid and accurate prediction of protein structures, expanding the scope of simulations beyond isolated biomolecules to complex assemblies. However, a structure alone is not sufficient to capture biological function. Molecular motion underlies almost all cellular processes, from enzyme catalysis to signal transduction. MD simulations breathe life into static models, revealing dynamic conformational changes and mechanistic pathways. With computational power and AI capabilities, we are now approaching the long-sought goal of simulating entire cellular processes with unprecedented resolution. This chapter explores how AI and MD are bridging the gap between static snapshots and dynamic cellular models, paving the way for whole-cell simulations. The ability to computationally reconstruct cellular behavior at the molecular scale is poised to transform biological research, drug discovery, and synthetic biology, marking an era in which digital cells become a fundamental tool in scientific exploration.

🗓️ Tuesday, Feb 10

Immunoinformatics and molecular docking reveal potential multi-epitope vaccine against Pseudomonas aeruginosa.

🧬 Abstract

Pseudomonas aeruginosa is a common opportunistic pathogen and a leading cause of hospital-acquired pneumonia, yet there is currently no approved vaccine to prevent its infections. This study utilizes immunoinformatics to identify cytotoxic T-lymphocyte (CTL) epitopes derived from conserved regions of 6 key virulence factors: Pili, FliD, AlgF, PelG, Exoenzyme T, and XcpQ. Conserved peptide fragments were identified using the Protein Variability Server. The CTL epitopes were evaluated for immunogenicity, antigenicity, post-translational modifications, allergenicity, cross-reactivity, toxicity, and population coverage analysis. Molecular docking between human leukocyte antigens (HLAs) and the corresponding CTL epitopes, along with binding affinity analysis, was also conducted. A multi-epitope vaccine (PaMEV) construct was designed using selected epitopes, and its secondary and tertiary structures were predicted, refined, and validated. All selected epitopes were highly conserved (Shannon index ≤0.1) and showed strong HLA binding (half maximal inhibitory concentration ≤500 nM). They were predicted to be non-allergenic, non-toxic, and non-cross-reactive. Molecular docking revealed stable HLA-epitope complexes with 8-14 hydrogen bonds and high binding affinity (values of the binding free energy <0 and dissociation constant <100 nM). A PaMEV was designed using the 6 CTL epitopes, and structure analysis confirmed its stability and effective epitope presentation. The selected epitopes showed strong potential for inclusion in a peptide-based PaMEV, with favorable immunogenicity and docking results supporting its design. The final construct exhibited structural stability and strong HLA interactions, suggesting it as a promising vaccine candidate against P. aeruginosa. Experimental validation through in vitro and in vivo studies is recommended.

🗓️ Wednesday, Feb 11

De novo protein design: a transformative frontier in clinical protein applications.

🧬 Abstract

Background Protein biologics are indispensable in disease prevention, diagnosis, and therapy, yet their development remains largely constrained by reliance on native protein scaffolds, resulting in long development timelines, limited structural and functional tunability, challenges in manufacturing consistency, and high production costs. Main body De novo protein design moves beyond the structural and functional constraints inherent to traditional approaches, enabling the direct creation of proteins with tailored structures and functions and offering a new avenue to address these challenges. In this review, we summarize the principal computational strategies underlying de novo protein design and the contribution of deep learning to its recent progress, and highlight prospective applications, major translational barriers, and the current limitations and future challenges of the field. Conclusions Despite notable methodological progress in de novo protein design, its path toward clinical application continues to be limited by a range of biological, technical, and translational considerations. Future work will need closer coordination between computational design, experimental validation, engineering optimization, and clinical needs, with clinical feasibility considered early and refined throughout development.

🗓️ Thursday, Feb 12

Unfreezing structural biology for drug discovery.

🧬 Abstract

Structure-based drug discovery relies on three-dimensional protein structures to provide the atomic blueprints for small-molecule design, indicating where to place each atom to maximize favorable interactions. The advent of cryo-cooling crystals in crystallography greatly accelerated the ease and accessibility of structural data, making it a mainstay of most drug discovery efforts. However, despite its successes, including producing numerous clinically successful molecules, cryo-cooled samples only tell part of the structural story: they may leave out dynamic details or introduce artifacts that may lead drug discovery campaigns astray. In this Perspective, we highlight recent studies characterizing temperature-sensitive structural phenomena observed by crystallography. We showcase how leveraging information on rare, hidden conformational states informs ligand discovery via molecular docking. This demonstrates the value of performing structural studies at elevated temperatures, closer to where biology occurs, to ‘unfreeze’ structural ensembles for drug discovery and design.

🗓️ Friday, Feb 13

Deconvolving mutation effects on protein stability and function with disentangled protein language models.

🧬 Abstract

Understanding how evolutionary constraints shape protein sequences is fundamental to deciphering the molecular mechanisms underlying protein stability and function, which has broad implications in protein engineering and therapeutics development. Recent advances in protein language models (pLMs) have enabled accurate prediction of mutation effects through evolutionary information, effectively capturing the selective pressure that governs protein sequence variation. A critical challenge, however, remains in disentangling the intertwined mutation effects on protein stability and function, as evolutionary signals conflate both stability-driven and function-driven pressures, obscuring the mechanistic basis of mutation effects and limiting their utility for rational protein engineering. In this work, we introduce DETANGO, a novel deep learning framework that explicitly deconvolves the mutation effects on protein functions by removing components attributable to stability perturbations from the pLM-predicted mutation effects. Guided by computational or experimental stability measurements, DETANGO estimates a functional plausibility score for each single-point mutation that is the component of the mutation effect not accounted for by changes in stability. Single-point mutations with low functional plausibilities are predicted to be stable-but-inactive (SBI) variants, whose compromised activities are caused by direct perturbations on functional mechanisms rather than structural stability. Residues enriched for such variants are inferred to be functionally critical, as indicated by the strong evolutionary pressures to maintain protein function. Through extensive benchmarking experiments, we show that DETANGO accurately identifies SBI variants and pinpoints functionally important residues across contexts, including ligand binding, catalysis, and allostery. Moreover, extending DETANGO from individual proteins to homologous protein families reveals shared and distinctive functional patterns across protein families. Collectively, these results establish DETANGO as a biologically grounded framework for disentangling evolutionary constraints on protein stability and function, advancing mechanistic understanding of protein function, and informing rational protein engineering.

📚 All Papers & Quick Reads

🗓️ Monday, Feb 09

🗓️ Tuesday, Feb 10

🗓️ Wednesday, Feb 11

🗓️ Thursday, Feb 12

🗓️ Friday, Feb 13

🛠️ Tools & Datasets

  • 🛠 Tool: OpenFold - Fast, trainable, and open implementation of AlphaFold2.
  • 🛠 Tool: ChimeraX - Next-gen molecular visualization for large data sets.
  • 💾 Dataset: UniRef - Clustered protein sequence sets for fast similarity searches.
  • 💾 Dataset: BFD - Big Fantastic Database for deep learning protein modeling.
  • 🛠 Tool: AlphaFold2 - Deep learning system for high-accuracy protein structure prediction.
  • 💾 Dataset: MGnify - Metagenomics resource for microbiome sequence data.
  • 🛠 Tool: ColabFold - Fast AlphaFold2/MMseqs2 pipeline for large-scale predictions.
  • 💾 Dataset: PDBbind - Binding affinity data with 3D structures of protein-ligand complexes.
  • 🛠 Tool: RoseTTAFold - End-to-end neural network for protein structure prediction.
  • 💾 Dataset: BioLiP - Verified biologically relevant ligand-protein interactions.
  • 🛠 Tool: ESMFold - Language-model-based protein structure prediction from sequences.
  • 💾 Dataset: SIFTS - Residue-level mapping between PDB, UniProt, and other resources.

🤖 AI in Research Recap

🏢 Industry & Real-World Applications

💼 Jobs & Opportunities

📅 Events

Enjoyed this digest? Subscribe above to get these dailies in your inbox every morning.

BS HF DK