Recep Adiyaman
Weekly Digest March 20, 2026 · 22 min read

Weekly Digest: Mar 16 - Mar 20, 2026

A curated summary of the top protein engineering and structure prediction signals from Mar 16 - Mar 20, 2026.

Share X LinkedIn
Protein Design Daily

Building something in Protein Design?

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

Subscribe to Protein Design Digest

Daily curated signals from arXiv, PubMed, and BioRxiv.

🧬 Weekly Recap

Mar 16 - Mar 20, 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, Mar 16

Advantages and Limitations of AlphaFold in Structural Biology: Insights from Recent Studies.

🧬 Abstract

Over the past three years, AlphaFold-a deep learning-based protein structure prediction system-has transformed structural biology by providing near-experimental accuracy models directly from amino acid sequences. This narrative review synthesizes applications reported in the 2022-2025 literature across human, microbial, and viral systems, drawing on peer-reviewed studies as our data source. Representative examples include modeling of SARS-CoV-2 spike and nucleocapsid proteins in virology, assisting cryo-EM interpretation of bacterial ribosomal and membrane-protein complexes in microbiology, and refining conformational hypotheses for human GPCRs in biomedicine. Across these cases, AlphaFold predictions have complemented experimental workflows by accelerating hypothesis generation, improving model fitting within ambiguous density regions (poorly resolved areas of cryo-EM maps), and guiding mutagenesis strategies to probe dynamic conformational states. We also summarize recent method extensions: AlphaFold-Multimer improves multi-chain complex assembly prediction, while molecular dynamics (MD) simulations augment AlphaFold’s static models by sampling conformational flexibility and testing stability. Despite these advances, important limitations remain-particularly for intrinsically disordered regions, protein-ligand and protein-cofactor interactions, and very large or transient assemblies-and current community benchmarks indicate that approximately one-third of residues may lack atomistic precision, underscoring uncertainty in flexible or modified segments. Framed within a clear chronological window and evidence base, our analysis highlights both the practical impact and the remaining challenges of integrating AlphaFold with experiment, outlining priorities where further methodological innovation and orthogonal validation are needed.

Why it matters: Critical for improving fold accuracy and reducing structural uncertainty in de novo design.

🗓️ Tuesday, Mar 17

Molecular embedding-based algorithm selection in protein-ligand docking.

🧬 Abstract

Selecting an effective docking algorithm is highly context-dependent, and no single method performs reliably across structural, chemical, and protocol regimes. MolAS is a lightweight algorithm-selection model that predicts per-algorithm performance from pretrained protein and ligand embeddings using attentional pooling and a shallow residual decoder. With hundreds to a few thousand labelled complexes, MolAS achieves up to a 15 percentage-point absolute improvement over the single best solver (SBS) and closes 17-66% of the virtual best solver (VBS)-SBS gap across five docking benchmarks. Analyses of selection frequencies, margin-conditioned reliability, and benchmark-level oracle structure indicate that MolAS is most effective when the workflow-defined oracle landscape has low winner entropy and a reasonably separable top-solver region, but degrades under protocol mismatch that shifts solver rankings and changes the induced labels. These results suggest that, in the evaluated regime, robustness is limited less by representational capacity than by workflow- and protocol-induced instability in solver hierarchies, positioning MolAS as an in-domain selector for fixed pipelines and as a diagnostic tool for assessing when docking algorithm selection is well-posed. Scientific Contribution: MolAS introduces a controlled, embedding-based selector that reduces dependence on heavy graph encoders, enabling a cleaner separation between representational choices and workflow-defined label structure. A cross-benchmark and cross-protocol analysis links selection success and failure to oracle entropy, near-ties among top solvers, and protocol-induced ranking shifts, providing an evidence-backed diagnostic account of when docking algorithm selection is likely to yield gains. The findings differentiate this work from prior docking AS studies that report in-domain improvements under a single fixed workflow by explicitly characterising protocol dependence and motivating protocol-aware modelling as a route to stronger generalisation.

Why it matters: Essential ground-truth data for validating next-gen foundation models like Boltz or Chai.

🗓️ Wednesday, Mar 18

Molecular Dynamics-Guided Design and Chemoproteomic Profiling of Covalent Kinase Activity Probes.

🧬 Abstract

Covalent small molecule probes can be powerful tools to interrogate protein activity state in native cellular environments. The design of familywide activity probes requires an understanding of the molecular sources of conserved and target-specific small molecule targeting across protein family members. Here, we developed and applied a multifaceted docking and molecular dynamics (MD) simulation pipeline to design cell-permeable covalent kinase activity probes from a set of hinge-binding pharmacophores. This computationally-guided approach yielded a series of cell-active indazole sulfonylfluorides that target a conserved catalytic lysine in active protein kinases. Chemoproteomic profiling of a lead probe, K60P, confirmed engagement of more than 100 unique native kinases across several cancer cell lines. Competitive profiling identified kinases as the predominant class of specific targets for K60P but also highlighted significant nonkinase targets for K60P and the established covalent kinase probe, XO44, underscoring the utility of native kinase profiling in situ to identify relevant targets of small molecule kinase inhibitors in cells. Dose-, time- and site-specific proteomic mapping with a known target kinase, ABL1, coupled with a Bayesian Metropolis Monte Carlo (BMMC) kinetic modeling method showed that key descriptors of covalent probe efficiency could be predicted with straightforward dose- and time-dependent covalent engagement studies and highlighted kinact/KI as a key variable to optimize for specific and broad kinase engagement. Finally, focused molecular dynamics simulations revealed that K60P, as well as the comparator probe XO44, preferentially engage with target kinases in their active, DFG-in conformations, which is driven by increasing population of reaction-ready small molecule conformation. These results together establish a computational and kinetic modeling framework for designing covalent activity probes and highlight the balance of target selectivity and kinetic efficiency as a key factor in determining their proteome-wide reactivity.

🗓️ Thursday, Mar 19

Design, Synthesis, Molecular Dynamics Simulations, and Biological Evaluation of PB2 Inhibitors as Anti-Influenza A Virus Agent.

🧬 Abstract

Influenza A virus continues to pose a significant global health threat, causing seasonal epidemics and occasional pandemics. Viral transcription and replication rely on the heterotrimeric polymerase complex where the PB2 subunit initiates RNA synthesis through binding to the host mRNA cap structure. In this study, we began with a structure-activity relationship analysis of the pioneering PB2 inhibitor VX-787. Through computer-aided drug design, combined with considerations of molecular docking scores, ADMET property predictions, and a prodrug esterification strategy, we ultimately designed eight novel compounds. Cytopathic effect assays demonstrated that all compounds exhibited superior inhibitory activity against both H1N1 and H3N2 strains compared to oseltamivir acid. In particular, compounds 11 and 15 displayed nanomolar-level activity against H1N1, while compound 18 showed activity against H3N2 superior to that of VX-787. These findings propose a rational design strategy that may offer new avenues for addressing the resistance and metabolic limitations associated with VX-787 and hold potential for advancing the development of next-generation PB2-targeted anti-influenza therapeutics.

🗓️ Friday, Mar 20

Design, Synthesis, Molecular Docking, and Biological Evaluation of Tanshinone IIA Derivatives as Antibreast Cancer Agents.

🧬 Abstract

In order to explore the effect of amino introduction of Tanshinone IIA on the antitumor activity, 18 novel N-substituted tanshinone IIA derivatives were synthesized and investigated for their anti-proliferative activity in a panel of cancer cell lines. The biological evaluation of antiproliferative assay led to the discovery of compound TA-16 with a highly potent cytotoxic effect using cervical, colon, liver and breast cancer cells, with IC50 = 1.25 µM against MCF-7 cell. The mechanistic studies indicated the ability of TA-16 in inducing apoptosis of MCF-7 cells through mitochondrial pathway and arresting the cell cycle at the G0/G1 phase. It exhibited significant anti-metastasis properties by inhibiting the expression of MMP-9 and MMP-2. Moreover, the cytotoxic study of compound TA-16 on the MCF-10A, a normal human breast epithelial cell line, further highlighted the potential of compound TA-16 as an anticancer agent for breast cancer with a selectivity index of 4.95. Molecular docking analyses confirmed the binding interaction between compound TA-16 and its target proteins, validating its mechanism of action and potential as a therapeutic agent for breast cancer.


📚 All Papers & Quick Reads

🗓️ Monday, Mar 16

🗓️ Tuesday, Mar 17

🗓️ Wednesday, Mar 18

🗓️ Thursday, Mar 19

🗓️ Friday, Mar 20


🛠️ Tools & Datasets

  • 🛠 Tool: HHSuite - Remote homology detection with HMM-HMM comparison.
  • 🛠 Tool: MAFFT - Multiple sequence alignment with high speed and accuracy.
  • 💾 Dataset: AlphaFold Structure Database - 200M+ predicted structures from DeepMind/EMBL-EBI.
  • 💾 Dataset: Uniprot Knowledgebase - The world’s most comprehensive resource for protein sequence and annotation.
  • 🛠 Tool: Clustal Omega - Scalable multiple sequence alignment for protein families.
  • 💾 Dataset: PDB-REDO - Optimized protein structure database with refined models.
  • 🛠 Tool: Rosetta - Protein modeling, docking, and design suite.
  • 💾 Dataset: CATH - Hierarchical protein domain classification for structure and function.
  • 🛠 Tool: AutoDock Vina - Molecular docking for ligand screening and scoring.
  • 💾 Dataset: SCOPe - Curated structural classification of proteins for fold analysis.
  • 🛠 Tool: GROMACS - High-performance molecular dynamics engine.
  • 💾 Dataset: Pfam - Protein families database with curated multiple sequence alignments.

🤖 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