Issue #90: Evaluating zero-shot prediction of monomeric protein design success by AlphaFold, ESMFold, and ProteinMPNN.
Protein Design Digest #90: Evaluating zero-shot prediction of monomeric protein design success by A…

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.
Signal of the Day
Evaluating zero-shot prediction of monomeric protein design success by AlphaFold, ESMFold, and ProteinMPNN.
De novo protein design has enabled the creation of proteins with diverse functionalities that are not found in nature. Despite recent advances, experimental success rates remain inconsistent and context-dependent, posing a bottleneck for broader applications of de novo design. To overcome this, structure and sequence prediction models have been applied to assess design quality prior to experimental testing to save time and resources. In this study, we examined the extent to which AlphaFold, Protein MPNN, and ESMFold can discriminate between experimentally successful and unsuccessful designs. We first curated a benchmark dataset of 614 experimentally characterized de novo designed monomers from 11 different design studies between 2012 and 2021. All predictive models demonstrated moderate ability to discriminate experimental successes (expressed, soluble, monomeric, and fold with the correct secondary structure) from failures. Still, many failed designs have better confidence metrics than successful designs, and confidence metrics were topology-dependent. Among all computational models evaluated, ESMFold average predicted local-distance difference test (pLDDT) yielded the best individual performance at distinguishing between successful and unsuccessful designs. A logistic regression model combining all confidence metrics provided only modest improvement over ESMFold pLDDT alone. Overall, these results show that these models can serve as an initial filtering strategy prior to experimental validation; however, their utility at accurately predicting experimentally successful designs remains limited without task-specific training.
Why this matters: Critical for improving fold accuracy and reducing structural uncertainty in de novo design.
Also Worth Reading
Comprehensive Molecular Docking and Molecular Dynamics Reveal Inhibitors of HER2 L755S, T798I, and T798M based on a Large Database of Curcumin Derivatives.
Objective This study presents a methodology employing virtual screening to identify curcumin derivatives with selective affinity for the HER2 mutations L755S, T798I, and T798M. Methods Curcumin derivatives were retrieved from the ChEMBL database and filtered using KNIME. HER2 mutations were modeled in silico using MOE software with PDB ID 3RCD. Molecular docking and dynamics simulations were conducted to screen high-affinity compounds and evaluate binding interactions. Result From 505 curcumin derivatives, the RDKit module implemented in KNIME successfully filtered 317 compounds. Subsequent molecular docking against wild-type HER2 identified 100 curcumin derivatives with low docking scores, among which the top 20 compounds exhibited better binding affinities than Lapatinib. Further molecular docking screening against the three HER2 mutations identified five lead compounds with the lowest docking scores. Molecular docking and molecular dynamics simulation revealed critical binding interactions with residues essential for kinase domain stability. Chemical structural analysis revealed key modifications, such as geranyl and tripeptide modifications. CHEMBL3758656 and CHEMBL3827366, two curcumin derivatives, demonstrated consistent binding across HER2 mutations and a favorable ADMET profile. Conclusion This study successfully identified CHEMBL3758656 and CHEMBL3827366 as promising HER2 inhibitors through comprehensive virtual screening. Their high binding affinity against L755S, T798I, and T798M mutations and favorable ADME and toxicity properties underscore their potential as alternative therapeutics for HER2-positive breast cancer.
Predicting the Mechanism of Action of Bawei Chufan Soup in Treating Teen Depression through Network Pharmacology, Molecular Docking and Molecular Dynamics Simulation.
Introduction The Bawei Chufan Soup (BWCFS) in Traditional Chinese Medicine (TCM) offers unique advantages in treating Teen Depression (TD). This study utilizes network pharmacology, molecular docking, and molecular dynamics simulations to predict the material basis and mechanism of action of the decoction. Methods The TCMSP, SwissADME, and SwissTargetPrediction databases were utilized to obtain the active ingredients and targets of the BWCFS. The GeneCards, OMIM, and Disgenet databases were used to identify disease targets, and the intersection of these sets was determined using the VENNY tool. The intersecting targets were imported into the String database for protein- protein interaction analysis and the screening of core targets. GO and KEGG enrichment analyses of the intersecting targets were conducted using the David database, and drugcomponent- target-pathway network diagrams were constructed using Cytoscape 3.10.0 software. The molecular docking models of the core components and key targets were generated using AutoDock Vina, and kinetic simulations were conducted using GROMACS 2020.3, paired with the best docking models. Results After screening, the study identified the core components of BWCFS as Baicalein, Kaempferol, Quercetin, Cerevisterol, and Cavidine, with the key targets for TD being AKT1, IL6, TNF, ESR1, and IL1B. GO enrichment analysis revealed that BWCFS may affect signal transduction in the treatment of TD, and is associated with cellular components such as the plasma membrane and dendrites, as well as the regulation of protein binding. KEGG analysis suggested that the intersecting genes are primarily enriched in the cyclic adenosine monophosphate (cAMP) signaling pathway. Molecular docking results indicated that AKT1 shows good binding affinity with Baicalein, Cavidine, Kaempferol, and Quercetin, while Cerevisterol exhibits strong binding with TNF. The molecular dynamics simulations were stable and reliable. During the protein-ligand complex simulation, the binding between the protein and ligand was stable, with van der Waals interactions as the primary force, while hydrogen bonds were present between both the protein and ligand. Discussion Though this study has several common limitations associated with network pharmacology, and no animal experiments have been conducted for verification, the study has successfully explored and validated the mechanism of action of BWCFS in treating TD using scientific computational methods. This study provides new perspectives and methods for the development and management of pharmacological treatments for TD, offering innovative insights into TCM approaches for its treatment. Conclusion Through network pharmacology, this study preliminarily predicted the material basis and mechanism of action of BWCFS in treating TD. Furthermore, the therapeutic effects of BWCFS on TD may be associated with neuroinflammation and structural and functional changes in neuronal dendrites. The cAMP-PKA-NF-κB and cAMP-PI3K-AKT-NF-κB pathways are proposed as potential therapeutic targets.
Exploration of potential neuroprotective agents from medicinal plants for the treatment of Alzheimer’s disease-approach through in silico ADMET, network pharmacology, docking, and dynamics studies.
Context A degenerative brain disorder that causes memory loss is Alzheimer’s disease (AD). Phytoconstituents represent a promising therapeutic strategy due to their diverse bioactivities and favourable safety profiles. This study aimed to identify potential neuroprotective phytoconstituents for AD by pharmacokinetic screening, network pharmacology, molecular docking and molecular dynamics simulation. Among 22 phytoconstituents analysed, the network revealed GSK3β, STAT3, MAOB, ESR1, and PTGS2 as key AD-associated targets. Docking results were supported by dynamic stability analysis. The combined computational results support rosmariquinone as a potential neuroprotective lead compound for AD treatment. Methods Pharmacokinetic and toxicity profiling of 22 phytoconstituents was performed using Swiss ADME and ProTox III software. Target prediction and construction of the phytoconstituent-disease target-gene interaction network were conducted using Swiss Target Prediction, Gene Card and Cytoscape. Pathway enrichment was evaluated via KEGG and GO analysis. Molecular docking of all shortlisted phytoconstituents against AD-related targets was carried out using AutoDock Vina, while 500 ns molecular dynamics simulations were performed using the Desmond module of the Schrödinger Suite to assess complex stability, RMSD, RMSF and hydrogen-bond fluctuation.
Research & AI Updates
- CRISPR variant selectively targets tumor DNA - Van Andel Institute — CRISPR variant selectively targets tumor DNA Van Andel Institute.
- FairJourney Bio opens US cryo-EM facility to accelerate antibody discovery - Manufacturing Chemist — FairJourney Bio opens US cryo-EM facility to accelerate antibody discovery Manufacturing Chemist.
- An AI-guided gene-editing tool for more precise and safer DNA correction - MSN — An AI-guided gene-editing tool for more precise and safer DNA correction MSN.
From the Industry
- Investigational New Drug CDMO Market Forecast Points Higher Toward 2035, Driven by Biologics Complexity - IndexBox — Investigational New Drug CDMO Market Forecast Points Higher Toward 2035, Driven by Biologics Complexity IndexBox.
- VALANX Biotech establishes Scientific Advisory Board to advance ADC therapeutics - News-Medical — VALANX Biotech establishes Scientific Advisory Board to advance ADC therapeutics News-Medical.
- Partner Therapeutics announces submission of supplemental Biologics License Application (sBLA) to FDA for BIZENGRI® (zenocutuzumab-zbco) in NRG1 Fusion Positive Cholangiocarcinoma and Inclusion in updated NCCN Clinical Practice Guidelines in O - PR Newswire — Partner Therapeutics announces submission of supplemental Biologics License Application (sBLA) to FDA for BIZENGRI® (zenocutuzumab-zbco) in NRG1 Fusion Positive Cholangiocarcinoma and Inclusion in updated NCCN Clinical Practice Guidelines in O PR Newswire.
- Pure Biologics S.A. stock (PLPURE000013): Why does its biologics platform matter more now for global - AD HOC NEWS — Pure Biologics S.A.
- AWS Launches Bio Discovery AI to Speed Drug Development - The Tech Buzz — AWS Launches Bio Discovery AI to Speed Drug Development The Tech Buzz.
- RoVa Labs is “the next step” in the valley’s biotech ecosystem - WFIR News — RoVa Labs is “the next step” in the valley’s biotech ecosystem WFIR News.
- Sana Biotechnology and Mayo Clinic Announce Strategic - GlobeNewswire — Sana Biotechnology and Mayo Clinic Announce Strategic GlobeNewswire.
Quick Reads
Comparative Phytochemical Profiling and α-Glucosidase Inhibitory Potential of Acca sellowiana (O.Berg) Burret Plant Parts: Antioxidant Activity Supported by LC-MS/MS and Molecular Docking.
Comparative data on different parts of Acca sellowiana and their enzyme-inhibitory mechanisms remain limited. Read more →
Site-specific post-translational modifications regulate the binding affinity of Conus amadis α-conotoxin Am2005 to Ac-AChBP.
Post-translational modifications (PTMs) play a pivotal role in diversifying the structure and function of peptide toxins from marine cone snails, which have proven applications in the treatment of neuropathic pain. Read more →
Identification of phosphodiesterase 10 A modulators for neurodegenerative and psychiatric disorders: Combination of physics-based virtual screening and machine learning approaches.
Phosphodiesterase (PDE) is a crucial enzyme that regulates intracellular signal transduction by breaking down cyclic adenosine monophosphate (cAMP) and cyclic guanosine monophosphate (cGMP) into inactive forms. Read more →
(-)-Guaiol Inhibits Lung Cancer via PPARG-Dependent Fatty Acid Oxidation.
The objective of this study was to explore the effect of (-)-guaiol on lung cancer using experimental validation, mRNA sequencing, and network pharmacology. Read more →
Exact tunneling splittings of rotationally excited states from symmetrized path-integral molecular dynamics
We extend our previous symmetrized path-integral molecular dynamics approach to calculate tunneling splittings of molecules in rotationally excited states. Read more →
In silico and in vitro study for the limonoid isolated from Swietenia macrophylla as potential α-glucosidase inhibitor.
Limonoids are important constituents of Swietenia macrophylla, exhibiting a range of biological activities that influence human health. Read more →
Identification of potential allosteric inhibitors-modulators for the heterodimer CDC34-UBC protein-protein complex.
To identify potential allosteric modulators targeting the allosteric site of the CDC34-UBC protein-protein interaction (PPI) complex, the current study employs advanced in-silico methods, including similarity searches, molecular docking, pharmacokinetics, and molecular dynamics (MD) simulation. Read more →
DNA-Encoded Library (DEL) Selection Identifies a Distinct DDB1 Ligand Binding Site.
Heterobifunctional proteolysis targeting chimeras (PROTACs) are proven to degrade disease-causing proteins, and many PROTACs have already entered into clinical trials. Read more →
Pipeline Tip
Always validate pLDDT scores before using AlphaFold models for docking.
Resources & Tools
- Dataset: CATH - Hierarchical protein domain classification for structure and function.
- Dataset: SCOPe - Curated structural classification of proteins for fold analysis.
- Tool: GROMACS - High-performance molecular dynamics engine. View all tools →
- Tool: OpenMM - GPU-accelerated molecular simulation toolkit. View all tools →
- Event: Protein Design Hub (LinkedIn Group) (Ongoing)
- Event: Structural Biology Events (Open)
- Job: Arcadia Science - Platform Scientist: Protein Evolution - Lever at Lever
- Job: Lyterian - Scientist I, Biology - Lever at Lever
The protein structure is the language of life; design is its poetry. — Recep Adiyaman