File contents name: 'molecular-glue-discovery-agent'
description: 'AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.'
measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes.
allowed-tools:
- read_file
- run_shell_command
Molecular Glue Discovery Agent
The Molecular Glue Discovery Agent enables AI-driven discovery of molecular glue degraders that induce protein-protein interactions between E3 ligases and neo-substrates for targeted protein degradation. Unlike PROTACs, molecular glues are smaller, more drug-like molecules that can access previously "undruggable" targets through induced proximity mechanisms.
When to Use This Skill
When discovering new molecular glue scaffolds.
For identifying neo-substrate targets for existing glues.
To design glues for specific E3-substrate pairs.
When optimizing glue selectivity and potency.
For virtual screening of glue candidates.
Core Capabilities
Glue Scaffold Discovery : Identify novel molecular glue chemotypes.
Neo-Substrate Prediction : Predict proteins degraded by glues.
Interface Modeling : Model E3-glue-substrate ternary interfaces.
Selectivity Optimization : Design for specific substrate profiles.
SAR Analysis : Structure-activity relationship modeling.
Virtual Screening : Screen compounds for glue activity.
Molecular Glue Mechanisms
Class
E3 Ligase
Mechanism
Example
IMiDs
CRBN
Degron recognition
Lenalidomide
CELMoDs
CRBN
Enhanced IKZF binding
Iberdomide
DCAF15 Glues
DCAF15
Splicing factor degradation
Indisulam
CDK12 Glues
DDB1-CRBN
Cyclin K degradation
CR8 derivatives
β-catenin Glues
Novel
WNT pathway targets
Emerging
Key Neo-Substrates
Substrate
Glue Class
Disease Relevance
IKZF1/3
IMiDs
Multiple myeloma
CK1α
Lenalidomide
MDS del(5q)
GSPT1
CC-885
AML
RBM39
Indisulam
Solid tumors
Cyclin K
CR8
Cancer
SALL4
Thalidomide
Teratogenicity
Workflow
Input : Target substrate, E3 ligase, screening library.
Interface Analysis : Model E3 surface and potential binding sites.
Virtual Screening : Screen compounds for interface binding.
Glue Scoring : Predict neo-substrate recruitment potential.
Selectivity Analysis : Predict off-target degradation.
Optimization : Iterative design for potency/selectivity.
Output : Ranked glue candidates with predicted profiles.
Example Usage
User : "Discover molecular glues that degrade IKZF1 through CRBN with improved selectivity over IKZF3."
Agent Action :
python3 Skills/Drug_Discovery/Molecular_Glue_Discovery_Agent/discover_glue.py \
--target_substrate IKZF1 \
--e3_ligase CRBN \
--selectivity_against IKZF3 \
--scaffold_library imid_derivatives.sdf \
--interface_model crbn_ikzf1_complex.pdb \
--n_candidates 100 \
--output glue_discovery/
Glue Design Parameters
Parameter
Consideration
Optimization
Interface Complementarity
E3-substrate fit
Shape/electrostatics
Degron Recognition
Substrate degron motifs
Motif compatibility
Binding Cooperativity
Positive cooperativity
Enhanced ternary
Selectivity
Off-target degradation
Substrate specificity
Drug Properties
MW, solubility, permeability
Standard optimization
Output Components
Output
Description
Format
Glue Candidates
Ranked molecules
.sdf, SMILES
Predicted Substrates
Neo-substrate profiles
.csv
Interface Models
Ternary complex structures
.pdb
Selectivity Scores
On-target vs off-target
.csv
Degradation Predictions
DC50, Dmax estimates
.csv
SAR Analysis
Structure-activity trends
.json
AI/ML Components
Interface Prediction :
Protein-protein docking
Molecular surface analysis
Deep learning interface scoring
Neo-Substrate Discovery :
Degron motif prediction
Proteome-wide screening
Structural similarity to known substrates
Glue Optimization :
Generative chemistry
Multi-objective optimization
Active learning for synthesis prioritization
Glue vs PROTAC Comparison
Feature
Molecular Glue
PROTAC
Molecular Weight
<500 Da
700-1500 Da
Target Discovery
Serendipitous/AI
Rational
Selectivity
Can be exquisite
Often broader
Substrate Range
Induced neo-substrates
Direct binders
Oral Bioavailability
Generally better
Challenging
Clinical Pipeline (2026)
Drug
Mechanism
Target
Phase
Iberdomide (CC-220)
CELMoD
IKZF1/3, Aiolos
Phase 3
Mezigdomide (CC-92480)
CELMoD
IKZF1/3
Phase 3
Golcadomide (CC-99282)
CELMoD
IKZF1/3
Phase 2
CFT7455
IKZF1/3
IKZF1/3
Phase 1
Degron Motif Analysis
Degron Type
Sequence Features
E3 Recognition
Zinc Finger
C2H2 ZF domain
CRBN-IMiD
Phosphodegron
pSer/pThr motifs
SCF E3s
N-degron
N-terminal residues
UBR1/2
Hydrophobic
Exposed hydrophobics
Quality control
Prerequisites
Python 3.10+
RDKit, Molecular modeling tools
AlphaFold2/3, docking software
Deep learning frameworks
Protein structure databases
Related Skills
PROTAC_Design_Agent - Bifunctional degraders
TPD_Ternary_Complex_Agent - Complex modeling
Virtual_Screening_Agent - High-throughput screening
Protein_Protein_Docking_Agent - PPI modeling
Discovery Strategies
Strategy
Approach
Success Examples
Phenotypic Screening
Degradation readout
IMiDs, indisulam
Target-Based
E3-substrate docking
Rational glues
Chemoproteomics
Pull-down identification
Neo-substrate discovery
AI-Guided
Computational prediction
Emerging
Special Considerations
Polypharmacology : Glues often degrade multiple substratesSpecies Differences : Neo-substrates may differ across speciesResistance : Substrate mutations, E3 downregulationToxicity : Off-target degradation (e.g., SALL4)Hook Effect : Less common than PROTACs
Quality Control
Metric
Purpose
Threshold
Interface Score
Complex stability
>0.6
Cooperativity
Enhanced binding
>1.5
Selectivity Index
On/off-target ratio
>10
Drug-likeness
Developability
Lipinski compliant
Future Directions
Direction
Status
Potential
New E3 Ligases
Active research
Expanded target space
Protein-Protein Glues
Emerging
Beyond degradation
AI-First Discovery
Advancing
Reduced serendipity
Combination Glues
Conceptual
Multi-target degradation
Author
AI Group - Biomedical AI Platform
1 --- 2 name: molecular-glue-discovery-agent 3 description: <!-- 4 --- 5 <!-- 6 # COPYRIGHT NOTICE 7 # This file is part of the "Universal Biomedical Skills" project. 8 # Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu> 9 # All Rights Reserved. 10 # 11 # This code is proprietary and confidential. 12 # Unauthorized copying of this file, via any medium is strictly prohibited. 13 # 14 # Provenance: Authenticated by MD BABU MIA 15 16 --> 17 18 --- 19 name: 'molecular-glue-discovery-agent' 20 description: 'AI-powered molecular glue discovery for targeted protein degradation, enabling neo-substrate recruitment and undruggable target degradation through E3 ligase interface modulation.' 21 measurable_outcome: Execute skill workflow successfully with valid output within 15 minutes. 22 allowed-tools: 23 - read_file 24 - run_shell_command 25 --- 26 27 28 # Molecular Glue Discovery Agent 29 30 The **Molecular Glue Discovery Agent** enables AI-driven discovery of molecular glue degraders that induce protein-protein interactions between E3 ligases and neo-substrates for targeted protein degradation. Unlike PROTACs, molecular glues are smaller, more drug-like molecules that can access previously "undruggable" targets through induced proximity mechanisms. 31 32 ## When to Use This Skill 33 34 * When discovering new molecular glue scaffolds. 35 * For identifying neo-substrate targets for existing glues. 36 * To design glues for specific E3-substrate pairs. 37 * When optimizing glue selectivity and potency. 38 * For virtual screening of glue candidates. 39 40 ## Core Capabilities 41 42 1. **Glue Scaffold Discovery**: Identify novel molecular glue chemotypes. 43 44 2. **Neo-Substrate Prediction**: Predict proteins degraded by glues. 45 46 3. **Interface Modeling**: Model E3-glue-substrate ternary interfaces. 47 48 4. **Selectivity Optimization**: Design for specific substrate profiles. 49 50 5. **SAR Analysis**: Structure-activity relationship modeling. 51 52 6. **Virtual Screening**: Screen compounds for glue activity. 53 54 ## Molecular Glue Mechanisms 55 56 | Class | E3 Ligase | Mechanism | Example | 57 |-------|-----------|-----------|---------| 58 | IMiDs | CRBN | Degron recognition | Lenalidomide | 59 | CELMoDs | CRBN | Enhanced IKZF binding | Iberdomide | 60 | DCAF15 Glues | DCAF15 | Splicing factor degradation | Indisulam | 61 | CDK12 Glues | DDB1-CRBN | Cyclin K degradation | CR8 derivatives | 62 | β-catenin Glues | Novel | WNT pathway targets | Emerging | 63 64 ## Key Neo-Substrates 65 66 | Substrate | Glue Class | Disease Relevance | 67 |-----------|------------|-------------------| 68 | IKZF1/3 | IMiDs | Multiple myeloma | 69 | CK1α | Lenalidomide | MDS del(5q) | 70 | GSPT1 | CC-885 | AML | 71 | RBM39 | Indisulam | Solid tumors | 72 | Cyclin K | CR8 | Cancer | 73 | SALL4 | Thalidomide | Teratogenicity | 74 75 ## Workflow 76 77 1. **Input**: Target substrate, E3 ligase, screening library. 78 79 2. **Interface Analysis**: Model E3 surface and potential binding sites. 80 81 3. **Virtual Screening**: Screen compounds for interface binding. 82 83 4. **Glue Scoring**: Predict neo-substrate recruitment potential. 84 85 5. **Selectivity Analysis**: Predict off-target degradation. 86 87 6. **Optimization**: Iterative design for potency/selectivity. 88 89 7. **Output**: Ranked glue candidates with predicted profiles. 90 91 ## Example Usage 92 93 **User**: "Discover molecular glues that degrade IKZF1 through CRBN with improved selectivity over IKZF3." 94 95 **Agent Action**: 96 ```bash 97 python3 Skills/Drug_Discovery/Molecular_Glue_Discovery_Agent/discover_glue.py \ 98 --target_substrate IKZF1 \ 99 --e3_ligase CRBN \ 100 --selectivity_against IKZF3 \ 101 --scaffold_library imid_derivatives.sdf \ 102 --interface_model crbn_ikzf1_complex.pdb \ 103 --n_candidates 100 \ 104 --output glue_discovery/ 105 ``` 106 107 ## Glue Design Parameters 108 109 | Parameter | Consideration | Optimization | 110 |-----------|---------------|--------------| 111 | Interface Complementarity | E3-substrate fit | Shape/electrostatics | 112 | Degron Recognition | Substrate degron motifs | Motif compatibility | 113 | Binding Cooperativity | Positive cooperativity | Enhanced ternary | 114 | Selectivity | Off-target degradation | Substrate specificity | 115 | Drug Properties | MW, solubility, permeability | Standard optimization | 116 117 ## Output Components 118 119 | Output | Description | Format | 120 |--------|-------------|--------| 121 | Glue Candidates | Ranked molecules | .sdf, SMILES | 122 | Predicted Substrates | Neo-substrate profiles | .csv | 123 | Interface Models | Ternary complex structures | .pdb | 124 | Selectivity Scores | On-target vs off-target | .csv | 125 | Degradation Predictions | DC50, Dmax estimates | .csv | 126 | SAR Analysis | Structure-activity trends | .json | 127 128 ## AI/ML Components 129 130 **Interface Prediction**: 131 - Protein-protein docking 132 - Molecular surface analysis 133 - Deep learning interface scoring 134 135 **Neo-Substrate Discovery**: 136 - Degron motif prediction 137 - Proteome-wide screening 138 - Structural similarity to known substrates 139 140 **Glue Optimization**: 141 - Generative chemistry 142 - Multi-objective optimization 143 - Active learning for synthesis prioritization 144 145 ## Glue vs PROTAC Comparison 146 147 | Feature | Molecular Glue | PROTAC | 148 |---------|----------------|--------| 149 | Molecular Weight | <500 Da | 700-1500 Da | 150 | Target Discovery | Serendipitous/AI | Rational | 151 | Selectivity | Can be exquisite | Often broader | 152 | Substrate Range | Induced neo-substrates | Direct binders | 153 | Oral Bioavailability | Generally better | Challenging | 154 155 ## Clinical Pipeline (2026) 156 157 | Drug | Mechanism | Target | Phase | 158 |------|-----------|--------|-------| 159 | Iberdomide (CC-220) | CELMoD | IKZF1/3, Aiolos | Phase 3 | 160 | Mezigdomide (CC-92480) | CELMoD | IKZF1/3 | Phase 3 | 161 | Golcadomide (CC-99282) | CELMoD | IKZF1/3 | Phase 2 | 162 | CFT7455 | IKZF1/3 | IKZF1/3 | Phase 1 | 163 164 ## Degron Motif Analysis 165 166 | Degron Type | Sequence Features | E3 Recognition | 167 |-------------|-------------------|----------------| 168 | Zinc Finger | C2H2 ZF domain | CRBN-IMiD | 169 | Phosphodegron | pSer/pThr motifs | SCF E3s | 170 | N-degron | N-terminal residues | UBR1/2 | 171 | Hydrophobic | Exposed hydrophobics | Quality control | 172 173 ## Prerequisites 174 175 * Python 3.10+ 176 * RDKit, Molecular modeling tools 177 * AlphaFold2/3, docking software 178 * Deep learning frameworks 179 * Protein structure databases 180 181 ## Related Skills 182 183 * PROTAC_Design_Agent - Bifunctional degraders 184 * TPD_Ternary_Complex_Agent - Complex modeling 185 * Virtual_Screening_Agent - High-throughput screening 186 * Protein_Protein_Docking_Agent - PPI modeling 187 188 ## Discovery Strategies 189 190 | Strategy | Approach | Success Examples | 191 |----------|----------|------------------| 192 | Phenotypic Screening | Degradation readout | IMiDs, indisulam | 193 | Target-Based | E3-substrate docking | Rational glues | 194 | Chemoproteomics | Pull-down identification | Neo-substrate discovery | 195 | AI-Guided | Computational prediction | Emerging | 196 197 ## Special Considerations 198 199 1. **Polypharmacology**: Glues often degrade multiple substrates 200 2. **Species Differences**: Neo-substrates may differ across species 201 3. **Resistance**: Substrate mutations, E3 downregulation 202 4. **Toxicity**: Off-target degradation (e.g., SALL4) 203 5. **Hook Effect**: Less common than PROTACs 204 205 ## Quality Control 206 207 | Metric | Purpose | Threshold | 208 |--------|---------|-----------| 209 | Interface Score | Complex stability | >0.6 | 210 | Cooperativity | Enhanced binding | >1.5 | 211 | Selectivity Index | On/off-target ratio | >10 | 212 | Drug-likeness | Developability | Lipinski compliant | 213 214 ## Future Directions 215 216 | Direction | Status | Potential | 217 |-----------|--------|-----------| 218 | New E3 Ligases | Active research | Expanded target space | 219 | Protein-Protein Glues | Emerging | Beyond degradation | 220 | AI-First Discovery | Advancing | Reduced serendipity | 221 | Combination Glues | Conceptual | Multi-target degradation | 222 223 ## Author 224 225 AI Group - Biomedical AI Platform 226 227 228 <!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->
commit dcac6b6459
Frequently asked questions How do I install the Molecular Glue Discovery Agent skill? Run npx skillmds@latest add biotender-max/molecular-glue-discovery-agent in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Molecular Glue Discovery Agent skill do? <!-- It is listed under Product & Planning on SkillMD.
Is Molecular Glue Discovery Agent safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Molecular Glue Discovery Agent? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Molecular Glue Discovery Agent free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Molecular Glue Discovery Agent? BioTender-max (@biotender-max) published this skill. Their other Agent Skills are listed on their SkillMD profile.
BioTender-max