ARXIV:2604.23924 · AGENTS · SUBMITTED 28 APR · 15:18 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions

Hung N. Do · Jessica Z. Kubicek-Sutherland · Oscar A. Negrete · S. Gnanakaran · arXiv

An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

Ship in 2-4 weeks›Score7.0Evidence unverified

Opportunity summary

Pain An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

Evidence 0 refs | 3 sources | 50% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability. The first agentic AI platform for autonomous training of predictive ML models for PPI is designed to…

METHOD

Full abstract

We instruct an AI agent to construct two separate agentic AI platforms: one for autonomous training of predictive ML models for human-human and virus-human PPI, and the other for inducing explicit general rules governing human-human and virus-human PPI. The first agentic AI platform for autonomous training of predictive ML models for PPI is designed to consist of five AI agents that handle autonomous data collection, data verification, feature embedding, model design, and training and validation on three-way protein-disjoint cross-fold datasets. For human-human and human-virus PPIs, the final three-way protein-disjoint ensemble achieves an accuracy of 87.3% and 86.5%, respectively. For cross-checking and interpretability purposes, the second agentic AI platform is designed to replace ML predictions with human-readable rules derived from protein embeddings, physicochemical autocovariance descriptors, compartment annotations, pathway-domain overlap, and graph contexts. For human-human PPI, it is defined by a two-rule induction, whereas human-virus is induced by a more complex set of weighted rules. The rules induced by the second agentic platform align with the SHAP-identified features from the predictive ML models built by the first agentic platform. Taken together, our work demonstrates the agentic AI's ability to orchestrate from data planning to execution, and from rule induction to explanation in ML, opening the door to various applications.

RESULT

ScienceToStartup currently rates this 7.0/10 on the public viability pass. For human-human and human-virus PPIs, the final three-way protein-disjoint ensemble achieves an accuracy of 87.3% and 86.5%, respectively. Code availability is flagged in the…

WHY NOW

Agents moved forward this cycle; last verified April 2026. Public score 7.0/10. Production flags indicate code availability.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score7.0

PainAn AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

Evidence0 refs | 3 sources | 50% coverage

Blockerno shell-level blocker reported

Analysis summary

An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

VerifiedSource: PDF linkedVerifiedPaperPack: citation fields availablePartialProof: unverified proof status

Competitive landscape

An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

Segment

Agents

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "40e86266-1914-42a0-8667-10ef223afe7a", "arxiv_id": "2604.23924", "canonical_route": "/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "endpoints": { "paper_pack": "/api/v1/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti/paper-pack", "build_passport": "/api/v1/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions", "normalized_query": "2604.23924", "route": "/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "paper_ref": "agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti#webpage", "url": "https://sciencetostartup.com/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "name": "Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions", "description": "An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti#scholarlyArticle", "headline": "Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions", "description": "An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.", "url": "https://sciencetostartup.com/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti", "sameAs": "https://arxiv.org/abs/2604.23924", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2604.23924" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-04-27T00:47:35.000Z", "author": [ { "@type": "Person", "name": "Hung N. Do" }, { "@type": "Person", "name": "Jessica Z. Kubicek-Sutherland" }, { "@type": "Person", "name": "Oscar A. Negrete" }, { "@type": "Person", "name": "S. Gnanakaran" } ], "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 7 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Agents" }, { "@type": "PropertyValue", "propertyID": "commercialReadiness", "value": "code" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Agents", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Agentic AI platforms for autonomous training and rule induct", "item": "https://sciencetostartup.com/paper/agentic-ai-platforms-for-autonomous-training-and-rule-induction-of-human-human-and-virus-human-protein-protein-interacti" } ] } ] }

Competitive landscape

An AI agent orchestrates autonomous training and rule induction for protein-protein interactions, achieving high accuracy and interpretability.

Segment

Agents

Adoption evidence

No public code link in the paper record yet

Commercial read

7.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions

Agentic AI platforms for autonomous training and rule induction of human-human and virus-human protein-protein interactions

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline