{"doi":"10.1101/2023.09.13.557628","title":"Machine Learning–Guided Differentiation Therapy Targets Cancer Stem Cells in Colorectal Cancers","abstract":"Abstract Despite advances in artificial intelligence (AI) within cancer research, its application toward realizing differentiation therapy in solid tumors remains limited. Using colorectal cancer (CRC) as a model, we developed a machine learning (ML) framework, CANDiT ( Cancer Associated Nodes for Differentiation Targeting ), to selectively induce differentiation and death of cancer stem cells (CSCs)—a key obstacle to durable response. Centering on one node, CDX2 , a master differentiation factor lost in high-risk, poorly differentiated CRCs, we built a transcriptomic network to identify therapeutic strategies for CDX2 restoration. Network-based prioritization identified PRKAB1 , a stress polarity sensor, as a top target. A clinical-grade PRKAB1 agonist reprogrammed transcriptional networks, induced crypt differentiation, and selectively eliminated CDX2-low CSCs in CRC cell lines, xenografts and patient-derived organoids (PDOs). Multivariate analyses in PDOs revealed a strong therapeutic index, linking efficacy (IC₅₀) to the biomarker-defined CDX2-low state. A 50-gene response signature—derived from an integrated analyses of all three models and trained across multiple datasets—revealed that CDX2 restoration therapy may translate into a ∼50% reduction in recurrence and mortality risk. Mechanistically, treatment activated a differentiation-associated stress polarity signaling axis while dismantling Wnt and YAP-driven stemness programs essential to CSC survival. Thus, CANDiT offers a scalable path to CSC–directed therapy in solid tumors by translating transcriptomic vulnerabilities into precision treatments. Graphic Abstract One sentence summary In this work, Sinha et al. introduce a machine learning–guided framework to identify and target transcriptomic vulnerabilities in colorectal cancer, demonstrating that differentiation therapy selectively eliminates cancer stem cells and reduces recurrence risk. Highlights An ML framework ( CANDiT ) identifies target for differentiation therapy for CRCs Therapy induces crypt differentiation and CSC-specific cytotoxicity CDX2-low state predicts therapeutic response; restoration improves prognosis Therapy dismantles stemness via reactivation of stress polarity signaling","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2023,"id":400787,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9575,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":701112,"name":"Joshua A. Alcantara","orcid":"0000-0002-7970-8970","position":1,"is_corresponding":false},{"id":970014,"name":"Kevin I. Perry","orcid":"0000-0003-1457-442X","position":2,"is_corresponding":false},{"id":552316,"name":"Vanessa Castillo","orcid":"0000-0002-4182-8846","position":3,"is_corresponding":false},{"id":1177506,"name":"Annelies Ondersma","orcid":null,"position":4,"is_corresponding":false},{"id":146473,"name":"Satarupa Banerjee","orcid":null,"position":5,"is_corresponding":false},{"id":1177507,"name":"Ella McLaren","orcid":null,"position":6,"is_corresponding":false},{"id":741477,"name":"Celia R. Espinoza","orcid":null,"position":7,"is_corresponding":false},{"id":356455,"name":"Sahar Taheri","orcid":"0000-0001-6716-7356","position":8,"is_corresponding":false},{"id":903449,"name":"Eleadah Vidales","orcid":null,"position":9,"is_corresponding":false},{"id":552312,"name":"Courtney Tindle","orcid":"0000-0002-8356-9707","position":10,"is_corresponding":false},{"id":1177508,"name":"Adel Adel","orcid":null,"position":11,"is_corresponding":false},{"id":429218,"name":"Siamak Amirfakhri","orcid":null,"position":12,"is_corresponding":false},{"id":825452,"name":"Joseph R. Sawires","orcid":null,"position":13,"is_corresponding":false},{"id":1177225,"name":"Jerry H. Yang","orcid":"0000-0002-7820-4463","position":14,"is_corresponding":false},{"id":399592,"name":"Michael Bouvet","orcid":"0000-0002-0086-2159","position":15,"is_corresponding":false},{"id":294967,"name":"Pradipta Ghosh","orcid":"0000-0002-8917-3201","position":16,"is_corresponding":false},{"id":807708,"name":"Saptarshi Sinha","orcid":"0000-0002-4100-5727","position":0,"is_corresponding":true}],"reference_count":152,"raw_metadata":null,"created_at":"2026-07-19T01:20:04.010538Z","pmid":"37745574","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}