Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma

Noah E. Berlow, Rishi Rikhi, Mathew Geltzeiler, Jinu Abraham, Matthew N. Svalina, Lara E. Davis, Erin Wise, Maria Mancini, Jonathan Noujaim, Atiya Mansoor, Michael J. Quist, Kevin L. Matlock, Martin W. Goros, Brian S. Hernandez, Yee C. Doung, Khin Thway, Tomohide Tsukahara, Jun Nishio, Elaine T. Huang, Susan AirhartCarol J. Bult, Regina Gandour-Edwards, Robert G. Maki, Robin L. Jones, Joel E. Michalek, Milan Milovancev, Souparno Ghosh, Ranadip Pal, Charles Keller

Research output: Contribution to journalArticle

Abstract

Background: Cancer patients with advanced disease routinely exhaust available clinical regimens and lack actionable genomic medicine results, leaving a large patient population without effective treatments options when their disease inevitably progresses. To address the unmet clinical need for evidence-based therapy assignment when standard clinical approaches have failed, we have developed a probabilistic computational modeling approach which integrates molecular sequencing data with functional assay data to develop patient-specific combination cancer treatments. Methods: Tissue taken from a murine model of alveolar rhabdomyosarcoma was used to perform single agent drug screening and DNA/RNA sequencing experiments; results integrated via our computational modeling approach identified a synergistic personalized two-drug combination. Cells derived from the primary murine tumor were allografted into mouse models and used to validate the personalized two-drug combination. Computational modeling of single agent drug screening and RNA sequencing of multiple heterogenous sites from a single patient's epithelioid sarcoma identified a personalized two-drug combination effective across all tumor regions. The heterogeneity-consensus combination was validated in a xenograft model derived from the patient's primary tumor. Cell cultures derived from human and canine undifferentiated pleomorphic sarcoma were assayed by drug screen; computational modeling identified a resistance-abrogating two-drug combination common to both cell cultures. This combination was validated in vitro via a cell regrowth assay. Results: Our computational modeling approach addresses three major challenges in personalized cancer therapy: synergistic drug combination predictions (validated in vitro and in vivo in a genetically engineered murine cancer model), identification of unifying therapeutic targets to overcome intra-tumor heterogeneity (validated in vivo in a human cancer xenograft), and mitigation of cancer cell resistance and rewiring mechanisms (validated in vitro in a human and canine cancer model). Conclusions: These proof-of-concept studies support the use of an integrative functional approach to personalized combination therapy prediction for the population of high-risk cancer patients lacking viable clinical options and without actionable DNA sequencing-based therapy.

Original languageEnglish (US)
Article number593
JournalBMC cancer
Volume19
Issue number1
DOIs
StatePublished - Jun 17 2019

Fingerprint

Drug Combinations
Sarcoma
Neoplasms
RNA Sequence Analysis
Preclinical Drug Evaluations
DNA Sequence Analysis
Heterografts
Canidae
Molecular Sequence Data
Therapeutics
Cell Culture Techniques
Alveolar Rhabdomyosarcoma
Combination Drug Therapy
Population
Medicine

Keywords

  • Artificial intelligence and machine learning
  • Combination therapy
  • Computational modeling
  • Drug screening
  • High-throughput sequencing
  • Pediatric cancer
  • Personalized therapy
  • Sarcoma

ASJC Scopus subject areas

  • Oncology
  • Genetics
  • Cancer Research

Cite this

Berlow, N. E., Rikhi, R., Geltzeiler, M., Abraham, J., Svalina, M. N., Davis, L. E., ... Keller, C. (2019). Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma. BMC cancer, 19(1), [593]. https://doi.org/10.1186/s12885-019-5681-6

Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma. / Berlow, Noah E.; Rikhi, Rishi; Geltzeiler, Mathew; Abraham, Jinu; Svalina, Matthew N.; Davis, Lara E.; Wise, Erin; Mancini, Maria; Noujaim, Jonathan; Mansoor, Atiya; Quist, Michael J.; Matlock, Kevin L.; Goros, Martin W.; Hernandez, Brian S.; Doung, Yee C.; Thway, Khin; Tsukahara, Tomohide; Nishio, Jun; Huang, Elaine T.; Airhart, Susan; Bult, Carol J.; Gandour-Edwards, Regina; Maki, Robert G.; Jones, Robin L.; Michalek, Joel E.; Milovancev, Milan; Ghosh, Souparno; Pal, Ranadip; Keller, Charles.

In: BMC cancer, Vol. 19, No. 1, 593, 17.06.2019.

Research output: Contribution to journalArticle

Berlow, NE, Rikhi, R, Geltzeiler, M, Abraham, J, Svalina, MN, Davis, LE, Wise, E, Mancini, M, Noujaim, J, Mansoor, A, Quist, MJ, Matlock, KL, Goros, MW, Hernandez, BS, Doung, YC, Thway, K, Tsukahara, T, Nishio, J, Huang, ET, Airhart, S, Bult, CJ, Gandour-Edwards, R, Maki, RG, Jones, RL, Michalek, JE, Milovancev, M, Ghosh, S, Pal, R & Keller, C 2019, 'Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma', BMC cancer, vol. 19, no. 1, 593. https://doi.org/10.1186/s12885-019-5681-6
Berlow, Noah E. ; Rikhi, Rishi ; Geltzeiler, Mathew ; Abraham, Jinu ; Svalina, Matthew N. ; Davis, Lara E. ; Wise, Erin ; Mancini, Maria ; Noujaim, Jonathan ; Mansoor, Atiya ; Quist, Michael J. ; Matlock, Kevin L. ; Goros, Martin W. ; Hernandez, Brian S. ; Doung, Yee C. ; Thway, Khin ; Tsukahara, Tomohide ; Nishio, Jun ; Huang, Elaine T. ; Airhart, Susan ; Bult, Carol J. ; Gandour-Edwards, Regina ; Maki, Robert G. ; Jones, Robin L. ; Michalek, Joel E. ; Milovancev, Milan ; Ghosh, Souparno ; Pal, Ranadip ; Keller, Charles. / Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma. In: BMC cancer. 2019 ; Vol. 19, No. 1.
@article{eba881aca78d43ec81dee4c9ad1b5b65,
title = "Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma",
abstract = "Background: Cancer patients with advanced disease routinely exhaust available clinical regimens and lack actionable genomic medicine results, leaving a large patient population without effective treatments options when their disease inevitably progresses. To address the unmet clinical need for evidence-based therapy assignment when standard clinical approaches have failed, we have developed a probabilistic computational modeling approach which integrates molecular sequencing data with functional assay data to develop patient-specific combination cancer treatments. Methods: Tissue taken from a murine model of alveolar rhabdomyosarcoma was used to perform single agent drug screening and DNA/RNA sequencing experiments; results integrated via our computational modeling approach identified a synergistic personalized two-drug combination. Cells derived from the primary murine tumor were allografted into mouse models and used to validate the personalized two-drug combination. Computational modeling of single agent drug screening and RNA sequencing of multiple heterogenous sites from a single patient's epithelioid sarcoma identified a personalized two-drug combination effective across all tumor regions. The heterogeneity-consensus combination was validated in a xenograft model derived from the patient's primary tumor. Cell cultures derived from human and canine undifferentiated pleomorphic sarcoma were assayed by drug screen; computational modeling identified a resistance-abrogating two-drug combination common to both cell cultures. This combination was validated in vitro via a cell regrowth assay. Results: Our computational modeling approach addresses three major challenges in personalized cancer therapy: synergistic drug combination predictions (validated in vitro and in vivo in a genetically engineered murine cancer model), identification of unifying therapeutic targets to overcome intra-tumor heterogeneity (validated in vivo in a human cancer xenograft), and mitigation of cancer cell resistance and rewiring mechanisms (validated in vitro in a human and canine cancer model). Conclusions: These proof-of-concept studies support the use of an integrative functional approach to personalized combination therapy prediction for the population of high-risk cancer patients lacking viable clinical options and without actionable DNA sequencing-based therapy.",
keywords = "Artificial intelligence and machine learning, Combination therapy, Computational modeling, Drug screening, High-throughput sequencing, Pediatric cancer, Personalized therapy, Sarcoma",
author = "Berlow, {Noah E.} and Rishi Rikhi and Mathew Geltzeiler and Jinu Abraham and Svalina, {Matthew N.} and Davis, {Lara E.} and Erin Wise and Maria Mancini and Jonathan Noujaim and Atiya Mansoor and Quist, {Michael J.} and Matlock, {Kevin L.} and Goros, {Martin W.} and Hernandez, {Brian S.} and Doung, {Yee C.} and Khin Thway and Tomohide Tsukahara and Jun Nishio and Huang, {Elaine T.} and Susan Airhart and Bult, {Carol J.} and Regina Gandour-Edwards and Maki, {Robert G.} and Jones, {Robin L.} and Michalek, {Joel E.} and Milan Milovancev and Souparno Ghosh and Ranadip Pal and Charles Keller",
year = "2019",
month = "6",
day = "17",
doi = "10.1186/s12885-019-5681-6",
language = "English (US)",
volume = "19",
journal = "BMC Cancer",
issn = "1471-2407",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Probabilistic modeling of personalized drug combinations from integrated chemical screen and molecular data in sarcoma

AU - Berlow, Noah E.

AU - Rikhi, Rishi

AU - Geltzeiler, Mathew

AU - Abraham, Jinu

AU - Svalina, Matthew N.

AU - Davis, Lara E.

AU - Wise, Erin

AU - Mancini, Maria

AU - Noujaim, Jonathan

AU - Mansoor, Atiya

AU - Quist, Michael J.

AU - Matlock, Kevin L.

AU - Goros, Martin W.

AU - Hernandez, Brian S.

AU - Doung, Yee C.

AU - Thway, Khin

AU - Tsukahara, Tomohide

AU - Nishio, Jun

AU - Huang, Elaine T.

AU - Airhart, Susan

AU - Bult, Carol J.

AU - Gandour-Edwards, Regina

AU - Maki, Robert G.

AU - Jones, Robin L.

AU - Michalek, Joel E.

AU - Milovancev, Milan

AU - Ghosh, Souparno

AU - Pal, Ranadip

AU - Keller, Charles

PY - 2019/6/17

Y1 - 2019/6/17

N2 - Background: Cancer patients with advanced disease routinely exhaust available clinical regimens and lack actionable genomic medicine results, leaving a large patient population without effective treatments options when their disease inevitably progresses. To address the unmet clinical need for evidence-based therapy assignment when standard clinical approaches have failed, we have developed a probabilistic computational modeling approach which integrates molecular sequencing data with functional assay data to develop patient-specific combination cancer treatments. Methods: Tissue taken from a murine model of alveolar rhabdomyosarcoma was used to perform single agent drug screening and DNA/RNA sequencing experiments; results integrated via our computational modeling approach identified a synergistic personalized two-drug combination. Cells derived from the primary murine tumor were allografted into mouse models and used to validate the personalized two-drug combination. Computational modeling of single agent drug screening and RNA sequencing of multiple heterogenous sites from a single patient's epithelioid sarcoma identified a personalized two-drug combination effective across all tumor regions. The heterogeneity-consensus combination was validated in a xenograft model derived from the patient's primary tumor. Cell cultures derived from human and canine undifferentiated pleomorphic sarcoma were assayed by drug screen; computational modeling identified a resistance-abrogating two-drug combination common to both cell cultures. This combination was validated in vitro via a cell regrowth assay. Results: Our computational modeling approach addresses three major challenges in personalized cancer therapy: synergistic drug combination predictions (validated in vitro and in vivo in a genetically engineered murine cancer model), identification of unifying therapeutic targets to overcome intra-tumor heterogeneity (validated in vivo in a human cancer xenograft), and mitigation of cancer cell resistance and rewiring mechanisms (validated in vitro in a human and canine cancer model). Conclusions: These proof-of-concept studies support the use of an integrative functional approach to personalized combination therapy prediction for the population of high-risk cancer patients lacking viable clinical options and without actionable DNA sequencing-based therapy.

AB - Background: Cancer patients with advanced disease routinely exhaust available clinical regimens and lack actionable genomic medicine results, leaving a large patient population without effective treatments options when their disease inevitably progresses. To address the unmet clinical need for evidence-based therapy assignment when standard clinical approaches have failed, we have developed a probabilistic computational modeling approach which integrates molecular sequencing data with functional assay data to develop patient-specific combination cancer treatments. Methods: Tissue taken from a murine model of alveolar rhabdomyosarcoma was used to perform single agent drug screening and DNA/RNA sequencing experiments; results integrated via our computational modeling approach identified a synergistic personalized two-drug combination. Cells derived from the primary murine tumor were allografted into mouse models and used to validate the personalized two-drug combination. Computational modeling of single agent drug screening and RNA sequencing of multiple heterogenous sites from a single patient's epithelioid sarcoma identified a personalized two-drug combination effective across all tumor regions. The heterogeneity-consensus combination was validated in a xenograft model derived from the patient's primary tumor. Cell cultures derived from human and canine undifferentiated pleomorphic sarcoma were assayed by drug screen; computational modeling identified a resistance-abrogating two-drug combination common to both cell cultures. This combination was validated in vitro via a cell regrowth assay. Results: Our computational modeling approach addresses three major challenges in personalized cancer therapy: synergistic drug combination predictions (validated in vitro and in vivo in a genetically engineered murine cancer model), identification of unifying therapeutic targets to overcome intra-tumor heterogeneity (validated in vivo in a human cancer xenograft), and mitigation of cancer cell resistance and rewiring mechanisms (validated in vitro in a human and canine cancer model). Conclusions: These proof-of-concept studies support the use of an integrative functional approach to personalized combination therapy prediction for the population of high-risk cancer patients lacking viable clinical options and without actionable DNA sequencing-based therapy.

KW - Artificial intelligence and machine learning

KW - Combination therapy

KW - Computational modeling

KW - Drug screening

KW - High-throughput sequencing

KW - Pediatric cancer

KW - Personalized therapy

KW - Sarcoma

UR - http://www.scopus.com/inward/record.url?scp=85067500287&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067500287&partnerID=8YFLogxK

U2 - 10.1186/s12885-019-5681-6

DO - 10.1186/s12885-019-5681-6

M3 - Article

C2 - 31208434

AN - SCOPUS:85067500287

VL - 19

JO - BMC Cancer

JF - BMC Cancer

SN - 1471-2407

IS - 1

M1 - 593

ER -