Orly Alter

Excited to share that my APL Quantum paper, with fantastic co-authors Elizabeth Newman, Sri Priya Ponnapalli @priyaponnapalli, and Jessica Tsai, MD, PhD, @jestsai accompanied by a @EurekAlert writeup— eurekalert.org/news-releases… and this @AIP_Publishing #Scilight— doi.org/10.1063/10.0044179 is now published— doi.org/10.1063/5.0305656 A #QuantumMechanics approach to #ArtificialIntelligence can improve #cancer outcomes For a child diagnosed with neuroblastoma, the path to treatment isn’t simple. Some types of neuroblastoma resolve on their own, while others require aggressive treatments. Researchers have tried matching treatments to patients based on one-gene mutations but with limited success, as patients’ outcomes depend on their entire molecular background containing millions of features, such as DNA and RNA from tissues and blood. Current artificial intelligence and #MachineLearning (#AI / #ML) approaches struggle to derive predictors from the 20-100 patient samples of a clinical trial because they require massive amounts of training data. But by using the mathematics of quantum mechanics, Alter et al. developed an AI/ML technique that can improve treatment selections and drug success rates. The technique features a suite of algorithms, called multitensor comparative spectral decompositions, which were built on the quantum mechanical concepts of entanglement and superposition. They separate the molecular data from a patient into outcome components represented by patterns entangled across the feature types, similarly to how a prism splits white light into its color components. The authors demonstrated their technique with an analysis of open-source data of neuroblastoma cases. Their algorithms discovered two new predictors, found in the tumor and blood genomes and tumor transcriptome, of patients’ life expectancy in response to treatment that all other methods missed. The two predictors consistently outperformed standard biomarkers across tumor and blood DNA and tumor RNA. “Neural network models are black boxes, but our predictors are interpretable; they point to disease mechanisms and suggest genes to target to sensitize tumors to treatment,” said author Orly Alter. “Our team recently experimentally validated our predictions of adult glioblastoma patient outcome and drug targets in clinical trials and CRISPR-Cas9 studies.” Thanks also to our wonderful supporters, including the NIH/ National Cancer Institute (NCI) Physical Sciences in Oncology Project "Multitensor Decompositions for Personalized Cancer Diagnostics and Prognostics," the NSF/ American Institute of Mathematics (AIM) Quantum Research Community Project "AIM Q," and the Musella Foundation in partnership with StacheStrong. #Genomics #MultiOmics #PrecisionMedicine #QuantumComputing

Tuesday 10/22 at 3:30pm in Room 251 DE, join the 2nd Rapid Fire Session on Making #Data Work for Us at #PharmSci360 in SLC! I will present the #PrecisionMedicine platform we are building at our @UUtah spin-off @PrismAIThera peutics, Inc., and our multi-tensor AI/ML powering it. cdmcd.co/va69jd Title: AI/ML-Derived Biomarkers from Small-Cohort and Noisy, High-Dimensional Multi-Omic Clinical Data Abstract: Prediction in medicine remains limited. The entire multi-ome affects cancer and other diseases. And, unlike typical #ArtificialIntelligence and #MachineLearning (#AI / #ML), e.g., neural networks and deep learning, our multi-tensor AI/ML is uniquely able to identify actionable and mechanistically interpretable biomarkers from multi-omic clinical data. We have been developing the algorithms, i.e., the "multi-tensor comparative spectral decompositions," to extend the mathematics that underlies #quantum mechanics to overcome the limitations of typical AI/ML. We demonstrated the algorithms in the discovery and validation of biomarkers in, e.g., astrocytoma, including glioblastoma (GBM), brain, lung, nerve, ovarian, and uterine cancers. The algorithms identified the biomarkers repeatedly, in federated and imbalanced public datasets from as few as 50–100 patients each, showing that the algorithms are batch- and demographics-agnostic, and the biomarkers are actionable in the general population. The GBM biomarker, the first to encompass the whole genome, was additionally prospectively and retrospectively experimentally validated to be the most accurate and precise predictor of survival and response to treatment. All other attempts to associate a GBM tumor’s DNA copy-number alterations with the patient’s outcome failed, establishing that the algorithms find what all others miss, and the biomarkers outperform all others where they exist. Recent experiments show that the GBM biomarker correctly identified previously unrecognized drug targets, i.e., genes that are required for the tumor’s cell proliferation and viability, further validating the mechanistic interpretability of the multi-tensor AI/ML. Let’s cure #cancer and other diseases together! @HuntsmanCancer @AAPSComms @NCIPhySci @UtahCOE @UTechLicensing @BioUtah @UUSCI @UtahBME @AltitudeLab @UtahCGM @OneU_RAI #DataScience #MultiTensorDecompositions #SingularValueDecomposition

Friday 9/20 at 2:30pm, join the panel on #AI for #Pediatric #Cancer at the 2024 #BrainStormSummit in DC! I will discuss the platform we are building at our @UUtah spin-off, and our multi-tensor AI/ #ML underlying it. The @PrismAIThera peutics, Inc. platform is uniquely able to accelerate #PrecisionMedicine. The multi-tensor AI/ML is uniquely able to identify actionable and mechanistically interpretable predictors from small-cohort and noisy, high-dimensional multi-omic clinical data. Let’s partner up to cure the most devastating diseases! #ArtificialIntelligence #Biomarkers #BrainCancer #DataScience #MachineLearning #MultiTensorDecompositions #SingularValueDecomposition @brainstormsmt @HuntsmanCancer @NCIPhySci @OneU_RAI @UofUNeurosurg @UtahBME @UtahCGM @UtahCOE @UTechLicensing @UUSCI @JesTsai

Meet Asaf Zviran & me, representing @UUtah spinoff @PrismAIThera peutics at #ASCO24! Our platform is your operating system for drug development, biomarker discovery, & #ClinicalTrials, & our team is on a mission to accelerate your precision therapeutics! Typical AI cannot generate effective biomarkers, or predictors, from your real-life, small-cohort, & noisy, multi-omic data. But #PrismAI can! And with #PrismAIInside, your biotech company & health system can too! Our AI extends the mathematics that underlies #quantum mechanics to overcome the typical AI limitations. Our algorithms (i) compare & integrate any data types, of any number & dimensions, & (ii) scale with data sizes. Our models (iii) are interpretable in terms of known biology & batch effects & (iv) correctly predict previously unknown mechanisms. Our prospective & retrospective validation of a genome-wide pattern of DNA copy-number alterations in brain tumors proved that the models discover biomarkers, or predictors, of survival & response to treatment that are (v) the most accurate & precise, (vi) clinically actionable in the general population based upon as few as 50–100 patients, & (vii) are consistent across studies & over time. On Saturday 6/1 from 12:30pm online & at 1:30–4:30pm in Hall A, join me as I discuss two recent @NCIPhySci -funded projects demonstrating the power of our platform. a. #AI / #ML-Derived Mechanistically-Interpretable Whole-Genome #Biomarkers of Patient Survival in Pre-Treatment Primary #Neuroblastoma Tumors & Whole Blood; meetings.asco.org/abstracts-… b. Prospective #Validation from a Retrospective Trial That Validated an AI/ML-Derived Whole-Genome Biomarker as the Most Accurate & Precise Predictor of Survival & Response to Treatment in #Glioblastoma; meetings.asco.org/abstracts-… Thanks as always to our fantastic collaborators, @JesTsai, @PriyaPonnapalli, Elizabeth Newman, Penelope Miron, @KristyLSMisk, @KristinWaite, @NSosonkina, Sara Coppens, Anthony Bryan, @EstevanKiernan, Huanming Yang, Jay Bowen, @GhunwaNakouzi, @NCIJBSloan, Andrew Sloan, & Tiffany Hodges, our amazing program managers, @Nas_Zahir, David Miller, @EMJChavarria, @SEHanlon, & Jennifer Couch, the awesome team at @AltitudeLab, @Chandanananana, Kapil Sharma, & Lauryn Narramore, & the wonderful team at @UTechLicensing, Aaron Duffy, & Eric Paulsen! Reach out to us to schedule a meeting! @UUSCI @HuntsmanCancer @UtahCGM @UtahBME @UtahCOE @UofUNeurosurg @OneU_RAI #ArtificialIntelligence #DataScience #MachineLearning #BrainCancer #Cancer #PrecisionMedicine #Research

Wednesday 4/24 from 1pm on, join my #Genomic #SignalProcessing Lab as we celebrate 30 years of @UUSCI at the @UUtah on the 3rd floor of WEB– lnkd.in/giJRAbmw We will present two of our @NCIPhySci-funded projects: a. #AI/#ML-Derived Mechanistically-Interpretable Whole-Genome #Biomarkers of Patient Survival in Pre-Treatment Primary #Neuroblastoma Tumors & Whole Blood; & b. Prospective #Validation from a Retrospective Trial That Validated an AI/ML-Derived Whole-Genome Biomarker as the Most Accurate & Precise Predictor of Survival & Response to Treatment in #Glioblastoma. Thanks to our amazing collaborators, including @JesTsai, @PriyaPonnapalli, Elizabeth Newman, Penelope Miron, @KristyLSMisk, @KristinWaite, @NSosonkina, Sara Coppens, Anthony Bryan, @EstevanKiernan, Huanming Yang, Jay Bowen, @GhunwaNakouzi, @NCIJBSloan, Andrew Sloan, & Tiffany Hodges! Thanks to our supportive program managers, including @Nas_Zahir, David Miller, @EMJChavarria, @SEHanlon, & Jennifer Couch! Thanks also to our photographing colleague @NCIKenAldape at @AACR: #BrainCancer (Minneapolis, MN, October 19–22, 2023); lnkd.in/grRt43Bd RSVP– lnkd.in/gRpuhiSS @TheNCI @HuntsmanCancer @UtahCOE @UtahBME #ArtificialIntelligence #DataScience #MachineLearning #BrainCancer #Cancer #PrecisionMedicine #Research

#HappyBirthday, #GeneGolub – a hero, a mentor & a friend – on your 23rd! Thank you for your awesome collaboration on the #comparative #spectral #decompositions, our #quantum mechanics-inspired #multi-#tensor generalizations of the singular value decomposition! youtu.be/vy8UZftSXKI via @YouTube @DynamicsSIAM @ICERM @ILAS_News @SIAMLA @UUSCI @UUtah #AI #ArtificialIntelligence #DataScience #MachineLearning #ML #MultiTensorDecompositions #SingularValueDecomposition