Hackathon Leveraged Genomic Datasets to Develop Drug Targets, Predict Variants and Correctly Classify Tumors for NF
Hack4NF, a global genomic data hackathon hosted by the Children’s Tumor Foundation (CTF), today announced the winners of the 2022 virtual event that brought together researchers, data analysts, genomic experts, computational biologists, statisticians, healthcare startups and hackathon enthusiasts for three weeks (October 15-November 7, 2022) to ideate and develop viable solutions for medical advancements in a rare genetic disorder called neurofibromatosis (NF).
Genetic disorders like neurofibromatosis represent a research area with high unmet medical need and an opportunity to make a difference in the lives of patients. Throughout the hackathon, CTF provided exclusive data sets, mentor support, and input from patients to foster the development of solutions with real-world applications for neurofibromatosis. This year’s teams worked with genomic data to develop drug targets, predict NF variants and correctly classify NF tumors. This year strategic supporters for the hackathon were the AACR Project GENIE, OpenCRAVAT, the Precision Medicine Platform provided by American Heart Association, and Sage Bionetworks.
Solutions ranged from predicting pathogenicity of NF1 germline mutations using deep learning to applying natural language processing techniques for tumor sampling and classification to identify opportunities for repurposing existing drugs for use in NF1 and NF2 using RNAseq.
Winners on each track received $1,500 with special prizes ($1,000) announced for best project documentation, best use of data, and best use of the Precision Medicine Platform for cloud computing that was provided by the American Heart Association. The winning projects of the 2022 Hack4NF announced today are:
Challenge 1 winner: Next GeNLP
The team built tumor sample embeddings by treating the mutated genes in a tumor sample like a sentence and applying techniques from Natural Language Processing (NLP). They then used these embeddings to predict a tumor's cancer type and to find structure in the genetic profiles of tumor samples. This structure can be used to identify NF tumor subtypes and to explore their relationship with more prevalent cancers.
T
he team also used the tensorflow projector to create an interactive tool to explore and visualize clusters or threads of interest by selecting different variables.
Challenge 2 winner: DITTO4NF
This project used publicly available datasets and several predictors ranging from genome level to protein 2D and 3D structure to predict variant deleteriousness. The team mapped these deleterious variants to individual's transcriptome and phenotype information to support variant classification and prioritization providing new evidence that could help in the prognosis of NF1. The team also created a web app for researchers to upload OpenCravat annotated variants for deleterious predictions along with explanations so that results are easily understandable for clinicians.
Challenge 3 winner: NF1 Drug Targeting
The team focused on identifying a list of possible drugs matched with genetic variants, biochemical assays, and clinical presentation data to support selection of potentially useful drugs for NF1. Drug sensitivity screenings were analyzed identifying a list of drugs classified by class targets of interest along with the hypothesis of chromosome 8 changes. The classification could differentiate drug sensitivity and resistance profile in malignant cancers including malignant peripheral nerve sheath tumors or MPNST, the malignant version of neurofibroma tumors.
Additional prizes ($1,000 each) were assigned for Best Use of Data to Drug Discovery in NF1; Best Project Page to Artificial Intelligence for neurofibromatosis; and Best Use of PMP platform to both DITTO4NF and Next GeNLP. NF1 Drug Targeting and DITTO4NF each received an additional $5K incubation prize to continue working on their projects for an additional 3-6 months, with support provided by Children’s Tumor Foundation and the Neurofibromatosis Therapeutic Acceleration Program (NTAP), respectively.
“We are very happy with the quality of the submissions we had in the Hack4NF 2022 edition. The focus on data and the specifics of the challenges helped us attract a highly-skilled audience that used machine learning techniques to create complex analyses and working prototypes with the potential to help researchers with new computational tools,” said Salvatore La Rosa, PhD, Chief Scientific Officer of the Children’s Tumor Foundation. “We also saw very strong incubation proposals with two winners and other very interesting ideas, that we hope to move forward.”
NF, short for neurofibromatosis, is a group of genetic disorders that causes tumors to grow on nerves throughout the body. It affects 2.5 million people worldwide and there is currently no cure. There is one approved drug for the treatment of inoperable plexiform neurofibromas, a subset of patients with neurofibromatosis type 1.
More than 300 active participants took part in Hack4NF from around the world.
“It was a great honor being involved in the 2022 Hack4NF again this year! I was inspired by the hard work and creativity of each of the teams,” said Carlos Romo, PhD, Director of Clinical Research, Neurofibromatosis Therapeutic Acceleration Program, Johns Hopkins University School of Medicine. “The challenges were difficult to tackle, but the degree of innovation in the proposals made selecting the winning teams difficult. I am grateful for the dedication of the participants and organizers, and confident the projects will yield great fruits for the NF community.”
“As a mom of a 5 year old with NF, I was overwhelmed by the outpouring of talent, expertise and enthusiasm participants in the Hackathon displayed,” said Danielle Bonadies, Hack4NF mentor.. “With an incredibly tight timeline, teams developed and submitted extraordinary projects that have the potential to push research and ideas in the NF community forward by leaps and bounds. It gives me a renewed sense of community and hope to know that so many are willing to donate their talents for the benefit of others.”
This is the fourth CTF-hosted hackathon; the first was held in 2019 over 3 days in San Francisco, followed by virtual, multi-week competitions drawing hundreds of participants across the globe in 2020 and 2021.
The 2022 Hack4NF was presented by Alexion AstraZeneca Rare Disease, Recursion, SpringWorks Therapeutics, and NTAP (Neurofibromatosis Therapy Acceleration Program) with cloud support from the American Heart Association’s Precision Medicine Platform, and datasets provided by Sage Bionetworks, NF Data Portal, NF Open Science Initiative, OpenCRAVAT, Dr. Rick Van Minkelen, and the American Association of Cancer Research’s Project GENIE.
To learn more about the Hack4NF, click here.
To learn more about the Children’s Tumor Foundation, click here.
About the Children’s Tumor Foundation
The Children’s Tumor Foundation is a 501(c)(3) not-for-profit organization dedicated to finding effective treatments for the millions of people worldwide living with neurofibromatosis (NF), a term for three distinct disorders: NF1, NF2, and schwannomatosis. NF causes tumors to grow on nerves throughout the body and may lead to blindness, deafness, bone abnormalities, disfigurement, learning disabilities, disabling pain, and cancer. NF affects 1 in every 3,000 births across all populations equally. There is one approved drug for the treatment of inoperable plexiform neurofibromas, a subset of the NF1 patients. The Children’s Tumor Foundation’s mission of driving research, expanding knowledge, and advancing care for the NF community fosters our vision of one day ending all manifestations of NF.
