Spencer Long Email & Phone Number

Seattle, Wa, Us

Honolulu, Hawaii, United States

• Bioinformatics Leadership: Helped found and lead LifeDNA's Bioinformatics department; developed and deployed 600+ customer-facing ML models for disease risk assessment, enhancing user experience and data-driven decision-making.• Innovative Analysis: Pioneered a novel method for ML model supervision without phenotype data, advancing bioinformatics research and setting new industry standards.• Acquisition Contributor: Central to LifeDNA's acquisition by Nu Skin, showcasing R&D and technological capabilities, significantly contributing to the deal's success.• Global Collaboration: Led global teams across biology, genetics, and marketing to develop customized bioinformatics solutions, leveraging diverse datasets and enhancing the company's international footprint.• Data Pipeline Development: Designed and implemented advanced data pipeline systems, optimizing access to proprietary data and supporting scalable analytics.• Strategic Leadership: Drove strategic direction with C-Suite through weekly business goal reviews, progress updates, and strategy sessions, aligning organizational efforts towards common objectives.• Initiated UK Biobank Project for LifeDNA: Crucial in obtaining access to the UK Biobank, enabling LifeDNA to begin exploring the integration of lifestyle and genetic data through innovative algorithms; established a comprehensive data pipeline and directed the initial R&D efforts of advanced risk models, positioning LifeDNA at the forefront of personalized health analytics.

Honolulu

SNR Analytics Inc. (SNRAI) develops sparse signal processing (SSP) techniques that are designed to identify small subsets of molecular variables in big genomic datasets (i.e., sparse signatures) that are predictive of immunotherapeutic response. As an SNRAI Data Scientist and Software Engineer my team and I developed data-driven models that leverage the surprising connection between signal sparsity and the immune status of the TME to better predict how a cancer patient will respond to Immune checkpoint blockade (ICB) and other immunotherapies. • Led Shallow Neural Network Pipeline Development: Spearheaded the end-to-end deployment of a Shallow Neural Network pipeline using TensorFlow for a liver cancer clinical trial at SNRAI, utilizing SSP techniques to boost predictive accuracy of immunotherapeutic responses.• Conducted Advanced Data Analysis: Performed in-depth analysis of cancer-related datasets using Sparse Modeling at SNRAI, identifying key molecular variables for immunotherapy outcomes and enhancing understanding of tumor microenvironment immune statuses.• Simplified JAMMIT Algorithm Integration: Oversaw the design and integration of the JAMMIT Algorithm into Jupyter & Google Colab, streamlining the end-user experience and expanding the use of SSP techniques for biomarker discovery and predictive modeling.• Supported NIH Grant Proposals: Assisted in drafting and submitting grant proposals to the NIH, securing funding to further cancer patient response prediction models and SSP technology research and development at SNRAI.• Strategic Leadership and C-Suite Communication: Led weekly strategy meetings and presentations with SNRAI's C-Suite to align data science projects with business goals, significantly contributing to the development of a cloud-based SSP pipeline for cancer research.

Honolulu

Project: “Global Volcanic Activity Profiles”Project Description: From violent and explosive volcanic eruptions, to quiet lava flow effusions, volcanic activity covers a wide spectrum. Generally, volcanoes can be categorized as either: active, dormant, or extinct. However, the classification of “active” is a bit of a misnomer as volcanoes often go through intermittent periods of variable thermal activity. There exists a general consensus regarding the underlying mechanisms involved in volcanic eruptions, however, a problem which has plagued geophysicists is: how do we predict the waxing and waning of volcanic activity? This is an essential step towards combating volcanic hazards. This project will use existing data to forecast volcanic behavior with machine learning methods in statistical learning theory.Deep learning has had significant recent success, and is outperforming other standard machine learning methods (such as support vector and other kernel machines) on a variety of tasks, including time series prediction. We wish to compare the results produced by the deep convolutional neural network approach, with more principle techniques that are well grounded in statistics and information theory. Techniques include, Bayesian inference, distributional clustering, and Gaussian Processes.• Applied machine learning techniques in Python to predict thermal output trends of volcanoes.• Designed and implemented a program to detect satellite geolocations and cross referenced them with NOAA databases to determine if data was corrupted by weather interference.

Honolulu

Project: "The Biases of Detecting High Velocity Asteroids"• Conducted data analysis of computer simulated data of over 10 million near Earth asteroids to help solve the issues of streaking asteroid detection.

Honolulu

Project: “Harmful Solar Energetic Particles and Geomagnetic Storms Impacting Earth”Project Description: The Alpha Magnetic Spectrometer (AMS-02) is a high energy particle detector that has been operational on the International Space Station (ISS) since May of 2011. AMS-02 measures particle rigidities from 0.5 GV to a few TV and proton energies over 125 MeV. These capabilities give the detector an advantage over the NASA satellite fleet because of its precision to measure these high energy ranges. Due to the fact that isolated Solar Energetic Particle (SEP) events are highly energetic and capable of reaching the ISS in low Earth orbit, AMS-02 is vital to future missions in space. A handful of other NASA satellites and detectors are also uniquely valuable to providing particle information. For this high energy SEP event and GM storm study, I will utilize the AMS-02 and a handful of other NASA solar observatories in space such as STEREO-A, STEREO-B, WIND, and NOAA’s GOES-13 and GOES-15 detectors. Data will also be taken from many ground based neutron monitors. From these instruments, I will be able to investigate data such as proton flux, gamma ray flux, type-III radio bursts, X-ray flux, and coronagraph images of events on the sun. With this data, I will focus on a list of unique SEP events and Geomagnetic (GM) storms that the AMS-02 team at UH Manoa has identified as some of the most intense, fastest, and most energetic particle events detected by AMS-02 at low earth orbit. My hypothesis is that there is a correlation between these solar parameters and the incidences of high energy events and if we can define that correlation, we may be able to predict the occurrence of high energy events in the future.• Analyzed data from NASA missions to help create an early warning system for potential space weather hazards. • Created a Python Pipeline to obtain entire NASA satellite fleet data and to extract desired end user preferences.

Spokane, Washington Area

• Supervised and managed a team of six and planned schedules based on demand. • Designed work flow and trained employees in department with lean methods in mind to achieve 38% increase in production. • Trained in lean manufacturing.

Bachelor'S Degree, Astrophysics

Activities and Societies: Society of Physics Students

Associate Of Arts - Aa

Activities and Societies: Astronomy Club