Darrell R
- Research Program Mentor
PhD candidate at State University of New York at Binghamton
Expertise
Bioinformatics, Immunology, Genetics, Computational Biology, Environmental Science, Water Treatment, Aviation Safety, Machine Learning, Artificial Intelligence, Statistics, Biostatistics, Epidemiology, Physics
Bio
Hello there. My name is Darrell and I am a Data Scientist, Computational Biologist, and Biomedical Engineer. My academic passion and focus is using Data Science and Machine Learning to create custom software processes to better understand the shared genetic and biological patterns between organ systems and disease. I currently conduct research on using bioinformatics and machine learning algorithms to find hidden states and vital information between the omics of Type 1 Diabetes and Non-Small Cell Lung Cancer. I also work with other organizations and research teams on a variety of subjects such as space travel, water treatment, environmental science, nanotechnology, market research, and intelligence. Other personal interests include entrepreneurship and investing to improve society and to become a better person. My hobbies include swimming, reading books, exercising, archery, watching sports events, and watching movies.Project ideas
Positive and Unlabeled Materials Machine Learning - Using Semi-Supervised Machine Learning to Identify and Accelerate New Material Synthesis.
Materials Synthesis is the chemical and physical means of using combinations of atoms and molecules to form novel and useful materials. Through materials synthesis, the pathways of the manufacture of new materials are invented. These combinations of atoms, molecules, and compounds have similar characteristics, but the data can be labeled and unlabeled data. Semi-Supervised Machine Learning can be used to identify and classify other unknown materials with the same similar characteristics. These characteristics can be accurately measured in the unknown materials and we could even better evaluate out how these characteristics interact in unknown materials.
Deep Learning Encoder-Decoder Frameworks for Drug Discovery Binding Affinities
Drug Discovery occurs where new candidates for medicines are discovered. On average, it takes at least 10 years for a potential new medicine to complete the journey from the initial discovery to the public commercial marketplace. Clinical trails by themselves take six to seven years on average and the average cost to perform research and develop successful drugs can be $2.6 billion or more. Artificial Intelligence for drug discovery has democratized and accelerated the drug discovery process greatly. These new techniques and processes combine machine learning and deep learning algorithms to improve workflow, data processing, error checking, and prediction. In this project, we will use artificial intelligence to create encoder-decoder frameworks to calculate and evaluate binding affinity scores for drugs and proteins to target particular activity sites of diseases.
Case Study Reporting on Rare Diseases
Case reports and case series or rather case study research are descriptive studies that are prepared for illustrating novel, unusual, or atypical features identified in patients in medical practice, and they potentially generate new research questions. They are empirical inquiries or investigations of a patient or a group of patients in a natural, real world clinical setting. Case study research is a method that focuses on the contextual analysis of a number of events or conditions and their relationships. Case research is a beneficial tool and learning experience in graduate medical education and among novice researchers. Rare disease patients have cases that extremely unique to the medical field due to frequency, hidden states, and lack of knowledge by medical & research professionals. By creating a case report for a certain kind of rare disease, we could help with the diagnosis and the mitigation of rare diseases, which heavily occur in young children at high mortality rates.