Home research People General Info Seminars Resources Intranet
| Algorithms & Applcations Group | Home | Research | Publications | People | Resources | News
Home Page for Benjamin Porter | Parasol Laboratory


Picture Benjamin Porter
High School Student
Algorithms & Applications Group

Parasol Laboratory url: http://parasol.tamu.edu/~bporter/
Department of Computer Science and Engineering email:
Texas A&M University office: 407 HRBB
College Station, TX 77843-3112 tel:
USA fax: (979) 458-0718


Hello! My name is Ben Porter and I am a senior at College Station High School. I am interested in majoring in computer science. I want to be part of this fascinating field that is so integral to how our world works.

In addition to my schoolwork, I enjoy participating in competitive events such as UIL computer science. These events have greatly improved my computer science knowledge and problem solving skills.

During the summer of 2016 I participated in a research internship in the Algorithms and Applications Group at Parasol Laboratory with Anthony Enem. My faculty advisor was Dr. Nancy Amato. My mentor for this project was Diane Uwacu and my postdoctoral advisor was Dr. Shawna Thomas. I worked on a computational biology project focusing on the application of uniform random sampling to generating candidate ligand samples for binding to a protein. The results suggested that using a machine learning method such as a neural network could improve prediction and this is a possibility to look into in the future. Details about the project can be found below.



Predicting Ligand Binding Sites Using UOBPRM and Machine Learning

Abstract:

Many approaches to predicting ligand binding sites on protein surfaces suffer from a reliance on unreliable and inaccurate evaluations of potential binding sites. In this work, we propose an approach to ligand binding that takes advantage of the motion planning paradigm of randomized sampling to uniformly generate samples of the ligand at various binding site candidates near the protein surface. We then compute metrics that describe the favorability of each configuration’s location as a potential binding site. We also propose future work to apply these metrics to a machine learning algorithm to take advantage of each metric’s strengths and weaknesses and reliably predict the locations of binding sites for ligands on proteins.


My technical report for this project can be found here, and the poster produced may be found here.