Resistance is Futile Codeathon Team Projects

Please note that the following project descriptions are summarized from the team GitHub repositories and are not comprehensive. To get a full understanding of what was accomplished, you can review all team GitHubs here.

Team Dave worked on a machine learning model to identify ESKAPE pathogens, a group of bacteria known for their drug resistance. The model used genomic and protein data to predict resistance patterns, aiding in diagnosis and treatment decisions.

• Kirtan Dave, Team Lead
• Abolhassan Bahari
• Edward Bird
• Precious Osadebamwen
• Narges SangaraniPour
• Priyal Visavadiya

Team Deng worked on a deep learning model to predict antibiotic resistance in bacteria. This model employed graph neural networks to analyze structural information of bacterial receptors and antibiotics, potentially identifying new AMR markers.

• Yixiang Deng, Team Lead
• Shu Cheng
• Sharvari Narendra
• Garima Rani
• Soham Shirolkar
• Wengang Zhang
• Steven Weaver

Team Lahti aimed to create R/Bioconductor tools to analyze antibiotic resistance data in human gut microbiomes. By integrating resistance gene profiles and epidemiological data, the development of these tools aid in studying the spread of resistance traits.

• Leo Lahti, Team Lead
• Nitin Bayal
• Shivang Bhanushali
• Akewak Jeba
• Dattatray Mongad
• Geraldson Teneng Muluh
• Mahkameh Salehi

Team Montes de Oca investigated the relationship between insertion sequences (IS) and antibiotic resistance in bacterial genomes. They compared IS distribution between resistant and susceptible isolates, shedding light on patterns associated with resistance.

• Marco Montes de Oca, Team Lead
• Weilong Hao
• Mackenzie Wilke
• Joe Wirth
• Axl Cepeda
• Genelle Jenkins

Team Mortimer worked on a bioinformatics pipeline to help identify loss-of-function mutations in efflux pump genes of Neisseria gonorrhoeae. This project aimed to assess the impact of these mutations on predicting antimicrobial susceptibility.

• Tatum Mortimer, Team Lead
• Shriya Garg
• Brittany Henry
• Farah Saeed
• Shanita Smrity

Team Nassar focused on identifying self-resistance genes in antibiotic-producing microorganisms, using machine learning models trained on large language models and whole genome sequences.

• Maaly Nassar, Team Lead
• Dae-young Kim
• Parul Sharma
• Madeline Galac
• Brendan Jeffrey

Team Nguyen worked to correlate specific patterns in antibiotic resistance profiles with the presence and location of resistance genes. This project aimed to improve understanding of how resistance is conferred and transmitted in bacteria.

• Marcus Nguyen, Team Lead
• Nicole Bowers
• Clark Cucinell
• Don Dempsey
• Curtis Hendrickson
• Andrew Warren

Team Prasad Feldgarden developed tools to identify loss-of-function mutations in genes known to cause antibiotic resistance. These tools used BLAST alignments to detect frameshift mutations and stop codons in bacterial genomes.

• Arjun Prasad, Team co-Lead
• Michael Feldgarden, Team co-Lead
• Adrien Assie
• EB Dickinson
• Chienchi Lo
• Ana Ramos
• Erin Young

Team Sridharan utilized graph neural networks to identify novel antibiotic resistance mechanisms in ESKAPE pathogens. This project involved creating a protein-drug interaction network and using protein sequence embeddings to train the model for novel AMR prediction.

• Ganeshiny Sridharan, Team Lead
• Nimna Alupotha Gamage
• Nuwan Medawaththa
• Ruwanthika Premarathne
• Janith Weeraman

Team Suravajhala integrated data and tools to analyze AMR genes in Acinetobacter bacteria, focusing on their location on plasmids and their association with resistance phenotypes. This project aimed to create a more comprehensive pangenomic resource for studying AMR in Acinetobacter.

• Prashanth Suravajhala, Team co-Lead
• R Shyama Prasad Rao, Team co-Lead
• Mandar Bedse
• Goutam Kumar Dhandh
• Girik Malik
• Vijayaraghava Seshadri Sundararajan