Khoury College of Computer Sciences, Northeastern University
John Rachlin

Dr. John Rachlin

Associate Teaching Professor · Khoury College of Computer Sciences · Northeastern University

j.rachlin@northeastern.edu · Office hours on Zoom, by appointment only

Research Projects

My research interests include AI, astronomical data-mining, bioinformatics, evolutionary computing, and artificial life — unified by one method: building AI-driven tools and pipelines that turn raw, messy data into something a scientist can actually reason about. This work is increasingly developed in direct collaboration with AI coding agents (see The Variable Zoo Project, below), which I treat as a genuine research methodology in its own right, not just a convenience.

I also oversee undergraduate independent research projects in these same areas. Students interested in collaborating with me should contact me with a proposal. At minimum, I expect my undergraduate collaborators to be fluent in relational databases (CS 3200: Introduction to Databases) and Python programming for data science (DS 3500: Advanced Programming with Data). Projects typically last one semester, with expected deliverables including a software repository, a research paper, and a poster presentation at Northeastern's RISE conference held each Spring on the Boston campus.

My interest in evolutionary computing goes back to the late 1990s, working as a software engineer at IBM Research, where our small team developed multi-agent decision-support solutions for paper and steel mills — work recognized with the 1998 Daniel H. Wagner Prize (INFORMS) for Excellence in the Practice of Advanced Analytics and Operations Research. In evolutionary computing, we mimic evolution by natural selection in silico to identify Pareto-optimal solutions, using the culling of dominated solutions to provide selective pressure on the candidate population. Years later, while working in drug discovery and pursuing my PhD at Boston University, I applied the same approach to designing Multiplex PCR assays for SNP genotyping. More recently, I've worked with undergraduates on evolutionary computing for machine learning model design — decision trees and deep neural networks that reveal tradeoffs between accuracy, performance, and fairness.


Explore the projects below. Filter by area, then click any project to read the full summary, collaborators, and related publications.



Past Papers


Chang YC, Hu Z, Rachlin J, Anton BP, Kasif S, Roberts RJ, Steffen M.; 2016. COMBREX-DB: an experiment centered database of protein function: knowledge, predictions and knowledge gaps. Nucleic Acids Res. 44(DB):D330-D335. [link]

Anton B., Chang Y., Brown P., et al.; 2013. The COMBREX project: design, methodology, and initial results.PLoS Biol. 11:8. [link]

Rachlin J. and McGettrick M.; 2011. A Variable Star Database for the iPhone/iPod Touch. Journal of the American Association of Variable Star Observers, 39(2):150. [link]

Roberts R.J., Chang Y-C, Hu Z., Rachlin J., et al.; 2010. COMBREX: a project to accelerate the functional annotation of prokaryotic genomes. Nucleic Acid Res. 39, D11-D14. [link]

Alon N., Asodi V., Cantor C., Kasif S., and Rachlin J.; 2006. Multi-node graphs: A framework for multiplexed biological assays. Journal of Computational Biology 13(10):1659-1672. [link]

Rachlin J., Cohen D., Cantor C., and Kasif S.; 2006. Biological Context Networks: a mosaic view of the interactome. Molecular Systems Biology (Nature/EMBO) 2:66 Epub 2006 Nov 28. [link]

Rachlin J., Ding C., Cantor C., and Kasif S.; 2005. Computational tradeoffs in multiplex PCR assay design for SNP genotyping. BMC Genomics 6(1):102 [link]

Rachlin J., Ding C., Cantor C., and Kasif S.; 2005. MuPlex: multi-objective multiplex PCR assay design. Nucleic Acids Res. 33(Web Server Issue):W544-7. [link]

Rachlin J., Akkiraju R.; 2001. Non-invasive networked-based customer support. US Patent Grant US6298457B1. Assigned to IBM. [link]

Akkiraju R., Dietrich B., Keskinocak P., Murthy S., Rachlin J., Wu F.; 2002. Optimization prediction for industrial processes. US Patent Grant: US6490572B2. Assigned to IBM. [link]

Fuhrer R., Henry R., Akkiraju R., Lougee-Heimer R., Murthy S., Rachlin J., Sturzenbecker M., Wu F.; 1999. Multi-objective decision-support methodology. US Patent Grant US5940816A. Assigned to IBM. [link]

Rachlin J., Goodwin R., Murthy S., Akkiraju R., Wu F., Kumaran S., and Das R.; 1999. A-Teams: An Agent Architecture for Optimization and Decision-Support. In Lecture Notes in Artificial Intelligence: Intelligent Agents V, J. Müeller, M. Singh and A. Rao eds. Vol. 1555 (Springer-Verlag). [link]

Murthy S., Akkiraju R., Goodwin R., Keskinocak P., Rachlin J., Wu F., Yeh J., Fuhrer R., Kumaran S., Aggarwal A., Sturzenbecker M., Jayaraman R., Daigle R.; 1999. Cooperative multiobjective decision support for the paper industry. INTERFACES 29(5):5-30. [link]

Kasif S., Salzberg S., Waltz D., Rachlin J., Aha D.W., 1998. A Probabilistic Framework for Memory-Based Reasoning. Artificial Intelligence 104(1-2):287-311. [link]

Murthy S., Rachlin J., Akkiraju R., Wu F.; 1997. Agent-Based Cooperative Scheduling. AAAI-97 Workshop on Constraints and Agents. [link]

Rachlin J., Kasif S., Salzberg S., and Aha D.W.; 1994. Towards a Better Understanding of Memory-Based Reasoning Systems. Machine Learning: Proceedings of the 11th International Conference, Morgan Kaufmann, San Francisco. [link]