Jekyll2026-09-10T22:31:46+00:00https://mhahsler.github.io/feed.xmlMichael HahslerClinical Associate Professor of Computer Science at SMU, Artificial Intelligence Researcher, and Software Developer.Michael HahslerResearch and Innovation Week: Cameron Tofani Presented Her Work on Missing Protein Prediction in Biological Pathways2026-03-24T00:00:00+00:002026-03-24T00:00:00+00:00https://mhahsler.github.io/research/2026/03/24/Research_and_Innovation_Week_PresentaitonCameron Tofani presented her work on biological pathway completion using transformers at the 2026 SMU Research and Innovation Week.

Abstract: Biological pathways describe how proteins work together inside a cell to carry out important processes such as metabolism and signaling. Many biological pathways are incomplete – reactions are known, but the enzymes (proteins) catalyzing them have not been identified. These missing enzymes create gaps known as pathway holes.

Filling pathway holes is critical for understanding disease mechanisms and identifying drug targets. This project investigates whether a BERT-based transformer model can predict candidate proteins for reactions where the enzyme is unknown.

Proteins and reactions are represented as tokens in sequences, allowing the model to learn biological context the way language models like BERT learn word context.

Experimentally identifying missing enzymes is slow and expensive. A computational approach could rapidly narrow the search space, which would accelerate disease research and drug discovery.

This work was supported by the Departmental Summer Seed Grant (DSSG), Department of Computer Science.

Poster

poster

]]>Michael HahslerNew Reinforcement Learning Course2026-01-19T00:00:00+00:002026-01-19T00:00:00+00:00https://mhahsler.github.io/research/2026/01/19/Reinforcement_Learning_CourseIn Sping 2026, I start offering a new course on Reinforcement Learning. It builds on knwolege from the introduction courses to Artificial Intelligence and Machine Learning to introduce the methods used by modern AI agents to learn from interactions with an dynamic environment.

The course material can be found my GitHub repository: Introduction to Reinforcement Learning

]]>Michael HahslerZerui Ma presented his work on Academic Recommender Systems at the 2025 AAAI Spring Symposium2025-03-30T00:00:00+00:002025-03-30T00:00:00+00:00https://mhahsler.github.io/research/2025/03/30/Zeruli_Ma_AAAIThe paper A Recommender System Architecture for University Curriculum Advising by Zerui Ma, Michael Hahsler and Peter Moore was presentated by Zerui and published in the proceedings of the 2025 AAAI Spring Symposium sponsored by the Association for the Advancement of Artificial Intelligence.

Paper abstract:

Effective academic advising plays a crucial role in student success, yet universities face challenges in optimizing advising processes and course enrollment. This task is complicated by the fact that several graduation requirements have to be met while also taking the students’ interests into account. Academic advising has historically been performed by a skilled human adviser. Universities can optimize course planning and help students make informed decisions about their academic path with recommender systems. This case study develops a goal-based agent recommender system based on a large language model tailored to undergraduate students, depending on curriculum requirements, prerequisite dependencies, and student preferences. The developed recommendation system helps universities increase student advising efficiency and create more intuitive and student-centric curricula. We show how to structure and process complex curriculum data to create an algorithm-ready environment, simplifying the relationships between degree requirements and course offerings. This study evaluates multiple algorithms based on recommendation accuracy, computational efficiency, and their ability to meet degree requirements while fostering academic engagement. By streamlining course selection and exploring possible degree paths, the system may also help students graduate on time and navigate complex curricula. This system also collects important metrics to accurately predict student enrollment for classes, enabling college departments to plan their course offerings better. The system poses a significant benefit to university advising offices by reducing advisor workloads and encouraging student engagement, advancing the academic achievement of the entire student body.

]]>Michael HahslerCommon Curriculum Reading of Artificial Unitelligence Kick-off Lecture2025-01-19T00:00:00+00:002025-01-19T00:00:00+00:00https://mhahsler.github.io/research/2025/01/19/CC_ReadingCC Reading Lecture Cover Slide

]]>Michael HahslerThe R Companion for Introduction to Data Mining is now a downloadable book2024-08-22T00:00:00+00:002024-08-22T00:00:00+00:00https://mhahsler.github.io/research/2024/08/22/R-Companion-for-Introduction-to-Data-MiningThe R examples used in my course CS 5/7331 Data Mining are now compiled into a downloadable PDF book (DOI 10.6084/m9.figshare.26750404) and an interactive online book.

The companion book is the official R Code for the popular textbook Introduction to Data Mining by Tan et al.

]]>Michael HahslerZerui Ma receives a Robert Mayer Undergraduate Research Fellowship2024-06-01T00:00:00+00:002024-06-01T00:00:00+00:00https://mhahsler.github.io/research/2024/06/01/Zeruli_Ma_Mayer_FellowshipStudent Zerui Ma was awarded a Robert Mayer Undergraduate Research Fellowship for 2024-25 by the Dedman College Interdisciplinary Institute (DCII). He will work on the project “Recommender Systems and Set-Cover Algorithms for University Curriculum Advising.” I act as his main mentor with Prof. Peter Moore (SMU, Math) as a co-mentor.

]]>Michael HahslerThe R package rBLAST was published on Bioconductor2024-04-28T00:00:00+00:002024-04-28T00:00:00+00:00https://mhahsler.github.io/research/2024/04/28/rBLAST_on_BiocThe R package rBLAST interfaces the Basic Local Alignment Search Tool (BLAST) to search genetic sequence data bases so it can be used in Bioconductor workflows.

Bioc rBlast landing page

Details about the package can be found on rBLAST’s Bioconductor page.

]]>Michael HahslerSMU Tower Center Forum on Ethical AI2023-09-21T00:00:00+00:002023-09-21T00:00:00+00:00https://mhahsler.github.io/research/2023/09/21/SMU_Tower_Forum_Ethical_AIThe SMU Tower Center Forum is hosting a discussion on Ethics in AI on September 21, 2023, in Dallas. The discussion with Dr. Ken Fleischmann, Professor in the School of Information at The University of Texas at Austin, will be moderated by Dr. Michael Hahsler.

Artificial intelligence is all around us with applications like self-driving cars and chatbots like ChatGPT. UNESCO (United Nations Educational, Scientific and Cultural Organization) produced the first-ever global standard on AI ethics – the ‘Recommendation on the Ethics of Artificial Intelligence’ in November 2021, which is based on a human rights perspective. All 193 member states adopted this framework. The US became the 194th UNESCO member in 2023. In addition, some company leaders in the US (Google, Microsoft, IBM, and OpenAI) have pointed out the need for regulation. In late July, Amazon, Google, Meta, Microsoft and other tech firms agree to AI safeguards set by the White House.

The discussion will cover the impact of AI on society and the ethical questions associated with the creation and application of intelligent machines.

Invitation

]]>Michael HahslerNew major release of the R package seriation2023-07-20T00:00:00+00:002023-07-20T00:00:00+00:00https://mhahsler.github.io/research/2023/07/20/seriation_1.5.0seriation logo

The new major release v1.5.0 of the R package seriation contains many changes:

  • New seriation methods include: AOE, isomap, monoMDS, metaMDS (from vegan), enumerate, mean, SGD, LLE.
  • Improved handling of heatmaps.
  • Support for reordering correlation matrices and better integration with other packages including corrplot, corrr and corrgram.
  • Seriation methods are now registered with the seriation criterion they try to optimize. This information is used in the new option to restart randomized methods and report the best found solution.
  • The README now includes howtos for reordering heatmaps, reordering correlation matrics, and evaluating clusters.

Details of the changes can be found in the package’s NEWS file. The new version is available from CRAN or GitHub.

]]>Michael Hahslerarulespy was published on the Python Package Index (PyPI)2023-05-15T00:00:00+00:002023-05-15T00:00:00+00:00https://mhahsler.github.io/research/2023/05/15/arulespy_on_pypiThe package arulespy which provides a Python interface to the arules R package family for association rule mining was published on PyPI and can now easily be installed using pip install arulespy

The Python package provides access to association rule mining and visualization.

PyPI: arulespy

References:

]]>Michael Hahsler