Grant McConachie

Biomedical Engineering PhD Student

Who Am I ?

I am a biomedical engineering PhD student at Boston University studying theoretical neuroscience under Dr. Brian DePasquale.

Grant McConachie

Research Interests

I am interested in leveraging the neurobiological information in the mosquito olfactory system to discover novel aversive molecules. Currently, I am exploring how sophisticated machine learning models can provide an avenue for repellant discovery and how they can potentially offer insight into how odors are encoded in the mosquito brain. I have a research background in computational chemistry, and had a position at the National Cancer Institute for a year before coming to Boston University.

In my free time I like to make music, graphic design, and run.




Recent Publications

Below are some of the recent papers that I have had a hand in publishing.

Screen for New Antimicrobial Natural Products from the NCI Program for Natural Product Discovery Prefractionated Extract Library

The continuing emergence of antibiotic-resistant microbes highlights the need for the identification of new chemotypes with antimicrobial activity. One of the most prolific sources of antimicrobial molecules has been the systematic screening of natural product samples. The National Institute of Allergy and Infectious Diseases and the National Cancer Institute here report a large screen of 326,656 partially purified natural product fractions against a panel of four microbial pathogens, resulting in the identification of >3000 fractions with antifungal and/or antibacterial activity. A small sample of these active fractions was further purified and the chemical structures responsible for the antimicrobial activity were elucidated. The proof-of-concept study identified many different chemotypes, several of which have not previously been reported to have antimicrobial activity. The results show that there remain many unidentified antibiotic compounds from nature.

DOI: https://doi.org/10.1021/acsinfecdis.3c00067

















National Cancer Institute (NCI) Program for Natural Product Discovery: Exploring NCI-60 Screening Data of Natural Product Samples with Artificial Neural Networks

National Cancer Institute (NCI) Program for Natural Product Discovery is a new initiative aimed at creating new technologies for natural product-based drug discovery. Here, we present the development of a neural network-based bioinformatics platform for visualization and analysis of natural product high-throughput screening data using the NCI’s 60 human tumor cell anticancer drug screen. We demonstrate how the tool enables visualization of similar patterns of response that can be parsed both chemically and taxonomically, grouping NCI-60 biological profiles in one easy-to-use bioinformatics interface.

DOI: https://doi.org/10.1021/acsomega.2c07416

Recommendation System to Predict Missing Adsorption Properties of Nanoporous Materials

Nanoporous materials (NPMs) selectively adsorb and concentrate gases into their pores and thus could be used to store, capture, and sense many different gases. Modularly synthesized classes of NPMs, such as covalent organic frameworks (COFs), offer a large number of candidate structures for each adsorption task. A complete NPM-property table, containing measurements of relevant adsorption properties in candidate NPMs, would enable the matching of NPMs with adsorption tasks. However, in practice, the NPM-property matrix is only partially observed (incomplete); many different properties of many different NPMs have not been measured. The idea in this work is to leverage the observed (NPM, property) values to impute the missing ones. Similarly, commercial recommendation systems impute missing entries in an incomplete product–customer ratings matrix to recommend products to customers. We demonstrate a COF recommendation system to match COFs with adsorption tasks by training a low-rank model of an incomplete COF–adsorption-property matrix constructed from simulated uptakes of CH4, H2O, H2S, Xe, Kr, CO2, N2, O2, and H2 at various conditions. A low-rank model of the COF–adsorption-property matrix, fit to the observed (COF, adsorption property) values, provides (i) predictions of the missing (COF, adsorption property) values and (ii) a “map” of COFs, wherein COFs, represented as points, with similar (dissimilar) adsorption properties congregate (separate). The COF recommendation system is able to rank COFs reasonably well for most of the adsorption properties, but imputation performance diminishes precipitously when the fraction of missing entries exceeds 60%. The concepts in our COF recommendation system can be applied broadly to impute missing data pertaining to many different materials and properties.

DOI: https://doi.org/10.1021/acs.chemmater.1c01201

Past Publications













News

Other things going on in my research career.

Conference Posters 2024

I presented work using self-supervised learning and graph neural networks to help improve prediction of different olfactory tasks at COSYNE and AChemS . This work explores how the generation of latent spaces from different self-supervised learning tasks can improve prediction for human perception or olfactory receptor neuron response to monomolecular odors. [Poster]

Grants Received 2024

I received the NSF GRFP grant in April for my proposed work using machine learning methods to discover novel mosquito repellants.

Contact

Feel free to contact me with any questions regarding my research!
Email: gdmac {at} bu {dot} edu