Search NASA⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 2572480

CAML: Commutative Algebra Machine Learning─A Case Study on Protein–Ligand Binding Affinity Prediction

Feng, Hongsong [University of North Carolina at Charlotte, NC (United States)] (ORCID:0000000180393059)·Suwayyid, Faisal [King Fahd University of Petroleum and Minerals, Dhahran (Saudi Arabia); Michigan State University, East Lansing, MI (United States)]·Zia, Mushal [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000245835437)·Wee, JunJie [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000184443252)·Hozumi, Yuta [Michigan State University, East Lansing, MI (United States); Georgia Institute of Technology, Atlanta, GA (United States)] (ORCID:0000000346742379)·Chen, Chun-Long [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:000000025584824X)·Wei, Guo-Wei [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000257812937)
View original source ↗Read source document ↗Export metadata ↓

Abstract

Recently, Suwayyid and Wei introduced commutative algebra as an emerging paradigm for machine learning and data science. In this work, we propose commutative algebra machine learning (CAML) for the prediction of protein−ligand binding affinities. Specifically, we apply persistent Stanley−Reisner theory, a key concept in combinatorial commutative algebra, to the affinity predictions of protein−ligand binding and metalloprotein−ligand binding. We present three new algorithms, i.e., element-specific commutative algebra, category-specific commutative algebra, and commutative algebra on bipartite complexes, to tackle the complexity of data involved in (metallo) protein−ligand complexes. We show that the proposed CAML outperforms other state-of-theart methods in (metallo) protein−ligand binding affinity predictions, indicating the great potential of commutative algebra learning.

Explore related subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRYFiltrationMolecular modelingMonomersPeptides and proteinsScreening assays

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Feng, Hongsong [University of North Carolina at Charlotte, NC (United States)] (ORCID:0000000180393059), Suwayyid, Faisal [King Fahd University of Petroleum and Minerals, Dhahran (Saudi Arabia); Michigan State University, East Lansing, MI (United States)], Zia, Mushal [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000245835437), Wee, JunJie [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000184443252), Hozumi, Yuta [Michigan State University, East Lansing, MI (United States); Georgia Institute of Technology, Atlanta, GA (United States)] (ORCID:0000000346742379), Chen, Chun-Long [Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)] (ORCID:000000025584824X), Wei, Guo-Wei [Michigan State University, East Lansing, MI (United States)] (ORCID:0000000257812937). 2025-06-15. CAML: Commutative Algebra Machine Learning─A Case Study on Protein–Ligand Binding Affinity Prediction. https://doi.org/10.1021/acs.jcim.5c00940

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Frontiers in divalent $f$-block chemistry

Divalent f-block chemistry has undergone rapid expansion in recent years, driven by advances in the stabilization of low-valent lanthanide and actinide complexes. Although f-elements were historically accessed in the +3 or higher oxidation states, the isolation of +2 species has revealed unusual spectroscopic signatures, distinct bonding motifs, and multiple accessible electronic configurations that influence their chemical and physical properties. These developments have generated opportunities in areas including quantum information science, molecular magnetism, catalysis, and luminescence. Computational chemistry has played a pivotal role in interpreting the electronic structure and reactivity of these systems. However, accurately modeling divalent f-block complexes remains challenging because of strong electronic correlation, multiconfigurational character, and the presence of close-in-energy competing electronic states. As experimental capabilities and theoretical methodologies continue to advance, a comprehensive assessment of divalent chemistry is both timely and needed. In this Review, we integrate experimental and theoretical perspectives to provide a systematic analysis of divalent lanthanide and actinide complexes across the f-block series. We critically assess the role of ligands in determining competing ground-state configurations (f n d 1 vs. f n+1 ) resulting in their distinct spectroscopic, magnetic, and bonding properties. Finally, we discuss emerging strategies for predictive modeling and rational design of low-valent f-block molecular systems, with potential applications ranging from dinitrogen reduction to quantum technologies.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Unveiling the electronic structure and chemical bonding of the deprotonated cisplatin anion [(NH 3 )(NH 2 )PtCl 2 ] − via low-temperature photoelectron spectroscopy and theoretical calculations

The dehydrogenated cisplatin anion, [(NH 3 )(NH 2 )PtCl 2 ] − , was investigated via low-temperature photoelectron spectroscopy and theoretical calculations. Seven and four spectral peaks are respectively resolved at 193 and 266 nm, yielding rich electronic structure information for both the anion and neutral. From the threshold and maximum of the lowest electron binding energy band, the experimental adiabatic (ADE) and vertical detachment energies (VDE) are determined to be 3.3 ± 0.1 and 3.525 ± 0.025 eV, respectively. Theoretical calculations indicate the dominant isomer adopting a cis-geometry, in which the platinum center is coplanar with two chlorine and two nitrogen ligands. The calculated VDE of 3.54 eV based on this structure agrees well with the experimental value. Charge analyses reveal that the excess electron in the anion is primarily localized on the Pt and Cl atoms. A suite of theoretical analysis tools was employed to elucidate the bonding characteristics and interaction strength between Pt and its ligands.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Adsorption, charge transfer and a coverage-driven transition of alkali metals on rutile TiO 2 (110)

The interaction of alkali metals with metal oxide surfaces is central to tuning surface reactivity in heterogeneous catalysis and photocatalysis. Here we present a comprehensive DFT+U study of the adsorption of alkali metals (Li, Na, K, Rb, Cs) on the (110) surface of rutile TiO 2 . At low coverage (θ = 1/8), all alkali metals bind preferentially to bridging oxygen sites with adsorption energies in the range −4.06 to −3.33 eV, transferring nearly one full electron (0.92–0.99 |e|) to the substrate and inducing Ti 4+ → Ti 3+ reduction. The excess charge localizes preferentially at subsurface Ti sites in the form of small polarons. Diffusion barriers indicate facile motion along bridging-oxygen rows, whereas inter-row hopping is strongly hindered. Coverage effects were examined systematically for potassium: adsorption energy and charge transfer per K atom decrease monotonically with increasing θ. Strikingly, a sharp energy discontinuity occurs between θ = 4/8 and θ = 5/8 (ΔE ≈ 1 eV per atom), which we identify as a coverage-driven structural transition arising from steric packing constraints and enhanced K–K electrostatic repulsion once every (1×1) surface cell is occupied. This structural transition perfectly correlates with a dramatic drop in the work function down to an ultra-low minimum of 0.84 eV at θ=5/8, followed by a metallization- driven recovery at higher coverages. Ab initio molecular dynamics simulations confirm zigzag K arrangements at moderate coverage (θ = 1/3), while at high coverage (θ = 2/3) short-range K–K correlations emerge without long-range order. These results provide atomistic insight into the structure–activity relationships underlying alkali promotion effects on oxide-supported catalysts.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗