AI Chemistry

Agave distillates are chemically heterogeneous matrices whose composition may affect the performance and transferability of spectroscopic calibration models. Accurate determination of their ethanol content is therefore essential for quality control and regulatory compliance. This study established a comparative ATR-FTIR chemometric framework for ethanol prediction using 46 agave-distillate samples measured in triplicate. Thirty-five samples were assigned to calibration and 11 to a validation set. Eighteen principal PLS configurations were developed by varying spectral-data strategy, spectral-region combination, and number of factors. Replicate dispersion, first- and second-derivative preprocessing, and model dimensionality were also evaluated, and PLS was benchmarked against PCR and PCA–SVR. Models based on averaged spectra produced lower RMSEP and higher r_Pred values than their corresponding individual-replicate configurations in all nine pairwise comparisons. The best averaged-spectrum PLS model achieved an RMSEP of 0.96% v/v and an r_Pred of 0.9897, whereas the best individual-replicate configuration yielded an RMSEP of 2.37% v/v. The benchmark showed that model performance depended on dimensionality and validation criterion; consequently, no regression approach was universally superior. Application of representative PLS, PCR, and PCA–SVR models to three additional samples produced similar descriptive mean absolute errors of 2.16 to 2.32% v/v. Overall, ATR-FTIR combined with multivariate regression provides a promising proof-of-concept strategy for the rapid estimation of ethanol in agave distillates. These findings support the future development of accessible and reliable quality-control protocols for agave spirits and other complex distilled beverages.

Transition-metal-catalyzed direct C-3 arylation of imidazo[1,2-a]pyridines has witnessed significant advances in recent years. However, identifying optimal reaction conditions for this transformation relies heavily on labor-intensive trial-and-error experiments, which consume significant time and costs. To address this challenge, 275 valid reaction data entries conforming to the reaction mechanism were collected as training data, including substrates, catalysts, additives, solvents, reaction temperature, and experimental yield. Three mainstream tree-based ensemble regression models, including GradientBoosting, Random Forest and ExtraTrees, were constructed after strict data cleaning and advanced feature engineering for systematic benchmark comparison. The GradientBoosting model, which delivered the best fitting and generalization performance among all candidates, was selected as the objective function for subsequent constrained Bayesian optimization. A constrained Bayesian optimization algorithm (with predicted yield bounded within 0–100%) was adopted to globally screen high-dimensional reaction parameters for maximum yield. Comprehensive cross-model evaluation indicated the test-set determination coefficients followed the order GradientBoosting (R² = 0.4416) > Random Forest (R² = 0.3864) > ExtraTrees (R² = 0.3544), while the root mean square error (RMSE) of GradientBoosting was 15.3144, outperforming the other two models in prediction stability. Under the optimal parameter set recommended by GradientBoosting (catalyst Pd(acac)₂BuAd₂P, reactants ref-5-1d and ref-9-2d, additive CsOAc, solvent DMA, 150 °C), the model predicted a theoretical maximum yield of 100%, whereas Random Forest and ExtraTrees only reached predicted peak yields of 83.63% and 80.80%, respectively. This multi-model benchmarking workflow eliminates the bias risk from single-model prediction, provides an efficient tool for optimizing metal-catalyzed C-3 arylation of imidazo[1,2-a]pyridines, and can be generalized to other complex transition-metal catalytic systems.

Somatostatin receptor subtype 2 (SSTR2), encoded at chromosome 17q25.1, is overexpressed in high-risk stage 4 neuroblastoma with a 17q gain, yet no non-peptide small-molecule ligand exists for this indication. From the agonist L-054,522, BROOD generated 5766 analogues, of which 292 were docked to SSTR2 (PDB 7XN9) with FRED, HYBRID, and POSIT; no physicochemical filter was applied. The query achieved an ROC AUC of 0.798 against known ligands and decoys. Eight compounds reaching GREAT pose confidence were re-docked with AutoDock Vina Extended, FITTED, Flare, and DiffDock and then assessed across five ADMET and two retrosynthesis platforms. Redocking the crystallographic ligand recovered the experimental pose with four site-directed programs (RMSD 0.85–1.79 Å), but none run blind or as ensembles, indicating that pose recovery depends on the search protocol rather than the scoring function. Docking scores were not reproducible across repeat runs, so candidates are not ranked. Compound 8 reproduced the Asp122, Gln126, and Thr194 contacts, alone received a Spaya RScore of 1.0 indicating a fully precedented route, and it held its pose over three 100 ns molecular dynamic simulations in a POPC bilayer (ligand RMSD 1.70 ± 0.12 Å). Because docking cannot distinguish agonism from antagonism, this work delivers a synthesisable hypothesis set, not a characterised pharmacological agent.