While many approaches to predict aqueous pK a values exist, the fast and accurate prediction of non-aqueous pK a values is still challenging. Based on the iBonD experimental pK a database (39 solvents), ah olistic pK a prediction model was established using machine learning.S tructural and physical-organic-parameter-based descriptors (SPOC) were introduced to represent the electronic and structural features of the molecules.The models trained with aneural network or the XGBoost algorithm showed the best prediction performance with alow MAE value of 0.87 pK a units.The approachallows ac omprehensive mapping of all possible pK a correlations between different solvents and it was validated by predicting the aqueous pK a and micro-pK a of pharmaceutical molecules and pK a values of organocatalysts in DMSO and MeCN with high accuracy.Anonline prediction platform was constructed based on the current model, which can providepK a prediction for different types of XÀHacidity in the most commonly used solvents.

BackgroundMicroRNAs (miRNAs) and other types of small regulatory RNAs play critical roles in the regulation of gene expression at the post-transcriptional level in plants. Cotton is one of the most economically important crops, but little is known about the roles of miRNAs during cotton fiber elongation.ResultsHere, we combined high-throughput sequencing with computational analysis to identify small RNAs (sRNAs) related to cotton fiber elongation in Gossypium hirsutum L. (G. hirsutum). The sequence analysis confirmed the expression of 79 known miRNA families in elongating fiber cells and identified 257 novel miRNAs, primarily derived from corresponding specific loci in the Gossypium raimondii Ulbr. (G. raimondii) genome. Furthermore, a comparison of the miRNAomes revealed that 46 miRNA families were differentially expressed throughout the elongation period. Importantly, the predicted and experimentally validated targets of eight miRNAs were associated with fiber elongation, with obvious functional relationships with calcium and auxin signal transduction, fatty acid metabolism, anthocyanin synthesis and the xylem tissue differentiation. Moreover, one tasiRNA was also identified, and its target, ARF4, was experimentally validated in vivo.ConclusionThis study not only facilitated the discovery of 257 novel low-abundance miRNAs in elongating cotton fiber cells but also revealed a potential regulatory network of nine sRNAs important for fiber elongation. The identification and characterization of miRNAs in elongating cotton fiber cells might promote the further study of fiber miRNA regulation mechanisms and provide insight into the importance of miRNAs in cotton.

While many approaches to predict aqueous pK a values exist, the fast and accurate prediction of non-aqueous pK a values is still challenging. Based on the iBonD experimental pK a database (39 solvents), ah olistic pK a prediction model was established using machine learning.S tructural and physical-organic-parameter-based descriptors (SPOC) were introduced to represent the electronic and structural features of the molecules.The models trained with aneural network or the XGBoost algorithm showed the best prediction performance with alow MAE value of 0.87 pK a units.The approachallows ac omprehensive mapping of all possible pK a correlations between different solvents and it was validated by predicting the aqueous pK a and micro-pK a of pharmaceutical molecules and pK a values of organocatalysts in DMSO and MeCN with high accuracy.Anonline prediction platform was constructed based on the current model, which can providepK a prediction for different types of XÀHacidity in the most commonly used solvents.

Feature representations, or descriptors, are machines’ chemical language that largely shapes the prediction capability, generalizability and interpretability of machine learning models. To develop a generally applicable descriptor is highly warranted for chemists to deal with conventional prediction tasks in the context of sparsely distributed and small datasets. Inspired by the chemist's vision on molecules, we presented herein an ensemble descriptor, SPOC, curated on the principles of physical organic chemistry that integrates Structure and Physicochemical property (SPOC) of a molecule. SPOC could be readily constructed by combining molecular fingerprints, representing the structure of a given molecule, and molecular physicochemical properties extracted from RDKit or Mordred molecular descriptors. The applicability of SPOC was fully surveyed in a range of well‐structured chemical databases with machine learning tasks varying from regression to classifications.

Nucleophilicity and electrophilicity dictate the reactivity of polar organic reactions. In the past decades, Mayr et al. established a quantitative scale for nucleophilicity (N) and electrophilicity (E), which proved to be a useful tool for the rationalization of chemical reactivity. In this study, a holistic prediction model was developed through a machine-learning approach. rSPOC, an ensemble molecular representation with structural, physicochemical and solvent features, was developed for this purpose. With 1115 nucleophiles, 285 electrophiles, and 22 solvents, the dataset is currently the largest one for reactivity prediction. The rSPOC model trained with the Extra Trees algorithm showed high accuracy in predicting Mayr's N and E parameters with R 2 of 0.92 and 0.93, MAE of 1.45 and 1.45, respectively. Furthermore, the practical applications of the model, for instance, nucleophilicity prediction of NADH, NADPH and a series of enamines showed potential in predicting molecules with unknown reactivity within seconds. An online prediction platform (http://isyn.luoszgroup.com/) was constructed based on the current model, which is available free to the scientific community.