We present four models of solution free-energy prediction for druglike molecules utilizing cheminformatics descriptors and theoretically calculated thermodynamic values. We make predictions of solution free energy using physics-based theory alone and using machine learning/quantitative structure–property relationship (QSPR) models. We also develop machine learning models where the theoretical energies and cheminformatics descriptors are used as combined input. These models are used to predict solvation free energy. While direct theoretical calculation does not give accurate results in this approach, machine learning is able to give predictions with a root mean squared error (RMSE) of ∼1.1 log S units in a 10-fold cross-validation for our Drug-Like-Solubility-100 (DLS-100) dataset of 100 druglike molecules. We find that a model built using energy terms from our theoretical methodology as descriptors is marginally less predictive than one built on Chemistry Development Kit (CDK) descriptors. Combining both sets of descriptors allows a further but very modest improvement in the predictions. However, in some cases, this is a statistically significant enhancement. These results suggest that there is little complementarity between the chemical information provided by these two sets of descriptors, despite their different sources and methods of calculation. Our machine learning models are also able to predict the well-known Solubility Challenge dataset with an RMSE value of 0.9–1.0 log S units.
Traditionally, housekeeping and tissue specific genes have been classified using direct assay of mRNA presence across different tissues, but these experiments are costly and the results not easy to compare and reproduce. In this work, a Naive Bayes classifier based only on physical and functional characteristics of genes already available in databases, like exon length and measures of chromatin compactness, has achieved a 97% success rate in classification of human housekeeping genes (93% for mouse and 90% for fruit fly). The newly obtained lists of housekeeping and tissue specific genes adhere to the expected functions and tissue expression patterns for the two classes. Overall, the classifier shows promise, and in the future additional attributes might be included to improve its discriminating power.
Background: Manual annotation of enzymatic functions cannot keep up with automatic genome sequencing. In this work we explore the capacity of InterPro sequence signatures to automatically predict enzymatic function.Results: We present EnzML, a multi-label classification method that can efficiently account also for proteins with multiple enzymatic functions: 50,000 in UniProt. EnzML was evaluated using a standard set of 300,747 proteins for which the manually curated Swiss-Prot and KEGG databases have agreeing Enzyme Commission (EC) annotations. EnzML achieved more than 98% subset accuracy (exact match ofallcorrect Enzyme Commission classes of a protein) for the entire dataset and between 87 and 97% subset accuracy in reannotating eight entire proteomes: human, mouse, rat, mouse-ear cress, fruit fly, theS. pombeyeast, theE. colibacterium and theM. jannaschiiarchaebacterium. To understand the role played by the dataset size, we compared the cross-evaluation results of smaller datasets, either constructed at random or from specific taxonomic domains such as archaea, bacteria, fungi, invertebrates, plants and vertebrates. The results were confirmed even when the redundancy in the dataset was reduced using UniRef100, UniRef90 or UniRef50 clusters.Conclusions: InterPro signatures are a compact and powerful attribute space for the prediction of enzymatic function. This representation makes multi-label machine learning feasible in reasonable time (30 minutes to train on 300,747 instances with 10,852 attributes and 2,201 class values) using the Mulan Binary Relevance Nearest Neighbours algorithm implementation (BR-kNN).
1 September 2012 in Current Topics in Medicinal Chemistry
Over the last 50 years, sequencing, structural biology and bioinformatics have completely revolutionised biomolecular science, with millions of sequences and tens of thousands of three dimensional structures becoming available. The bioinformatics of enzymes is well served by, mostly free, online databases. BRENDA describes the chemistry, substrate specificity, kinetics, preparation and biological sources of enzymes, while KEGG is valuable for understanding enzymes and metabolic pathways. EzCatDB, SFLD and MACiE are key repositories for data on the chemical mechanisms by which enzymes operate. At the current rate of genome sequencing and manual annotation, human curation will never finish the functional annotation of the ever-expanding list of known enzymes. Hence there is an increasing need for automated annotation, though it is not yet widespread for enzyme data. In contrast, functional ontologies such as the Gene Ontology already profit from automation. Despite our growing understanding of enzyme structure and dynamics, we are only beginning to be able to design novel enzymes. One can now begin to trace the functional evolution of enzymes using phylogenetics. The ability of enzymes to perform secondary functions, albeit relatively inefficiently, gives clues as to how enzyme function evolves. Substrate promiscuity in enzymes is one example of imperfect specificity in protein-ligand interactions. Similarly, most drugs bind to more than one protein target. This may sometimes result in helpful polypharmacology as a drug modulates plural targets, but also often leads to adverse side-effects. Many chemoinformatics approaches can be used to model the interactions between druglike molecules and proteins in silico. We can even use quantum chemical techniques like DFT and QM/MM to compute the structural and energetic course of enzyme catalysed chemical reaction mechanisms, including a full description of bond making and breaking.
Objective: This umbrella review will synthesize evidence on the effectiveness of holistic assessment–based interventions in improving health outcomes in adults (aged ≥18) with multiple long-term conditions and/or frailty. Introduction: Health systems need effective, evidence-based interventions to improve health outcomes for adults with multiple long-term conditions. Holistic assessment–based interventions are effective in older people admitted to hospital (usually called “comprehensive geriatric assessments” in that context); however, the evidence is inconclusive on whether similar interventions are effective in community settings. Inclusion criteria: We will include systematic reviews examining the effectiveness of community and/or hospital holistic assessment–based interventions in improving health outcomes for community-dwelling and hospitalized adults aged ≥ 18 with multiple long-term conditions and/or frailty. Methods: The review will follow the JBI methodology for umbrella reviews. MEDLINE, Embase, PsycINFO, CINAHL Plus, Scopus, ASSIA, Cochrane Library, and the TRIP Medical Database will be searched to identify reviews published in English from 2010 till the present. This will be followed by a manual search of reference lists of included reviews to identify additional reviews. Two reviewers will independently screen titles and abstracts against the selection criteria, followed by screening of full texts. Methodological quality will be assessed using the JBI critical appraisal checklist for systematic reviews and research syntheses and data will be extracted using an adapted and piloted JBI data extraction tool. The summary of findings will be presented in tabular format, with narrative descriptions and visual indications. The citation matrix will be generated and the corrected covered area calculated to analyze the overlap in primary studies across the reviews. Review registration: PROSPERO CRD42022363217
Studies of how multiple long-term conditions (MLTC) cluster together in individuals vary in the populations studied, and whether they age and/or sex stratify, which limits comparison between studies and reproducibility. This study uses a large, UK primary-care dataset to examine how pairwise strength of association between 74 conditions varies by age in both men and women aged 30-99 years, and to explore implications for MLT cluster analyses. Joint prevalence of conditions was lowest in younger age-groups and progressively increased with age, whereas Association Beyond Chance (ABC) was highest in younger age-groups and progressively decreased with age. Condition clustering based on ABC identified different clusters in all men and all women aged 30-99 years, and these clusters differed from those identified in each age-group. Researchers examining how MLTC cluster should consider whether age and sex stratification is appropriate given their study aims and/or would improve comparability and reproducibility, and explicitly justify their choices.