Drug discovery and development pipelines are long, complex and depend on numerous factors. Machine learning (ML) approaches provide a set of tools that can improve discovery and decision making for ...well-specified questions with abundant, high-quality data. Opportunities to apply ML occur in all stages of drug discovery. Examples include target validation, identification of prognostic biomarkers and analysis of digital pathology data in clinical trials. Applications have ranged in context and methodology, with some approaches yielding accurate predictions and insights. The challenges of applying ML lie primarily with the lack of interpretability and repeatability of ML-generated results, which may limit their application. In all areas, systematic and comprehensive high-dimensional data still need to be generated. With ongoing efforts to tackle these issues, as well as increasing awareness of the factors needed to validate ML approaches, the application of ML can promote data-driven decision making and has the potential to speed up the process and reduce failure rates in drug discovery and development.
The DLS‐VS strategy was developed as an integrated method for identifying chemical modulators for orphan GPCRs. It combines differential low‐throughput screening (DLS) and virtual screening (VS). The ...two cascaded techniques offer complementary advantages and allow the experimental testing of a minimal number of compounds. First, DLS identifies modulators specific for the considered receptor among a set of receptors, through the screening of a small library with diverse chemical compounds. Then, an active molecular model of the receptor is built by homology to a validated template, and it is progressively refined by rotamers modification for key side‐chains, by VS of the already screened library, and by iterative selection of the model generating the best enrichment. The refined active model is finally used for the VS of a large chemical library and the selection of a small set of compounds for experimental testing. Applied to the orphan receptor GPR34, the DLS‐VS strategy combined the experimental screening of 20 000 compounds and the virtual screening of 1 250 000 compounds. It identified one agonist and eight inverse agonists, showing a high chemical diversity. We describe the method. The strategy can be applied to other GPCRs.
Dysregulation of Toll-like receptor (TLR) responses to pathogens can lead to pathological inflammation or to immune hyporesponsiveness and susceptibility to infections, and may affect adaptive immune ...responses. TLRs are therefore attractive therapeutic targets. We assessed the potential of the TLR co-receptor CD14 as a target for therapeutics by investigating the magnitude of its influence on TLR responses. We studied the interaction of CD14 with TLR2 by conducting peptide screening and site-directed mutagenesis analysis and found TLR2 leucine-rich repeats 5, 9, 15, and 20 involved in interaction with CD14. Peptides representing these regions interacted with CD14 and enhanced TLR2- and TLR4-mediated proinflammatory responses to bacterial pathogens in vitro. Notably, the peptides' immune boosting capacity helped to rescue proinflammatory responses of immunosuppressed sepsis patients ex vivo. In vivo, peptide treatment increased phagocyte recruitment and accelerated bacterial clearance in murine models of Gram-negative and Gram-positive bacterial peritonitis. Up-modulating CD14's co-receptor activity with TLR2-derived peptides also enhanced antigen-induced dendritic cell (DC) maturation and interleukin-2 production and, most notably, differentially affected DC cytokine profile upon antigen stimulation, promoting a T helper 1-skewed adaptive immune response. Biochemical, cell imaging, and molecular docking studies showed that peptide binding to CD14 accelerates microbial ligand transfer from CD14 to TLR2, resulting in increased and sustained ligand occupancy of TLR2 and receptor clustering for signaling. These findings reveal the influence that CD14 exerts on TLR activities and describe a potential therapeutic strategy to amplify responses to different pathogens mediated by different TLRs by targeting the common TLR co-receptor, CD14.
We discovered a constitutively activating mutation (CAM) V308E for the neurotensin NT1 receptor. Molecular dynamics (MD) performed for the CAM NT1‐V308E exhibiting a high spontaneous activity, and ...for the wild‐type NT1 without basal activity, show dramatic conformational changes for the CAM. To test if the two MD models could be valuable active and inactive templates for building molecular models for other class‐A GPCR, supposed active and inactive models were built by homology for the cholecystokinin CCK1 receptor. Virtual screening of a corporate library with 250 000 compounds was performed with the two CCK1 models, and a differential virtual screening analysis (DVS), led us to isolate 250 predicted agonists and 250 predicted antagonists. The two sets were merged and the compounds were tested in CCK1 agonist and antagonist cellular assays. An excellent correlation was obtained between predictions and biological results. The effective profiling provided by DVS with active and inactive molecular models, opens new perspectives for finding agonists and antagonists for other class‐A GPCR, notably for orphan GPCRs for which no ligands are known.
A cDNA library was generated from rat brain tissues and organized into 1536-well plates, using a fluorescence activated cell sorter (FACS), acting as a single cell deposition system. The organized ...library containing 10 000 clones, with 60% full-length cDNA inserts, allowed the generation of multiple identical membrane replicas. Each replica was hybridized with a complex probe obtained from a particular brain tissue or a given cultured cell. The signal intensity for each of the clones present on the membrane, quantified with a standard image-analysis software, is proportional both to the abundance of the corresponding mRNA in the probe and to the amount of plasmid template on the membrane. The latter value was thus used to normalize the signals produced with complex probes, to optimize the comparison of mRNA expression levels for the different systems under study. The construction of high-quality cDNA libraries, the generation of identical membrane replicas and comparable probes, and the utilization of an image-analysis software package, coupled with the normalization of the spot intensity by assaying plasmid quantity, significantly improves the differential screening approach. Altogether, these technical improvements open the possibility to compare a great number of different probes and, in consequence, to accumulate biological information for each clone present in an organized cDNA library. The functional information obtained should complement data from DNA sequencing projects.
We have recently described a method based on artificial neural networks to cluster protein sequences into families. The network was trained with Kohonen's unsupervised learning algorithm using, as ...inputs, the matrix patterns derived from the dipeptide composition of the proteins. We present here a large‐scale application of that method to classify the 1,758 human protein sequences stored in the SwissProt database (release 19.0), whose lengths are greater than 50 amino acids. In the final 2‐dimensional topologically ordered map of 15 × 15 neurons, proteins belonging to known families were associated with the same neuron or with neighboring ones. Also, as an attempt to reduce the time‐consuming learning procedure, we compared 2 learning protocols: one of 500 epochs (100 SUN CPU‐hours CPU‐h), and another one of 30 epochs (6.7 CPU‐h). A further reduction of learning‐computing time, by a factor of about 3.3, with similar protein clustering results, was achieved using a matrix of 11×11 components to represent the sequences. Although network training is time consuming, the classification of a new protein in the final ordered map is very fast (14.6 CPU‐seconds). We also show a comparison between the artificial neural network approach and conventional methods of biosequence analysis.