Data Mining Practical Machine Learning Tools and Techniques

A newly described coronavirus named severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which is the causative agent of coronavirus disease 2019 (COVID-19), has infected over 2.3 million people, led to the death of more than 160,000 individuals and caused worldwide social and economic disruption1,2. There are no antiviral drugs with proven clinical efficacy for the treatment of COVID-19, nor are there any vaccines that prevent infection with SARS-CoV-2, and efforts to develop drugs and vaccines are hampered by the limited knowledge of the molecular details of how SARS-CoV-2 infects cells. Here we cloned, tagged and expressed 26 of the 29 SARS-CoV-2 proteins in human cells and identified the human proteins that physically associated with each of the SARS-CoV-2 proteins using affinity-purification mass spectrometry, identifying 332 high-confidence protein–protein interactions between SARS-CoV-2 and human proteins. Among these, we identify 66 druggable human proteins or host factors targeted by 69 compounds (of which, 29 drugs are approved by the US Food and Drug Administration, 12 are in clinical trials and 28 are preclinical compounds). We screened a subset of these in multiple viral assays and found two sets of pharmacological agents that displayed antiviral activity: inhibitors of mRNA translation and predicted regulators of the sigma-1 and sigma-2 receptors. Further studies of these host-factor-targeting agents, including their combination with drugs that directly target viral enzymes, could lead to a therapeutic regimen to treat COVID-19. A human–SARS-CoV-2 protein interaction map highlights cellular processes that are hijacked by the virus and that can be targeted by existing drugs, including inhibitors of mRNA translation and predicted regulators of the sigma receptors.

/pdf/a-sars-cov-2-protein-interaction-map-reveals-targets-for-5d1m2n6hc1.pdf

A SARS-CoV-2 protein interaction map reveals targets for drug repurposing.

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder, and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations of molecules allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous represent...

http://pubs.acs.org/doi/pdf/10.1021/acscentsci.7b00572

Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules

We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration and optimization through open-ended spaces of chemical compounds. A deep neural network was trained on hundreds of thousands of existing chemical structures to construct three coupled functions: an encoder, a decoder and a predictor. The encoder converts the discrete representation of a molecule into a real-valued continuous vector, and the decoder converts these continuous vectors back to discrete molecular representations. The predictor estimates chemical properties from the latent continuous vector representation of the molecule. Continuous representations allow us to automatically generate novel chemical structures by performing simple operations in the latent space, such as decoding random vectors, perturbing known chemical structures, or interpolating between molecules. Continuous representations also allow the use of powerful gradient-based optimization to efficiently guide the search for optimized functional compounds. We demonstrate our method in the domain of drug-like molecules and also in the set of molecules with fewer that nine heavy atoms.

Automatic chemical design using a data-driven continuous representation of molecules

Computer-aided drug discovery/design methods have played a major role in the development of therapeutically important small molecules for over three decades. These methods are broadly classified as either structure-based or ligand-based methods. Structure-based methods are in principle analogous to high-throughput screening in that both target and ligand structure information is imperative. Structure-based approaches include ligand docking, pharmacophore, and ligand design methods. The article discusses theory behind the most important methods and recent successful applications. Ligand-based methods use only ligand information for predicting activity depending on its similarity/dissimilarity to previously known active ligands. We review widely used ligand-based methods such as ligand-based pharmacophores, molecular descriptors, and quantitative structure-activity relationships. In addition, important tools such as target/ligand data bases, homology modeling, ligand fingerprint methods, etc., necessary for successful implementation of various computer-aided drug discovery/design methods in a drug discovery campaign are discussed. Finally, computational methods for toxicity prediction and optimization for favorable physiologic properties are discussed with successful examples from literature.

/pdf/computational-methods-in-drug-discovery-3sww6kbvd5.pdf

Computational Methods in Drug Discovery

Drug-likeness is a key consideration when selecting compounds during the early stages of drug discovery. However, evaluation of drug-likeness in absolute terms does not reflect adequately the whole spectrum of compound quality. More worryingly, widely used rules may inadvertently foster undesirable molecular property inflation as they permit the encroachment of rule-compliant compounds towards their boundaries. We propose a measure of drug-likeness based on the concept of desirability called the quantitative estimate of drug-likeness (QED). The empirical rationale of QED reflects the underlying distribution of molecular properties. QED is intuitive, transparent, straightforward to implement in many practical settings and allows compounds to be ranked by their relative merit. We extended the utility of QED by applying it to the problem of molecular target druggability assessment by prioritizing a large set of published bioactive compounds. The measure may also capture the abstract notion of aesthetics in medicinal chemistry.

/pdf/quantifying-the-chemical-beauty-of-drugs-48hax4bgv8.pdf

Quantifying the chemical beauty of drugs

The clinical efficacy and safety of a drug is determined by its activity profile across many proteins in the proteome. However, designing drugs with a specific multi-target profile is both complex and difficult. Therefore methods to design drugs rationally a priori against profiles of several proteins would have immense value in drug discovery. Here we describe a new approach for the automated design of ligands against profiles of multiple drug targets. The method is demonstrated by the evolution of an approved acetylcholinesterase inhibitor drug into brain-penetrable ligands with either specific polypharmacology or exquisite selectivity profiles for G-protein-coupled receptors. Overall, 800 ligand-target predictions of prospectively designed ligands were tested experimentally, of which 75% were confirmed to be correct. We also demonstrate target engagement in vivo. The approach can be a useful source of drug leads when multi-target profiles are required to achieve either selectivity over other drug targets or a desired polypharmacology.

/pdf/automated-design-of-ligands-to-polypharmacological-profiles-48578za63i.pdf

Automated design of ligands to polypharmacological profiles

G-protein coupled receptors (GPCRs) are a class of drug targets of primary importance. However, receptor assays are based on measurement of either ligand displacement or downstream functional responses, rather than direct observation of ligand binding. Issues of allosteric modulation, probe dependence, and functional selectivity create challenges in selecting suitable assays formats. Therefore, a method that directly measures GPCR-ligand interactions, independent of binding site, probe, and signaling pathway would be a useful primary and orthogonal screening method. We have developed a GPCR biosensor assay protocol that offers the opportunity for high-throughput label-free screening that directly measures GPCR-ligand interactions. The biosensor-based direct screening method identifies the interaction of both orthosteric and allosteric ligands with solubilized, native GPCRs, in a label-free and cell-free environment, thus overcoming the limitations of indirect and displacement assay methods. We exemplify the method by the discovery of novel ligands for the chemokine receptor, CCR5, that are ligand efficient fragments.

http://pubs.acs.org/doi/pdf/10.1021/ml2000017

Screening for GPCR Ligands Using Surface Plasmon Resonance.

https://discovery.dundee.ac.uk/ws/files/6515862/1_s2.0_S1359644614003419_main.pdf

The Joint European Compound Library: boosting precompetitive research

A method for computational drug design using an evolutionary algorithm, comprises evaluating virtual molecules according to vector distance (VD) to at least one achievement objective that defines a desired ideal molecule. In one method the invention comprises defining a set of n achievement objectives (O A 1-n ), where n is at least one; defining a population (P G=0 ) of at least one molecule; selecting an initial population (P parent ) of at least one molecule (I 1 -I n ) from the population (P G=0 ); and evaluating members (I 1 -I n ) of the initial population (P parent ) against at least one of the n achievement objectives (O A 1-x ), where x is from 1 to n.

Jérémy Besnard

Papers

Quantifying the chemical beauty of drugs

Automated design of ligands to polypharmacological profiles

Screening for GPCR Ligands Using Surface Plasmon Resonance.

The Joint European Compound Library: boosting precompetitive research

Design of molecules