A multi-scale convolutional neural network for phenotyping high-content cellular images.

MOTIVATION: Identifying phenotypes based on high-content cellular images is challenging. Conventional image analysis pipelines for phenotype identification comprise multiple independent steps, with each step requiring method customization and adjustment of multiple parameters. RESULTS: Here, we present an approach based on a multi-scale convolutional neural network (M-CNN) that classifies, in a single cohesive step, cellular images into phenotypes by using directly and solely the images' pixel intensity values. The only parameters in the approach are the weights of the neural network, which are automatically optimized based on training images. The approach requires no a priori knowledge or manual customization, and is applicable to single- or multi-channel images displaying single or multiple cells. We evaluated the classification performance of the approach on eight diverse benchmark datasets. The approach yielded overall a higher classification accuracy compared with state-of-the-art results, including those of other deep CNN architectures. In addition to using the network to simply obtain a yes-or-no prediction for a given phenotype, we use the probability outputs calculated by the network to quantitatively describe the phenotypes. This study shows that these probability values correlate with chemical treatment concentrations. This finding validates further our approach and enables chemical treatment potency estimation via CNNs. AVAILABILITY AND IMPLEMENTATION: The network specifications and solver definitions are provided in Supplementary Software 1. CONTACT: william_jose.godinez_navarro@novartis.com or xian-1.zhang@novartis.com. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Dark chemical matter as a promising starting point for drug lead discovery.

High-throughput screening (HTS) is an integral part of early drug discovery. Herein, we focused on those small molecules in a screening collection that have never shown biological activity despite having been exhaustively tested in HTS assays. These compounds are referred to as 'dark chemical matter' (DCM). We quantified DCM, validated it in quality control experiments, described its physicochemical properties and mapped it into chemical space. Through analysis of prospective reporter-gene assay, gene expression and yeast chemogenomics experiments, we evaluated the potential of DCM to show biological activity in future screens. We demonstrated that, despite the apparent lack of activity, occasionally these compounds can result in potent hits with unique activity and clean safety profiles, which makes them valuable starting points for lead optimization efforts. Among the identified DCM hits was a new antifungal chemotype with strong activity against the pathogen Cryptococcus neoformans but little activity at targets relevant to human safety.

Grasslands and flood mitigation - Contrasting forages improve surface water infiltration rates.

Grasslands globally deliver many ecosystem services, including water management to alleviate flood risk reduction. Two replicated field experiments were conducted to study how agricultural forage species with diverse rooting systems, sown as single species, affected rooting, soil structure and earthworm populations, and consequently water infiltration to understand how they each might influence flood risk from grasslands. Experiment One showed soils under red clover (Trifolium pratense), white clover (Trifolium repens) and chicory (Cichorium intybus) had higher infiltration rates three years after establishment, compared to perennial ryegrass (Lolium perenne). Higher red clover and chicory root biomass or increased earthworm abundance under white clover may have caused these effects. Experiment Two monitored infiltration at intervals over several years post establishment to understand the timeframe for changes in rates; plantain (Plantago lanceolata) was sown as an additional forage. Infiltration declined post establishment, the timing and extent of decline varying with forages; forage effects were significant after 27 months (P < 0.05). Infiltration rates were higher under red and white clover compared to ryegrass, with chicory and plantain intermediate (P < 0.05). Forages again differed in likely mechanisms delivering higher water infiltration, notably between the two clover species. White clover had higher earthworm biomass (P < 0.05), whereas red clover had a higher average root diameter compared to the other forages (P < 0.05). Drivers of intermediate benefits of chicory and plantain also differed: chicory had higher earthworm abundance (month 38) compared to plantain, which had higher average root diameter compared to ryegrass (month 41); 30 months post-establishment soil bulk density was lower under both forages compared to ryegrass and red clover, with white clover intermediate (P < 0.05); bulk density and penetration resistance did not relate to infiltration. Findings demonstrate that a shift from perennial ryegrass-dominated pastures to swards with more contrasting forages provides an ecohydrological approach to mitigating flood risk and climate adaptation.

Designing agricultural grasses to help mitigate proteolysis during ensiling to optimize protein feed provisions for livestock.

The efficient preservation of protein in silage for livestock feed is dependent on the rate and extent of proteolysis. Previous research on fresh forage indicated enhanced protein stability in certain Festulolium (ryegrass × fescue hybrids) cultivars compared to ryegrass. This is the first report of an experiment to test the hypothesis that a Lolium perenne × Festuca arundinacea var glaucescens cultivar had reduced proteolysis compared to perennial ryegrass (L. perenne) during the ensiling process. Forages were harvested in May (Cut 2) and August (Cut 4), wilted for 24 h and ensiled in laboratory-scale silos. Silage was destructively sampled at 0 h, 9 h, 24 h, 48 h, 72 h, 14 days and 90 days post-ensiling, and dry matter (DM), pH and chemical composition were determined. At Cut 2, there was no difference in crude protein between treatments but ryegrass had higher soluble nitrogen (SN) (P < 0.001) and grass × time interactions (p = 0.03) indicated higher rates of proteolysis. By Cut 4, Festulolium had (5.5% units) higher CP than ryegrass (p < 0.001) but SN did not differ. Ammonia-N did not differ between silages in either cut. DM differences (11.8% units) between treatments in Cut 4 (v.2.2% in Cut 2) may have masked effects on proteolysis, highlighting the importance of management on silage quality. This was despite higher WSC in ryegrass in both cuts (p < 0.001), with grass × time interactions (Cut 2; p = 0.03) showing slower WSC decline in ryegrass in Cut 4 (p < 0.001). Silage pH values did not differ between grasses in either cut, but grass × time interactions (p < 0.001) showed a slower decline in both ryegrass cuts, resulting in higher (p < 0.05) pH at 24 h and 72 h for Cuts 2 and 4, respectively. Overall, the hypothesis for an enhanced protein stability in Festulolium when ensiled as ruminant feed was evidenced by lower SN but not ammonia-N in an early-cut silage with a comparable DM to ryegrass.

Chemotography for multi-target SAR analysis in the context of biological pathways.

The increasing amount of chemogenomics data, that is, activity measurements of many compounds across a variety of biological targets, allows for better understanding of pharmacology in a broad biological context. Rather than assessing activity at individual biological targets, today understanding of compound interaction with complex biological systems and molecular pathways is often sought in phenotypic screens. This perspective poses novel challenges to structure-activity relationship (SAR) assessment. Today, the bottleneck of drug discovery lies in the understanding of SAR of rich datasets that go beyond single targets in the context of biological pathways, potential off-targets, and complex selectivity profiles. To aid in the understanding and interpretation of such complex SAR, we introduce Chemotography (chemotype chromatography), which encodes chemical space using a color spectrum by combining clustering and multidimensional scaling. Rich biological data in our approach were visualized using spatial dimensions traditionally reserved for chemical space. This allowed us to analyze SAR in the context of target hierarchies and phylogenetic trees, two-target activity scatter plots, and biological pathways. Chemotography, in combination with the Kyoto Encyclopedia of Genes and Genomes (KEGG), also allowed us to extract pathway-relevant SAR from the ChEMBL database. We identified chemotypes showing polypharmacology and selectivity-conferring scaffolds, even in cases where individual compounds have not been tested against all relevant targets. In addition, we analyzed SAR in ChEMBL across the entire Kinome, going beyond individual compounds. Our method combines the strengths of chemical space visualization for SAR analysis and graphical representation of complex biological data. Chemotography is a new paradigm for chemogenomic data visualization and its versatile applications presented here may allow for improved assessment of SAR in biological context, such as phenotypic assay hit lists.

Targeting angiogenesis with a conjugate of HPMA copolymer and TNP-470.

Angiogenesis is crucial for tumor growth. Angiogenesis inhibitors, such as O-(chloracetyl-carbamoyl) fumagillol (TNP-470), are thus emerging as a new class of anticancer drugs. In clinical trials, TNP-470 slowed tumor growth in patients with metastatic cancer. However, at higher doses necessary for tumor regression, many patients experienced neurotoxicity. We therefore synthesized and characterized a water-soluble conjugate of N-(2-hydroxypropyl)methacrylamide (HPMA) copolymer, Gly-Phe-Leu-Gly linker and TNP-470. This conjugate accumulated selectively in tumor vessels because of the enhanced permeability and retention (EPR) effect. HPMA copolymer-TNP-470 substantially enhanced and prolonged the activity of TNP-470 in vivo in tumor and hepatectomy models. Polymer conjugation prevented TNP-470 from crossing the blood-brain barrier (BBB) and decreased its accumulation in normal organs, thereby avoiding drug-related toxicities. Treatment with TNP-470 caused weight loss and neurotoxic effects in mice, whereas treatment with the conjugate did not. This new approach for targeting angiogenesis inhibitors specifically to the tumor vasculature may provide a new strategy for the rational design of cancer therapies.

Do agricultural grasses bred for improved root systems provide resilience to machinery-derived soil compaction?

The increasing frequency of droughts and floods on grasslands, due to climate change, increases the risk of soil compaction. Soil compaction affects both soil and forage productivity. Differing grasses may counteract some effects of compaction due to differences in their root architecture and ontogeny. To compare their resilience to soil compaction, three Festulolium (ryegrass and fescue species' hybrids) forage grass cultivars comprising differing root architecture and ontogeny were compared in replicated field plots, together with a ryegrass and tall fescue variety as controls. Pre-compaction soil and forage properties were determined in spring using > four-year-old plots to generate baseline data. Half of each field plot was then artificially compacted using farm machinery. Forage dry matter yield (DMY) was determined over four cuts. After the final harvest, post compaction soil characteristics and root biomass (RB) were compared between grasses in the non-compacted and compacted soils. Pre-compaction data showed that soil under Festulolium and ryegrass had similar water infiltration rates, higher than soil under tall fescue plots. Tiller density of the Festulolium at this time was significantly higher than fescue but not the ryegrass control. Forage DMY was significantly lower (p < .001) with compacted soil at the first cut but, by the completion of the growing season, there was no effect of soil compaction on total DMY. Tall fescue had a higher total DMY than other grasses, which all produced similar annual yields. Soil bulk density and penetration resistance were higher, and grass tiller density was lower in compacted soils. Root biomass in compacted soils showed a tendency for Festulolium cv Lp × Fg to have higher RB than the ryegrass at 0-15 cm depth. Overall, findings showed alternative grass root structures provide differing resilience to machinery compaction, and root biomass production can be encouraged without negative impacts on forage productivity.

Plate-based diversity selection based on empirical HTS data to enhance the number of hits and their chemical diversity.

Typically, screening collections of pharmaceutical companies contain more than a million compounds today. However, for certain high-throughput screening (HTS) campaigns, constraints posed by the assay throughput and/or the reagent costs make it impractical to screen the entire deck. Therefore, it is desirable to effectively screen subsets of the collection based on a hypothesis or a diversity selection. How to select compound subsets is a subject of ongoing debate. The authors present an approach based on extended connectivity fingerprints to carry out diversity selection on a per plate basis (instead of a per compound basis). HTS data from 35 Novartis screens spanning 5 target classes were investigated to assess the performance of this approach. The analysis shows that selecting a fingerprint-diverse subset of 250K compounds, representing 20% of the screening deck, would have achieved significantly higher hit rates for 86% of the screens. This measure also outperforms the Murcko scaffold-based plate selection described previously, where only 49% of the screens showed similar improvements. Strikingly, the 2-fold improvement in average hit rates observed for 3 of 5 target classes in the data set indicates a target bias of the plate (and thus compound) selection method. Even though the diverse subset selection lacks any target hypothesis, its application shows significantly better results for some targets-namely, G-protein-coupled receptors, proteases, and protein-protein interactions-but not for kinase and pathway screens. The synthetic origin of the compounds in the diverse subset appears to influence the screening hit rates. Natural products were the most diverse compound class, with significantly higher hit rates compared to the compounds from the traditional synthetic and combinatorial libraries. These results offer empirical guidelines for plate-based diversity selection to enhance hit rates, based on target class and the library type being screened.

Which aspects of HTS are empirically correlated with downstream success?

High-throughput screening (HTS) is a well-established hit-finding approach used in the pharmaceutical industry. In this article, recent experience at Novartis with respect to factors influencing the success of HTS campaigns is discussed. An inherent measure of HTS quality could be defined by the assay Z and Z' factors, the number of hits and their biological potencies; however, such measures of quality do not always correlate with the advancement of hits to the later stages of drug discovery. Also, for many target classes, such as kinases, it is easy to identify hits, but, as a result of selectivity, intellectual property and other issues, the projects do not result in lead declarations. In this article, HTS success is defined as the fraction of HTS campaigns that advance into the later stages of drug discovery, and the major influencing factors are examined. Interestingly, screening compounds in individual wells or in mixtures did not have a major impact on the HTS success and, equally interesting, there was no difference in the progression rates of biochemical and cell-based assays. Particular target types, assay technologies, structure-activity relationships and powder availability had a much greater impact on success as defined above. In addition, significant mutual dependencies can be observed - while one assay format works well with one target type, this situation might be completely reversed for a combination of the same readout technology with a different target type. The results and opinions presented here should be regarded as groundwork, and a plethora of factors that influence the fate of a project, such as biophysical measurements, chemical attractiveness of the hits, strategic reasons and safety pharmacology, are not covered here. Nonetheless, it is hoped that this information will be used industry-wide to improve success rates in terms of hits progressing into exploratory chemistry and beyond. The support that can be obtained from new in silico approaches to phase transitions are also described, along with the gaps they are designed to fill.

"Virtual fragment linking": an approach to identify potent binders from low affinity fragment hits.

In this work we explore the possibilities of using fragment-based screening data to prioritize compounds from a full HTS library, a method we call virtual fragment linking (VFL). The ability of VFL to identify compounds of nanomolar potency based on micromolar fragment binding data was tested on 75 target classes from the WOMBAT database and succeeded in 57 cases. Further, the method was demonstrated for seven drug targets from in-house screening programs that performed both FBS of 8800 fragments and screens of the full library. VFL captured between 28% and 67% of the hits (IC 50 < 10microM) in the top 5% of the ranked library for four of the targets (enrichment between 5-fold and 13-fold). Our findings lead us to conclude that proper coverage of chemical space by the fragment library is crucial for the VFL methodology to be successful in prioritizing HTS libraries from fragment-based screening data.

Streamlining lead discovery by aligning in silico and high-throughput screening.

Lead discovery in the pharmaceutical environment is largely an industrial-scale process in which it is typical to screen 1-5 million compounds in a matter of weeks using High Throughput Screening (HTS). This process is a very costly endeavor. Typically a HTS campaign of 1 million compounds will cost anywhere from $500000 to $1000000. There is consequently a great deal of pressure to maximize the return on investment by finding fast and more effective ways to screen. A panacea that has emerged over the past few years to help address this issue is in silico screening. In silico screening is now incorporated in all areas of lead discovery; from target identification and library design, to hit analysis and compound profiling. However, as lead discovery has evolved over the past few years, so has the role of in silico screening.

"Plate cherry picking": a novel semi-sequential screening paradigm for cheaper, faster, information-rich compound selection.

This work describes a novel semi-sequential technique for in silico enhancement of high-throughput screening (HTS) experiments now employed at Novartis. It is used in situations in which the size of the screen is limited by the readout (e.g., high-content screens) or the amount of reagents or tools (proteins or cells) available. By performing computational chemical diversity selection on a per plate basis (instead of a per compound basis), 25% of the 1,000,000-compound screening was optimized for general initial HTS. Statistical models are then generated from target-specific primary results (percentage inhibition data) to drive the cherry picking and testing from the entire collection. Using retrospective analysis of 11 HTS campaigns, the authors show that this method would have captured on average two thirds of the active compounds (IC(50) < 10 microM) and three fourths of the active Murcko scaffolds while decreasing screening expenditure by nearly 75%. This result is true for a wide variety of targets, including G-protein-coupled receptors, chemokine receptors, kinases, metalloproteinases, pathway screens, and protein-protein interactions. Unlike time-consuming "classic" sequential approaches that require multiple iterations of cherry picking, testing, and building statistical models, here individual compounds are cherry picked just once, based directly on primary screening data. Strikingly, the authors demonstrate that models built from primary data are as robust as models built from IC(50) data. This is true for all HTS campaigns analyzed, which represent a wide variety of target classes and assay types.

Chemogenomic data analysis: prediction of small-molecule targets and the advent of biological fingerprint.

Chemogenomics comprises a systematic relationship between targets and ligands that are used as target modulators in living systems such as cells or organisms. In recent years, data on small molecule-bioactivity relationships have become increasingly available, and consequently so have the number of approaches used to translate bioactivity data into knowledge. This review will focus on two aspects of chemogenomics. Firstly, in cases such as cell-based screens, the question of which target(s) a compound is modulating in order to cause the observed phenotype is crucial. In silico target prediction tools can suggest likely biological targets of small molecules via data mining in target-annotated chemical databases. This review presents some of the current tools available for this task and shows some sample applications relevant to a pharmaceutical industry setting. These applications are the prediction of false-positives in cell-based reporter gene assays, the prediction of targets by linking bioassay data with protein domain annotations, and the direct prediction of adverse reactions. Secondly, in recent years a shift from structure-derived chemical descriptors to biological descriptors has occurred. Here, the effect of a compound on a number of biological endpoints is used to make predictions about other properties, such as putative targets, associated adverse reactions, and pathways modulated by the compound. This review further summarizes these "performance" descriptors and their applications, focusing on gene expression profiles and high-content screening data. The advent of such biological fingerprints suggests that the field of drug discovery is currently at a crossroads, where single target bioassay results are supplanted by multidimensional biological fingerprints that reflect a new awareness of biological networks and polypharmacology.

Entangled palladium nanoparticles in resin plugs.

Palladium nanoparticles were entrapped within resin plugs and used in a range of ligand-free cross-coupling reactions; the convenient modular format of the resin plug enhanced resin handling and allowed the catalysts to be easily recovered and multiply reused.

Flexible 3D pharmacophores as descriptors of dynamic biological space.

Development of a pharmacophore hypothesis related to small-molecule activity is pivotal to chemical optimization of a series, since it defines features beneficial or detrimental to activity. Although crystal structures may provide detailed 3D interaction information for one molecule with its receptor, docking a different ligand to that model often leads to unreliable results due to protein flexibility. Graham Richards' lab was one of the first groups to utilize "fuzzy" pattern recognition algorithms taken from the field of image processing to solve problems in protein modeling. Thus, descriptor "fuzziness" was partly able to emulate conformational flexibility of the target while simultaneously enhancing the speed of the search. In this work, we extend these developments to a ligand-based method for describing and aligning molecules in flexible chemical space termed FEature POint PharmacophoreS (FEPOPS), which allows exploration of dynamic biological space. We develop a novel, combinatorial algorithm for molecular comparisons and evaluate it using the WOMBAT dataset. The new approach shows superior retrospective virtual screening performance than earlier shape-based or charge-based algorithms. Additionally, we use target prediction to evaluate how FEPOPS alignments match the molecules biological activity by identifying the atoms and features that make the key contributions to overall chemical similarity. Overall, we find that FEPOPS are sufficiently fuzzy and flexible to find not only new ligand scaffolds, but also challenging molecules that occupy different conformational states of dynamic biological space as from induced fits.

Bridging chemical and biological space: "target fishing" using 2D and 3D molecular descriptors.

Bridging chemical and biological space is the key to drug discovery and development. Typically, cheminformatics methods operate under the assumption that similar chemicals have similar biological activity. Ideally then, one could predict a drug's biological function(s) given only its chemical structure by similarity searching in libraries of compounds with known activities. In practice, effectively choosing a similarity metric is case dependent. This work compares both 2D and 3D chemical descriptors as tools for predicting the biological targets of ligand probes, on the basis of their similarity to reference molecules in a 46,000 compound, biologically annotated chemical database. Overall, we found that the 2D methods employed here outperform the 3D (88% vs 67% success) in correct target prediction. However, the 3D descriptors proved superior in cases of probes with low structural similarity to other compounds in the database (singletons). Additionally, the 3D method (FEPOPS) shows promise for providing pharmacophoric alignment of the small molecules' chemical features consistent with those seen in experimental ligand/ receptor complexes. These results suggest that querying annotated chemical databases with a systematic combination of both 2D and 3D descriptors will prove more effective than employing single methods.

The opportunities of mining historical and collective data in drug discovery.

Vast amounts of bioactivity data have been generated for small molecules across public and corporate domains. Biological signatures, either derived from systematic profiling efforts or from existing historical assay data, have been successfully employed for small molecule mechanism-of-action elucidation, drug repositioning, hit expansion and screening subset design. This article reviews different types of biological descriptors and applications, and we demonstrate how biological data can outlive the original purpose or project for which it was generated. By comparing 150 HTS campaigns run at Novartis over the past decade on the basis of their active and inactive chemical matter, we highlight the opportunities and challenges associated with cross-project learning in drug discovery.

A 3D similarity method for scaffold hopping from known drugs or natural ligands to new chemotypes.

A primary goal of 3D similarity searching is to find compounds with similar bioactivity to a reference ligand but with different chemotypes, i.e., "scaffold hopping". However, an adequate description of chemical structures in 3D conformational space is difficult due to the high-dimensionality of the problem. We present an automated method that simplifies flexible 3D chemical descriptions in which clustering techniques traditionally used in data mining are exploited to create "fuzzy" molecular representations called FEPOPS (feature point pharmacophores). The representations can be used for flexible 3D similarity searching given one or more active compounds without a priori knowledge of bioactive conformations or pharmacophores. We demonstrate that similarity searching with FEPOPS significantly enriches for actives taken from in-house high-throughput screening datasets and from MDDR activity classes COX-2, 5-HT3A, and HIV-RT, while also scaffold or ring-system hopping to new chemical frameworks. Further, inhibitors of target proteins (dopamine 2 and retinoic acid receptor) are recalled by FEPOPS by scaffold hopping from their associated endogenous ligands (dopamine and retinoic acid). Importantly, the method excels in comparison to commonly used 2D similarity methods (DAYLIGHT, MACCS, Pipeline Pilot fingerprints) and a commercial 3D method (Pharmacophore Distance Triplets) at finding novel scaffold classes given a single query molecule.

Combination of a naive Bayes classifier with consensus scoring improves enrichment of high-throughput docking results.

We have previously shown that a machine learning technique can improve the enrichment of high-throughput docking (HTD) results. In the previous cases studied, however, the application of a naive Bayes classifier failed to improve enrichment for instances where HTD alone was unable to generate an acceptable enrichment. We present here a protocol to rescue poor docking results a priori using a combination of rank-by-median consensus scoring and naive Bayesian categorization.

Finding more needles in the haystack: A simple and efficient method for improving high-throughput docking results.

The technology underpinning high-throughput docking (HTD) has developed over the past few years to where it has become a vital tool in modern drug discovery. Although the performance of various docking algorithms is adequate, the ability to accurately and consistently rank compounds using a scoring function remains problematic. We show that by employing a simple machine learning method (naïve Bayes) it is possible to significantly overcome this deficiency. Compounds from the Available Chemical Directory (ACD), along with known active compounds, were docked into two protein targets using three software packages. In cases where HTD alone was able to show some enrichment, the application of naïve Bayes was able to improve upon the enrichment. The application of this methodology to enrich HTD results can be carried out without a priori knowledge of the activity of compounds and results in superior enrichment of known actives compared to the use of scoring methods alone.