DeepSort: deep convolutional networks for sorting haploid maize seeds.

BACKGROUND: Maize is a leading crop in the modern agricultural industry that accounts for more than 40% grain production worldwide. THe double haploid technique that uses fewer breeding generations for generating a maize line has accelerated the pace of development of superior commercial seed varieties and has been transforming the agricultural industry. In this technique the chromosomes of the haploid seeds are doubled and taken forward in the process while the diploids marked for elimination. Traditionally, selective visual expression of a molecular marker within the embryo region of a maize seed has been used to manually discriminate diploids from haploids. Large scale production of inbred maize lines within the agricultural industry would benefit from the development of computer vision methods for this discriminatory task. However the variability in the phenotypic expression of the molecular marker system and the heterogeneity arising out of the maize genotypes and image acquisition have been an enduring challenge towards such efforts. RESULTS: In this work, we propose a novel application of a deep convolutional network (DeepSort) for the sorting of haploid seeds in these realistic settings. Our proposed approach outperforms existing state-of-the-art machine learning classifiers that uses features based on color, texture and morphology. We demonstrate the network derives features that can discriminate the embryo regions using the activations of the neurons in the convolutional layers. Our experiments with different architectures show that the performance decreases with the decrease in the depth of the layers. CONCLUSION: Our proposed method DeepSort based on the convolutional network is robust to the variation in the phenotypic expression, shape of the corn seeds, and the embryo pose with respect to the camera. In the era of modern digital agriculture, deep learning and convolutional networks will continue to play an important role in advancing research and product development within the agricultural industry.

Relating molecular properties and in vitro assay results to in vivo drug disposition and toxicity outcomes.

A primary goal of lead optimization is to identify compounds with improved absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. A number of reports have linked computed molecular properties to desirable in vivo ADMET outcomes, but a significant limitation of these analyses is the failure to control statistically for possible covariates. We examine the relationship between molecular properties and in vitro surrogate assays vs in vivo properties within 173 chemical series from a database of 3773 compounds with rodent pharmacokinetic and toxicology data. This approach identifies the following pairs of surrogates as most predictive among those examined: rat primary hepatocyte (RPH) cytolethality/volume of distribution (V(d)) for in vivo toxicology outcomes, scaled microsome metabolism/calculated logP for in vivo unbound clearance, and calculated logD/kinetic aqueous solubility for thermodynamic solubility. The impact of common functional group substitutions is examined and provides insights for compound design.

The flexible alignment of molecular structures using simulated annealing with weighted Lagrangian multipliers.

A framework for superimposing small molecules is presented. The proposed method consists of a simple atom-based, flexible alignment. The optimization procedure used in the alignment is based on a recently published variant of the simulated annealing whereby nonlinear constraints are accommodated using Lagrangian multipliers. It differs from other published superposition algorithms in that any number of nonlinear constraints can be readily imposed on the structural alignment directly through the objective function without assuming an a priori trade-off between competing conditions. These can include equality and equality constraints on distances, angles, and energy states. Examples illustrating the use of the proposed approach are also provided.

Rationalizing lead optimization by associating quantitative relevance with molecular structure modification.

Historically, one of the characteristic activities of the medicinal chemist has been the iterative improvement of lead compounds until a suitable therapeutic entity is achieved. Often referred to as lead optimization, this process typically takes the form of minor structural modifications to an existing lead in an attempt to ameliorate deleterious attributes while simultaneously trying to maintain or improve desirable properties. The cumulative effect of this exercise performed over the course of several decades of pharmaceutical research by thousands of trained researchers has resulted in large collections of pharmaceutically relevant chemical structures. As far as the authors are aware, this work represents the first attempt to use that data to define a framework to quantifiably catalogue and summate this information into a medicinal chemistry expert system. A method is proposed that first comprehensively mines a compendium of chemical structures compiling the structural modifications, abridges them to rectify artificially inflated support levels, and then performs an association rule mining experiment to ascribe relative confidences to each transformation. The result is a catalogue of statistically relevant structural modifications that can potentially be used in a number of pharmaceutical applications.

An automated method for exploring targeted substructural diversity within sets of chemical structures.

Practicing medicinal chemists tend to treat a lead compound as an assemblage of its substructural parts. By iteratively confining their synthetic efforts in a localized fashion, they are able to systematically investigate how minor changes in certain portions of the molecule effect the properties of interest in the logical expectation that the observed beneficial changes will be cumulative. One disadvantage to this approach arises when large amounts of structure data begin to accumulate which is often the case in recent times due to such developments as high-throughput screening, virtual screening, and combinatorial chemistry. How then does one interactively mine this diverse data consistent with the desired substructural template, so those desirable structural features can be discovered and interpreted, especially when they may not occur in the most active compounds due to structural deficiencies in other portions of the molecule? In this paper, we present an algorithm to automate this process that has historically been performed in an ad-hoc and manual fashion. Using the proposed method, significantly larger numbers of compounds can be analyzed in this fashion, potentially discovering useful structural feature combinations that would not have otherwise been detected due to the sheer scale of modern structural and biological data collections.

Conditional probability: a new fusion method for merging disparate virtual screening results.

This paper introduces a new consensus scoring approach for merging the results of different virtual screening methods based on conditional probabilities. The technique is experimentally evaluated using several ligand-based virtual screening methods and compared to two variations of the established Sum-rank fusion method where it performs as well or better than the Sum-rank methods. Our experiments confirm that consensus scoring increases the number of active compounds retrieved with respect to the best individual methods on average.

Similarity searching in databases of flexible 3D structures using smoothed bounded distance matrices.

This paper describes a method for calculating the similarity between pairs of chemical structures represented by 3D molecular graphs. The method is based on a graph matching procedure that accommodates conformational flexibility by using distance ranges between pairs of atoms, rather than fixing the atom pair distances. These distance ranges are generated using triangle and tetrangle bound smoothing techniques from distance geometry. The effectiveness of the proposed method in retrieving other compounds of like biological activity is evaluated, and the results are compared with those obtained from other, 2D-based methods for similarity searching.

Comparison of chemical clustering methods using graph- and fingerprint-based similarity measures.

This paper compares several published methods for clustering chemical structures, using both graph- and fingerprint-based similarity measures. The clusterings from each method were compared to determine the degree of cluster overlap. Each method was also evaluated on how well it grouped structures into clusters possessing a non-trivial substructural commonality. The methods which employ adjustable parameters were tested to determine the stability of each parameter for datasets of varying size and composition. Our experiments suggest that both graph- and fingerprint-based similarity measures can be used effectively for generating chemical clusterings; it is also suggested that the CAST and Yin-Chen methods, suggested recently for the clustering of gene expression patterns, may also prove effective for the clustering of 2D chemical structures.

Effectiveness of graph-based and fingerprint-based similarity measures for virtual screening of 2D chemical structure databases.

This paper reports an evaluation of both graph-based and fingerprint-based measures of structural similarity, when used for virtual screening of sets of 2D molecules drawn from the MDDR and ID Alert databases. The graph-based measures employ a new maximum common edge subgraph isomorphism algorithm, called RASCAL, with several similarity coefficients described previously for quantifying the similarity between pairs of graphs. The effectiveness of these graph-based searches is compared with that resulting from similarity searches using BCI, Daylight and Unity 2D fingerprints. Our results suggest that graph-based approaches provide an effective complement to existing fingerprint-based approaches to virtual screening.

Heuristics for similarity searching of chemical graphs using a maximum common edge subgraph algorithm.

Recently a method (RASCAL) for determining graph similarity using a maximum common edge subgraph algorithm has been proposed which has proven to be very efficient when used to calculate the relative similarity of chemical structures represented as graphs. This paper describes heuristics which simplify a RASCAL similarity calculation by taking advantage of certain properties specific to chemical graph representations of molecular structure. These heuristics are shown experimentally to increase the efficiency of the algorithm, especially at more distant values of chemical graph similarity.

Maximum common subgraph isomorphism algorithms for the matching of chemical structures.

The maximum common subgraph (MCS) problem has become increasingly important in those aspects of chemoinformatics that involve the matching of 2D or 3D chemical structures. This paper provides a classification and a review of the many MCS algorithms, both exact and approximate, that have been described in the literature, and makes recommendations regarding their applicability to typical chemoinformatics tasks.