Religious institutions as a link to substance use treatment: Characterizing the potential service population through national survey data.

Background: Relatively few Americans with current alcohol or drug use disorders receive outpatient or residential treatment. Outreach initiatives at local places of religious worship have been proposed as a way of facilitating such service use, but the number and characteristics of adults who may be reached in this way has not been studied. Methods: Data from the 2012-2013 National Epidemiologic Survey on Alcohol and Related Conditions-III, a nationally representative cross-sectional survey of U.S. adults were used to estimate the number of and proportion of adults with substance use disorders (SUDs) who attended monthly religious service and did not receive SUD treatment in the past year and used multinomial logistic regression to compare them to three SUD groups who did or did not receive treatment and/or attend religious services. Results: A total of 5,795 respondents representing 35.8 million Americans met criteria for a past-year SUD, of whom 8.3 million (23.1%) attended religious services monthly and did not receive substance use treatment. This more often African-American group had substantially fewer socio-demographic disadvantages (e.g., unemployment), behavioral problem indicators (e.g., police involvement), a higher quality of life score and less likelihood of an illicit drug use diagnosis than those who received treatment and either did or did not attend religious services. Conclusion: Almost one quarter of adults with a SUD attend religious services monthly and do not receive SUD treatment. Although they have fewer adversities than people who receive treatment, outreach to this population may link this substantial group of people to needed services.Highlights/reviewNational survey data suggest 8 of 36 million Americans with substance use diagnoses' (23%) do not receive specialized SUD treatment, but they do attend religious services monthly or more.This group, notably, has less numerous problems, such as unemployment, police involvement, and drug use disorder, and have higher quality of life scores than those who receive treatment for SUD.Outreach and linkage initiatives with religious institutions may facilitate use of services by this population.

Multi-task generative topographic mapping in virtual screening.

The previously reported procedure to generate "universal" Generative Topographic Maps (GTMs) of the drug-like chemical space is in practice a multi-task learning process, in which both operational GTM parameters (example: map grid size) and hyperparameters (key example: the molecular descriptor space to be used) are being chosen by an evolutionary process in order to fit/select "universal" GTM manifolds. After selection (a one-time task aimed at optimizing the compromise in terms of neighborhood behavior compliance, over a large pool of various biological targets), for any further use the manifolds are ready to provide "fit-free" predictive models. Using any structure-activity set-irrespectively whether the associated target served at map fitting stage or not-the generation or "coloring" a property landscape enables predicting the property for any external molecule, with zero additional fitable parameters involved. While previous works have signaled the excellent behavior of such models in aggressive three-fold cross-validation assessments of their predictive power, the present work wished to explore their behavior in Virtual Screening (VS), here simulated on hand of external DUD ligand and decoy series that are fully disjoint from the ChEMBL-extracted landscape coloring sets. Beyond the rather robust results of the universal GTM manifolds in this challenge, it could be shown that the descriptor spaces selected by the evolutionary multi-task learner were intrinsically able to serve as an excellent support for many other VS procedures, starting from parameter-free similarity searching, to local (target-specific) GTM models, to parameter-rich, nonlinear Random Forest and Neural Network approaches.

Dysfunctional elimination syndromes--how closely linked are constipation and encopresis with specific lower urinary tract conditions?

PURPOSE: It is recognized that there is a strong association between bladder and bowel dysfunction. We determined the association of constipation and/or encopresis with specific lower urinary tract conditions. MATERIALS AND METHODS: We reviewed our database of children with lower urinary tract dysfunction and divided cases into 3 categories of bowel dysfunction (constipation, encopresis and constipation plus encopresis) and 4 lower urinary tract conditions (dysfunctional voiding, idiopathic detrusor overactivity disorder, detrusor underutilization disorder and primary bladder neck dysfunction). Associations between bowel dysfunction types and each lower urinary tract condition were determined. RESULTS: Of 163 males and 205 females with a mean age of 8.5 years constipation was the most common bowel dysfunction (27%). Although encopresis is generally thought to reflect underlying constipation, only half of children with encopresis in this series had constipation. Dysfunctional voiding was associated with the highest incidence of bowel dysfunction. All but 1 patient with encopresis had associated urgency and detrusor overactivity, and the encopresis resolved in 75% of patients after initiation of anticholinergic therapy. Constipation was significantly more common in girls (27%) than in boys (11%, p <0.01), while encopresis was more common in boys (9%) than in girls (3%, p = 0.02), likely reflecting the higher incidence of dysfunctional voiding in girls and idiopathic detrusor overactivity disorder in boys. CONCLUSIONS: Active bowel dysfunction was seen in half of the children with a lower urinary tract condition. Constipation was more common in patients with dysfunctional voiding, while encopresis was significantly increased in those with idiopathic detrusor overactivity disorder and in those with dysfunctional voiding, severe urgency and detrusor overactivity. Anticholinergics, despite their constipating effect, given for treatment of detrusor overactivity resolved encopresis in most children with this bowel dysfunction.

Outcomes of targeted treatment for vesicoureteral reflux in children with nonneurogenic lower urinary tract dysfunction.

PURPOSE: There is a known association between nonneurogenic lower urinary tract conditions and vesicoureteral reflux. Whether reflux is secondary to the lower urinary tract condition or coincidental is controversial. We determined the rate of reflux resolution in patients with lower urinary tract dysfunction using targeted treatment for the underlying condition. MATERIALS AND METHODS: Patients diagnosed and treated for a lower urinary tract condition who had concomitant vesicoureteral reflux at or near the time of diagnosis were included. Patients underwent targeted treatment and antibiotic prophylaxis, and reflux was monitored with voiding cystourethrography or videourodynamics. RESULTS: Vesicoureteral reflux was identified in 58 ureters in 36 females and 5 males with a mean age of 6.2 years. After a mean of 3.1 years of treatment reflux resolved with targeted treatment in 26 of 58 ureters (45%). All of these patients had a history of urinary tract infections before starting targeted treatment. Resolution rates of vesicoureteral reflux were similar for all reflux grades. Resolution or significant improvement of reflux was greater in the ureters of patients with dysfunctional voiding (70%) compared to those with idiopathic detrusor overactivity disorder (38%) or detrusor underutilization (40%). CONCLUSIONS: Vesicoureteral reflux associated with lower urinary tract conditions resolved with targeted treatment and antibiotic prophylaxis in 45% of ureters. Unlike the resolution rates reported in patients with reflux without a coexisting lower urinary tract condition, we found that there were no differences in resolution rates among grades I to V reflux in patients with lower urinary tract conditions. Patients with dysfunctional voiding had the most improvement and greatest resolution of reflux. Additionally grade V reflux resolved in some patients.

Prevalence of urinary tract infection and vesicoureteral reflux in children with lower urinary tract dysfunction.

PURPOSE: Lower urinary tract dysfunction is a common pediatric urological problem that is often associated with urinary tract infection. We determined the prevalence of a urinary tract infection history in children with lower urinary tract dysfunction and its association, if any, with gender, bowel dysfunction, vesicoureteral reflux and specific lower urinary tract conditions. MATERIALS AND METHODS: We retrospectively reviewed the charts of children diagnosed with and treated for lower urinary tract dysfunction, noting a history of urinary tract infection with or without fever, gender, bowel dysfunction and vesicoureteral reflux in association with specific lower urinary tract conditions. RESULTS: Of the 257 boys and 366 girls with a mean age of 9.1 years 207 (33%) had a urinary tract infection history, including 88 with at least 1 febrile infection. A total of 64 patients underwent voiding cystourethrogram/videourodynamics, which revealed reflux in 44 (69%). In 119 of the 207 patients all infections were afebrile and 18 underwent voiding cystourethrogram/videourodynamics, which revealed reflux in 5 (28%). A urinary tract infection history was noted in 53% of girls but only 5% of boys (p <0.001). Patients with detrusor underutilization disorder were statistically more likely to present with an infection history than patients with idiopathic detrusor overactivity disorder or primary bladder neck dysfunction (each p <0.01). CONCLUSIONS: Females with lower urinary tract dysfunction have a much higher urinary tract infection incidence than males. This association was most often noted for lower urinary tract conditions in which urinary stasis occurs, including detrusor underutilization disorder and dysfunctional voiding. Reflux was found in most girls with a history of febrile infections. Since reflux was identified in more than a quarter of girls with only afebrile infections who were evaluated for reflux, it may be reasonable to perform voiding cystourethrogram or videourodynamics in some of them to identify reflux.

When alternative hypotheses shape your beliefs: Context effects in probability judgments.

When people are asked to estimate the probability of an event occurring, they sometimes make different subjective probability judgments for different descriptions of the same event. This implies the evidence or support recruited to make these judgments is based on the descriptions of the events (hypotheses) instead of the events themselves, as captured by Tversky and Koehler's (1994) support theory. Support theory, however, assumes each hypothesis elicits a fixed level of support (support invariance). Here, across three studies, we tested this support invariance assumption by asking participants to estimate the probability that an event would occur given a set of relevant statistics. We show that the support recruited about a target hypothesis can depend on the other hypotheses under consideration. Results reveal that for a pair of competing hypotheses, one hypothesis (the target hypothesis) appears more competitive relative to the other when a dud-a hypothesis dominated by the target hypothesis-is present. We also find that the target hypothesis can appear less competitive relative to the other when a resembler-a hypothesis that is similar to the target hypothesis-is present. These context effects invalidate the support invariance assumption in support theory and suggest that a similar process that drives preference construction may also underlie belief construction.

Extracting prime protein targets as possible drug candidates: machine learning evaluation.

Extracting "high ranking" or "prime protein targets" (PPTs) as potent MRSA drug candidates from a given set of ligands is a key challenge in efficient molecular docking. This study combines protein-versus-ligand matching molecular docking (MD) data extracted from 10 independent molecular docking (MD) evaluations - ADFR, DOCK, Gemdock, Ledock, Plants, Psovina, Quickvina2, smina, vina, and vinaxb to identify top MRSA drug candidates. Twenty-nine active protein targets (APT) from the enhanced DUD-E repository ( http://DUD-E.decoys.org ) are matched against 1040 ligands using "forward modeling" machine learning for initial "data mining and modeling" (DDM) to extract PPTs and the corresponding high affinity ligands (HALs). K-means clustering (KMC) is then performed on 400 ligands matched against 29 PTs, with each cluster accommodating HALs, and the corresponding PPTs. Performance of KMC is then validated against randomly chosen head, tail, and middle active ligands (ALs). KMC outcomes have been validated against two other clustering methods, namely, Gaussian mixture model (GMM) and density based spatial clustering of applications with noise (DBSCAN). While GMM shows similar results as with KMC, DBSCAN has failed to yield more than one cluster and handle the noise (outliers), thus affirming the choice of KMC or GMM. Databases obtained from ADFR to mine PPTs are then ranked according to the number of the corresponding HAL-PPT combinations (HPC) inside the derived clusters, an approach called "reverse modeling" (RM). From the set of 29 PTs studied, RM predicts high fidelity of 5 PPTs (17%) that bind with 76 out of 400, i.e., 19% ligands leading to a prediction of next-generation MRSA drug candidates: PPT2 (average HPC is 41.1%) is the top choice, followed by PPT14 (average HPC 25.46%), and then PPT15 (average HPC 23.12%). This algorithm can be generically implemented irrespective of pathogenic forms and is particularly effective for sparse data.

A memory-interference versus the "dud"-effect account of a DRM false memory result: Fewer related targets at test, higher critical-lure false recognition.

Memory interference theories hold that exposure to more similar information to a target item impairs memory of the target item. The dud effect refers to the finding in eyewitness lineup identification that fillers dissimilar to the suspect cause more false identification of the suspect than similar fillers, contrary to the interference concept. Previous studies on the Deese-Roediger-McDermott false memory typically showed a testing priming effect that a larger number of studied items presented at test leads to a higher level of false recognition of the critical lure (CL). In the present study, either all, or all but one studied item were replaced by unrelated distractors at test. Subjects made more false recognitions of the CL in the no- or only-one-studied item than in the multiple-studied-item condition, supporting the dud-effect account. The slower response time in the "dud" condition suggested a deliberate, monitoring-like approach taken by subjects in that condition.

Trajectories of NEET (Not in Education, Employment, and Training) in emerging adulthood, and later drug use disorder - a national cohort study.

BACKGROUND: Being not in education, employment, or training (NEET) has been associated with poor health outcomes. This study aimed to investigate the association between NEET during emerging adulthood and later drug use disorder (DUD) among males and females. METHOD: A national cohort comprising 383,116 Swedish males and 362,002 females born between 1984 and 1990. NEET exposure was assessed annually between the ages 17 and 24 years, and follow-up for DUD between ages 25-33. Trajectories of NEET were estimated using group-based trajectory analysis. Cox regression analysis was used to estimate hazard ratios (HR) of DUD. Sibling-comparison model was performed to account for potential shared genetic and environmental factors. RESULTS: Four trajectories of NEET were identified: "constant low", "transient peak", "late increase", and "constant high". Compared with the "constant low", all other trajectories were associated with increased HRs of DUD. HR was highest among males and females in the "late increase trajectory"; HR = 4.10 (3.79-4.44, 95% CI) and HR = 3.73 (3.29-4.24, 95% CI), after adjusting for domicile, origin, birth year, psychiatric diagnoses, and parental psychiatric diagnoses. This association was reduced to about a twofold increased risk in the sibling comparison analysis. CONCLUSION: Being NEET during emerging adulthood was associated with later DUD for both males and females. Neither origin, psychiatric diagnoses, parental psychiatric diagnoses, nor shared familial factors did fully explain the association. Males and females belonging to the late increase NEET trajectory had about a twofold increased risk of DUD.

A validation study of the clinical diagnosis of Dup15q syndrome: Which symptoms matter most?

PURPOSE: Dup15q syndrome is a rare genetic disease with a fairly nonspecific phenotype, clinical heterogeneity, and a wide spectrum of severity. However, no formal characterization has been attempted to select clusters of symptoms, signs and instrumental tests, to be used in the differential diagnosis with other neurodevelopmental disorders. Thus, our purpose was to identify symptoms, signs and instrumental findings, singly or in various combinations, favoring the early diagnosis of the Dup15q syndrome and the indication for genetic testing. METHODS: 25 patients with Dup15q syndrome and 25 age and sex matched controls with other neurodevelopmental disorders were the study population. Patients' history, clinical and instrumental assessment were examined by five expert child neurologists blind to the genetic diagnosis. Each rater was asked to make the diagnosis in three subsequent steps: 1. Revision of the medical records; 2. Examination of the videorecorded clinical findings; 3. Assessment of the instrumental tests. Inter-rater agreement was measured with the Kendall's coefficient of concordance) and the Kappa statistic. Sensitivity, specificity and predictive values for symptoms, signs and instrumental findings, singly or in various combinations, were measured. RESULTS: The Kendall's coefficient for the diagnosis of Dup15q syndrome was 0.43 at step 1 was 0.43, at step 2 was 0.42, at step 3. Patients with past feeding difficulties, hypotonia during the neonatal period, and epilepsy had >80 % probability of having the Dup15q syndrome. CONCLUSION: Feeding difficulties, hypotonia and epilepsy, though unspecific, can be used as signals of Dup15q syndrome and focused search of genetic abnormalities.

Evaluation of consensus scoring methods for AutoDock Vina, smina and idock.

We investigated the application of consensus scoring using the freely available and open source structure-based virtual screening docking programs AutoDock Vina, smina and idock. These individual programs and several simple consensus scoring methods were tested for their ability to identify hits against 20 DUD-E benchmark targets using the AUC and EF1 metrics. We found that all of the consensus scoring methods, however normalized, fared worse, on average, than simply using the output from a single program, smina. Additionally, the effect of a significant increase in the run time of all three programs was tested to find if a longer run time yielded improved results. Our results indicated that a longer run time than the default had little impact on the performance of these three programs or on consensus scoring methods based on their output. Thus, we have found that using the smina program alone at default settings is the best approach for researchers that do not have access to a suite of commercial docking software packages.

Improving the Virtual Screening Ability of Target-Specific Scoring Functions Using Deep Learning Methods.

Scoring functions play an important role in structure-based virtual screening. It has been widely accepted that target-specific scoring functions (TSSFs) may achieve better performance compared with universal scoring functions in actual drug research and development processes. A method that can effectively construct TSSFs will be of great value to drug design and discovery. In this work, we proposed a deep learning-based model named DeepScore to achieve this goal. DeepScore adopted the form of PMF scoring function to calculate protein-ligand binding affinity. However, different from PMF scoring function, in DeepScore, the score for each protein-ligand atom pair was calculated using a feedforward neural network. Our model significantly outperformed Glide Gscore on validation data set DUD-E. The average ROC-AUC on 102 targets was 0.98. We also combined Gscore and DeepScore together using a consensus method and put forward a consensus model named DeepScoreCS. The comparison results showed that DeepScore outperformed other machine learning-based TSSFs building methods. Furthermore, we presented a strategy to visualize the prediction of DeepScore. All of these results clearly demonstrated that DeepScore would be a useful model in constructing TSSFs and represented a novel way incorporating deep learning and drug design.

Interaction prediction in structure-based virtual screening using deep learning.

We introduce a deep learning architecture for structure-based virtual screening that generates fixed-sized fingerprints of proteins and small molecules by applying learnable atom convolution and softmax operations to each molecule separately. These fingerprints are further non-linearly transformed, their inner product is calculated and used to predict the binding potential. Moreover, we show that widely used benchmark datasets may be insufficient for testing structure-based virtual screening methods that utilize machine learning. Therefore, we introduce a new benchmark dataset, which we constructed based on DUD-E, MUV and PDBBind databases.

An Improved Receptor-Based Pharmacophore Generation Algorithm Guided by Atomic Chemical Characteristics and Hybridization Types.

Pharmacophore-based virtual screening is an important and leading compound discovery method. However, current pharmacophore generation algorithms suffer from difficulties, such as ligand-dependent computation and massive extractive chemical features. On the basis of the features extracted by the five probes in Pocket v.3, this paper presents an improved receptor-based pharmacophore generation algorithm guided by atomic chemical characteristics and hybridization types. The algorithm works under the constraint of receptor atom hybridization types and space distance. Four chemical characteristics (H-A, H-D, and positive and negative charges) were extracted using the hybridization type of receptor atoms, and the feature point sets were merged with 3 Å space constraints. Furthermore, on the basis of the original extraction of hydrophobic characteristics, extraction of aromatic ring chemical characteristics was achieved by counting the number of aromatics, searching for residual base aromatic ring, and determining the direction of aromatic rings. Accordingly, extraction of six kinds of chemical characteristics of the pharmacophore was achieved. In view of the pharmacophore characteristics, our algorithm was compared with the existing LigandScout algorithm. The results demonstrate that the pharmacophore possessing six chemical characteristics can be characterized using our algorithm, which features fewer pharmacophore characteristics and is ligand independent. The computation of many instances from the directory of useful decoy dataset show that the active molecules and decoy molecules can be effectively differentiated through the presented method in this paper.

Efficient conformational sampling and weak scoring in docking programs? Strategy of the wisdom of crowds.

BACKGROUND: In drug design, an efficient structure-based optimization of a ligand needs the precise knowledge of the protein-ligand interactions. In the absence of experimental information, docking programs are necessary for ligand positioning, and the choice of a reliable program is essential for the success of such an optimization. The performances of four popular docking programs, Gold, Glide, Surflex and FlexX, were investigated using 100 crystal structures of complexes taken from the Directory of Useful Decoys-Enhanced database. RESULTS: The ligand conformational sampling was rather efficient, with a correct pose found for a maximum of 84 complexes, obtained by Surflex. However, the ranking of the correct poses was not as efficient, with a maximum of 68 top-rank or 75 top-4 rank correct poses given by Glidescore. No relationship was found between either the sampling or the scoring performance of the four programs and the properties of either the targets or the small molecules, except for the number of ligand rotatable bonds. As well, no exploitable relationship was found between each program performance in docking and in virtual screening; a wrong top-rank pose may obtain a good score that allows it to be ranked among the most active compounds and vice versa. Also, to improve the results of docking, the strengths of the programs were combined either by using a rescoring procedure or the United Subset Consensus (USC). Oddly, positioning with Surflex and rescoring with Glidescore did not improve the results. However, USC based on docking allowed us to obtain a correct pose in the top-4 rank for 87 complexes. Finally, nine complexes were scrutinized, because a correct pose was found by at least one program but poorly ranked by all four programs. Contrarily to what was expected, except for one case, this was not due to weaknesses of the scoring functions. CONCLUSIONS: We conclude that the scoring functions should be improved to detect the correct poses, but sometimes their failure may be due to other varied considerations. To increase the chances of success, we recommend to use several programs and combine their results. Graphical abstract Summary of the results obtained by semi-rigid docking of crystallographic ligands. The docking was done on 100 protein-ligand X-ray structures, taken from the DUD-E database, and using four programs, Glide, Gold, Surflex and FlexX. Based on the docking results, we applied our United Subset Consensus method (USC), for which only the top4-rank poses are relevant. The number of complexes for which the best pose is correct, is represented by the gray boxes, the blue and red boxes correspond to the number of complexes with a correct pose ranked as the top 1 or within the top 4. A pose is considered correct when its root-mean-square deviation from the crystal structure is less than 2 Å.

Benchmark of four popular virtual screening programs: construction of the active/decoy dataset remains a major determinant of measured performance.

BACKGROUND: In a structure-based virtual screening, the choice of the docking program is essential for the success of a hit identification. Benchmarks are meant to help in guiding this choice, especially when undertaken on a large variety of protein targets. Here, the performance of four popular virtual screening programs, Gold, Glide, Surflex and FlexX, is compared using the Directory of Useful Decoys-Enhanced database (DUD-E), which includes 102 targets with an average of 224 ligands per target and 50 decoys per ligand, generated to avoid biases in the benchmarking. Then, a relationship between these program performances and the properties of the targets or the small molecules was investigated. RESULTS: The comparison was based on two metrics, with three different parameters each. The BEDROC scores with α = 80.5, indicated that, on the overall database, Glide succeeded (score > 0.5) for 30 targets, Gold for 27, FlexX for 14 and Surflex for 11. The performance did not depend on the hydrophobicity nor the openness of the protein cavities, neither on the families to which the proteins belong. However, despite the care in the construction of the DUD-E database, the small differences that remain between the actives and the decoys likely explain the successes of Gold, Surflex and FlexX. Moreover, the similarity between the actives of a target and its crystal structure ligand seems to be at the basis of the good performance of Glide. When all targets with significant biases are removed from the benchmarking, a subset of 47 targets remains, for which Glide succeeded for only 5 targets, Gold for 4 and FlexX and Surflex for 2. CONCLUSION: The performance dramatic drop of all four programs when the biases are removed shows that we should beware of virtual screening benchmarks, because good performances may be due to wrong reasons. Therefore, benchmarking would hardly provide guidelines for virtual screening experiments, despite the tendency that is maintained, i.e., Glide and Gold display better performance than FlexX and Surflex. We recommend to always use several programs and combine their results. Graphical AbstractSummary of the results obtained by virtual screening with the four programs, Glide, Gold, Surflex and FlexX, on the 102 targets of the DUD-E database. The percentage of targets with successful results, i.e., with BDEROC(α = 80.5) > 0.5, when the entire database is considered are in Blue, and when targets with biased chemical libraries are removed are in Red.

vSDC: a method to improve early recognition in virtual screening when limited experimental resources are available.

BACKGROUND: In drug design, one may be confronted to the problem of finding hits for targets for which no small inhibiting molecules are known and only low-throughput experiments are available (like ITC or NMR studies), two common difficulties encountered in a typical academic setting. Using a virtual screening strategy like docking can alleviate some of the problems and save a considerable amount of time by selecting only top-ranking molecules, but only if the method is very efficient, i.e. when a good proportion of actives are found in the 1-10 % best ranked molecules. RESULTS: The use of several programs (in our study, Gold, Surflex, FlexX and Glide were considered) shows a divergence of the results, which presents a difficulty in guiding the experiments. To overcome this divergence and increase the yield of the virtual screening, we created the standard deviation consensus (SDC) and variable SDC (vSDC) methods, consisting of the intersection of molecule sets from several virtual screening programs, based on the standard deviations of their ranking distributions. CONCLUSIONS: SDC allowed us to find hits for two new protein targets by testing only 9 and 11 small molecules from a chemical library of circa 15,000 compounds. Furthermore, vSDC, when applied to the 102 proteins of the DUD-E benchmarking database, succeeded in finding more hits than any of the four isolated programs for 13-60 % of the targets. In addition, when only 10 molecules of each of the 102 chemical libraries were considered, vSDC performed better in the number of hits found, with an improvement of 6-24 % over the 10 best-ranked molecules given by the individual docking programs.Graphical abstractIn drug design, for a given target and a given chemical library, the results obtained with different virtual screening programs are divergent. So how to rationally guide the experimental tests, especially when only a few number of experiments can be made? The variable Standard Deviation Consensus (vSDC) method was developed to answer this issue. Left panel the vSDC principle consists of intersecting molecule sets, chosen on the basis of the standard deviations of their ranking distributions, obtained from various virtual screening programs. In this study Glide, Gold, FlexX and Surflex were used and tested on the 102 targets of the DUD-E database. Right panel Comparison of the average percentage of hits found with vSDC and each of the four programs, when only 10 molecules from each of the 102 chemical libraries of the DUD-E database were considered. On average, vSDC was capable of finding 38 % of the findable hits, against 34 % for Glide, 32 % for Gold, 16 % for FlexX and 14 % for Surflex, showing that with vSDC, it was possible to overcome the unpredictability of the virtual screening results and to improve them.

Transductive Support Vector Machines: Promising Approach to Model Small and Unbalanced Datasets.

Semi-supervised methods dealing with a combination of labeled and unlabeled data become more and more popular in machine-learning area, but not still used in chemoinformatics. Here, we demonstrate that Transductive Support Vector Machines (TSVM) - a semi-supervised large-margin classification method - can be particularly useful to build the models on small and unbalanced datasets which often represent a difficult problem in QSAR. Both TSVM and ordinary SVM have been applied to build classification models on 10 DUD datasets. The "transductive effect" (the difference in predictive performance between transductive and ordinary support vector machines) was investigated as a function of: (a) active/inactive ratio, (b) descriptor weighting, and (c) the training and test sets size and composition.