A fully differentiable ligand pose optimization framework guided by deep learning and a traditional scoring function.

The recently reported machine learning- or deep learning-based scoring functions (SFs) have shown exciting performance in predicting protein-ligand binding affinities with fruitful application prospects. However, the differentiation between highly similar ligand conformations, including the native binding pose (the global energy minimum state), remains challenging that could greatly enhance the docking. In this work, we propose a fully differentiable, end-to-end framework for ligand pose optimization based on a hybrid SF called DeepRMSD+Vina combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF. The DeepRMSD+Vina, which combines (1) the root mean square deviation (RMSD) of the docking pose with respect to the native pose and (2) the AutoDock Vina score, is fully differentiable; thus is capable of optimizing the ligand binding pose to the energy-lowest conformation. Evaluated by the CASF-2016 docking power dataset, the DeepRMSD+Vina reaches a success rate of 94.4%, which outperforms most reported SFs to date. We evaluated the ligand conformation optimization framework in practical molecular docking scenarios (redocking and cross-docking tasks), revealing the high potentialities of this framework in drug design and discovery. Structural analysis shows that this framework has the ability to identify key physical interactions in protein-ligand binding, such as hydrogen-bonding. Our work provides a paradigm for optimizing ligand conformations based on deep learning algorithms. The DeepRMSD+Vina model and the optimization framework are available at GitHub repository https://github.com/zchwang/DeepRMSD-Vina_Optimization.

OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs.

MOTIVATION: Deep graph learning (DGL) has been widely employed in the realm of ligand-based virtual screening. Within this field, a key hurdle is the existence of activity cliffs (ACs), where minor chemical alterations can lead to significant changes in bioactivity. In response, several DGL models have been developed to enhance ligand bioactivity prediction in the presence of ACs. Yet, there remains a largely unexplored opportunity within ACs for optimizing ligand bioactivity, making it an area ripe for further investigation. RESULTS: We present a novel approach to simultaneously predict and optimize ligand bioactivities through DGL and ACs (OLB-AC). OLB-AC possesses the capability to optimize ligand molecules located near ACs, providing a direct reference for optimizing ligand bioactivities with the matching of original ligands. To accomplish this, a novel attentive graph reconstruction neural network and ligand optimization scheme are proposed. Attentive graph reconstruction neural network reconstructs original ligands and optimizes them through adversarial representations derived from their bioactivity prediction process. Experimental results on nine drug targets reveal that out of the 667 molecules generated through OLB-AC optimization on datasets comprising 974 low-activity, noninhibitor, or highly toxic ligands, 49 are recognized as known highly active, inhibitor, or nontoxic ligands beyond the datasets' scope. The 27 out of 49 matched molecular pairs generated by OLB-AC reveal novel transformations not present in their training sets. The adversarial representations employed for ligand optimization originate from the gradients of bioactivity predictions. Therefore, we also assess OLB-AC's prediction accuracy across 33 different bioactivity datasets. Results show that OLB-AC achieves the best Pearson correlation coefficient (r2) on 27/33 datasets, with an average improvement of 7.2%-22.9% against the state-of-the-art bioactivity prediction methods. AVAILABILITY AND IMPLEMENTATION: The code and dataset developed in this work are available at github.com/Yueming-Yin/OLB-AC.

Inter- and intra-observer agreement in dermatologists' diagnoses of hyperpigmented facial lesions and development of an algorithm for automated diagnosis.

BACKGROUND: Hyperpigmentation has varied aetio-pathologies. Hence, accurate and reproducible diagnosis of the type of hyperpigmentation is essential for effective management. It is typically made clinically by dermatologists but the rate of inter- and intra-observer agreement/variability is unknown. Hyperpigmented facial lesions are extremely common but access to dermatological services is difficult or costly in most countries. Thus, it is desired to evaluate dermatologists' inter- and intra-observer agreement in the diagnosis and to develop an algorithm for automated diagnosis. MATERIALS AND METHODS: Hyperpigmented lesions on 392 facial images were diagnosed by three experienced dermatologists either jointly or independently, and this process was subsequently repeated for 52 randomly selected images. When there was non-concordance amongst the dermatologists for the diagnosis, a majority decision was taken as correct diagnosis. Inter-observer and intra-observer agreement were analysed for the diagnosis of the hyperpigmented lesions. Thereafter, a multiclass classification method was developed to perform the task in an automatic manner. The developed algorithm was compared and validated against the ground truth derived from the dermatologists. RESULTS: Both inter- and intra-observer agreements are in the moderate range. The algorithm agreed well with the derived ground truth, with a Kappa value of 0.492, which is similar to the Kappa values of inter- and intra- observer agreements. CONCLUSION: The rates of inter- and intra-observer agreement in the diagnosis of hyperpigmented facial lesions amongst dermatologists were moderate in this study. Compared to visual assessment from the dermatologists, automated diagnosis using the developed algorithm achieved a high rate of concordance.

Bridging the Gap Between Vitiligo Segmentation and Clinical Scores.

Quantitative evaluation of vitiligo is crucial for assessing treatment response. Dermatologists evaluate vitiligo regularly to adjust their treatment plans, which requires extra work. Furthermore, the evaluations may not be objective due to inter- and intra-assessor variability. Though automatic vitiligo segmentation methods provide an objective evaluation, previous methods mainly focus on patch-wise images, and their results cannot be translated into clinical scores for treatment adjustment. Thus, full-body vitiligo segmentation needs to be developed for recording vitiligo changes in different body parts of a patient and for calculating the clinical scores. To bridge this gap, the first full-body vitiligo dataset with 1740 images, following the international vitiligo photo standard, was established. Compared with patch-wise images, full-body images have more complicated ambient light conditions and larger variances in lesion size and distribution. Additionally, in some hand and foot images, skin can be fully covered by either vitiligo or healthy skin. Previous patch-wise segmentation studies completely ignore these cases, as they assume that the contrast between vitiligo and healthy skin is available in each image for segmentation. To address the aforementioned challenges, the proposed algorithm in this study exploits a tailor-made contrast enhancement scheme and long-range comparison. Furthermore, a novel confidence score refinement module is proposed to manage images fully covered by vitiligo or healthy skin. Our results can be converted to clinical scores and used by clinicians. Compared to the state-of-the-art method, the proposed algorithm reduces the average per-image vitiligo involvement percentage error from 3.69% to 1.81%, and the top 10% per-image errors from 23.17% to 8.29%. Our algorithm achieves 1.17% and 3.11% for the mean and max error for the per-patient vitiligo involvement percentage, which is better than an experienced dermatologist's naked-eye evaluation.

Advancing Bioactivity Prediction through Molecular Docking and Self-Attention.

Bioactivity refers to the ability of a substance to induce biological effects within living systems, often describing the influence of molecules, drugs, or chemicals on organisms. In drug discovery, predicting bioactivity streamlines early-stage candidate screening by swiftly identifying potential active molecules. The popular deep learning methods in bioactivity prediction primarily model the ligand structure-bioactivity relationship under the premise of Quantitative Structure-Activity Relationship (QSAR). However, bioactivity is determined by multiple factors, including not only the ligand structure but also drug-target interactions, signaling pathways, reaction environments, pharmacokinetic properties, and species differences. Our study first integrates drug-target interactions into bioactivity prediction using protein-ligand complex data from molecular docking. We devise a Drug-Target Interaction Graph Neural Network (DTIGN), infusing interatomic forces into intermolecular graphs. DTIGN employs multi-head self-attention to identify native-like binding pockets and poses within molecular docking results. To validate the fidelity of the self-attention mechanism, we gather ground truth data from crystal structure databases. Subsequently, we employ these limited native structures to refine bioactivity prediction via semi-supervised learning. For this study, we establish a unique benchmark dataset for evaluating bioactivity prediction models in the context of protein-ligand complexes, showcasing the superior performance of our method (with an average improvement of 27.03%) through comparison with 9 leading deep learning-based bioactivity prediction methods.

Data considerations for predictive modeling applied to the discovery of bioactive natural products.

Natural products (NPs) constitute a large reserve of bioactive compounds useful for drug development. Recent advances in high-throughput technologies facilitate functional analysis of therapeutic effects and NP-based drug discovery. However, the large amount of generated data is complex and difficult to analyze effectively. This limitation is increasingly surmounted by artificial intelligence (AI) techniques but more needs to be done. Here, we present and discuss two crucial issues limiting NP-AI drug discovery: the first is on knowledge and resource development (data integration) to bridge the gap between NPs and functional or therapeutic effects. The second issue is on NP-AI modeling considerations, limitations and challenges.

Segmenting Vitiligo on Clinical Face Images Using CNN Trained on Synthetic and Internet Images.

Accurately diagnosing and describing the severity of vitiligo is crucial for prognostication, treatment selection and comparison. Currently, disease severity scores require dermatologists to estimate percentage area of involvement, which is subjected to inter and intra-assessor variability. Previous studies focus on pure skin but vitiligo on the face, which has a more serious impact on patients' quality of life, was completely neglected. Convolutional neural networks (CNNs) have good performance on many segmentation tasks. However, due to data privacy, it is hard to have a large clinical vitiligo face image dataset to train a CNN. To address this challenge, images from two different sources, the Internet and the proposed vitiligo face synthesis algorithm, are employed in training. 843 vitiligo images taken from different viewpoints were collected from the Internet. These images are hugely different from the target clinical images collected according to a newly established international standard. To have more vitiligo face images similar to the target clinical images to enhance segmentation performance, an image synthesis algorithm is proposed. Both synthetic and Internet images are used to train a CNN which is modified from the fully convolutional network (FCN) to segment face vitiligo lesions. The results show that 1) the synthetic images effectively improve segmentation performance; 2) the proposed algorithm achieves 1.06 % error for the face vitiligo area estimation and 3) it is more accurate than two dermatologists and all the previous automated vitiligo segmentation methods, which were designed for segmentation vitiligo on pure skin.

A study on giant panda recognition based on images of a large proportion of captive pandas.

As a highly endangered species, the giant panda (panda) has attracted significant attention in the past decades. Considerable efforts have been put on panda conservation and reproduction, offering the promising outcome of maintaining the population size of pandas. To evaluate the effectiveness of conservation and management strategies, recognizing individual pandas is critical. However, it remains a challenging task because the existing methods, such as traditional tracking method, discrimination method based on footprint identification, and molecular biology method, are invasive, inaccurate, expensive, or challenging to perform. The advances of imaging technologies have led to the wide applications of digital images and videos in panda conservation and management, which makes it possible for individual panda recognition in a noninvasive manner by using image-based panda face recognition method.In recent years, deep learning has achieved great success in the field of computer vision and pattern recognition. For panda face recognition, a fully automatic deep learning algorithm which consists of a sequence of deep neural networks (DNNs) used for panda face detection, segmentation, alignment, and identity prediction is developed in this study. To develop and evaluate the algorithm, the largest panda image dataset containing 6,441 images from 218 different pandas, which is 39.78% of captive pandas in the world, is established.The algorithm achieved 96.27% accuracy in panda recognition and 100% accuracy in detection.This study shows that panda faces can be used for panda recognition. It enables the use of the cameras installed in their habitat for monitoring their population and behavior. This noninvasive approach is much more cost-effective than the approaches used in the previous panda surveys.

Relatively Permanent Pigmented or Vascular Skin Marks for Identification: A Pilot Reliability Study.

In child sexual exploitation offenses, the collected evidence images often show the skin of nonfacial body parts of the criminals and victims. For identification in this scenario, "relatively permanent pigmented or vascular skin marks," abbreviated as RPPVSM, were recently introduced as the basis for a novel biometric trait. This pilot study evaluated the interexaminer variability of RPPVSM identification. Four dermatology physicians were recruited to examine RPPVSM from 75 skin images collected from a total of 51 Caucasian and Asian subjects. The images were separated into 50 reference ("suspect") images and 25 evaluation ("evidence") images. The examiners were asked to perform identification by annotating RPPVSM in each of the 25 evaluation images and matching them with the reference images. The rate of misidentification was 0% while the mean rate at which examiners failed to find a match was 6%, indicating the potential of dermatology physicians performing the role of RPPVSM examiners.

A Statistical Analysis of IrisCode and Its Security Implications.

IrisCode has been used to gather iris data for 430 million people. Because of the huge impact of IrisCode, it is vital that it is completely understood. This paper first studies the relationship between bit probabilities and a mean of iris images (The mean of iris images is defined as the average of independent iris images.) and then uses the Chi-square statistic, the correlation coefficient and a resampling algorithm to detect statistical dependence between bits. The results show that the statistical dependence forms a graph with a sparse and structural adjacency matrix. A comparison of this graph with a graph whose edges are defined by the inner product of the Gabor filters that produce IrisCodes shows that partial statistical dependence is induced by the filters and propagates through the graph. Using this statistical information, the security risk associated with two patented template protection schemes that have been deployed in commercial systems for producing application-specific IrisCodes is analyzed. To retain high identification speed, they use the same key to lock all IrisCodes in a database. The belief has been that if the key is not compromised, the IrisCodes are secure. This study shows that even without the key, application-specific IrisCodes can be unlocked and that the key can be obtained through the statistical dependence detected.

Modeling IrisCode and its variants as convex polyhedral cones and its security implications.

IrisCode, developed by Daugman, in 1993, is the most influential iris recognition algorithm. A thorough understanding of IrisCode is essential, because over 100 million persons have been enrolled by this algorithm and many biometric personal identification and template protection methods have been developed based on IrisCode. This paper indicates that a template produced by IrisCode or its variants is a convex polyhedral cone in a hyperspace. Its central ray, being a rough representation of the original biometric signal, can be computed by a simple algorithm, which can often be implemented in one Matlab command line. The central ray is an expected ray and also an optimal ray of an objective function on a group of distributions. This algorithm is derived from geometric properties of a convex polyhedral cone but does not rely on any prior knowledge (e.g., iris images). The experimental results show that biometric templates, including iris and palmprint templates, produced by different recognition methods can be matched through the central rays in their convex polyhedral cones and that templates protected by a method extended from IrisCode can be broken into. These experimental results indicate that, without a thorough security analysis, convex polyhedral cone templates cannot be assumed secure. Additionally, the simplicity of the algorithm implies that even junior hackers without knowledge of advanced image processing and biometric databases can still break into protected templates and reveal relationships among templates produced by different recognition methods.

IrisCode decompression based on the dependence between its bit pairs.

IrisCode is an iris recognition algorithm developed in 1993 and continuously improved by Daugman. Understanding IrisCode's properties is extremely important because over 60 million people have been mathematically enrolled by the algorithm. In this paper, IrisCode is proved to be a compression algorithm, which is to say its templates are compressed iris images. In our experiments, the compression ratio of these images is 1:655. An algorithm is designed to perform this decompression by exploiting a graph composed of the bit pairs in IrisCode, prior knowledge from iris image databases, and the theoretical results. To remove artifacts, two postprocessing techniques that carry out optimization in the Fourier domain are developed. Decompressed iris images obtained from two public iris image databases are evaluated by visual comparison, two objective image quality assessment metrics, and eight iris recognition methods. The experimental results show that the decompressed iris images retain iris texture that their quality is roughly equivalent to a JPEG quality factor of 10 and that the iris recognition methods can match the original images with the decompressed images. This paper also discusses the impacts of these theoretical and experimental findings on privacy and security.