Artificial intelligence in drug discovery: applications and techniques.

Artificial intelligence (AI) has been transforming the practice of drug discovery in the past decade. Various AI techniques have been used in many drug discovery applications, such as virtual screening and drug design. In this survey, we first give an overview on drug discovery and discuss related applications, which can be reduced to two major tasks, i.e. molecular property prediction and molecule generation. We then present common data resources, molecule representations and benchmark platforms. As a major part of the survey, AI techniques are dissected into model architectures and learning paradigms. To reflect the technical development of AI in drug discovery over the years, the surveyed works are organized chronologically. We expect that this survey provides a comprehensive review on AI in drug discovery. We also provide a GitHub repository with a collection of papers (and codes, if applicable) as a learning resource, which is regularly updated.

Keratin 17 modulates the immune topography of pancreatic cancer.

BACKGROUND: The immune microenvironment impacts tumor growth, invasion, metastasis, and patient survival and may provide opportunities for therapeutic intervention in pancreatic ductal adenocarcinoma (PDAC). Although never studied as a potential modulator of the immune response in most cancers, Keratin 17 (K17), a biomarker of the most aggressive (basal) molecular subtype of PDAC, is intimately involved in the histogenesis of the immune response in psoriasis, basal cell carcinoma, and cervical squamous cell carcinoma. Thus, we hypothesized that K17 expression could also impact the immune cell response in PDAC, and that uncovering this relationship could provide insight to guide the development of immunotherapeutic opportunities to extend patient survival. METHODS: Multiplex immunohistochemistry (mIHC) and automated image analysis based on novel computational imaging technology were used to decipher the abundance and spatial distribution of T cells, macrophages, and tumor cells, relative to K17 expression in 235 PDACs. RESULTS: K17 expression had profound effects on the exclusion of intratumoral CD8+ T cells and was also associated with decreased numbers of peritumoral CD8+ T cells, CD16+ macrophages, and CD163+ macrophages (p < 0.0001). The differences in the intratumor and peritumoral CD8+ T cell abundance were not impacted by neoadjuvant therapy, tumor stage, grade, lymph node status, histologic subtype, nor KRAS, p53, SMAD4, or CDKN2A mutations. CONCLUSIONS: Thus, K17 expression correlates with major differences in the immune microenvironment that are independent of any tested clinicopathologic or tumor intrinsic variables, suggesting that targeting K17-mediated immune effects on the immune system could restore the innate immunologic response to PDAC and might provide novel opportunities to restore immunotherapeutic approaches for this most deadly form of cancer.

Weighting the factors affecting attention guidance during free viewing and visual search: The unexpected role of object recognition uncertainty.

The factors determining how attention is allocated during visual tasks have been studied for decades, but few studies have attempted to model the weighting of several of these factors within and across tasks to better understand their relative contributions. Here we consider the roles of saliency, center bias, target features, and object recognition uncertainty in predicting the first nine changes in fixation made during free viewing and visual search tasks in the OSIE and COCO-Search18 datasets, respectively. We focus on the latter-most and least familiar of these factors by proposing a new method of quantifying uncertainty in an image, one based on object recognition. We hypothesize that the greater the number of object categories competing for an object proposal, the greater the uncertainty of how that object should be recognized and, hence, the greater the need for attention to resolve this uncertainty. As expected, we found that target features best predicted target-present search, with their dominance obscuring the use of other features. Unexpectedly, we found that target features were only weakly used during target-absent search. We also found that object recognition uncertainty outperformed an unsupervised saliency model in predicting free-viewing fixations, although saliency was slightly more predictive of search. We conclude that uncertainty in object recognition, a measure that is image computable and highly interpretable, is better than bottom-up saliency in predicting attention during free viewing.

Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor-Infiltrating Lymphocytes in Invasive Breast Cancer.

Quantitative assessment of spatial relations between tumor and tumor-infiltrating lymphocytes (TIL) is increasingly important in both basic science and clinical aspects of breast cancer research. We have developed and evaluated convolutional neural network analysis pipelines to generate combined maps of cancer regions and TILs in routine diagnostic breast cancer whole slide tissue images. The combined maps provide insight about the structural patterns and spatial distribution of lymphocytic infiltrates and facilitate improved quantification of TILs. Both tumor and TIL analyses were evaluated by using three convolutional neural network networks (34-layer ResNet, 16-layer VGG, and Inception v4); the results compared favorably with those obtained by using the best published methods. We have produced open-source tools and a public data set consisting of tumor/TIL maps for 1090 invasive breast cancer images from The Cancer Genome Atlas. The maps can be downloaded for further downstream analyses.

Sparse Autoencoder for Unsupervised Nucleus Detection and Representation in Histopathology Images.

We propose a sparse Convolutional Autoencoder (CAE) for simultaneous nucleus detection and feature extraction in histopathology tissue images. Our CAE detects and encodes nuclei in image patches in tissue images into sparse feature maps that encode both the location and appearance of nuclei. A primary contribution of our work is the development of an unsupervised detection network by using the characteristics of histopathology image patches. The pretrained nucleus detection and feature extraction modules in our CAE can be fine-tuned for supervised learning in an end-to-end fashion. We evaluate our method on four datasets and achieve state-of-the-art results. In addition, we are able to achieve comparable performance with only 5% of the fully- supervised annotation cost.

Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example.

Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropathologies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes to compensate for this complexity, at the cost of uncontrolled heterogeneity. This heterogeneity raises new challenges, akin to those face in realistic diagnostic applications. Here, we demonstrate the feasibility of inter-site classification of neuropsychiatric status, with an application to the Autism Brain Imaging Data Exchange (ABIDE) database, a large (N=871) multi-site autism dataset. For this purpose, we investigate pipelines that extract the most predictive biomarkers from the data. These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas. Connectomes are then compared across participants to learn patterns of connectivity that differentiate typical controls from individuals with autism. We predict this neuropsychiatric status for participants from the same acquisition sites or different, unseen, ones. Good choices of methods for the various steps of the pipeline lead to 67% prediction accuracy on the full ABIDE data, which is significantly better than previously reported results. We perform extensive validation on multiple subsets of the data defined by different inclusion criteria. These enables detailed analysis of the factors contributing to successful connectome-based prediction. First, prediction accuracy improves as we include more subjects, up to the maximum amount of subjects available. Second, the definition of functional brain areas is of paramount importance for biomarker discovery: brain areas extracted from large R-fMRI datasets outperform reference atlases in the classification tasks.

Modeling visual clutter perception using proto-object segmentation.

We introduce the proto-object model of visual clutter perception. This unsupervised model segments an image into superpixels, then merges neighboring superpixels that share a common color cluster to obtain proto-objects-defined here as spatially extended regions of coherent features. Clutter is estimated by simply counting the number of proto-objects. We tested this model using 90 images of realistic scenes that were ranked by observers from least to most cluttered. Comparing this behaviorally obtained ranking to a ranking based on the model clutter estimates, we found a significant correlation between the two (Spearman's ρ = 0.814, p < 0.001). We also found that the proto-object model was highly robust to changes in its parameters and was generalizable to unseen images. We compared the proto-object model to six other models of clutter perception and demonstrated that it outperformed each, in some cases dramatically. Importantly, we also showed that the proto-object model was a better predictor of clutter perception than an actual count of the number of objects in the scenes, suggesting that the set size of a scene may be better described by proto-objects than objects. We conclude that the success of the proto-object model is due in part to its use of an intermediate level of visual representation-one between features and objects-and that this is evidence for the potential importance of a proto-object representation in many common visual percepts and tasks.

PathLDM: Text conditioned Latent Diffusion Model for Histopathology.

To achieve high-quality results, diffusion models must be trained on large datasets. This can be notably prohibitive for models in specialized domains, such as computational pathology. Conditioning on labeled data is known to help in data-efficient model training. Therefore, histopathology reports, which are rich in valuable clinical information, are an ideal choice as guidance for a histopathology generative model. In this paper, we introduce PathLDM, the first text-conditioned Latent Diffusion Model tailored for generating high-quality histopathology images. Leveraging the rich contextual information provided by pathology text reports, our approach fuses image and textual data to enhance the generation process. By utilizing GPT's capabilities to distill and summarize complex text reports, we establish an effective conditioning mechanism. Through strategic conditioning and necessary architectural enhancements, we achieved a SoTA FID score of 7.64 for text-to-image generation on the TCGA-BRCA dataset, significantly outperforming the closest text-conditioned competitor with FID 30.1.

Attention De-sparsification Matters: Inducing diversity in digital pathology representation learning.

We propose DiRL, a Diversity-inducing Representation Learning technique for histopathology imaging. Self-supervised learning (SSL) techniques, such as contrastive and non-contrastive approaches, have been shown to learn rich and effective representations of digitized tissue samples with limited pathologist supervision. Our analysis of vanilla SSL-pretrained models' attention distribution reveals an insightful observation: sparsity in attention, i.e, models tends to localize most of their attention to some prominent patterns in the image. Although attention sparsity can be beneficial in natural images due to these prominent patterns being the object of interest itself, this can be sub-optimal in digital pathology; this is because, unlike natural images, digital pathology scans are not object-centric, but rather a complex phenotype of various spatially intermixed biological components. Inadequate diversification of attention in these complex images could result in crucial information loss. To address this, we leverage cell segmentation to densely extract multiple histopathology-specific representations, and then propose a prior-guided dense pretext task, designed to match the multiple corresponding representations between the views. Through this, the model learns to attend to various components more closely and evenly, thus inducing adequate diversification in attention for capturing context-rich representations. Through quantitative and qualitative analysis on multiple tasks across cancer types, we demonstrate the efficacy of our method and observe that the attention is more globally distributed.

Behavioral meaures of psychotic disorders: Using automatic facial coding to detect nonverbal expressions in video.

Emotional deficits in psychosis are prevalent and difficult to treat. In particular, much remains unknown about facial expression abnormalities, and a key reason is that expressions are very labor-intensive to code. Automatic facial coding (AFC) can remove this barrier. The current study sought to both provide evidence for the utility of AFC in psychosis for research purposes and to provide evidence that AFC are valid measures of clinical constructs. Changes of facial expressions and head position of participants-39 with schizophrenia/schizoaffective disorder (SZ), 46 with other psychotic disorders (OP), and 108 never psychotic individuals (NP)-were assessed via FaceReader, a commercially available automated facial expression analysis software, using video recorded during a clinical interview. We first examined the behavioral measures of the psychotic disorder groups and tested if they can discriminate between the groups. Next, we evaluated links of behavioral measures with clinical symptoms, controlling for group membership. We found the SZ group was characterized by significantly less variation in neutral expressions, happy expressions, arousal, and head movements compared to NP. These measures discriminated SZ from NP well (AUC = 0.79, sensitivity = 0.79, specificity = 0.67) but discriminated SZ from OP less well (AUC = 0.66, sensitivity = 0.77, specificity = 0.46). We also found significant correlations between clinician-rated symptoms and most behavioral measures (particularly happy expressions, arousal, and head movements). Taken together, these results suggest that AFC can provide useful behavioral measures of psychosis, which could improve research on non-verbal expressions in psychosis and, ultimately, enhance treatment.

Computational pathology: A survey review and the way forward.

Computational Pathology (CPath) is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath. For updated information on this survey review paper and accessing to the original model cards repository, please refer to GitHub. Updated version of this draft can also be found from arXiv.

Keratin 17 modulates the immune topography of pancreatic cancer.

Background: The immune microenvironment impacts tumor growth, invasion, metastasis, and patient survival and may provide opportunities for therapeutic intervention in pancreatic ductal adenocarcinoma (PDAC). Although never studied as a potential modulator of the immune response in most cancers, Keratin 17 (K17), a biomarker of the most aggressive (basal) molecular subtype of PDAC, is intimately involved in the histogenesis of the immune response in psoriasis, basal cell carcinoma, and cervical squamous cell carcinoma. Thus, we hypothesized that K17 expression could also impact the immune cell response in PDAC, and that uncovering this relationship could provide insight to guide the development of immunotherapeutic opportunities to extend patient survival. Methods: Multiplex immunohistochemistry (mIHC) and automated image analysis based on novel computational imaging technology were used to decipher the abundance and spatial distribution of T cells, macrophages, and tumor cells, relative to K17 expression in 235 PDACs. Results: K17 expression had profound effects on the exclusion of intratumoral CD8 + T cells and was also associated with decreased numbers of peritumoral CD8 + T cells, CD16 + macrophages, and CD163 + macrophages (p < 0.0001). The differences in the intratumor and peritumoral CD8 + T cell abundance were not impacted by neoadjuvant therapy, tumor stage, grade, lymph node status, histologic subtype, nor KRAS, p53, SMAD4, or CDKN2A mutations. Conclusions: Thus, K17 expression correlates with major differences in the immune microenvironment that are independent of any tested clinicopathologic or tumor intrinsic variables, suggesting that targeting K17-mediated immune effects on the immune system could restore the innate immunologic response to PDAC and might provide novel opportunities to restore immunotherapeutic approaches for this most deadly form of cancer.

Multi-voxel pattern analysis of selective representation of visual working memory in ventral temporal and occipital regions.

While previous results from univariate analysis showed that the activity level of the parahippocampal gyrus (PHG) but not the fusiform gyrus (FG) reflects selective maintenance of the cued picture category, present results from multi-voxel pattern analysis (MVPA) showed that the spatial response patterns of both regions can be used to differentiate the selected picture category in working memory. The ventral temporal and occipital areas including the PHG and FG have been shown to be specialized in perceiving and processing different kinds of visual information, though their role in the representation of visual working memory remains unclear. To test whether the PHG and FG show spatial response patterns that reflect selective maintenance of task-relevant visual working memory in comparison with other posterior association regions, we reanalyzed data from a previous fMRI study of visual working memory with a cue inserted during the delay period of a delayed recognition task. Classification of FG and PHG activation patterns for the selected category (face or scene) during the cue phase was well above chance using classifiers trained with fMRI data from the cue or probe phase. Classification of activity in other temporal and occipital regions for the cued picture category during the cue phase was relatively less consistent even though classification of their activity during the probe recognition was comparable with the FG and PHG. In sum, these findings suggest that the FG and PHG carry information relevant to the cued visual category, and their spatial activation patterns during selective maintenance seem to match those during visual recognition.

Oral methylphenidate normalizes cingulate activity in cocaine addiction during a salient cognitive task.

Anterior cingulate cortex (ACC) hypoactivations during cognitive demand are a hallmark deficit in drug addiction. Methylphenidate (MPH) normalizes cortical function, enhancing task salience and improving associated cognitive abilities, in other frontal lobe pathologies; however, in clinical trials, MPH did not improve treatment outcome in cocaine addiction. We hypothesized that oral MPH will attenuate ACC hypoactivations and improve associated performance during a salient cognitive task in individuals with cocaine-use disorders (CUD). In the current functional MRI study, we used a rewarded drug cue-reactivity task previously shown to be associated with hypoactivations in both major ACC subdivisions (implicated in default brain function) in CUD compared with healthy controls. The task was performed by 13 CUD and 14 matched healthy controls on 2 d: after ingesting a single dose of oral MPH (20 mg) or placebo (lactose) in a counterbalanced fashion. Results show that oral MPH increased responses to this salient cognitive task in both major ACC subdivisions (including the caudal-dorsal ACC and rostroventromedial ACC extending to the medial orbitofrontal cortex) in the CUD. These functional MRI results were associated with reduced errors of commission (a common impulsivity measure) and improved task accuracy, especially during the drug (vs. neutral) cue-reactivity condition in all subjects. The clinical application of such MPH-induced brain-behavior enhancements remains to be tested.

Eye can read your mind: decoding gaze fixations to reveal categorical search targets.

Is it possible to infer a person's goal by decoding their fixations on objects? Two groups of participants categorically searched for either a teddy bear or butterfly among random category distractors, each rated as high, medium, or low in similarity to the target classes. Target-similar objects were preferentially fixated in both search tasks, demonstrating information about target category in looking behavior. Different participants then viewed the searchers' scanpaths, superimposed over the target-absent displays, and attempted to decode the target category (bear/butterfly). Bear searchers were classified perfectly; butterfly searchers were classified at 77%. Bear and butterfly Support Vector Machine (SVM) classifiers were also used to decode the same preferentially fixated objects and found to yield highly comparable classification rates. We conclude that information about a person's search goal exists in fixation behavior, and that this information can be behaviorally decoded to reveal a search target-essentially reading a person's mind by analyzing their fixations.

Modeling guidance and recognition in categorical search: bridging human and computer object detection.

Search is commonly described as a repeating cycle of guidance to target-like objects, followed by the recognition of these objects as targets or distractors. Are these indeed separate processes using different visual features? We addressed this question by comparing observer behavior to that of support vector machine (SVM) models trained on guidance and recognition tasks. Observers searched for a categorically defined teddy bear target in four-object arrays. Target-absent trials consisted of random category distractors rated in their visual similarity to teddy bears. Guidance, quantified as first-fixated objects during search, was strongest for targets, followed by target-similar, medium-similarity, and target-dissimilar distractors. False positive errors to first-fixated distractors also decreased with increasing dissimilarity to the target category. To model guidance, nine teddy bear detectors, using features ranging in biological plausibility, were trained on unblurred bears then tested on blurred versions of the same objects appearing in each search display. Guidance estimates were based on target probabilities obtained from these detectors. To model recognition, nine bear/nonbear classifiers, trained and tested on unblurred objects, were used to classify the object that would be fixated first (based on the detector estimates) as a teddy bear or a distractor. Patterns of categorical guidance and recognition accuracy were modeled almost perfectly by an HMAX model in combination with a color histogram feature. We conclude that guidance and recognition in the context of search are not separate processes mediated by different features, and that what the literature knows as guidance is really recognition performed on blurred objects viewed in the visual periphery.

A systematic study of key elements underlying molecular property prediction.

Artificial intelligence (AI) has been widely applied in drug discovery with a major task as molecular property prediction. Despite booming techniques in molecular representation learning, key elements underlying molecular property prediction remain largely unexplored, which impedes further advancements in this field. Herein, we conduct an extensive evaluation of representative models using various representations on the MoleculeNet datasets, a suite of opioids-related datasets and two additional activity datasets from the literature. To investigate the predictive power in low-data and high-data space, a series of descriptors datasets of varying sizes are also assembled to evaluate the models. In total, we have trained 62,820 models, including 50,220 models on fixed representations, 4200 models on SMILES sequences and 8400 models on molecular graphs. Based on extensive experimentation and rigorous comparison, we show that representation learning models exhibit limited performance in molecular property prediction in most datasets. Besides, multiple key elements underlying molecular property prediction can affect the evaluation results. Furthermore, we show that activity cliffs can significantly impact model prediction. Finally, we explore into potential causes why representation learning models can fail and show that dataset size is essential for representation learning models to excel.

Token Sparsification for Faster Medical Image Segmentation.

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens. To this end, we reformulate segmentation as a sparse encoding → token completion → dense decoding (SCD) pipeline. We first empirically show that naïvely applying existing approaches from classification token pruning and masked image modeling (MIM) leads to failure and inefficient training caused by inappropriate sampling algorithms and the low quality of the restored dense features. In this paper, we propose Soft-topK Token Pruning (STP) and Multi-layer Token Assembly (MTA) to address these problems. In sparse encoding, STP predicts token importance scores with a lightweight sub-network and samples the topK tokens. The intractable topK gradients are approximated through a continuous perturbed score distribution. In token completion, MTA restores a full token sequence by assembling both sparse output tokens and pruned multi-layer intermediate ones. The last dense decoding stage is compatible with existing segmentation decoders, e.g., UNETR. Experiments show SCD pipelines equipped with STP and MTA are much faster than baselines without token pruning in both training (up to 120% higher throughput) and inference (up to 60.6% higher throughput) while maintaining segmentation quality. Code is available here: https://github.com/cvlab-stonybrook/TokenSparse-for-MedSeg.

Topology-Guided Multi-Class Cell Context Generation for Digital Pathology.

In digital pathology, the spatial context of cells is important for cell classification, cancer diagnosis and prognosis. To model such complex cell context, however, is challenging. Cells form different mixtures, lineages, clusters and holes. To model such structural patterns in a learnable fashion, we introduce several mathematical tools from spatial statistics and topological data analysis. We incorporate such structural descriptors into a deep generative model as both conditional inputs and a differentiable loss. This way, we are able to generate high quality multi-class cell layouts for the first time. We show that the topology-rich cell layouts can be used for data augmentation and improve the performance of downstream tasks such as cell classification.

Unsupervised Stain Decomposition via Inversion Regulation for Multiplex Immunohistochemistry Images.

Multiplex Immunohistochemistry (mIHC) is a cost-effective and accessible method for in situ labeling of multiple protein biomarkers in a tissue sample. By assigning a different stain to each biomarker, it allows the visualization of different types of cells within the tumor vicinity for downstream analysis. However, to detect different types of stains in a given mIHC image is a challenging problem, especially when the number of stains is high. Previous deep-learning-based methods mostly assume full supervision; yet the annotation can be costly. In this paper, we propose a novel unsupervised stain decomposition method to detect different stains simultaneously. Our method does not require any supervision, except for color samples of different stains. A main technical challenge is that the problem is underdetermined and can have multiple solutions. To conquer this issue, we propose a novel inversion regulation technique, which eliminates most undesirable solutions. On a 7-plexed IHC images dataset, the proposed method achieves high quality stain decomposition results without human annotation.