A CT-based Radiomics Signature Is Associated with Response to Immune Checkpoint Inhibitors in Advanced Solid Tumors.

Background Reliable predictive imaging markers of response to immune checkpoint inhibitors are needed. Purpose To develop and validate a pretreatment CT-based radiomics signature to predict response to immune checkpoint inhibitors in advanced solid tumors. Materials and Methods In this retrospective study, a radiomics signature was developed in patients with advanced solid tumors (including breast, cervix, gastrointestinal) treated with anti-programmed cell death-1 or programmed cell death ligand-1 monotherapy from August 2012 to May 2018 (cohort 1). This was tested in patients with bladder and lung cancer (cohorts 2 and 3). Radiomics variables were extracted from all metastases delineated at pretreatment CT and selected by using an elastic-net model. A regression model combined radiomics and clinical variables with response as the end point. Biologic validation of the radiomics score with RNA profiling of cytotoxic cells (cohort 4) was assessed with Mann-Whitney analysis. Results The radiomics signature was developed in 85 patients (cohort 1: mean age, 58 years ± 13 [standard deviation]; 43 men) and tested on 46 patients (cohort 2: mean age, 70 years ± 12; 37 men) and 47 patients (cohort 3: mean age, 64 years ± 11; 40 men). Biologic validation was performed in a further cohort of 20 patients (cohort 4: mean age, 60 years ± 13; 14 men). The radiomics signature was associated with clinical response to immune checkpoint inhibitors (area under the curve [AUC], 0.70; 95% CI: 0.64, 0.77; P < .001). In cohorts 2 and 3, the AUC was 0.67 (95% CI: 0.58, 0.76) and 0.67 (95% CI: 0.56, 0.77; P < .001), respectively. A radiomics-clinical signature (including baseline albumin level and lymphocyte count) improved on radiomics-only performance (AUC, 0.74 [95% CI: 0.63, 0.84; P < .001]; Akaike information criterion, 107.00 and 109.90, respectively). Conclusion A pretreatment CT-based radiomics signature is associated with response to immune checkpoint inhibitors, likely reflecting the tumor immunophenotype. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Summers in this issue.

Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis.

OBJECTIVE: To identify CT-acquisition parameters accounting for radiomics variability and to develop a post-acquisition CT-image correction method to reduce variability and improve radiomics classification in both phantom and clinical applications. METHODS: CT-acquisition protocols were prospectively tested in a phantom. The multi-centric retrospective clinical study included CT scans of patients with colorectal/renal cancer liver metastases. Ninety-three radiomics features of first order and texture were extracted. Intraclass correlation coefficients (ICCs) between CT-acquisition protocols were evaluated to define sources of variability. Voxel size, ComBat, and singular value decomposition (SVD) compensation methods were explored for reducing the radiomics variability. The number of robust features was compared before and after correction using two-proportion z test. The radiomics classification accuracy (K-means purity) was assessed before and after ComBat- and SVD-based correction. RESULTS: Fifty-three acquisition protocols in 13 tissue densities were analyzed. Ninety-seven liver metastases from 43 patients with CT from two vendors were included. Pixel size, reconstruction slice spacing, convolution kernel, and acquisition slice thickness are relevant sources of radiomics variability with a percentage of robust features lower than 80%. Resampling to isometric voxels increased the number of robust features when images were acquired with different pixel sizes (p < 0.05). SVD-based for thickness correction and ComBat correction for thickness and combined thickness-kernel increased the number of reproducible features (p < 0.05). ComBat showed the highest improvement of radiomics-based classification in both the phantom and clinical applications (K-means purity 65.98 vs 73.20). CONCLUSION: CT-image post-acquisition processing and radiomics normalization by means of batch effect correction allow for standardization of large-scale data analysis and improve the classification accuracy. KEY POINTS: • The voxel size (accounting for the pixel size and slice spacing), slice thickness, and convolution kernel are relevant sources of CT-radiomics variability. • Voxel size resampling increased the mean percentage of robust CT-radiomics features from 59.50 to 89.25% when comparing CT scans acquired with different pixel sizes and from 71.62 to 82.58% when the scans were acquired with different slice spacings. • ComBat batch effect correction reduced the CT-radiomics variability secondary to the slice thickness and convolution kernel, improving the capacity of CT-radiomics to differentiate tissues (in the phantom application) and the primary tumor type from liver metastases (in the clinical application).

Metabolic-associated fatty liver voxel-based quantification on CT images using a contrast adapted automatic tool.

BACKGROUND & AIMS: Metabolic-dysfunction associated fatty liver disease (MAFLD) is highly prevalent and can lead to liver complications and comorbidities, with non-invasive tests such as vibration-controlled transient elastography (VCTE) and invasive liver biopsies being used for diagnosis The aim of the present study was to develop a new fully automatized method for quantifying the percentage of fat in the liver based on a voxel analysis on computed tomography (CT) images to solve previously unconcluded diagnostic deficiencies either in contrast (CE) or non-contrast enhanced (NCE) assessments. METHODS: Liver and spleen were segmented using nn-UNet on CE- and NCE-CT images. Radiodensity values were obtained for both organs for defining the key benchmarks for fatty liver assessment: liver mean, liver-to-spleen ratio, liver-spleen difference, and their average. VCTE was used for validation. A classification task method was developed for detection of suitable patients to fulfill maximum reproducibility across cohorts and highlight subjects with other potential radiodensity-related diseases. RESULTS: Best accuracy was attained using the average of all proposed benchmarks being the liver-to-spleen ratio highly useful for CE and the liver-to-spleen difference for NCE. The proposed whole-organ automatic segmentation displayed superior potential when compared to the typically used manual region-of-interest drawing as it allows to accurately obtain the percent of fat in liver, among other improvements. Atypical patients were successfully stratified through a function based on biochemical data. CONCLUSIONS: The developed method tackles the current drawbacks including biopsy invasiveness, and CT-related weaknesses such as lack of automaticity, dependency on contrast agent, no quantification of the percentage of fat in liver, and limited information on region-to-organ affectation. We propose this tool as an alternative for individualized MAFLD evaluation by an early detection of abnormal CT patterns based in radiodensity whilst abording detection of non-suitable patients to avoid unnecessary exposure to CT radiation. Furthermore, this work presents a surrogate aid for assessing fatty liver at a primary assessment of MAFLD using elastography data.

Identification of Precise 3D CT Radiomics for Habitat Computation by Machine Learning in Cancer.

Purpose To identify precise three-dimensional radiomics features in CT images that enable computation of stable and biologically meaningful habitats with machine learning for cancer heterogeneity assessment. Materials and Methods This retrospective study included 2436 liver or lung lesions from 605 CT scans (November 2010-December 2021) in 331 patients with cancer (mean age, 64.5 years ± 10.1 [SD]; 185 male patients). Three-dimensional radiomics were computed from original and perturbed (simulated retest) images with different combinations of feature computation kernel radius and bin size. The lower 95% confidence limit (LCL) of the intraclass correlation coefficient (ICC) was used to measure repeatability and reproducibility. Precise features were identified by combining repeatability and reproducibility results (LCL of ICC ≥ 0.50). Habitats were obtained with Gaussian mixture models in original and perturbed data using precise radiomics features and compared with habitats obtained using all features. The Dice similarity coefficient (DSC) was used to assess habitat stability. Biologic correlates of CT habitats were explored in a case study, with a cohort of 13 patients with CT, multiparametric MRI, and tumor biopsies. Results Three-dimensional radiomics showed poor repeatability (LCL of ICC: median [IQR], 0.442 [0.312-0.516]) and poor reproducibility against kernel radius (LCL of ICC: median [IQR], 0.440 [0.33-0.526]) but excellent reproducibility against bin size (LCL of ICC: median [IQR], 0.929 [0.853-0.988]). Twenty-six radiomics features were precise, differing in lung and liver lesions. Habitats obtained with precise features (DSC: median [IQR], 0.601 [0.494-0.712] and 0.651 [0.52-0.784] for lung and liver lesions, respectively) were more stable than those obtained with all features (DSC: median [IQR], 0.532 [0.424-0.637] and 0.587 [0.465-0.703] for lung and liver lesions, respectively; P < .001). In the case study, CT habitats correlated quantitatively and qualitatively with heterogeneity observed in multiparametric MRI habitats and histology. Conclusion Precise three-dimensional radiomics features were identified on CT images that enabled tumor heterogeneity assessment through stable tumor habitat computation. Keywords: CT, Diffusion-weighted Imaging, Dynamic Contrast-enhanced MRI, MRI, Radiomics, Unsupervised Learning, Oncology, Liver, Lung Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Sagreiya in this issue.

Tropical Trees Will Need to Acclimate to Rising Temperatures-But Can They?

For tropical forests to survive anthropogenic global warming, trees will need to avoid rising temperatures through range shifts and "species migrations" or tolerate the newly emerging conditions through adaptation and/or acclimation. In this literature review, we synthesize the available knowledge to show that although many tropical tree species are shifting their distributions to higher, cooler elevations, the rates of these migrations are too slow to offset ongoing changes in temperatures, especially in lowland tropical rainforests where thermal gradients are shallow or nonexistent. We also show that the rapidity and severity of global warming make it unlikely that tropical tree species can adapt (with some possible exceptions). We argue that the best hope for tropical tree species to avoid becoming "committed to extinction" is individual-level acclimation. Although several new methods are being used to test for acclimation, we unfortunately still do not know if tropical tree species can acclimate, how acclimation abilities vary between species, or what factors may prevent or facilitate acclimation. Until all of these questions are answered, our ability to predict the fate of tropical species and tropical forests-and the many services that they provide to humanity-remains critically impaired.

New Markov-Shannon Entropy models to assess connectivity quality in complex networks: from molecular to cellular pathway, Parasite-Host, Neural, Industry, and Legal-Social networks.

Graph and Complex Network theory is expanding its application to different levels of matter organization such as molecular, biological, technological, and social networks. A network is a set of items, usually called nodes, with connections between them, which are called links or edges. There are many different experimental and/or theoretical methods to assign node-node links depending on the type of network we want to construct. Unfortunately, the use of a method for experimental reevaluation of the entire network is very expensive in terms of time and resources; thus the development of cheaper theoretical methods is of major importance. In addition, different methods to link nodes in the same type of network are not totally accurate in such a way that they do not always coincide. In this sense, the development of computational methods useful to evaluate connectivity quality in complex networks (a posteriori of network assemble) is a goal of major interest. In this work, we report for the first time a new method to calculate numerical quality scores S(L(ij)) for network links L(ij) (connectivity) based on the Markov-Shannon Entropy indices of order k-th (θ(k)) for network nodes. The algorithm may be summarized as follows: (i) first, the θ(k)(j) values are calculated for all j-th nodes in a complex network already constructed; (ii) A Linear Discriminant Analysis (LDA) is used to seek a linear equation that discriminates connected or linked (L(ij)=1) pairs of nodes experimentally confirmed from non-linked ones (L(ij)=0); (iii) the new model is validated with external series of pairs of nodes; (iv) the equation obtained is used to re-evaluate the connectivity quality of the network, connecting/disconnecting nodes based on the quality scores calculated with the new connectivity function. This method was used to study different types of large networks. The linear models obtained produced the following results in terms of overall accuracy for network reconstruction: Metabolic networks (72.3%), Parasite-Host networks (93.3%), CoCoMac brain cortex co-activation network (89.6%), NW Spain fasciolosis spreading network (97.2%), Spanish financial law network (89.9%) and World trade network for Intelligent & Active Food Packaging (92.8%). In order to seek these models, we studied an average of 55,388 pairs of nodes in each model and a total of 332,326 pairs of nodes in all models. Finally, this method was used to solve a more complicated problem. A model was developed to score the connectivity quality in the Drug-Target network of US FDA approved drugs. In this last model the θ(k) values were calculated for three types of molecular networks representing different levels of organization: drug molecular graphs (atom-atom bonds), protein residue networks (amino acid interactions), and drug-target network (compound-protein binding). The overall accuracy of this model was 76.3%. This work opens a new door to the computational reevaluation of network connectivity quality (collation) for complex systems in molecular, biomedical, technological, and legal-social sciences as well as in world trade and industry.

The current state of knowledge on imaging informatics: a survey among Spanish radiologists.

BACKGROUND: There is growing concern about the impact of artificial intelligence (AI) on radiology and the future of the profession. The aim of this study is to evaluate general knowledge and concerns about trends on imaging informatics among radiologists working in Spain (residents and attending physicians). For this purpose, an online survey among radiologists working in Spain was conducted with questions related to: knowledge about terminology and technologies, need for a regulated academic training on AI and concerns about the implications of the use of these technologies. RESULTS: A total of 223 radiologists answered the survey, of whom 76.7% were attending physicians and 23.3% residents. General terms such as AI and algorithm had been heard of or read in at least 75.8% and 57.4% of the cases, respectively, while more specific terms were scarcely known. All the respondents consider that they should pursue academic training in medical informatics and new technologies, and 92.9% of them reckon this preparation should be incorporated in the training program of the specialty. Patient safety was found to be the main concern for 54.2% of the respondents. Job loss was not seen as a peril by 45.7% of the participants. CONCLUSIONS: Although there is a lack of knowledge about AI among Spanish radiologists, there is a will to explore such topics and a general belief that radiologists should be trained in these matters. Based on the results, a consensus is needed to change the current training curriculum to better prepare future radiologists.

Experience and results after the implementation of a radiology day unit in a reference hospital.

BACKGROUND: Interventional radiological procedures have significantly increased in recent years. Most of them are minimally invasive and require a short hospitalization, mainly done in other non-radiological units nowadays. Limited bed availability and high occupancy rates in these units create longer waiting lists and cancellations. The aim of this retrospective study is to assess the creation and functioning of a Radiology Day Unit (RDU) and evaluating its outcomes. For this purpose, data about interventional procedures and its complications, incidents, patient safety, quality and satisfaction rates were collected from May 2018 to December 2020, and posteriorly analyzed to evaluate its implementation. RESULTS: During the assessed period, 3841 patients were admitted into the RDU, with a net increase of 13% and 26% in the second and third year, respectively. Procedures performed by the Abdominal Radiology section were the most frequent (76-85%) followed by Interventional Vascular Radiology and Thoracic Radiology. Complication rates were low (1.5%) and most of them were self-limited and managed in the own department. Waiting lists were significantly reduced, from 2 months to 1 week in case of procedures performed by the Abdominal Radiology section. Patient satisfaction was higher than 80% in all the items evaluated with a global satisfaction of 93%. CONCLUSION: The RDU in our hospital has become a vital section for the management and post-procedure caring of patients undergoing interventional procedures in the Radiology Service with low complication rates and overall high levels of quality and patient safety, allowing the reduction of waiting lists and occupancy rates.

The valve uptake index: improving assessment of prosthetic valve endocarditis and updating [18F]FDG PET/CT(A) imaging criteria.

AIMS: Diagnosis of prosthetic valve endocarditis (PVE) by positron emission computed tomography angiography (PET/CTA) is based on visual and quantitative morpho-metabolic features. However, the fluorodeoxyglucose (FDG) uptake pattern can be sometimes visually unclear and susceptible to subjectivity. This study aimed to validate a new parameter, the valve uptake index [VUI, maximum standardized uptake value (SUVmax)-mean standardized uptake value (SUVmean)/SUVmax], designed to provide a more objective indication of the distribution of metabolic activity. Secondly, to re-evaluate the utility of traditionally used PVE imaging criteria and determine the potential value of adding the VUI in the diagnostic algorithm of PVE. METHODS AND RESULTS: Retrospective analysis of 122 patients (135 prosthetic valves) admitted for suspicion of endocarditis, with a conclusive diagnosis of definite (N = 57) or rejected (N = 65) PVE, and who had undergone a cardiac PET/CTA scan as part of the diagnostic evaluation. We measured the VUI and recorded the SUVmax, SUVratio, uptake pattern, and the presence of endocarditis-related anatomic lesions. The VUI, SUVmax, and SUVratio values were 0.54 ± 0.1 vs. 0.36 ± 0.08, 7.68 ± 3.07 vs. 3.72 ± 1.11, and 4.28 ± 1.93 vs. 2.16 ± 0.95 in the 'definite' PVE group vs. the 'rejected' group, respectively (mean ± SD; P < 0.001). A cut-off value of VUI > 0.45 showed a sensitivity, specificity, and diagnostic accuracy for PVE of 85%, 88%, and 86.7% and increased diagnostic ability for confirming endocarditis when combined with the standard diagnostic criteria. CONCLUSIONS: The VUI demonstrated good diagnostic accuracy for PVE, even increasing the diagnostic power of the traditionally used morphometabolic parameters, which also confirmed their own diagnostic performance. More research is needed to assess whether the integration of the VUI into the PVE diagnostic algorithm may clarify doubtful cases and thus improve the diagnostic yield of PET/CTA.

Contrast-Enhanced Ultrasound: A Useful Tool to Study and Monitor Hepatic Tumors Treated With Histotripsy.

Histotripsy is a novel noninvasive nonthermal, nonionizing, and precise treatment technique for tissue destruction. Contrast-enhanced ultrasound (CEUS) improves the detection, characterization, and follow-up of hepatic lesions because it depicts accurately the vascular perfusion of both normal hepatic tissue and hepatic tumors. We present the spectrum of imaging findings of CEUS after histotripsy treatment of hepatic tumors. CEUS provides real-time information, a close approximation to the dimension of the lesion, and a clear definition of its margins. Hepatic tumors detected by ultrasound can be potentially treated using B-mode ultrasound-guided histotripsy and characterized and monitored with CEUS. CEUS has shown to be very useful after tissue treatment to monitor and assess the evolution of the treated zone. Histotripsy treated zones are practically isoechogenic and slightly heterogeneous, and their limits are difficult to establish using standard B-mode ultrasound. The use of CEUS after histotripsy showing uptake of contrast protruding into the treated zone is clinically relevant to identify residual tumors and establish the most appropriate management strategy avoiding unnecessary treatments. We here describe CEUS findings after histotripsy for hepatic tumors.

Differences in the Area of Proximal and Distal Entry Tears at CT Angiography Predict Long-term Clinical Outcomes in Aortic Dissection.

PURPOSE: To identify entry tear variables that are related to adverse clinical events by using CT angiography (CTA) performed during the subacute phase of aortic dissection. MATERIALS AND METHODS: In this prospective study conducted from January 2000 to December 2013, participants with an aortic dissection with a patent false lumen and no comorbidities underwent CTA during the subacute phase. Participants were followed up for a survival analysis to assess the time to an adverse aortic event (AAE). The maximum aortic diameter (MAD), proximal and distal tear areas and difference between these areas, and partial false-lumen thrombosis were assessed by using Cox regression for adverse events. RESULTS: Seventy-two participants (mean age, 55 years ± 12 [standard deviation]; 55 men) were evaluated: 47 were surgically treated (type A aortic dissection) and 25 were medically treated (type B aortic dissection). Twenty-two participants had an AAE manifest during follow-up (9.22 years ± 5.78): There were 18 elective surgeries for aneurysmal degeneration, two emergent surgeries for acute aortic syndrome, and two aortic condition-related deaths. A categorical model composed of genetic aortic disease (GAD) (hazard ratio [HR], 3.4 [95% CI: 1.2, 9.9]; P = .02), MAD greater than 45 mm (HR, 6.1 [95% CI: 2.4, 15.8]; P < .001), and tear dominance (HR, 5.2 [95% CI: 2.1, 13]; P < .001), defined as an absolute tear area difference of greater than 1.2 cm2, was used to stratify participants into three risk groups: low, without any risk factors (57% [41 of 72] and 7% [three of 41] had events); intermediate, with one risk factor (31% [22 of 72] and 50% [11 of 22] had events); and high, with two or more risk factors (13% [nine of 72] and 89% [eight of nine] had events; log rank P < .001). CONCLUSION: Tear dominance demonstrated at CTA performed in the subacute phase of aortic dissection was related to long-term adverse events. Participants without GAD, dominant tears, or MAD greater than 45 mm had conditions that were safely managed with optimal medical treatment and imaging follow-up.Keywords: CT Angiography, Vascular, Aorta, Dissection Supplemental material is available for this article. © RSNA, 2021See also commentary by Fleischmann and Burris in this issue.

Morpho-metabolic post-surgical patterns of non-infected prosthetic heart valves by [18F]FDG PET/CTA: "normality" is a possible diagnosis.

AIMS: To define characteristic PET/CTA patterns of FDG uptake and anatomic changes following prosthetic heart valves (PVs) implantation over time, to help not to misdiagnose post-operative inflammation and avoid false-positive cases. METHODS AND RESULTS: Prospective evaluation of 37 post-operative patients without suspected infection that underwent serial cardiac PET/CTA examinations at 1, 6, and 12 months after surgery, in which metabolic features (FDG uptake distribution pattern and intensity) and anatomic changes were evaluated. Standardized uptake values (SUVs) were obtained and a new measure, the valve uptake index (VUI), (SUVmax-SUVmean)/SUVmax, was tested to homogenize SUV results.In total, 111 PET/CTA scans were performed in 37 patients (19 aortic and 18 mitral valves). FDG uptake was visually detectable in 79.3% of patients and showed a diffuse, homogeneous distribution pattern in 93%. Quantitative analysis yielded a mean maximum standardized uptake value (SUVmax) of 4.46 ± 1.50 and VUI of 0.35 ± 0.10. There were no significant differences in FDG distribution or uptake values between 1, 6, or 12 months. No abnormal anatomic changes or endocarditis lesions were detected in any patient during follow-up. CONCLUSIONS: FDG uptake, often seen in recently implanted PVs, shows a characteristic pattern of post-operative inflammation and, in the absence of associated anatomic lesions, could be considered a normal finding. These features remain stable for at least 1 year after surgery, so questioning the recommended 3-month safety period. A new measure, the VUI, can be useful for evaluating the FDG distribution pattern.

Spatial radial maze procedures and setups to dissociate local and distal relational spatial frameworks in humans.

BACKGROUND: Radial maze tasks have been used to assess optimal foraging and spatial abilities in rodents. The spatial performance was based on a capacity to rely on a configuration of local and distant cues. We adapted maze procedures assessing the relative weight of local cues and distant landmarks for arm choice in humans. NEW METHOD: The procedure allowed testing memory of places in four experimental setups: a fingertip texture-groove maze, a tactile screen maze, a virtual radial maze and a walking size maze. During training, the four reinforced positions remained fixed relative to local and distal cues. During subsequent conflict trials, these frameworks were made conflictive in the prediction of reward locations. RESULTS: Three experiments showed that the relative weight of local and distal relational cues is affected by different factors such as cues' nature, visual access to the environment, real vs. virtual environment, and gender. A fourth experiment illustrated how a walking maze can be used with people suffering intellectual disability. COMPARISON WITH EXISTING METHODS: In our procedure, long-term (reference) and short-term (working) memory can be assessed. It is the first radial task adapted to human that enables dissociating local and distal cues, to provides an indication as to their relative salience. Our mazes are moveable and easily used in limited spaces. Tasks are performed with realistic and spontaneous though controlled exploratory movements. CONCLUSION: Our tasks enabled highlighting the use of different strategies. In a clinical perspective, considering the use of compensatory strategies should orient towards adapted behavioural rehabilitation.

3D MI-DRAGON: new model for the reconstruction of US FDA drug- target network and theoretical-experimental studies of inhibitors of rasagiline derivatives for AChE.

The number of neurodegenerative diseases has been increasing in recent years. Many of the drug candidates to be used in the treatment of neurodegenerative diseases present specific 3D structural features. An important protein in this sense is the acetylcholinesterase (AChE), which is the target of many Alzheimer's dementia drugs. Consequently, the prediction of Drug-Protein Interactions (DPIs/nDPIs) between new drug candidates and specific 3D structure and targets is of major importance. To this end, we can use Quantitative Structure-Activity Relationships (QSAR) models to carry out a rational DPIs prediction. Unfortunately, many previous QSAR models developed to predict DPIs take into consideration only 2D structural information and codify the activity against only one target. To solve this problem we can develop some 3D multi-target QSAR (3D mt-QSAR) models. In this study, using the 3D MI-DRAGON technique, we have introduced a new predictor for DPIs based on two different well-known software. We have used the MARCH-INSIDE (MI) and DRAGON software to calculate 3D structural parameters for drugs and targets respectively. Both classes of 3D parameters were used as input to train Artificial Neuronal Network (ANN) algorithms using as benchmark dataset the complex network (CN) made up of all DPIs between US FDA approved drugs and their targets. The entire dataset was downloaded from the DrugBank database. The best 3D mt-QSAR predictor found was an ANN of Multi-Layer Perceptron-type (MLP) with profile MLP 37:37-24-1:1. This MLP classifies correctly 274 out of 321 DPIs (Sensitivity = 85.35%) and 1041 out of 1190 nDPIs (Specificity = 87.48%), corresponding to training Accuracy = 87.03%. We have validated the model with external predicting series with Sensitivity = 84.16% (542/644 DPIs; Specificity = 87.51% (2039/2330 nDPIs) and Accuracy = 86.78%. The new CNs of DPIs reconstructed from US FDA can be used to explore large DPI databases in order to discover both new drugs and/or targets. We have carried out some theoretical-experimental studies to illustrate the practical use of 3D MI-DRAGON. First, we have reported the prediction and pharmacological assay of 22 different rasagiline derivatives with possible AChE inhibitory activity. In this work, we have reviewed different computational studies on Drug- Protein models. First, we have reviewed 10 studies on DP computational models. Next, we have reviewed 2D QSAR, 3D QSAR, CoMFA, CoMSIA and Docking with different compounds to find Drug-Protein QSAR models. Last, we have developped a 3D multi-target QSAR (3D mt-QSAR) models for the prediction of the activity of new compounds against different targets or the discovery of new targets.

From QSAR models of drugs to complex networks: state-of-art review and introduction of new Markov-spectral moments indices.

Quantitative Structure-Activity/Property Relationships (QSAR/QSPR) models have been largely used for different kind of problems in Medicinal Chemistry and other Biosciences as well. Nevertheless, the applications of QSAR models have been restricted to the study of small molecules in the past. In this context, many authors use molecular graphs, atoms (nodes) connected by chemical bonds (links) to represent and numerically characterize the molecular structure. On the other hand, Complex Networks are useful in solving problems in drug research and industry, developing mathematical representations of different systems. These systems move in a wide range from relatively simple graph representations of drug molecular structures (molecular graphs used in classic QSAR) to large systems. We can cite for instance, drug-target interaction networks, protein structure networks, protein interaction networks (PINs), or drug treatment in large geographical disease spreading networks. In any case, all complex networks have essentially the same components: nodes (atoms, drugs, proteins, microorganisms and/or parasites, geographical areas, drug policy legislations, etc.) and links (chemical bonds, drug-target interactions, drug-parasite treatment, drug use, etc.). Consequently, we can use the same type of numeric parameters called Topological Indices (TIs) to describe the connectivity patterns in all these kinds of Complex Networks irrespective the nature of the object they represent and use these TIs to develop QSAR/QSPR models beyond the classic frontiers of drugs small-sized molecules. The goal of this work, in first instance, is to offer a common background to all the manuscripts presented in this special issue. In so doing, we make a review of the most used software and databases, common types of QSAR/QSPR models, and complex networks involving drugs or their targets. In addition, we review both classic TIs that have been used to describe the molecular structure of drugs and/or larger complex networks. In second instance, we use for the first time a Markov chain model to generalize Spectral moments to higher order analogues coined here as the Stochastic Spectral Moments TIs of order k (πk). Lastly, we report for the first time different QSAR/QSPR models for different classes of networks found in drug research, nature, technology, and social-legal sciences using πk values. This work updates our previous reviews Gonzalez-Diaz et al. Curr Top Med Chem. 2007; 7(10): 1015-29 and Gonzalez-Diaz et al. Curr Top Med Chem. 2008; 8(18):1676-90. It has been prepared in response to the kind invitation of the editor Prof. AB Reitz in commemoration of the 10th anniversary of this journal in 2010.