GMP-grade human neural progenitors delivered subretinally protect vision in rat model of retinal degeneration and survive in minipigs.

BACKGROUND: Stem cell products are increasingly entering early stage clinical trials for treating retinal degeneration. The field is learning from experience about comparability of cells proposed for preclinical and clinical use. Without this, preclinical data supporting translation to a clinical study might not adequately reflect the performance of subsequent clinical-grade cells in patients. METHODS: Research-grade human neural progenitor cells (hNPC) and clinical-grade hNPC (termed CNS10-NPC) were injected into the subretinal space of the Royal College of Surgeons (RCS) rat, a rodent model of retinal degeneration such as retinitis pigmentosa. An investigational new drug (IND)-enabling study with CNS10-NPC was performed in the same rodent model. Finally, surgical methodology for subretinal cell delivery in the clinic was optimized in a large animal model with Yucatan minipigs. RESULTS: Both research-grade hNPC and clinical-grade hNPC can survive and provide functional and morphological protection in a dose-dependent fashion in RCS rats and the optimal cell dose was defined and used in IND-enabling studies. Grafted CNS10-NPC migrated from the injection site without differentiation into retinal cell phenotypes. Additionally, CNS10-NPC showed long-term survival, safety and efficacy in a good laboratory practice (GLP) toxicity and tumorigenicity study, with no observed cell overgrowth even at the maximum deliverable dose. Finally, using a large animal model with the Yucatan minipig, which has an eye size comparable to the human, we optimized the surgical methodology for subretinal cell delivery in the clinic. CONCLUSIONS: These extensive studies supported an approved IND and the translation of CNS10-NPC to an ongoing Phase 1/2a clinical trial (NCT04284293) for the treatment of retinitis pigmentosa.

Ligand Binding Prediction Using Protein Structure Graphs and Residual Graph Attention Networks.

Computational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein-ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)-the hallmark target of SARS-CoV-2 coronavirus.

DeepCOP: deep learning-based approach to predict gene regulating effects of small molecules.

MOTIVATION: Recent advances in the areas of bioinformatics and chemogenomics are poised to accelerate the discovery of small molecule regulators of cell development. Combining large genomics and molecular data sources with powerful deep learning techniques has the potential to revolutionize predictive biology. In this study, we present Deep gene COmpound Profiler (DeepCOP), a deep learning based model that can predict gene regulating effects of low-molecular weight compounds. This model can be used for direct identification of a drug candidate causing a desired gene expression response, without utilizing any information on its interactions with protein target(s). RESULTS: In this study, we successfully combined molecular fingerprint descriptors and gene descriptors (derived from gene ontology terms) to train deep neural networks that predict differential gene regulation endpoints collected in LINCS database. We achieved 10-fold cross-validation RAUC scores of and above 0.80, as well as enrichment factors of >5. We validated our models using an external RNA-Seq dataset generated in-house that described the effect of three potent antiandrogens (with different modes of action) on gene expression in LNCaP prostate cancer cell line. The results of this pilot study demonstrate that deep learning models can effectively synergize molecular and genomic descriptors and can be used to screen for novel drug candidates with the desired effect on gene expression. We anticipate that such models can find a broad use in developing novel cancer therapeutics and can facilitate precision oncology efforts. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Quantitative Structure-Price Relationship (QS$R) Modeling and the Development of Economically Feasible Drug Discovery Projects.

In recent years, the field of quantitative structure-activity/property relationship (QSAR/QSPR) modeling has developed into a stable technology capable of reliably predicting new bioactive molecules. With the availability of inexpensive commercial sources of both synthetic chemicals and bioactivity assays, a cheminformatics-savvy scientist can readily establish a virtual drug discovery enterprise. A skilled computational chemist can not only develop a computer-aided drug discovery pipeline but also acquire or have the drug candidates made inexpensively for economical screening of desired on-target activity, critical off-target effects, and essential drug-likeness properties. As part of our drug discovery pipeline, a novel machine-learning model was built to relate chemical structures of synthetically accessible molecules to their prices. The model was trained from our "in stock" and "made on demand" diverse chemical entities, ranging in price from $20 to >$10,000. This novel model is encoded here as the quantitative structure-price relationship (QS$R) model.

Toxic Colors: The Use of Deep Learning for Predicting Toxicity of Compounds Merely from Their Graphic Images.

The majority of computational methods for predicting toxicity of chemicals are typically based on "nonmechanistic" cheminformatics solutions, relying on an arsenal of QSAR descriptors, often vaguely associated with chemical structures, and typically employing "black-box" mathematical algorithms. Nonetheless, such machine learning models, while having lower generalization capacity and interpretability, typically achieve a very high accuracy in predicting various toxicity endpoints, as unambiguously reflected by the results of the recent Tox21 competition. In the current study, we capitalize on the power of modern AI to predict Tox21 benchmark data using merely simple 2D drawings of chemicals, without employing any chemical descriptors. In particular, we have processed rather trivial 2D sketches of molecules with a supervised 2D convolutional neural network (2DConvNet) and demonstrated that the modern image recognition technology results in prediction accuracies comparable to the state-of-the-art cheminformatics tools. Furthermore, the performance of the image-based 2DConvNet model was comparatively evaluated on an external set of compounds from the Prestwick chemical library and resulted in experimental identification of significant and previously unreported antiandrogen potentials for several well-established generic drugs.

Role of endoscopy in primary sclerosing cholangitis: European Society of Gastrointestinal Endoscopy (ESGE) and European Association for the Study of the Liver (EASL) Clinical Guideline.

1 ESGE/EASL recommend that, as the primary diagnostic modality for PSC, magnetic resonance cholangiography (MRC) should be preferred over endoscopic retrograde cholangiopancreatography (ERCP).Moderate quality evidence, strong recommendation. 2 ESGE/EASL suggest that ERCP can be considered if MRC plus liver biopsy is equivocal or contraindicated in patients with persisting clinical suspicion of PSC. The risks of ERCP have to be weighed against the potential benefit with regard to surveillance and treatment recommendations.Low quality evidence, weak recommendation. 6 ESGE/EASL suggest that, in patients with an established diagnosis of PSC, MRC should be considered before therapeutic ERCP.Weak recommendation, low quality evidence. 7 ESGE/EASL suggest performing endoscopic treatment with concomitant ductal sampling (brush cytology, endobiliary biopsies) of suspected significant strictures identified at MRC in PSC patients who present with symptoms likely to improve following endoscopic treatment.Strong recommendation, low quality evidence. 9 ESGE/EASL recommend weighing the anticipated benefits of biliary papillotomy/sphincterotomy against its risks on a case-by-case basis.Strong recommendation, moderate quality evidence.Biliary papillotomy/sphincterotomy should be considered especially after difficult cannulation.Strong recommendation, low quality evidence. 16 ESGE/EASL suggest routine administration of prophylactic antibiotics before ERCP in patients with PSC.Strong recommendation, low quality evidence. 17 EASL/ESGE recommend that cholangiocarcinoma (CCA) should be suspected in any patient with worsening cholestasis, weight loss, raised serum CA19-9, and/or new or progressive dominant stricture, particularly with an associated enhancing mass lesion.Strong recommendation, moderate quality evidence. 19 ESGE/EASL recommend ductal sampling (brush cytology, endobiliary biopsies) as part of the initial investigation for the diagnosis and staging of suspected CCA in patients with PSC.Strong recommendation, high quality evidence.

Machine Learning for Silver Nanoparticle Electron Transfer Property Prediction.

Nanoparticles exhibit diverse structural and morphological features that are often interconnected, making the correlation of structure/property relationships challenging. In this study a multi-structure/single-property relationship of silver nanoparticles is developed for the energy of Fermi level, which can be tuned to improve the transfer of electrons in a variety of applications. By combining different machine learning analytical algorithms, including k-mean, logistic regression, and random forest with electronic structure simulations, we find that the degree of twinning (characterized by the fraction of hexagonal closed packed atoms) and the population of the {111} facet (characterized by a surface coordination number of nine) are strongly correlated to the Fermi energy of silver nanoparticles. A concise three layer artificial neural network together with principal component analysis is built to predict this property, with reduced geometrical, structural, and topological features, making the method ideal for efficient and accurate high-throughput screening of large-scale virtual nanoparticle libraries and the creation of single-structure/single-property, multi-structure/single-property, and single-structure/multi-property relationships in the near future.

Machine learning and genetic algorithm prediction of energy differences between electronic calculations of graphene nanoflakes.

Computational screening is key to understanding structure-function relationships at the nanoscale but the high computational cost of accurate electronic structure calculations remains a bottleneck for the screening of large nanomaterial libraries. In this work we propose a data-driven strategy to predict accuracy differences between different levels of theory. Machine learning (ML) models are trained with structural features of graphene nanoflakes to predict the differences between electronic properties at two levels of approximation. The ML models yield an overall accuracy of 94% and 88%, for energy of the Fermi level and the band gap, respectively. This strategy represents a successful application of established ML methods to the selection of optimum level of theory, enabling more rapid and efficient screening of nanomaterials, and is extensible to other materials and computational methods.

A Parameterized Ultrasound-Based Finite Element Analysis of the Mechanical Environment of Pregnancy.

Preterm birth is the leading cause of childhood mortality and can lead to health risks in survivors. The mechanical functions of the uterus, fetal membranes, and cervix have dynamic roles to protect the fetus during gestation. To understand their mechanical function and relation to preterm birth, we built a three-dimensional parameterized finite element model of pregnancy. This model is generated by an automated procedure that is informed by maternal ultrasound measurements. A baseline model at 25 weeks of gestation was characterized, and to visualize the impact of cervical structural parameters on tissue stretch, we evaluated the model sensitivity to (1) anterior uterocervical angle, (2) cervical length, (3) posterior cervical offset, and (4) cervical stiffness. We found that cervical tissue stretching is minimal when the cervical canal is aligned with the longitudinal uterine axis, and a softer cervix is more sensitive to changes in the geometric variables tested.

Quantitative Structure-Property Relationship Modeling of Electronic Properties of Graphene Using Atomic Radial Distribution Function Scores.

The intrinsic relationships between nanoscale features and electronic properties of nanomaterials remain poorly investigated. In this work, electronic properties of 622 computationally optimized graphene structures were mapped to their structures using partial-least-squares regression and radial distributions function (RDF) scores. Quantitative structure-property relationship (QSPR) models were calibrated with 70% of a virtual data set of 622 passivated and nonpassivated graphenes, and we predicted the properties of the remaining 30% of the structures. The analysis of the optimum QSPR models revealed that the most relevant RDF scores appear at interatomic distances in the range of 2.0 to 10.0 Å for the energy of the Fermi level and the electron affinity, while the electronic band gap and the ionization potential correlate to RDF scores in a wider range from 3.0 to 30.0 Å. The predictions were more accurate for the energy of the Fermi level and the ionization potential, with more than 83% of explained data variance, while the electron affinity exhibits a value of ∼80% and the energy of the band gap a lower 70%. QSPR models have tremendous potential to rapidly identify hypothetical nanomaterials with desired electronic properties that could be experimentally prepared in the near future.

Genome-wide enhancer prediction from epigenetic signatures using genetic algorithm-optimized support vector machines.

The chemical modification of histones at specific DNA regulatory elements is linked to the activation, inactivation and poising of genes. A number of tools exist to predict enhancers from chromatin modification maps, but their practical application is limited because they either (i) consider a smaller number of marks than those necessary to define the various enhancer classes or (ii) work with an excessive number of marks, which is experimentally unviable. We have developed a method for chromatin state detection using support vector machines in combination with genetic algorithm optimization, called ChromaGenSVM. ChromaGenSVM selects optimum combinations of specific histone epigenetic marks to predict enhancers. In an independent test, ChromaGenSVM recovered 88% of the experimentally supported enhancers in the pilot ENCODE region of interferon gamma-treated HeLa cells. Furthermore, ChromaGenSVM successfully combined the profiles of only five distinct methylation and acetylation marks from ChIP-seq libraries done in human CD4(+) T cells to predict ∼21,000 experimentally supported enhancers within 1.0 kb regions and with a precision of ∼90%, thereby improving previous predictions on the same dataset by 21%. The combined results indicate that ChromaGenSVM comfortably outperforms previously published methods and that enhancers are best predicted by specific combinations of histone methylation and acetylation marks.

Bilateral Subdiaphragmatic Vagal Nerve Stimulation Using a Novel Waveform Decreases Body Weight, Food Consumption, Adiposity, and Activity in Obesity-Prone Rats.

INTRODUCTION: Obesity affects millions of Americans. The vagal nerves convey the degree of stomach fullness to the brain via afferent visceral fibers. Studies have found that vagal nerve stimulation (VNS) promotes reduced food intake, causes weight loss, and reduces cravings and appetite. METHODS: Here, we evaluate the efficacy of a novel stimulus waveform applied bilaterally to the subdiaphragmatic vagal nerve stimulation (sVNS) for almost 13 weeks. A stimulating cuff electrode was implanted in obesity-prone Sprague Dawley rats maintained on a high-fat diet. Body weight, food consumption, and daily movement were tracked over time and compared against three control groups: sham rats on a high-fat diet that were implanted with non-operational cuffs, rats on a high-fat diet that were not implanted, and rats on a standard diet that were not implanted. RESULTS: Results showed that rats on a high-fat diet that received sVNS attained a similar weight to rats on a standard diet due primarily to a reduction in daily caloric intake. Rats on a high-fat diet that received sVNS had significantly less body fat than other high-fat controls. Rats receiving sVNS also began moving a similar amount to rats on the standard diet. CONCLUSION: Results from this study suggest that bilateral subdiaphragmatic vagal nerve stimulation can alter the rate of growth of rats maintained on a high-fat diet through a reduction in daily caloric intake, returning their body weight to that which is similar to rats on a standard diet over approximately 13 weeks.

Circulating microRNAs let-7a and miR-16 predict progression-free survival and overall survival in patients with myelodysplastic syndrome.

Circulating microRNAs (miRNAs) are potential biomarkers for cancer. We examined plasma levels of 2 miRNAs, let-7a and miR-16, in 50 patients with myelodysplastic syndrome (MDS) and 76 healthy persons using quantitative real-time PCR. Circulating levels of both miRNAs were similar among healthy controls but were significantly lower in MDS patients (P = .001 and P < .001, respectively). The distributions of these 2 miRNA levels were bimodal in MDS patients, and these levels were significantly associated with their progression-free survival and overall survival (both P < .001 for let-7a; P < .001 and P = .001 for miR-16). This association persisted even after patients were stratified according to the International Prognostic Scoring System. Multivariate analysis revealed that let-7a level was a strong independent predictor for overall survival in this patient cohort. These findings suggest that let-7a and miR-16 plasma levels can serve as noninvasive prognostic markers in MDS patients.

Direct measurement of the permeability of human cervical tissue.

The mechanical integrity of the uterine cervix is critical for a pregnancy to successfully reach full term. It must be strong to retain the fetus throughout gestation and then undergo a remodeling and softening process before labor for delivery of the fetus. It is believed that cervical insufficiency (CI), a condition in pregnancy resulting in preterm birth (PTB), is related to a cervix with compromised mechanical strength which cannot resist deformation caused by external forces generated by the growing fetus. Such PTBs are responsible for infant developmental problems and in severe cases infant mortality. To understand the etiologies of CI, our overall research goal is to investigate the mechanical behavior of the cervix. Permeability is a mechanical property of hydrated collagenous tissues that dictates the time-dependent response of the tissue to mechanical loading. The goal of this study was to design a novel soft tissue permeability testing device and to present direct hydraulic permeability measurements of excised nonpregnant (NP) and pregnant (PG) human cervical tissue from women with different obstetric histories. Results of hydraulic permeability testing indicate repeatability for specimens from single patients, with an order of magnitude separating the NP and PG group means (2.1 ± 1.4×10(-14) and 3.2 ± 4.8×10(-13)m(4)/N[middle dot]s, respectively), and large variability within the NP and PG sample groups. Differences were found between samples with similar obstetric histories, supporting the view that medical history may not be a good predictor of permeability (and therefore mechanical behavior) and highlighting the need for patient-specific measurements of cervical mechanical properties. The permeability measurements from this study will be used in future work to model the constitutive material behavior of cervical tissue and to develop in vivo diagnostic tools to stage the progression of labor.

Enabling AI in synthetic biology through Construction File specification.

The Construction File (CF) specification establishes a standardized interface for molecular biology operations, laying a foundation for automation and enhanced efficiency in experiment design. It is implemented across three distinct software projects: PyDNA_CF_Simulator, a Python project featuring a ChatGPT plugin for interactive parsing and simulating experiments; ConstructionFileSimulator, a field-tested Java project that showcases 'Experiment' objects expressed as flat files; and C6-Tools, a JavaScript project integrated with Google Sheets via Apps Script, providing a user-friendly interface for authoring and simulation of CF. The CF specification not only standardizes and modularizes molecular biology operations but also promotes collaboration, automation, and reuse, significantly reducing potential errors. The potential integration of CF with artificial intelligence, particularly GPT-4, suggests innovative automation strategies for synthetic biology. While challenges such as token limits, data storage, and biosecurity remain, proposed solutions promise a way forward in harnessing AI for experiment design. This shift from human-driven design to AI-assisted workflows, steered by high-level objectives, charts a potential future path in synthetic biology, envisioning an environment where complexities are managed more effectively.

Human Neural Progenitors Expressing GDNF Enhance Retinal Protection in a Rodent Model of Retinal Degeneration.

Stem cell therapy for retinal degenerative diseases has been extensively tested in preclinical and clinical studies. However, preclinical studies performed in animal models at the early stage of disease do not optimally translate to patients that present to the clinic at a later stage of disease. As the retina degenerates, inflammation and oxidative stress increase and trophic factor support declines. Testing stem cell therapies in animal models at a clinically relevant stage is critical for translation to the clinic. Human neural progenitor cells (hNPC) and hNPC engineered to stably express GDNF (hNPCGDNF) were subretinally injected into the Royal College of Surgeon (RCS) rats, a well-established model for retinal degeneration, at early and later stages of the disease. hNPCGDNF treatment at the early stage of retinal degeneration provided enhanced visual function compared to hNPC alone. Treatment with both cell types resulted in preserved retinal morphology compared to controls. hNPCGDNF treatment led to significantly broader photoreceptor protection than hNPC treatment at both early and later times of intervention. The phagocytic role of hNPC appears to support RPE cell functions and the secreted GDNF offers neuroprotection and enables the extended survival of photoreceptor cells in transplanted animal eyes. Donor cells in the RCS rat retina survived with only limited proliferation, and hNPCGDNF produced GDNF in vivo. Cell treatment led to significant changes in various pathways related to cell survival, antioxidative stress, phagocytosis, and autophagy. A combined stem cell and trophic factor therapy holds great promise for treating retinal degenerative diseases including retinitis pigmentosa and age-related macular degeneration.

Targeting SARS-CoV-2 papain-like protease in the postvaccine era.

While vaccines remain at the forefront of global healthcare responses, pioneering therapeutics against SARS-CoV-2 are expected to fill the gaps for waning immunity. Rapid development and approval of orally available direct-acting antivirals targeting crucial SARS-CoV-2 proteins marked the beginning of the era of small-molecule drugs for COVID-19. In that regard, the papain-like protease (PLpro) can be considered a major SARS-CoV-2 therapeutic target due to its dual biological role in suppressing host innate immune responses and in ensuring viral replication. Here, we summarize the challenges of targeting PLpro and innovative early-stage PLpro-specific small molecules. We propose that state-of-the-art computer-aided drug design (CADD) methodologies will play a critical role in the discovery of PLpro compounds as a novel class of COVID-19 drugs.

Weight loss after endoscopic sleeve gastroplasty is independent of suture pattern: results from a randomized controlled trial.

Background and study aims This was a single-blind, single-center, prospective randomized controlled trial aimed at comparing the efficacy of three different suture patterns for endoscopic sleeve gastroplasty using Endomina (E-ESG). Patients and methods The suture patterns aimed to modify gastric accommodation by increasing the fundus distention ability (Group A), to reduce gastric volume (Group B) or to interrupt gastric emptying (Group C). Patients were randomized 1:1:1 and underwent clinical follow-up, gastric emptying scintigraphy, and satiety tests at baseline and 6 and 12 months post-procedure. The primary outcome was total body weight loss (TBWL) and excess weight loss (EWL) at 12 months post-procedure. Secondary outcomes included the impact of the suture patterns on gastric emptying and satiety. Results Overall, 48 patients (40 [83.3 %] female, aged 41.9 ±â€Š9.5 years, body mass indexI 33.8 ±â€Š2.7 kg/m 2 ) were randomized (16 in each group). In the entire cohort, mean (95 % confidence interval [CI]) TBWL and EWL at the end of the follow-up were 10.11 % (7.1-13.12) and 42.56 (28.23-56.9), respectively. There was no difference among the three study groups in terms of TBWL (95 %CI) (9.13 % [2.16-16.11] vs. 11.29 % [5.79-16.80] vs. 9.96 % [4.58-15.35]; P  = 0.589) and EWL (95 %CI) (34.54 % [6.09-62.99] vs. 44.75 % [23.63-65.88] vs. 46.94 % [16.72-77.15]; P  = 0.888) at 12 months post-procedure. The three groups did not differ in terms of mean gastric emptying time or in terms of satiety tests at the end of the follow-up. No serious adverse events occurred. Conclusions Three different suture patterns during E-ESG demonstrated comparable efficacy in terms of weight loss, with an overall EWL of > 25 % and TBWL of > 10 % at 12 months.

Artificial intelligence-enabled virtual screening of ultra-large chemical libraries with deep docking.

With the recent explosion of chemical libraries beyond a billion molecules, more efficient virtual screening approaches are needed. The Deep Docking (DD) platform enables up to 100-fold acceleration of structure-based virtual screening by docking only a subset of a chemical library, iteratively synchronized with a ligand-based prediction of the remaining docking scores. This method results in hundreds- to thousands-fold virtual hit enrichment (without significant loss of potential drug candidates) and hence enables the screening of billion molecule-sized chemical libraries without using extraordinary computational resources. Herein, we present and discuss the generalized DD protocol that has been proven successful in various computer-aided drug discovery (CADD) campaigns and can be applied in conjunction with any conventional docking program. The protocol encompasses eight consecutive stages: molecular library preparation, receptor preparation, random sampling of a library, ligand preparation, molecular docking, model training, model inference and the residual docking. The standard DD workflow enables iterative application of stages 3-7 with continuous augmentation of the training set, and the number of such iterations can be adjusted by the user. A predefined recall value allows for control of the percentage of top-scoring molecules that are retained by DD and can be adjusted to control the library size reduction. The procedure takes 1-2 weeks (depending on the available resources) and can be completely automated on computing clusters managed by job schedulers. This open-source protocol, at https://github.com/jamesgleave/DD_protocol , can be readily deployed by CADD researchers and can significantly accelerate the effective exploration of ultra-large portions of a chemical space.

Prediction of dinucleotide-specific RNA-binding sites in proteins.

BACKGROUND: Regulation of gene expression, protein synthesis, replication and assembly of many viruses involve RNA-protein interactions. Although some successful computational tools have been reported to recognize RNA binding sites in proteins, the problem of specificity remains poorly investigated. After the nucleotide base composition, the dinucleotide is the smallest unit of RNA sequence information and many RNA-binding proteins simply bind to regions enriched in one dinucleotide. Interaction preferences of protein subsequences and dinucleotides can be inferred from protein-RNA complex structures, enabling a training-based prediction approach. RESULTS: We analyzed basic statistics of amino acid-dinucleotide contacts in protein-RNA complexes and found their pairing preferences could be identified. Using a standard approach to represent protein subsequences by their evolutionary profile, we trained neural networks to predict multiclass target vectors corresponding to 16 possible contacting dinucleotide subsequences. In the cross-validation experiments, the accuracies of the optimum network, measured as areas under the curve (AUC) of the receiver operating characteristic (ROC) graphs, were in the range of 65-80%. CONCLUSIONS: Dinucleotide-specific contact predictions have also been extended to the prediction of interacting protein and RNA fragment pairs, which shows the applicability of this method to predict targets of RNA-binding proteins. A web server predicting the 16-dimensional contact probability matrix directly from a user-defined protein sequence was implemented and made available at: http://tardis.nibio.go.jp/netasa/srcpred.