skip to main content

Title: DeepRefiner: high-accuracy protein structure refinement by deep network calibration
Abstract The DeepRefiner webserver, freely available at, is an interactive and fully configurable online system for high-accuracy protein structure refinement. Fuelled by deep learning, DeepRefiner offers the ability to leverage cutting-edge deep neural network architectures which can be calibrated for on-demand selection of adventurous or conservative refinement modes targeted at degree or consistency of refinement. The method has been extensively tested in the Critical Assessment of Techniques for Protein Structure Prediction (CASP) experiments under the group name ‘Bhattacharya-Server’ and was officially ranked as the No. 2 refinement server in CASP13 (second only to ‘Seok-server’ and outperforming all other refinement servers) and No. 2 refinement server in CASP14 (second only to ‘FEIG-S’ and outperforming all other refinement servers including ‘Seok-server’). The DeepRefiner web interface offers a number of convenient features, including (i) fully customizable refinement job submission and validation; (ii) automated job status update, tracking, and notifications; (ii) interactive and interpretable web-based results retrieval with quantitative and visual analysis and (iv) extensive help information on job submission and results interpretation via web-based tutorial and help tooltips.
; ;
Award ID(s):
2030722 1942692 2208679
Publication Date:
Journal Name:
Nucleic Acids Research
Sponsoring Org:
National Science Foundation
More Like this
  1. The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors:,,,, ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert datamore »scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge.« less
  2. Introduction: Vaso-occlusive crises (VOCs) are a leading cause of morbidity and early mortality in individuals with sickle cell disease (SCD). These crises are triggered by sickle red blood cell (sRBC) aggregation in blood vessels and are influenced by factors such as enhanced sRBC and white blood cell (WBC) adhesion to inflamed endothelium. Advances in microfluidic biomarker assays (i.e., SCD Biochip systems) have led to clinical studies of blood cell adhesion onto endothelial proteins, including, fibronectin, laminin, P-selectin, ICAM-1, functionalized in microchannels. These microfluidic assays allow mimicking the physiological aspects of human microvasculature and help characterize biomechanical properties of adhered sRBCs under flow. However, analysis of the microfluidic biomarker assay data has so far relied on manual cell counting and exhaustive visual morphological characterization of cells by trained personnel. Integrating deep learning algorithms with microscopic imaging of adhesion protein functionalized microfluidic channels can accelerate and standardize accurate classification of blood cells in microfluidic biomarker assays. Here we present a deep learning approach into a general-purpose analytical tool covering a wide range of conditions: channels functionalized with different proteins (laminin or P-selectin), with varying degrees of adhesion by both sRBCs and WBCs, and in both normoxic and hypoxic environments. Methods: Our neuralmore »networks were trained on a repository of manually labeled SCD Biochip microfluidic biomarker assay whole channel images. Each channel contained adhered cells pertaining to clinical whole blood under constant shear stress of 0.1 Pa, mimicking physiological levels in post-capillary venules. The machine learning (ML) framework consists of two phases: Phase I segments pixels belonging to blood cells adhered to the microfluidic channel surface, while Phase II associates pixel clusters with specific cell types (sRBCs or WBCs). Phase I is implemented through an ensemble of seven generative fully convolutional neural networks, and Phase II is an ensemble of five neural networks based on a Resnet50 backbone. Each pixel cluster is given a probability of belonging to one of three classes: adhered sRBC, adhered WBC, or non-adhered / other. Results and Discussion: We applied our trained ML framework to 107 novel whole channel images not used during training and compared the results against counts from human experts. As seen in Fig. 1A, there was excellent agreement in counts across all protein and cell types investigated: sRBCs adhered to laminin, sRBCs adhered to P-selectin, and WBCs adhered to P-selectin. Not only was the approach able to handle surfaces functionalized with different proteins, but it also performed well for high cell density images (up to 5000 cells per image) in both normoxic and hypoxic conditions (Fig. 1B). The average uncertainty for the ML counts, obtained from accuracy metrics on the test dataset, was 3%. This uncertainty is a significant improvement on the 20% average uncertainty of the human counts, estimated from the variance in repeated manual analyses of the images. Moreover, manual classification of each image may take up to 2 hours, versus about 6 minutes per image for the ML analysis. Thus, ML provides greater consistency in the classification at a fraction of the processing time. To assess which features the network used to distinguish adhered cells, we generated class activation maps (Fig. 1C-E). These heat maps indicate the regions of focus for the algorithm in making each classification decision. Intriguingly, the highlighted features were similar to those used by human experts: the dimple in partially sickled RBCs, the sharp endpoints for highly sickled RBCs, and the uniform curvature of the WBCs. Overall the robust performance of the ML approach in our study sets the stage for generalizing it to other endothelial proteins and experimental conditions, a first step toward a universal microfluidic ML framework targeting blood disorders. Such a framework would not only be able to integrate advanced biophysical characterization into fast, point-of-care diagnostic devices, but also provide a standardized and reliable way of monitoring patients undergoing targeted therapies and curative interventions, including, stem cell and gene-based therapies for SCD. Disclosures Gurkan: Dx Now Inc.: Patents & Royalties; Xatek Inc.: Patents & Royalties; BioChip Labs: Patents & Royalties; Hemex Health, Inc.: Consultancy, Current Employment, Patents & Royalties, Research Funding.« less
  3. Responding to the need to teach remotely due to COVID-19, we used readily available computational approaches (and developed associated tutorials ( to teach virtual Course-Based Undergraduate Research Experience (CURE) laboratories that fulfil generally accepted main components of CUREs or Undergraduate Research Experiences (UREs): Scientific Background, Hypothesis Development, Proposal, Experiments, Teamwork, Data Analysis, Conclusions, and Presentation1. We then developed and taught remotely, in three phases, protein-centric CURE activities that are adaptable to virtually any protein, emphasizing contributions of noncovalent interactions to structure, binding and catalysis (an ASBMB learning framework2 foundational concept). The courses had five learning goals (unchanged in the virtual format),focused on i) use of primary literature and bioinformatics, ii) the roles of non-covalent interactions, iii) keeping accurate laboratory notebooks, iv) hypothesis development and research proposal writing, and, v) presenting the project and drawing evidence based conclusions The first phase, Developing a Research Proposal, contains three modules, and develops hallmarks of a good student-developed hypothesis using available literature (PubMed3) and preliminary observations obtained using bioinformatics, Module 1: Using Primary Literature and Data Bases (Protein Data Base4, Blast5 and Clustal Omega6), Module 2: Molecular Visualization (PyMol7 and Chimera8), culminating in a research proposal (Module 3). Provided rubrics guide student expectations. Inmore »the second phase, Preparing the Proteins, students prepared necessary proteins and mutants using Module 4: Creating and Validating Models, which leads users through creating mutants with PyMol, homology modeling with Phyre29 or Missense10, energy minimization using RefineD11 or ModRefiner12, and structure validation using MolProbity13. In the third phase, Computational Experimental Approaches to Explore the Questions developed from the Hypothesis, students selected appropriate tools to perform their experiments, chosen from computational techniques suitable for a CURE laboratory class taught remotely. Questions, paired with computational approaches were selected from Modules 5: Exploring Titratable Groups in a Protein using H++14, 6: Exploring Small Molecule Ligand Binding (with SwissDock15), 7: Exploring Protein-Protein Interaction (with HawkDock16), 8: Detecting and Exploring Potential Binding Sites on a Protein (with POCASA17 and SwissDock), and 9: Structure-Activity Relationships of Ligand Binding & Drug Design (with SwissDock, Open Eye18 or the Molecular Operating Environment (MOE)19). All involve freely available computational approaches on publicly accessible web-based servers around the world (with the exception of MOE). Original literature/Journal club activities on approaches helped students suggest tie-ins to wet lab experiments they could conduct in the future to complement their computational approaches. This approach allowed us to continue using high impact CURE teaching, without changing our course learning goals. Quantitative data (including replicates) was collected and analyzed during regular class periods. Students developed evidence-based conclusions and related them to their research questions and hypotheses. Projects culminated in a presentation where faculty feedback was facilitated with the Virtual Presentation platform from QUBES20 These computational approaches are readily adaptable for topics accessible for first to senior year classes and individual research projects (UREs). We used them in both partial and full semester CUREs in various institutional settings. We believe this format can benefit faculty and students from a wide variety of teaching institutions under conditions where remote teaching is necessary.« less
  4. Elucidating protein rigidity offers insights about protein conformational changes. An understanding of protein motion can help speed drug development, and provide general insights into the dynamic behaviors of biomolecules. Existing rigidity analysis techniques employ fine-grained, all-atom modeling, which has a costly run-time, particularly for proteins made up of more than 500 residues. In this work, we introduce coarse-grained rigidity analysis, and showcase that it provides flexibility information about a protein that is similar in accuracy to an all-atom modeling approach. We assess the accuracy of the coarse-grained method relative to an all-atom approach via a comparison metric that reasons about the largest rigid clusters of the two methods. The apparent symmetry between the all-atom and coarse-grained methods yields very similar results, but the coarse-grained method routinely exhibits 40% reduced run-times. The CGRAP web server outputs rigid cluster information, and provides data visualization capabilities, including a interactive protein visualizer.
  5. Abstract

    Deep learning techniques have significantly advanced the field of protein structure prediction. LOMETS3 ( is a new generation meta-server approach to template-based protein structure prediction and function annotation, which integrates newly developed deep learning threading methods. For the first time, we have extended LOMETS3 to handle multi-domain proteins and to construct full-length models with gradient-based optimizations. Starting from a FASTA-formatted sequence, LOMETS3 performs four steps of domain boundary prediction, domain-level template identification, full-length template/model assembly and structure-based function prediction. The output of LOMETS3 contains (i) top-ranked templates from LOMETS3 and its component threading programs, (ii) up to 5 full-length structure models constructed by L-BFGS (limited-memory Broyden–Fletcher–Goldfarb–Shanno algorithm) optimization, (iii) the 10 closest Protein Data Bank (PDB) structures to the target, (iv) structure-based functional predictions, (v) domain partition and assembly results, and (vi) the domain-level threading results, including items (i)–(iii) for each identified domain. LOMETS3 was tested in large-scale benchmarks and the blind CASP14 (14th Critical Assessment of Structure Prediction) experiment, where the overall template recognition and function prediction accuracy is significantly beyond its predecessors and other state-of-the-art threading approaches, especially for hard targets without homologous templates in the PDB. Based on the improved developments, LOMETS3 should help significantly advance the capabilitymore »of broader biomedical community for template-based protein structure and function modelling.

    « less