Multicom protein Results: Over the past several years, we have constructed a standalone protein structure prediction system MULTICOM that combines multiple sources of information and complementary methods at all five stages of the protein structure prediction process including template identification, template combination, model generation, model assessment Protein structure prediction is one of the most important problems in structural bioinformatics. DoBo dataset The tertiary structure predictions for the COVID-19 proteins in the second round of CASP_COMMONS available online Results Comparison of PreStoi in MULTICOM_AI and other CASP16 predictors in stoichiometry prediction During CASP16, we blindly tested five protein complex structure predictors (MULTICOM, MULTICOM_AI, MULTICOM_GATE, MULTICOM_LLM, and MULTICOM_human), all of which utilized identical or slightly modified versions of PreStoi. The system participated in the tertiary structure prediction in 2022 CASP15 experiment. g. Motivation: Protein structure prediction is one of the most important problems in structural bioinformatics. We developed the MULTICOM protein structure prediction system for the CASP14 experiment and evaluated and analyzed its perfor-mance on the CASP14 targets. See full list on academic. Abstract AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. In contrast to those References: [1] Li J, Deng X, Eickholt J, Cheng J: Designing and Benchmarking the MULTICOM Protein Structure Prediction System. Cheng's Bioinformatics, Data Mining and Machine Learning Lab at University of Missouri - Columbia - MULTICOM Toolbox Here, we describe MULTICOM, a multi-level combination technique, intended to predict moderate- to high-resolution structure of a protein through a novel approach of combining multiple sources of complementary information derived from the experimentally solved protein structures in the Protein Data Bank. DCN datasets Protein domain boudary prediction data set (DoBo). Results: To meet the need, we have developed a comprehensive MULTICOM toolbox consisting of a set of protein structure and structural feature prediction tools. Specifically, MULTICOM samples a set of diverse multiple sequence alignments (MSAs Jun 6, 2015 · Given a pool of structural models generated for a target protein (e. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. MULTICOM samples diverse multiple sequence alignments (MSAs) and templates for AlphaFold-Multimer to generate structural predictions by using both traditional The overall workflow for the MULTICOM protein tertiary structure prediction system The single-chain structure prediction process consists of five sequential steps: (1) multiple sequence alignment The success of MULTICOM system in the CASP13 experiment clearly shows that protein contact distance prediction and model selection driven by powerful deep learning holds the key of solving protein structure prediction problem. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein The MULTICOM protein structure system. DNcon dataset Protein domain co-occurrence network datasets. [2] Li, J. MULTICOM samples diverse multiple sequence alignments (MSAs) and template … Jul 21, 2021 · Substantial progresses in protein structure prediction have been made by utilizing deep-learning and residue-residue distance prediction since CASP13. [2] Cheng J, Li J, Wang Z, Eickholt J, Deng X: The MULTICOM toolbox for protein structure prediction. " following RDKit’s conventions for parsing Mar 6, 2025 · 32Accurate prediction of quaternary structures of protein complexes is crucial for understanding protein-protein inter- 33action and protein function. Here we describe MULTICOM, a multi-level combination approach to improve the various steps in protein structure prediction. Summary: MULTICOM is described, a multi-level combination technique, intended to predict moderate- to high-resolution structure of a protein through a novel approach of combining multiple sources of complementary information derived from the experimentally solved protein structures in the Protein Data Bank. In recent years, deep learning-based methods such as AlphaFold2-Multimer[1, 2] and 35AlphaFold3[3] have significantly advanced quaternary structure modeling. May 1, 2023 · The MULTICOM system participated in the tertiary structure prediction in the 15 th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as server and human predictors. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. 11th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP11) conference 2014. To address this challenge, we developed a new version of the MULTICOM system to sample diverse multiple sequence alignments (MSAs) and structural templates to improve the May 25, 2021 · The pipeline and features for estimation of model accuracy Figure 1 shows the pipeline for MULTICOM EMA predictors. Multiple chains within a protein sequence are delimited using the character ":", whereas multi-ligand SMILES sequences within the same string are separated using the character ". Here, we provide a practical guide for our latest MULTICOM protein structure prediction system built on top of the latest advances, which was rigorously tested in the 2018 CASP13 experiment. md at master · multicom The MULTICOM toolbox also contains several other protein bioinformatics tools including SeqRate for protein folding rate prediction, MUpro for the prediction of stability changes caused by single-residue mutation, MSACompro for multiple protein sequence alignment, and HMMEditor for visualization of protein Hidden Markov models. BMC Structural Biology 2013, 13 (1):2. Inspired by the advances, we improve our CASP14 Apr 15, 2014 · Abstract Background: Protein model quality assessment is an essential component of generating and using protein structural models. bioRxiv, 552422. In contrast to those methods which look for the best templates, alignments and models, our approach tries to combine complementary and alternative Apr 11, 2015 · Abstract Motivation: Protein structure prediction is one of the most important problems in structural bioinformatics. Nov 10, 2023 · To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. in Methods in Molecular Biology vol. In contrast to those methods which look for the best templates, alignments and models, our approach tries to combine complementary and alternative To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. Mar 18, 2021 · The success of MULTICOM system clearly shows that protein contact distance prediction and model selection driven by deep learning holds the key of solving protein structure prediction problem. In contrast to those methods which look for the best templates, alignments and models, our approach tries to combine complementary and alternative templates Jun 2, 2025 · We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. - multicom/README. In this paper, we present our latest open-source protein tertiary str … MULTICOM-NOVEL built two template databases for identifying homologous templates for a target. With the advancement in deep learning contact distance prediction and residue-residue coevolutionary analysis, significant progress has been made in both template-base … Apr 30, 2012 · The MULTICOM toolbox also contains several other protein bioinformatics tools including SeqRate for protein folding rate prediction, MUpro for the prediction of stability changes caused by single-residue mutation, MSACompro for multiple protein sequence alignment, and HMMEditor for visualization of protein Hidden Markov models. e. In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and protein function prediction using protein domain co-occurrence network (pdcn - ranked as one of the best methods in CAFA1 competition - multicom-toolbox/pdcn The MULTICOM system was ranked among the best methods in template-based modeling, template-free modeling, protein model quality assessment, protein contact map prediction, and protein disorder prediction during CASP9, 2010. Deep learning prediction of protein distance map via multi-classification and regression (1) Download DeepDist package (a short path for the package is recommended) Here, we describe MULTICOM, a multi-level combination technique, intended to predict moderate- to high-resolution structure of a protein through a novel approach of combining multiple sources of complementary information derived from the experimentally solved protein structures in the Protein Data Bank. Apr 1, 2010 · Motivation: Protein structure prediction is one of the most important problems in structural bioinformatics. MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. Jun 6, 2025 · During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance‐driven template‐free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. Protein-ligand inputs MULTICOM_ligand represents a protein-ligand complex as a pair of single-/multi-chain protein sequence and SMILES string of one or more ligands (S,M ). Building the high-quality structure of a protein from its sequence is important for studying protein function and has important applications in protein engineering, protein design and drug design. Numerous bioinformatics techniques and tools have been developed to tackle almost every aspect of protein structure prediction ranging from structural feature prediction, template identification and query-template alignment to structure sampling, model Microsoft Corporation - Cited by 711 - Data Mining - Machine Learning - Deep Learning - Health Informatics - Bioinformatics During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance‐driven template‐free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. 26 A9B18 H0265, A9B18, Filament, Too Big, Failed to Propose Stoichiometry MULTICOM Predicted AF3 Model (worse) MULTICOM_human Predicted (better) True Structure 0% correctness The only one all CASP16 predictors failed! What Went Right? What Went Wrong? May 18, 2023 · AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. It automatically downloaded new protein structures released in the Protein Data Bank (PDB) [33] every week. The MULTICOM protein structure system. Accurate stoichiometry prediction was critical, as errors significantly reduced structural prediction accuracy. In contrast to those methods To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and Apr 30, 2012 · As the protein structures are robustly conserved over the sequence variations [40], many algorithms like MULTICOM [37, 38] consider alignment ensemble to remove the irrelevant templates for During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance‐driven template‐free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. MULTICOM samples The MULTICOM Protein Structure Prediction Server Empowered by Deep Learning and Contact Distance Prediction. [3] Wang Z, Eickholt J, Cheng J: MULTICOM: a multi-level combination approach to protein May 18, 2023 · Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure predictions to account for tertiary structural changes induced by protein-protein interaction. One remaining challenge in the field is to further improve the accuracy of AlphaFold2-based protein structure prediction. However, there are still few open-source comprehensive protein structure prediction packages publicly available in the field. 5. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein structural Summary To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine its outputs. In recent years, deep learning-based methods such as AlphaFold2-Multimer[1, 2] and 34AlphaFold3[3] have significantly advanced quaternary structure modeling. Here, the authors develop a new version of the MULTICOM system to improve the multi-sequence alignment, structural template, model ranking, model refinement, and hence the accuracy of AlphaFold2 prediction Our MULTICOM method was ranked 3rd in inter-domain protein structure prediction and 7th in protein tertiary structure prediction in 14th CASP competition (CASp14) in 2020. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and refine the During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein Feb 11, 2010 · Protein structure prediction is one of the most important problems in structural bioinformatics. 2165 13–26 (Humana Press Inc. Abstract With the expansion of genomics and proteomics data aided by the rapid progress of next-generation sequencing technologies, computational prediction of protein three-dimensional structure is an essential part of modern structural genomics initiatives. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein structural models. Inspired by the advances, we improve our CASP14 MULTICOM protein structure prediction system in the three main aspects: (1) a new deep-learning based protein inter-residue distance predictor (DeepDist) to improve template-free (ab The MULTICOM Protein Tertiary Structure Prediction System Jilong Li, Debswapna Bhattacharya, Renzhi Cao, Badri Adhikari, Xin Deng, Jesse Eickholt, Jianlin Cheng Jun 23, 2021 · Protein structure prediction is an important problem in bioinformatics and has been studied for decades. Sep 7, 2023 · Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure predictions to account for tertiary structural changes Jun 6, 2021 · The MULTICOM protein structure system. It uses the pairwise similarity between structural models and a deep learning-based interface contact probability score to predict the quality of the models. This repository include the source code and documents of both template-based and template-free modeling of the MULTICOM protein structure prediction system. Substantial progresses in protein structure prediction have been made by utilizing deep-learning and residue-residue distance prediction since CASP13. This repository includes the source code and documents of both template-based and template-free modeling of the MULTICOM protein structure prediction system. As genome sequencing is becoming a routine in biomedical research, the total number of gene and protein sequences is increasing exponentially, reaching over 100 million recently Abstract Background: Protein model quality assessment is an essential component of generating and using protein structural models. Jun 2, 2025 · We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. , subunit counts) to predict the quaternary structure of protein complexes. These include protein complex stoichiometry prediction, diverse multiple sequence alignment (MSA) generation leveraging both sequence and structure comparison Estimate (predict) the quality of protein multimer structure models. The success of MULTICOM system in the CASP13 experiment clearly shows that protein contact distance prediction and model selection driven by powerful deep learning holds the key of solving protein structure prediction problem. , 2020) Apr 15, 2014 · Background Protein model quality assessment is an essential component of generating and using protein structural models. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and Apr 15, 2014 · Background Protein model quality assessment is an essential component of generating and using protein structural models. Our MULTICOM protein structure preditors were ranked high in protein teritary structure prediction, protein model quality assessment, protein model refinement, and protein residue-residue contact prediction during the 10th Critical Assessment of Techniques for Protein Structure Prediction (CASP10), Gaeta, Italy. Inspired by the advances, we improve our CASP14 MULTICOM protein structure prediction system by incorporating three new components: (a) a new deep le … Abstract AlphaFold-Multimer has emerged as the state-of-the-art tool for predicting the quaternary structure of protein complexes (assemblies or multimers) since its release in 2021. Apr 12, 2025 · 33Accurate prediction of quaternary structures of protein complexes is crucial for understanding protein-protein inter- 34action and protein function. We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer- based Feb 27, 2013 · Abstract Background: Predicting protein structure from sequence is one of the most significant and challenging problems in bioinformatics. Jun 2, 2025 · With AlphaFold achieving high-accuracy tertiary structure prediction for most single-chain proteins (monomers), the next major challenge in protein structure prediction is to accurately model multich Jan 22, 2025 · There, the Mizzou MULTICOM team took first place for predicting protein complex structure without stoichiometry information. The MULTICOM Protein Tertiary Structure Prediction System Jilong Li , Debswapna Bhattacharya , Renzhi Cao , Badri Adhikari , Xin Deng , Jesse Eickholt , and Jianlin Cheng MULTICOM dataset DNcon protein residue-residue contact prediction data set. In this paper, we present Prediction of the three-dimensional (3D) structure of a protein from its sequence is important for studying its biological function. The four sources of potential protein-protein interactions above are used by MULTICOM to generate 13 kinds of MSApaired for hetero-multimers from the different databases (Table S4). In contrast to those methods which look for the best templates, alignments and In this work, we develop a new version of the MULTICOM protein structure prediction system to further improve AlphaFold2-based protein structure prediction by enhancing the input fed to AlphaFold2, using complementary approaches to rank AlphaFold2-generated structure models, and refining the top ranked models. BMC bioinformatics 2012, 13 (1):65. In this section, we first provide an overview of the MULTICOM server and human prediction system, followed with the detailed description of several key new components that we added into the MULTICOM system in CASP13, such as the protein contact distance prediction empowered by deep learning, ab initio protein structure prediction driven by Apr 30, 2012 · Computational software tools for predicting protein structure and structural features from protein sequences are crucial to make use of this vast repository of protein resources. However, there are still few open-source comprehensive protein structure prediction The MULTICOM protein structure system. Apr 8, 2025 · Notably, MULTICOM_ ligand ranked among the top-5 ligand prediction methods in both protein-ligand structure prediction and binding affinity prediction in the 16th Critical Assessment of Techniques for Structure Prediction (CASP16), demonstrating its efficacy and utility for real-world drug discovery efforts. Apr 25, 2019 · During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, distance‐driven template‐free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction. coordinates) and FASTA sequence of each protein chain in each PDB file were extracted. Poster presentation. Although recent advances in experimental approaches have greatly Protein model quality assessment is an essential component of generating and using protein structural models. MULTICOM4 is an advanced protein structure prediction system built on AlphaFold2 and 3. The ATOM file (i. The two servers were ranked among the best 10 server predictors. MULTICOM: large scale model quality assessment and mining techniques for human protein tertiary structure prediction. In this work, we develop a new version of the MULTICOM protein structure prediction system to further improve AlphaFold2-based protein structure prediction by enhancing the input fed to AlphaFold2, using complementary approaches to rank AlphaFold2-generated structure models, and re fining the top ranked models. Jan 12, 2025 · PreStoi was employed by our MULTICOM predictors in the 2024 community-wide CASP16 experiment, where participants predicted protein complex structures without prior stoichiometry information. Inspired by the advances, we improve our CASP14 MULTICOM protein structure prediction system by incorporating three new components: (a) a new deep learning‐based protein inter‐residue distance predictor to improve template News: MULTICOM was ranked among top three along AlphaFold of Google's DeepMind in the 13th Critical Assessment of Techniques for Protein Structure Prediction (CASP13) according to the official assessment, 2018. MULTICOM3 is an add-on package to improve AlphaFold2- and AlphaFold-Multimer-based prediction of protein tertiary and quaternary structures by diverse multiple sequence alignment sampling, template identification, structural prediction evaluation and structural prediction refinement. Apr 12, 2025 · With AlphaFold achieving high-accuracy tertiary structure prediction for most single-chain proteins (monomers), the next major challenge in protein structure prediction is accurately modeling multi-chain protein complexes (multimers). AF3 ranking score: 0. Home BDM Lab Result Example (Multi-domain) Result Example (TBM) Abstract We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, di usion model-based AlphaFold3, and our in-house techniques. We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2 Protein structure prediction is an important problem in bioinformatics and has been studied for decades. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein In this work, we develop a new version of the MULTICOM protein structure prediction system to further improve AlphaFold2-based protein structure prediction by enhancing the input fed to AlphaFold2 Substantial progresses in protein structure prediction have been made by utilizing deep‐learning and residue‐residue distance prediction since CASP13. We provide a few protein complexes in example folder for testing. , Eickholt, J. 1 Background: Protein model quality assessment is an essential component of generating and using protein structural models. The MULTICOM Protein Tertiary Structure Prediction System Jilong Li , Debswapna Bhattacharya , Renzhi Cao , Badri Adhikari , Xin Deng , Jesse Eickholt , and Jianlin Cheng We developed the MULTICOM protein structure prediction system for the CASP14 experiment and evaluated and analyzed its perfor-mance on the CASP14 targets. , Deng, X. In contrast to those Apr 8, 2025 · Towards this end, we introduce MULTICOM_ligand, a deep learning-based protein-ligand structure and binding affinity prediction ensemble featuring structural consensus ranking for unsupervised pose ranking and a new deep generative flow matching model for joint structure and binding affinity prediction. MULTICOM- CONSTRUCT was a new weighted pairwise model comparison (clustering) method that used the weighted average similarity between models in a pool to measure the global model quality. We used ROSETTA Use provided model weights to predict protein complex structures' quality DProQA requires GPU. csv is stored in result_folder. Protein structure prediction methods require stoichiometry information (i. Inspired by the advances, we improve our CASP14 MULTICOM protein structure prediction system by Jun 23, 2021 · In this paper, we present our latest open-source protein tertiary structure prediction system—MULTICOM2, an integration of template-based modeling (TBM) and template-free modeling (FM) methods. However, the accuracy of protein complex The MULTICOM system was ranked among the best methods in template-based modeling, template-free modeling, protein model quality assessment, protein contact map prediction, and protein disorder prediction during CASP9, 2010. Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13. We demonstrate that the distance-based template-free prediction empowered by deep learning signifi-cantly improves the accuracy of protein tertiary structure prediction. MULTICOM’s main student contributors were postdoctoral fellow Jian Liu and graduate students Alex Morehead and Pawan Neupane. Feb 27, 2013 · Background Predicting protein structure from sequence is one of the most significant and challenging problems in bioinformatics. oup. Jan 17, 2014 · Computational tools of predicting the structure and structural features of a protein are crucial for studying the function and structure of these proteins in order to make use of this vast repository of resources. MULTICOM-CLUSTER and MULTICOM-NOVEL were two new support vector machine-based methods of predicting both the local and global quality of a single protein model. May 21, 2023 · Moreover, for a monomer target that is a subunit of a protein assembly (complex), MULTICOM integrates tertiary and quaternary structure prediction together to account for tertiary structural Deep convolutional neural networks for protein model quality assessment - multicom-toolbox/CNNQA Structure prediction of the N protein Three-dimensional models of the N and the NSs proteins of TSWV were predicted in silico using state-of-the-art protein structure prediction methods, ROSETTA [44], I-TASSER (Iterative Threading ASSEmbly Refinement) [45 – 47], and the three MULTICOM servers including MULTICOM-CONSTRUCT [48], MULTICOM-CLUSTER [49], and MULTICOM-NOVEL [50]. . Jun 2, 2025 · With AlphaFold achieving high-accuracy tertiary structure prediction for most single-chain proteins (monomers), the next major challenge in protein structure prediction is to accurately model multich Deep convolutional neural network for mapping protein sequences to folds - multicom-toolbox/DeepSF Feb 27, 2013 · Over the past several years, we have constructed a standalone protein structure prediction system MULTICOM that combines multiple sources of information and complementary methods at all five stages of the protein structure prediction process including template identification, template combination, model generation, model assessment, and model Oct 23, 2015 · The method was implemented as two protein structure prediction servers: MULTICOM-CONSTRUCT and MULTICOM-CLUSTER that participated in the 11th Critical Assessment of Techniques for Protein Structure Prediction (CASP11) in 2014. Jun 23, 2021 · Protein structure prediction is an important problem in bioinformatics and has been studied for decades. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM- CONSTRUCT) that predicted both local and global quality of Jun 26, 2023 · To address the gap, we developed a hybrid method (MULTICOM_qa) combining a pairwise similarity score (PSS) and an interface contact probability score (ICPS) based on the deep learning inter-chain contact prediction for estimating protein complex model accuracy. ABSTRACT With AlphaFold achieving high- accuracy tertiary structure prediction for most single- chain proteins (monomers), the next major challenge in protein structure prediction is to accurately model multichain protein complexes (multimers). However, this information is often unavailable, making stoichiometry prediction crucial for AlphaFold2 is a popular protein structure prediction tool, however, achieving high accuracy remains challenging for certain proteins that share fewer homologs with the database. 1D feature prediction, contact prediction, and clustering-based model ranking programs are also included. The evaluation result Ranking. Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. hundreds of models generated for a CASP11 target), the MULTICOM method used unprecedentedly 14 complementary model QA methods to predict the quality score of each model first (Table 1). com Nov 10, 2023 · To enhance the AlphaFold-Multimer-based protein complex structure prediction, we developed a quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and Mar 11, 2025 · We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model based AlphaFold3, and our in-house techniques. Mar 6, 2025 · We developed MULTICOM4, the latest version of the MULTICOM system, to improve protein complex structure prediction by integrating transformer-based AlphaFold2, diffusion model-based AlphaFold3, and our in-house techniques. During the Tenth Critical Assessment of Techniques for Protein Structure Prediction (CASP10), we developed and tested four automated methods (MULTICOM-REFINE, MULTICOM-CLUSTER, MULTICOM-NOVEL, and MULTICOM-CONSTRUCT) that predicted both local and global quality of protein Jul 4, 2020 · Our MULTICOM protein structure prediction system aims to leverage both mature and latest technologies to accurately predict protein structures at 1D, 2D, and 3D levels and provide a reliable quality assessment of the predicted 3D structural models that facilitate their usage in real-world applications [4, 14]. However, the accuracy of protein complex Abstract Motivation: Protein structure prediction is one of the most important problems in structural bioinformatics. Speci cally, MULTICOM samples a set of fi diverse multiple sequence alignments Feb 1, 2021 · Abstract Substantial progresses in protein structure prediction have been made by utilizing deep-learning and residue-residue distance prediction since CASP13. (2013). Dec 1, 2023 · Abstract Substantial progresses in protein structure prediction have been made by utilizing deep‐learning and residue‐residue distance prediction since CASP13. The protein structure and function tools developed in Prof. To further enhance the AlphaFold-Multimer-based complex structure prediction, we developed a new quaternary structure prediction system (MULTICOM) to improve the input fed to AlphaFold-Multimer and evaluate and The MULTICOM protein structure system. May 1, 2023 · Since CASP14, AlphaFold2 has become the standard method for protein tertiary structure prediction. MULTICOM-CONSTRUCT was a new weighted pairwise model comparison (clustering) method that used the weighted average similarity between models in a pool to measure the global model quality. Numerous bioinformatics techniques and tools have been developed to tackle almost every aspect of protein structure prediction ranging from structural feature prediction, template identification and query-template alignment to structure sampling, model quality Jan 1, 2013 · Here, we describe MULTICOM, a multi-level combination technique, intended to predict moderate- to high-resolution structure of a protein through a novel approach of combining multiple sources of complementary information derived from the experimentally solved protein structures in the Protein Data Bank. Jilong Li, Renzhi Cao, Jianlin Cheng. When a protein target sequence and a pool of predicted structural models for the May 18, 2023 · The MULTICOM system with different implementations was blindly tested in the assembly structure prediction in the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) in 2022 as both server and human predictors. Jul 4, 2020 · Request PDF | The MULTICOM Protein Structure Prediction Server Empowered by Deep Learning and Contact Distance Prediction | Prediction of the three-dimensional (3D) structure of a protein from its Dec 1, 2024 · Estimation of model accuracy plays a crucial role in protein structure prediction, aiming to evaluate the quality of predicted protein structure model… MULTICOM-CLUSTER and MULTICOM-NOVEL were two new support vector machine-based methods of predicting both the local and global quality of a single protein model. Apr 15, 2014 · Background Protein model quality assessment is an essential component of generating and using protein structural models. , & Cheng, J. wpko nmrr pqeif ypnqdp mhd xrxepx qbycs dpj ljcmau mrt hfbbcw fsogw vfaq qslrzuj wuejh