List of recent publications

@article{
 title = {A Structurally-Validated Multiple Sequence Alignment of 497 Human Protein Kinase Domains},
 type = {article},
 year = {2019},
 pages = {1-16},
 volume = {9},
 id = {ff563fe1-e182-3914-a69d-705d4248a946},
 created = {2020-04-11T12:42:38.660Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2020-04-14T02:35:32.158Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {Studies on the structures and functions of individual kinases have been used to understand the biological properties of other kinases that do not yet have experimental structures. The key factor in accurate inference by homology is an accurate sequence alignment. We present a parsimonious, structure-based multiple sequence alignment (MSA) of 497 human protein kinase domains excluding atypical kinases. The alignment is arranged in 17 blocks of conserved regions and unaligned blocks in between that contain insertions of varying lengths present in only a subset of kinases. The aligned blocks contain well-conserved elements of secondary structure and well-known functional motifs, such as the DFG and HRD motifs. From pairwise, all-against-all alignment of 272 human kinase structures, we estimate the accuracy of our MSA to be 97%. The remaining inaccuracy comes from a few structures with shifted elements of secondary structure, and from the boundaries of aligned and unaligned regions, where compromises need to be made to encompass the majority of kinases. A new phylogeny of the protein kinase domains in the human genome based on our alignment indicates that ten kinases previously labeled as “OTHER” can be confidently placed into the CAMK group. These kinases comprise the Aurora kinases, Polo kinases, and calcium/calmodulin-dependent kinase kinases.},
 bibtype = {article},
 author = {Modi, Vivek and Dunbrack, Roland L.},
 doi = {10.1038/s41598-019-56499-4},
 journal = {Scientific Reports},
 number = {1}
}

Studies on the structures and functions of individual kinases have been used to understand the biological properties of other kinases that do not yet have experimental structures. The key factor in accurate inference by homology is an accurate sequence alignment. We present a parsimonious, structure-based multiple sequence alignment (MSA) of 497 human protein kinase domains excluding atypical kinases. The alignment is arranged in 17 blocks of conserved regions and unaligned blocks in between that contain insertions of varying lengths present in only a subset of kinases. The aligned blocks contain well-conserved elements of secondary structure and well-known functional motifs, such as the DFG and HRD motifs. From pairwise, all-against-all alignment of 272 human kinase structures, we estimate the accuracy of our MSA to be 97%. The remaining inaccuracy comes from a few structures with shifted elements of secondary structure, and from the boundaries of aligned and unaligned regions, where compromises need to be made to encompass the majority of kinases. A new phylogeny of the protein kinase domains in the human genome based on our alignment indicates that ten kinases previously labeled as “OTHER” can be confidently placed into the CAMK group. These kinases comprise the Aurora kinases, Polo kinases, and calcium/calmodulin-dependent kinase kinases.

@article{
 title = {Defining a new nomenclature for the structures of active and inactive kinases},
 type = {article},
 year = {2019},
 keywords = {Cell signaling,Protein kinases,Structural bioinformatics},
 pages = {6818-6827},
 volume = {116},
 id = {f1e37290-d5f1-33bc-a76f-0fbee1c4a5f3},
 created = {2020-09-22T15:56:23.391Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2020-09-22T15:56:27.429Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {Targeting protein kinases is an important strategy for intervention in cancer. Inhibitors are directed at the active conformation or a variety of inactive conformations. While attempts have been made to classify these conformations, a structurally rigorous catalog of states has not been achieved. The kinase activation loop is crucial for catalysis and begins with the conserved DFGmotif. This motif is observed in two major classes of conformations, DFGin—a set of active and inactive conformations where the Phe residue is in contact with the C-helix of the N-terminal lobe—and DFGout—an inactive form where Phe occupies the ATP site exposing the C-helix pocket. We have developed a clustering of kinase conformations based on the location of the Phe side chain (DFGin, DFGout, and DFGinter or intermediate) and the backbone dihedral angles of the sequence X-D-F, where X is the residue before the DFGmotif, and the DFG-Phe side-chain rotamer, utilizing a density-based clustering algorithm. We have identified eight distinct conformations and labeled them based on the Ramachandran regions (A, alpha; B, beta; L, left) of the XDF motif and the Phe rotamer (minus, plus, trans). Our clustering divides the DFGin group into six clusters including BLAminus, which contains active structures, and two common inactive forms, BLBplus and ABAminus. DFGout structures are predominantly in the BBAminus conformation, which is essentially required for binding type II inhibitors. The inactive conformations have specific features that make them unable to bind ATP, magnesium, and/or substrates. Our structurally intuitive nomenclature will aid in understanding the conformational dynamics of kinases and structure-based development of kinase drugs.},
 bibtype = {article},
 author = {Modi, Vivek and Dunbrack, Roland L.},
 doi = {10.1073/pnas.1814279116},
 journal = {Proceedings of the National Academy of Sciences of the United States of America},
 number = {14}
}

Targeting protein kinases is an important strategy for intervention in cancer. Inhibitors are directed at the active conformation or a variety of inactive conformations. While attempts have been made to classify these conformations, a structurally rigorous catalog of states has not been achieved. The kinase activation loop is crucial for catalysis and begins with the conserved DFGmotif. This motif is observed in two major classes of conformations, DFGin—a set of active and inactive conformations where the Phe residue is in contact with the C-helix of the N-terminal lobe—and DFGout—an inactive form where Phe occupies the ATP site exposing the C-helix pocket. We have developed a clustering of kinase conformations based on the location of the Phe side chain (DFGin, DFGout, and DFGinter or intermediate) and the backbone dihedral angles of the sequence X-D-F, where X is the residue before the DFGmotif, and the DFG-Phe side-chain rotamer, utilizing a density-based clustering algorithm. We have identified eight distinct conformations and labeled them based on the Ramachandran regions (A, alpha; B, beta; L, left) of the XDF motif and the Phe rotamer (minus, plus, trans). Our clustering divides the DFGin group into six clusters including BLAminus, which contains active structures, and two common inactive forms, BLBplus and ABAminus. DFGout structures are predominantly in the BBAminus conformation, which is essentially required for binding type II inhibitors. The inactive conformations have specific features that make them unable to bind ATP, magnesium, and/or substrates. Our structurally intuitive nomenclature will aid in understanding the conformational dynamics of kinases and structure-based development of kinase drugs.

@article{
 title = {Binding Affinity of Pro-apoptotic BH3 peptides for the Anti-apoptotic Mcl-1 and A1 proteins: Molecular Dynamics Simulations of Mcl-1 and A1 in Complex with Six Different BH3 peptides},
 type = {article},
 year = {2017},
 websites = {http://linkinghub.elsevier.com/retrieve/pii/S109332631630184X},
 publisher = {Elsevier Inc.},
 id = {44df4ea9-8bc5-3699-b85c-5217c628a321},
 created = {2017-02-16T22:05:03.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:50:43.628Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {article},
 author = {Modi, Vivek and Sankararamakrishnan, Ramasubbu},
 doi = {10.1016/j.jmgm.2016.12.006},
 journal = {Journal of Molecular Graphics and Modelling}
}

@article{
 title = {Assessment of template-based modeling of protein structure in CASP11},
 type = {article},
 year = {2016},
 keywords = {[CASP, Homology modeling, Protein structure predic},
 id = {fa009942-c232-3c18-a1db-439ee1c10e89},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:37:30.998Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {? 2016 Wiley Periodicals, Inc.We present the assessment of predictions submitted in the template-based modeling (TBM) category of CASP11 (Critical Assessment of Protein Structure Prediction). Model quality was judged on the basis of global and local measures of accuracy on all atoms including side chains. The top groups on 39 human-server targets based on model 1 predictions were LEER, Zhang, LEE, MULTICOM, and Zhang-Server. The top groups on 81 targets by server groups based on model 1 predictions were Zhang-Server, nns, BAKER-ROSETTASERVER, QUARK, and myprotein-me. In CASP11, the best models for most targets were equal to or better than the best template available in the Protein Data Bank, even for targets with poor templates. The overall performance in CASP11 is similar to the performance of predictors in CASP10 with slightly better performance on the hardest targets. For most targets, assessment measures exhibited bimodal probability density distributions. Multi-dimensional scaling of an RMSD matrix for each target typically revealed a single cluster with models similar to the target structure, with a mode in the GDT-TS density between 40 and 90, and a wide distribution of models highly divergent from each other and from the experimental structure, with density mode at a GDT-TS value of ?20. The models in this peak in the density were either compact models with entirely the wrong fold, or highly non-compact models. The results argue for a density-driven approach in future CASP TBM assessments that accounts for the bimodal nature of these distributions instead of Z scores, which assume a unimodal, Gaussian distribution.},
 bibtype = {article},
 author = {Modi, V. and Xu, Q. and Adhikari, S. and Dunbrack, R.L.},
 doi = {10.1002/prot.25049},
 journal = {Proteins: Structure, Function and Bioinformatics}
}

? 2016 Wiley Periodicals, Inc.We present the assessment of predictions submitted in the template-based modeling (TBM) category of CASP11 (Critical Assessment of Protein Structure Prediction). Model quality was judged on the basis of global and local measures of accuracy on all atoms including side chains. The top groups on 39 human-server targets based on model 1 predictions were LEER, Zhang, LEE, MULTICOM, and Zhang-Server. The top groups on 81 targets by server groups based on model 1 predictions were Zhang-Server, nns, BAKER-ROSETTASERVER, QUARK, and myprotein-me. In CASP11, the best models for most targets were equal to or better than the best template available in the Protein Data Bank, even for targets with poor templates. The overall performance in CASP11 is similar to the performance of predictors in CASP10 with slightly better performance on the hardest targets. For most targets, assessment measures exhibited bimodal probability density distributions. Multi-dimensional scaling of an RMSD matrix for each target typically revealed a single cluster with models similar to the target structure, with a mode in the GDT-TS density between 40 and 90, and a wide distribution of models highly divergent from each other and from the experimental structure, with density mode at a GDT-TS value of ?20. The models in this peak in the density were either compact models with entirely the wrong fold, or highly non-compact models. The results argue for a density-driven approach in future CASP TBM assessments that accounts for the bimodal nature of these distributions instead of Z scores, which assume a unimodal, Gaussian distribution.

@article{
 title = {Biological function derived from predicted structures in CASP11},
 type = {article},
 year = {2016},
 keywords = {Missense mutation phenotype prediction,P,[CASP11, Missense mutation phenotype prediction, P},
 id = {67a6477a-f046-3ed5-a21a-cbbc73c983b9},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:37:28.520Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {? 2016 Wiley Periodicals, Inc.In CASP11, the organizers sought to bring the biological inferences from predicted structures to the fore. To accomplish this, we assessed the models for their ability to perform quantifiable tasks related to biological function. First, for 10 targets that were probable homodimers, we measured the accuracy of docking the models into homodimers as a function of GDT-TS of the monomers, which produced characteristic L-shaped plots. At low GDT-TS, none of the models could be docked correctly as homodimers. Above GDT-TS of ?60%, some models formed correct homodimers in one of the largest docked clusters, while many other models at the same values of GDT-TS did not. Docking was more successful when many of the templates shared the same homodimer. Second, we docked a ligand from an experimental structure into each of the models of one of the targets. Docking to the models with two different programs produced poor ligand RMSDs with the experimental structure. Measures that evaluated similarity of contacts were reasonable for some of the models, although there was not a significant correlation with model accuracy. Finally, we assessed whether models would be useful in predicting the phenotypes of missense mutations in three human targets by comparing features calculated from the models with those calculated from the experimental structures. The models were successful in reproducing accessible surface areas but there was little correlation of model accuracy with calculation of FoldX evaluation of the change in free energy between the wild-type and the mutant.},
 bibtype = {article},
 author = {Huwe, P.J. and Xu, Q. and Shapovalov, M.V. and Modi, V. and Andrake, M.D. and Dunbrack, R.L.},
 doi = {10.1002/prot.24997},
 journal = {Proteins: Structure, Function and Bioinformatics}
}

? 2016 Wiley Periodicals, Inc.In CASP11, the organizers sought to bring the biological inferences from predicted structures to the fore. To accomplish this, we assessed the models for their ability to perform quantifiable tasks related to biological function. First, for 10 targets that were probable homodimers, we measured the accuracy of docking the models into homodimers as a function of GDT-TS of the monomers, which produced characteristic L-shaped plots. At low GDT-TS, none of the models could be docked correctly as homodimers. Above GDT-TS of ?60%, some models formed correct homodimers in one of the largest docked clusters, while many other models at the same values of GDT-TS did not. Docking was more successful when many of the templates shared the same homodimer. Second, we docked a ligand from an experimental structure into each of the models of one of the targets. Docking to the models with two different programs produced poor ligand RMSDs with the experimental structure. Measures that evaluated similarity of contacts were reasonable for some of the models, although there was not a significant correlation with model accuracy. Finally, we assessed whether models would be useful in predicting the phenotypes of missense mutations in three human targets by comparing features calculated from the models with those calculated from the experimental structures. The models were successful in reproducing accessible surface areas but there was little correlation of model accuracy with calculation of FoldX evaluation of the change in free energy between the wild-type and the mutant.

@article{
 title = {Assessment of refinement of template-based models in CASP11},
 type = {article},
 year = {2016},
 pages = {260-281},
 volume = {84},
 id = {59158049-0dc6-39da-903c-bcfa72d9f4a8},
 created = {2017-02-13T21:47:38.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:37:17.370Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {CASP11 (the 11th Meeting on the Critical Assessment of Protein Structure Prediction) ran a blind experiment in the refine-ment of protein structure predictions, the fourth such experiment since CASP8. As with the previous experiments, the pre-dictors were provided with one starting structure from the server models of each of a selected set of template-based modeling targets and asked to refine the coordinates of the starting structure toward native. We assessed the refined struc-tures with the Z-scores of the standard CASP measures, which compare the model-target similarities of the models from all the predictors. Furthermore, we assessed the refined structures with " relative measures, " which compare the improvement in accuracy of each model with respect to the starting structure. The latter provides an assessment of the extent to which each predictor group is able to improve the starting structures toward native. We utilized heat maps to display improve-ments in the Calpha–Calpha distance matrix for each model. The heat maps labeled with each element of secondary struc-ture helped us to identify regions of refinement toward native in each model. Most positively scoring models show modest improvements in multiple regions of the structure, while in some models we were able to identify significant repositioning of N/C-terminal segments and internal elements of secondary structure. The best groups were able to improve more than 70% of the targets from the starting models, and by an average of 3–5% in the standard CASP measures.},
 bibtype = {article},
 author = {Modi, Vivek and Dunbrack, Roland L},
 doi = {10.1002/prot.25048},
 journal = {Proteins}
}

CASP11 (the 11th Meeting on the Critical Assessment of Protein Structure Prediction) ran a blind experiment in the refine-ment of protein structure predictions, the fourth such experiment since CASP8. As with the previous experiments, the pre-dictors were provided with one starting structure from the server models of each of a selected set of template-based modeling targets and asked to refine the coordinates of the starting structure toward native. We assessed the refined struc-tures with the Z-scores of the standard CASP measures, which compare the model-target similarities of the models from all the predictors. Furthermore, we assessed the refined structures with " relative measures, " which compare the improvement in accuracy of each model with respect to the starting structure. The latter provides an assessment of the extent to which each predictor group is able to improve the starting structures toward native. We utilized heat maps to display improve-ments in the Calpha–Calpha distance matrix for each model. The heat maps labeled with each element of secondary struc-ture helped us to identify regions of refinement toward native in each model. Most positively scoring models show modest improvements in multiple regions of the structure, while in some models we were able to identify significant repositioning of N/C-terminal segments and internal elements of secondary structure. The best groups were able to improve more than 70% of the targets from the starting models, and by an average of 3–5% in the standard CASP measures.

@article{
 title = {Conformational analysis of the DFG-out kinase motif and biochemical profiling of structurally validated type II inhibitors},
 type = {article},
 year = {2015},
 pages = {466-479},
 volume = {58},
 id = {c79a455b-2431-337e-9d11-1959af7dd7d6},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:37:26.177Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {a0fac510-3b24-4e83-8388-6a4f961d2fb4},
 private_publication = {false},
 abstract = {Structural coverage of the human kinome has been steadily increasing over time. The structures provide valuable insights into the molecular basis of kinase function and also provide a foundation for understanding the mechanisms of kinase inhibitors. There are a large number of kinase structures in the PDB for which the Asp and Phe of the DFG motif on the activation loop swap positions, resulting in the formation of a new allosteric pocket. We refer to these structures as "classical DFG-out" conformations in order to distinguish them from conformations that have also been referred to as DFG-out in the literature but that do not have a fully formed allosteric pocket. We have completed a structural analysis of almost 200 small molecule inhibitors bound to classical DFG-out conformations; we find that they are recognized by both type I and type II inhibitors. In contrast, we find that nonclassical DFG-out conformations strongly select against type II inhibitors because these structures have not formed a large enough allosteric pocket to accommodate this type of binding mode. In the course of this study we discovered that the number of structurally validated type II inhibitors that can be found in the PDB and that are also represented in publicly available biochemical profiling studies of kinase inhibitors is very small. We have obtained new profiling results for several additional structurally validated type II inhibitors identified through our conformational analysis. Although the available profiling data for type II inhibitors is still much smaller than for type I inhibitors, a comparison of the two data sets supports the conclusion that type II inhibitors are more selective than type I. We comment on the possible contribution of the DFG-in to DFG-out conformational reorganization to the selectivity.},
 bibtype = {article},
 author = {Vijayan, R. S K and He, Peng and Modi, Vivek and Duong-Ly, Krisna C. and Ma, Haiching and Peterson, Jeffrey R. and Dunbrack, Roland L. and Levy, Ronald M.},
 doi = {10.1021/jm501603h},
 journal = {Journal of Medicinal Chemistry},
 number = {1}
}

Structural coverage of the human kinome has been steadily increasing over time. The structures provide valuable insights into the molecular basis of kinase function and also provide a foundation for understanding the mechanisms of kinase inhibitors. There are a large number of kinase structures in the PDB for which the Asp and Phe of the DFG motif on the activation loop swap positions, resulting in the formation of a new allosteric pocket. We refer to these structures as "classical DFG-out" conformations in order to distinguish them from conformations that have also been referred to as DFG-out in the literature but that do not have a fully formed allosteric pocket. We have completed a structural analysis of almost 200 small molecule inhibitors bound to classical DFG-out conformations; we find that they are recognized by both type I and type II inhibitors. In contrast, we find that nonclassical DFG-out conformations strongly select against type II inhibitors because these structures have not formed a large enough allosteric pocket to accommodate this type of binding mode. In the course of this study we discovered that the number of structurally validated type II inhibitors that can be found in the PDB and that are also represented in publicly available biochemical profiling studies of kinase inhibitors is very small. We have obtained new profiling results for several additional structurally validated type II inhibitors identified through our conformational analysis. Although the available profiling data for type II inhibitors is still much smaller than for type I inhibitors, a comparison of the two data sets supports the conclusion that type II inhibitors are more selective than type I. We comment on the possible contribution of the DFG-in to DFG-out conformational reorganization to the selectivity.

@article{
 title = {Antiapoptotic Bcl-2 homolog CED-9 in Caenorhabditis elegans: Dynamics of BH3 and CED-4 binding regions and comparison with mammalian antiapoptotic Bcl-2 proteins},
 type = {article},
 year = {2014},
 keywords = {[Accessible surface area, Comparative simulations,},
 volume = {82},
 id = {5b572d31-d891-3c1d-9b1b-ad4469121f54},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:40:01.971Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {Proteins belonging to Bcl-2 family regulate intrinsic cell death pathway. Although mammalian antiapoptotic Bcl-2 members interact with multiple proapoptotic proteins, the Caenorhabditis elegans Bcl-2 homolog CED-9 is known to have only two proapoptotic partners. The BH3-motif of proapoptotic proteins bind to the hydrophobic groove of prosurvival proteins formed by the Bcl-2 helical fold. CED-9 is also known to interact with CED-4, a homolog of the human cell death activator Apaf1. We have performed molecular dynamics simulations of CED-9 in two forms and compared the results with those of mammalian counterparts Bcl-XL, Bcl-w, and Bcl-2. Our studies demonstrate that the region forming the hydrophobic cleft is more flexible compared with the CED-4-binding region, and this is generally true for all antiapoptotic Bcl-2 proteins studied. CED-9 is the most stable protein during simulations and its hydrophobic pocket is relatively rigid explaining the absence of functional redundancy in CED-9. The BH3-binding region of Bcl-2 is less flexible among the mammalian proteins and this lends support to the studies that Bcl-2 binds to less number of BH3 peptides with high affinity. The C-terminal helix of CED-9 lost its helical character because of a large number of charged residues. We speculate that this region probably plays a role in intracellular localization of CED-9. The BH4-motif accessibility in CED-9 and Bcl-w is controlled by the loop connecting the first two helices. Although CED-9 adopts the same Bcl-2 fold, our studies highlight important differences in the dynamic behavior of CED-9 and mammalian antiapoptotic homologs. ? 2013 Wiley Periodicals, Inc.},
 bibtype = {article},
 author = {Modi, V. and Sankararamakrishnan, R.},
 doi = {10.1002/prot.24476},
 journal = {Proteins: Structure, Function and Bioinformatics},
 number = {6}
}

Proteins belonging to Bcl-2 family regulate intrinsic cell death pathway. Although mammalian antiapoptotic Bcl-2 members interact with multiple proapoptotic proteins, the Caenorhabditis elegans Bcl-2 homolog CED-9 is known to have only two proapoptotic partners. The BH3-motif of proapoptotic proteins bind to the hydrophobic groove of prosurvival proteins formed by the Bcl-2 helical fold. CED-9 is also known to interact with CED-4, a homolog of the human cell death activator Apaf1. We have performed molecular dynamics simulations of CED-9 in two forms and compared the results with those of mammalian counterparts Bcl-XL, Bcl-w, and Bcl-2. Our studies demonstrate that the region forming the hydrophobic cleft is more flexible compared with the CED-4-binding region, and this is generally true for all antiapoptotic Bcl-2 proteins studied. CED-9 is the most stable protein during simulations and its hydrophobic pocket is relatively rigid explaining the absence of functional redundancy in CED-9. The BH3-binding region of Bcl-2 is less flexible among the mammalian proteins and this lends support to the studies that Bcl-2 binds to less number of BH3 peptides with high affinity. The C-terminal helix of CED-9 lost its helical character because of a large number of charged residues. We speculate that this region probably plays a role in intracellular localization of CED-9. The BH4-motif accessibility in CED-9 and Bcl-w is controlled by the loop connecting the first two helices. Although CED-9 adopts the same Bcl-2 fold, our studies highlight important differences in the dynamic behavior of CED-9 and mammalian antiapoptotic homologs. ? 2013 Wiley Periodicals, Inc.

@article{
 title = {Behavior of Solvent-Exposed Hydrophobic Groove in the Anti-Apoptotic Bcl-XL Protein: Clues for Its Ability to Bind Diverse BH3 Ligands from MD Simulations},
 type = {article},
 year = {2013},
 volume = {8},
 id = {d837e937-830a-3558-9827-9729a708bb90},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2019-03-01T23:21:26.355Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {a0fac510-3b24-4e83-8388-6a4f961d2fb4},
 private_publication = {false},
 abstract = {Bcl-XL is a member of Bcl-2 family of proteins involved in the regulation of intrinsic pathway of apoptosis. Its overexpression in many human cancers makes it an important target for anti-cancer drugs. Bcl-XL interacts with the BH3 domain of several pro-apoptotic Bcl-2 partners. This helical bundle protein has a pronounced hydrophobic groove which acts as a binding region for the BH3 domains. Eight independent molecular dynamics simulations of the apo/holo forms of Bcl-XL were carried out to investigate the behavior of solvent-exposed hydrophobic groove. The simulations used either a twin-range cut-off or particle mesh Ewald (PME) scheme to treat long-range interactions. Destabilization of the BH3 domain-containing helix H2 was observed in all four twin-range cut-off simulations. Most of the other major helices remained stable. The unwinding of H2 can be related to the ability of Bcl-XL to bind diverse BH3 ligands. The loss of helical character can also be linked to the formation of homo- or hetero-dimers in Bcl-2 proteins. Several experimental studies have suggested that exposure of BH3 domain is a crucial event before they form dimers. Thus unwinding of H2 seems to be functionally very important. The four PME simulations, however, revealed a stable helix H2. It is possible that the H2 unfolding might occur in PME simulations at longer time scales. Hydrophobic residues in the hydrophobic groove are involved in stable interactions among themselves. The solvent accessible surface areas of bulky hydrophobic residues in the groove are significantly buried by the loop LB connecting the helix H2 and subsequent helix. These observations help to understand how the hydrophobic patch in Bcl-XL remains stable in the solvent-exposed state. We suggest that both the destabilization of helix H2 and the conformational heterogeneity of loop LB are important factors for binding of diverse ligands in the hydrophobic groove of Bcl-XL. ? 2013 Lama et al.},
 bibtype = {article},
 author = {Lama, D. and Modi, V. and Sankararamakrishnan, R.},
 doi = {10.1371/journal.pone.0054397},
 journal = {PLoS ONE},
 number = {2}
}

Bcl-XL is a member of Bcl-2 family of proteins involved in the regulation of intrinsic pathway of apoptosis. Its overexpression in many human cancers makes it an important target for anti-cancer drugs. Bcl-XL interacts with the BH3 domain of several pro-apoptotic Bcl-2 partners. This helical bundle protein has a pronounced hydrophobic groove which acts as a binding region for the BH3 domains. Eight independent molecular dynamics simulations of the apo/holo forms of Bcl-XL were carried out to investigate the behavior of solvent-exposed hydrophobic groove. The simulations used either a twin-range cut-off or particle mesh Ewald (PME) scheme to treat long-range interactions. Destabilization of the BH3 domain-containing helix H2 was observed in all four twin-range cut-off simulations. Most of the other major helices remained stable. The unwinding of H2 can be related to the ability of Bcl-XL to bind diverse BH3 ligands. The loss of helical character can also be linked to the formation of homo- or hetero-dimers in Bcl-2 proteins. Several experimental studies have suggested that exposure of BH3 domain is a crucial event before they form dimers. Thus unwinding of H2 seems to be functionally very important. The four PME simulations, however, revealed a stable helix H2. It is possible that the H2 unfolding might occur in PME simulations at longer time scales. Hydrophobic residues in the hydrophobic groove are involved in stable interactions among themselves. The solvent accessible surface areas of bulky hydrophobic residues in the groove are significantly buried by the loop LB connecting the helix H2 and subsequent helix. These observations help to understand how the hydrophobic patch in Bcl-XL remains stable in the solvent-exposed state. We suggest that both the destabilization of helix H2 and the conformational heterogeneity of loop LB are important factors for binding of diverse ligands in the hydrophobic groove of Bcl-XL. ? 2013 Lama et al.

@book{
 title = {Plasticity of Bh3 Domain-Binding Hydrophobic Grooves in the Anti-Apoptotic Mcl-1 and a1 Proteins},
 type = {book},
 year = {2013},
 source = {Biomolecular Forms and Functions},
 pages = {468-481},
 websites = {http://www.worldscientific.com/doi/abs/10.1142/9789814449144_0036},
 id = {c6ef87c8-9fbe-39bc-bd11-0e3ca82e28d6},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:37:20.783Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {? 2013 by World Scientific Publishing Co. Pte. Ltd. All rights reserved.Mcl-1 and A1 constitute a subclass within the group of anti-apoptotic Bcl-2 proteins and are shown to be overcxpressed in several human cancers. Diverse BH3 domains of different pro-apoptotic Bcl-2 protein& bind to the hydrophobic groove of both these helical bundle proteins with different affinities. Development of any inhibitors for Mcl-1 and A1 requires the knowledge of the behavior of the binding region. In this study, we have carried out molecular dynamics simulations of apo-Mcl-1 and holo-Al systems for a period of 100 ns and compared the results with our earlier studies on Bcl-XL. another anti-apoptotic protein from a different subclass. During the course of the simulation, the BID-containing helix H2 is destabilized in Mcl-1, a behavior observed in Bcl-XL also. The unwinding is attributed to the presence of glycine residues in the segment containing H2. Additionally, this region also contains eight basic residues including three doublets. We have hypothesized that the dibasic motifs could be the cleavage sites for the enzymes that will generate smaller isoforms of Mcl-1 and the unwinding of H2 can aid in the exposure of these cleavage sites. As far as Al is concerned, the BID-containing helix H2 is mostly stable except the last two helical turns. However, it adopts a completely different orientation within the first 10 ns. This change in orientation realigns the loop region that links H2 and the next helix so that most of the exposed hydrophobic residues can be shielded. The charged residues in both the proteins that are projected towards the hydrophobic groove in the experimentally determined structures are exposed to the solvent during the simulations. This is due to the destabilization of helical regions in which they are present. The unwinding of helix H2 in Mcl-1 and the change in orientation of the same helix in Al point to the flexible nature of hydrophobic groove and this could be important for the binding of diverse BH3 peptides.},
 bibtype = {book},
 author = {MODI, VIVEK and LAMA, DILRAJ and SANKARARAMAKRISHNAN, RAMASUBBU},
 doi = {10.1142/9789814449144_0036}
}

? 2013 by World Scientific Publishing Co. Pte. Ltd. All rights reserved.Mcl-1 and A1 constitute a subclass within the group of anti-apoptotic Bcl-2 proteins and are shown to be overcxpressed in several human cancers. Diverse BH3 domains of different pro-apoptotic Bcl-2 protein& bind to the hydrophobic groove of both these helical bundle proteins with different affinities. Development of any inhibitors for Mcl-1 and A1 requires the knowledge of the behavior of the binding region. In this study, we have carried out molecular dynamics simulations of apo-Mcl-1 and holo-Al systems for a period of 100 ns and compared the results with our earlier studies on Bcl-XL. another anti-apoptotic protein from a different subclass. During the course of the simulation, the BID-containing helix H2 is destabilized in Mcl-1, a behavior observed in Bcl-XL also. The unwinding is attributed to the presence of glycine residues in the segment containing H2. Additionally, this region also contains eight basic residues including three doublets. We have hypothesized that the dibasic motifs could be the cleavage sites for the enzymes that will generate smaller isoforms of Mcl-1 and the unwinding of H2 can aid in the exposure of these cleavage sites. As far as Al is concerned, the BID-containing helix H2 is mostly stable except the last two helical turns. However, it adopts a completely different orientation within the first 10 ns. This change in orientation realigns the loop region that links H2 and the next helix so that most of the exposed hydrophobic residues can be shielded. The charged residues in both the proteins that are projected towards the hydrophobic groove in the experimentally determined structures are exposed to the solvent during the simulations. This is due to the destabilization of helical regions in which they are present. The unwinding of helix H2 in Mcl-1 and the change in orientation of the same helix in Al point to the flexible nature of hydrophobic groove and this could be important for the binding of diverse BH3 peptides.

@article{
 title = {Relationship between helix stability and binding affinities: Molecular dynamics simulations of Bfl-1/A1-binding pro-apoptotic BH3 peptide helices in explicit solvent},
 type = {article},
 year = {2013},
 keywords = {[Anti-cancer drug design, Bcl-2 family, BH3 mimeti},
 volume = {31},
 id = {4fdb6992-37b1-3d81-9dc3-f6cae300ade4},
 created = {2017-02-12T23:44:37.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:38:56.292Z},
 read = {true},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {The anti-apoptotic protein Bfl-1, also known as A1, belongs to the Bcl-2 family of proteins and interacts with proapoptotic Bcl-2 counterparts to regulate programed cell death. As demonstrated for other anti-apoptotic Bcl-2 proteins, Bfl-1/A1 has also been shown to be overexpressed in various human cancers and hence they are attractive targets for anticancer drugs. Peptides derived from the BH3 region of pro-apoptotic Bcl-2 proteins have been shown to elicit similar biological response as that of parent proteins. BH3 peptides from different pro-apoptotic proteins have wide range of affinities for Bfl-1/A1. Experimentally determined complex structures show that the hydrophobic side of amphipathic BH3 peptides binds to the hydrophobic groove formed by the a-helical bundle of Bfl-1/A1 protein. Apart from the length and amino acid composition, a BH3 peptide's ability to form a stable helical structure has been suggested to be important for its high binding affinity. Molecular dynamics simulations of three BH3 peptides derived from the pro-apoptotic proteins Bak, Bid, and Bmf were carried out each for a period of at least 100 ns after 2 ns equilibration run. The length of simulated BH3 peptides varied from 22 to 24 residues and their binding affinities for Bfl-1/A1 varied from 1 to 180 nM. Our results show that the hydrophobic residues from the hydrophobic face of BH3 peptides tend to cluster together quickly to avoid being exposed to the solvent. This resulted in either reduction of helix length or complete loss of helical character. Bak and Bid BH3 peptides with high affinities for Bf1-1/A1 have stable helical segments in the N-terminal region. The highly conserved Leu residue lies just outside the helical region at the C-terminal end. Capping interactions arising out of N-cap residues seem to be extremely important to maintain the helical stability. Favorable hydrophilic interactions between residues also give further stability to the helix fragment and at least one of the interacting residues resides within the helical region. Bmf BH3 peptide with a weaker binding affinity for Bmf-1/A1 completely lost its helical character at the end of 100 ns production run and a further 50 ns simulation showed that the Bmf peptide continues to remain in random conformation. The present study clearly establishes a link between a BH3 peptide's ability to form a stable helical segment and its high binding affinity for an anti-apoptotic protein. To further test this hypothesis, we simulated a mutant Bmf peptide for 100 ns in which two residues R129 and H146 were substituted by Asn in silico in the wild-type peptide. Introduction of N-terminal Asn clearly enabled the formation of capping interactions at the N-terminus and resulted in a stable Nterminal helical segment. This demonstrates that the knowledge of interactions that help to maintain stable helical segments in a high-affinity BH3 peptide will help in designing highly specific peptide-based drugs/inhibitors. Such molecules will have the ability to bind a particular anti-apoptotic protein with high affinity. Copyright ? 2013 Taylor & Francis.},
 bibtype = {article},
 author = {Modi, V. and Lama, D. and Sankararamakrishnan, R.},
 doi = {10.1080/07391102.2012.691363},
 journal = {Journal of Biomolecular Structure and Dynamics},
 number = {1}
}

The anti-apoptotic protein Bfl-1, also known as A1, belongs to the Bcl-2 family of proteins and interacts with proapoptotic Bcl-2 counterparts to regulate programed cell death. As demonstrated for other anti-apoptotic Bcl-2 proteins, Bfl-1/A1 has also been shown to be overexpressed in various human cancers and hence they are attractive targets for anticancer drugs. Peptides derived from the BH3 region of pro-apoptotic Bcl-2 proteins have been shown to elicit similar biological response as that of parent proteins. BH3 peptides from different pro-apoptotic proteins have wide range of affinities for Bfl-1/A1. Experimentally determined complex structures show that the hydrophobic side of amphipathic BH3 peptides binds to the hydrophobic groove formed by the a-helical bundle of Bfl-1/A1 protein. Apart from the length and amino acid composition, a BH3 peptide's ability to form a stable helical structure has been suggested to be important for its high binding affinity. Molecular dynamics simulations of three BH3 peptides derived from the pro-apoptotic proteins Bak, Bid, and Bmf were carried out each for a period of at least 100 ns after 2 ns equilibration run. The length of simulated BH3 peptides varied from 22 to 24 residues and their binding affinities for Bfl-1/A1 varied from 1 to 180 nM. Our results show that the hydrophobic residues from the hydrophobic face of BH3 peptides tend to cluster together quickly to avoid being exposed to the solvent. This resulted in either reduction of helix length or complete loss of helical character. Bak and Bid BH3 peptides with high affinities for Bf1-1/A1 have stable helical segments in the N-terminal region. The highly conserved Leu residue lies just outside the helical region at the C-terminal end. Capping interactions arising out of N-cap residues seem to be extremely important to maintain the helical stability. Favorable hydrophilic interactions between residues also give further stability to the helix fragment and at least one of the interacting residues resides within the helical region. Bmf BH3 peptide with a weaker binding affinity for Bmf-1/A1 completely lost its helical character at the end of 100 ns production run and a further 50 ns simulation showed that the Bmf peptide continues to remain in random conformation. The present study clearly establishes a link between a BH3 peptide's ability to form a stable helical segment and its high binding affinity for an anti-apoptotic protein. To further test this hypothesis, we simulated a mutant Bmf peptide for 100 ns in which two residues R129 and H146 were substituted by Asn in silico in the wild-type peptide. Introduction of N-terminal Asn clearly enabled the formation of capping interactions at the N-terminus and resulted in a stable Nterminal helical segment. This demonstrates that the knowledge of interactions that help to maintain stable helical segments in a high-affinity BH3 peptide will help in designing highly specific peptide-based drugs/inhibitors. Such molecules will have the ability to bind a particular anti-apoptotic protein with high affinity. Copyright ? 2013 Taylor & Francis.

@phdthesis{
 title = {Thesis},
 type = {phdthesis},
 year = {2013},
 id = {a9e5749b-8cb7-3cd2-b4f6-ba3aaf6cba9c},
 created = {2017-02-14T16:22:42.000Z},
 file_attached = {true},
 profile_id = {4b9ec6d4-c859-345e-a693-df960ed211b8},
 last_modified = {2018-05-31T12:42:32.303Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 bibtype = {phdthesis},
 author = {Modi, Vivek}
}

@article{
 title = {PDBrenum: A webserver and program providing Protein Data Bank files renumbered according to their UniProt sequences},
 type = {article},
 year = {2021},
 volume = {16},
 id = {63684916-7b6d-3735-9ed2-64197390c318},
 created = {2022-04-14T19:22:42.189Z},
 file_attached = {false},
 profile_id = {15907a83-415d-372c-9535-a6ff3937b322},
 last_modified = {2022-04-14T19:22:42.189Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {The Protein Data Bank (PDB) was established at Brookhaven National Laboratories in 1971 as an archive for biological macromolecular crystal structures. In mid 2021, the database has almost 180,000 structures solved by X-ray crystallography, nuclear magnetic resonance, cryo-electron microscopy, and other methods. Many proteins have been studied under different conditions, including binding partners such as ligands, nucleic acids, or other proteins; mutations, and post-Translational modifications, thus enabling extensive comparative structure-function studies. However, these studies are made more difficult because authors are allowed by the PDB to number the amino acids in each protein sequence in any manner they wish. This results in the same protein being numbered differently in the available PDB entries. For instance, some authors may include N-Terminal signal peptides or the N-Terminal methionine in the sequence numbering and others may not. In addition to the coordinates, there are many fields that contain structural and functional information regarding specific residues numbered according to the author. Here we provide a webserver and Python3 application that fixes the PDB sequence numbering problem by replacing the author numbering with numbering derived from the corresponding UniProt sequences. We obtain this correspondence from the SIFTS database from PDBe. The server and program can take a list of PDB entries or a list of UniProt identifiers (e.g., "P04637"or "P53-HUMAN") and provide renumbered files in mmCIF format and the legacy PDB format for both asymmetric unit files and biological assembly files provided by PDBe.},
 bibtype = {article},
 author = {Faezov, B. and Dunbrack, R.L.},
 doi = {10.1371/journal.pone.0253411},
 journal = {PLoS ONE},
 number = {7 July}
}

The Protein Data Bank (PDB) was established at Brookhaven National Laboratories in 1971 as an archive for biological macromolecular crystal structures. In mid 2021, the database has almost 180,000 structures solved by X-ray crystallography, nuclear magnetic resonance, cryo-electron microscopy, and other methods. Many proteins have been studied under different conditions, including binding partners such as ligands, nucleic acids, or other proteins; mutations, and post-Translational modifications, thus enabling extensive comparative structure-function studies. However, these studies are made more difficult because authors are allowed by the PDB to number the amino acids in each protein sequence in any manner they wish. This results in the same protein being numbered differently in the available PDB entries. For instance, some authors may include N-Terminal signal peptides or the N-Terminal methionine in the sequence numbering and others may not. In addition to the coordinates, there are many fields that contain structural and functional information regarding specific residues numbered according to the author. Here we provide a webserver and Python3 application that fixes the PDB sequence numbering problem by replacing the author numbering with numbering derived from the corresponding UniProt sequences. We obtain this correspondence from the SIFTS database from PDBe. The server and program can take a list of PDB entries or a list of UniProt identifiers (e.g., "P04637"or "P53-HUMAN") and provide renumbered files in mmCIF format and the legacy PDB format for both asymmetric unit files and biological assembly files provided by PDBe.

@article{
 title = {Musashi-2 (MSI2) regulates epidermal growth factor receptor (EGFR) expression and response to EGFR inhibitors in EGFR-mutated non-small cell lung cancer (NSCLC)},
 type = {article},
 year = {2021},
 volume = {10},
 id = {67e56ced-1b53-3027-8e41-193e6a7b0439},
 created = {2022-04-14T19:22:42.242Z},
 file_attached = {false},
 profile_id = {15907a83-415d-372c-9535-a6ff3937b322},
 last_modified = {2022-04-14T19:22:42.242Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {Non-small cell lung cancer (NSCLC) has limited treatment options. Expression of the RNA-binding protein (RBP) Musashi-2 (MSI2) is elevated in a subset of non-small cell lung cancer (NSCLC) tumors upon progression, and drives NSCLC metastasis. We evaluated the mechanism of MSI2 action in NSCLC to gain therapeutically useful insights. Reverse phase protein array (RPPA) analysis of MSI2-depleted versus control KrasLA1/+; Trp53R172HΔG/+ NSCLC cell lines identified EGFR as a MSI2-regulated protein. MSI2 control of EGFR expression and activity in an NSCLC cell line panel was studied using RT-PCR, Western blots, and RNA immunoprecipitation. Functional consequences of MSI2 depletion were explored for cell growth and response to EGFR-targeting drugs, in vitro and in vivo. Expression relationships were validated using human tissue microarrays. MSI2 depletion significantly reduced EGFR protein expression, phosphorylation, or both. Comparison of protein and mRNA expression indicated a post-transcriptional activity of MSI2 in control of steady state levels of EGFR. RNA immunoprecipitation analysis demonstrated that MSI2 directly binds to EGFR mRNA, and sequence analysis predicted MSI2 binding sites in the murine and human EGFR mRNAs. MSI2 depletion selectively impaired cell proliferation in NSCLC cell lines with activating mutations of EGFR (EGFRmut). Further, depletion of MSI2 in combination with EGFR inhibitors such as erlotinib, afatinib, and osimertinib selectively reduced the growth of EGFRmut NSCLC cells and xenografts. EGFR and MSI2 were significantly co-expressed in EGFRmut human NSCLCs. These results define MSI2 as a direct regulator of EGFR protein expression, and suggest inhibition of MSI2 could be of clinical value in EGFRmut NSCLC.},
 bibtype = {article},
 author = {Makhov, P. and Bychkov, I. and Faezov, B. and Deneka, A. and Kudinov, A. and Nicolas, E. and Brebion, R. and Avril, E. and Cai, K.Q. and Kharin, L.V. and Voloshin, M. and Frantsiyants, E. and Karnaukhov, N. and Kit, O.I. and Topchu, I. and Fazliyeva, R. and Nikonova, A.S. and Serebriiskii, I.G. and Borghaei, H. and Edelman, M. and Dulaimi, E. and Golemis, E.A. and Boumber, Y.},
 doi = {10.1038/s41389-021-00317-y},
 journal = {Oncogenesis},
 number = {3}
}

Non-small cell lung cancer (NSCLC) has limited treatment options. Expression of the RNA-binding protein (RBP) Musashi-2 (MSI2) is elevated in a subset of non-small cell lung cancer (NSCLC) tumors upon progression, and drives NSCLC metastasis. We evaluated the mechanism of MSI2 action in NSCLC to gain therapeutically useful insights. Reverse phase protein array (RPPA) analysis of MSI2-depleted versus control KrasLA1/+; Trp53R172HΔG/+ NSCLC cell lines identified EGFR as a MSI2-regulated protein. MSI2 control of EGFR expression and activity in an NSCLC cell line panel was studied using RT-PCR, Western blots, and RNA immunoprecipitation. Functional consequences of MSI2 depletion were explored for cell growth and response to EGFR-targeting drugs, in vitro and in vivo. Expression relationships were validated using human tissue microarrays. MSI2 depletion significantly reduced EGFR protein expression, phosphorylation, or both. Comparison of protein and mRNA expression indicated a post-transcriptional activity of MSI2 in control of steady state levels of EGFR. RNA immunoprecipitation analysis demonstrated that MSI2 directly binds to EGFR mRNA, and sequence analysis predicted MSI2 binding sites in the murine and human EGFR mRNAs. MSI2 depletion selectively impaired cell proliferation in NSCLC cell lines with activating mutations of EGFR (EGFRmut). Further, depletion of MSI2 in combination with EGFR inhibitors such as erlotinib, afatinib, and osimertinib selectively reduced the growth of EGFRmut NSCLC cells and xenografts. EGFR and MSI2 were significantly co-expressed in EGFRmut human NSCLCs. These results define MSI2 as a direct regulator of EGFR protein expression, and suggest inhibition of MSI2 could be of clinical value in EGFRmut NSCLC.

@misc{
 title = {PDBrenum: A webserver and program providing Protein Data Bank files renumbered according to their UniProt sequences},
 type = {misc},
 year = {2021},
 source = {bioRxiv},
 id = {656ec7a0-cc36-35d1-8a21-c6b7b85aa35b},
 created = {2022-04-14T19:22:42.258Z},
 file_attached = {false},
 profile_id = {15907a83-415d-372c-9535-a6ff3937b322},
 last_modified = {2022-04-14T19:22:42.258Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {false},
 hidden = {false},
 private_publication = {true},
 abstract = {The Protein Data Bank (PDB) was established at Brookhaven National Laboratories in 1971 as an archive for biological macromolecular crystal structures. In the beginning the archive held only seven structures but in early 2021, the database has more than 170,000 structures solved by X-ray crystallography, nuclear magnetic resonance, cryo-electron microscopy, and other methods. Many proteins have been studied under different conditions (e.g., binding partners such as ligands, nucleic acids, or other proteins; mutations and post-translational modifications), thus enabling comparative structure-function studies. However, these studies are made more difficult because authors are allowed by the PDB to number the amino acids in each protein sequence in any manner they wish. This results in the same protein being numbered differently in the available PDB entries. In addition to the coordinates, there are many fields that contain information regarding specific residues in the sequence of each protein in the entry. Here we provide a webserver and Python3 application that fixes the PDB sequence numbering problem by replacing the author numbering with numbering derived from the corresponding UniProt sequences. We obtain this correspondence from the SIFTS database from PDBe. The server and program can take a list of PDB entries and provide renumbered files in mmCIF format and the legacy PDB format for both asymmetric unit files and biological assembly files provided by PDBe. The server can also take a list of UniProt identifiers (“P04637” or “P53_HUMAN”) and return the desired files. Availability: Source code is freely available at https://github.com/Faezov/PDBrenum. The webserver is located at: http://dunbrack3.fccc.edu/PDBrenum. Contact: bulat.faezov@fccc.edu or roland.dunbrack@fccc.edu.},
 bibtype = {misc},
 author = {Faezov, B. and Dunbrack, R.L.},
 doi = {10.1101/2021.02.14.431128}
}

The Protein Data Bank (PDB) was established at Brookhaven National Laboratories in 1971 as an archive for biological macromolecular crystal structures. In the beginning the archive held only seven structures but in early 2021, the database has more than 170,000 structures solved by X-ray crystallography, nuclear magnetic resonance, cryo-electron microscopy, and other methods. Many proteins have been studied under different conditions (e.g., binding partners such as ligands, nucleic acids, or other proteins; mutations and post-translational modifications), thus enabling comparative structure-function studies. However, these studies are made more difficult because authors are allowed by the PDB to number the amino acids in each protein sequence in any manner they wish. This results in the same protein being numbered differently in the available PDB entries. In addition to the coordinates, there are many fields that contain information regarding specific residues in the sequence of each protein in the entry. Here we provide a webserver and Python3 application that fixes the PDB sequence numbering problem by replacing the author numbering with numbering derived from the corresponding UniProt sequences. We obtain this correspondence from the SIFTS database from PDBe. The server and program can take a list of PDB entries and provide renumbered files in mmCIF format and the legacy PDB format for both asymmetric unit files and biological assembly files provided by PDBe. The server can also take a list of UniProt identifiers (“P04637” or “P53_HUMAN”) and return the desired files. Availability: Source code is freely available at https://github.com/Faezov/PDBrenum. The webserver is located at: http://dunbrack3.fccc.edu/PDBrenum. Contact: bulat.faezov@fccc.edu or roland.dunbrack@fccc.edu.