skip to main content

Search for: All records

Award ID contains: 2025426

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Abstract

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

    « less
  2. Kolodny, Rachel (Ed.)
    The topology of protein folds can be specified by the inter-residue contact-maps and accurate contact-map prediction can help ab initio structure folding. We developed TripletRes to deduce protein contact-maps from discretized distance profiles by end-to-end training of deep residual neural-networks. Compared to previous approaches, the major advantage of TripletRes is in its ability to learn and directly fuse a triplet of coevolutionary matrices extracted from the whole-genome and metagenome databases and therefore minimize the information loss during the course of contact model training. TripletRes was tested on a large set of 245 non-homologous proteins from CASP 11&12 and CAMEO experiments and outperformed other top methods from CASP12 by at least 58.4% for the CASP 11&12 targets and 44.4% for the CAMEO targets in the top- L long-range contact precision. On the 31 FM targets from the latest CASP13 challenge, TripletRes achieved the highest precision (71.6%) for the top- L /5 long-range contact predictions. It was also shown that a simple re-training of the TripletRes model with more proteins can lead to further improvement with precisions comparable to state-of-the-art methods developed after CASP13. These results demonstrate a novel efficient approach to extend the power of deep convolutional networks for high-accuracy medium-more »and long-range protein contact-map predictions starting from primary sequences, which are critical for constructing 3D structure of proteins that lack homologous templates in the PDB library.« less
  3. ABSTRACT Inactivation of DNA mismatch repair propels colorectal cancer (CRC) tumorigenesis. CRCs exhibiting e levated m icrosatellite a lterations at s elected t etranucleotide repeats (EMAST) show reduced nuclear MutS homolog 3 (MSH3) expression with surrounding inflammation and portend poor patient outcomes. MSH3 reversibly exits from the nucleus to the cytosol in response to the proinflammatory cytokine interleukin-6 (IL-6), suggesting that MSH3 may be a shuttling protein. In this study, we manipulated three putative nuclear localization (NLS1 to -3) and two potential nuclear export signals (NES1 and -2) within MSH3. We found that both NLS1 and NLS2 possess nuclear import function, with NLS1 responsible for nuclear localization within full-length MSH3. We also found that NES1 and NES2 work synergistically to maximize nuclear export, with both being required for IL-6-induced MSH3 export. We examined a 27-bp deletion (Δ27bp) within the polymorphic exon 1 that occurs frequently in human CRC cells and neighbors NLS1. With oxidative stress, MSH3 with this deletion (Δ27bp MSH3) localizes to the cytoplasm, suggesting that NLS1 function in Δ27bp MSH3 is compromised. Overall, MSH3’s shuttling in response to inflammation enables accumulation in the cytoplasm; reduced nuclear MSH3 increases EMAST and DNA damage. We suggest that polymorphic sequences adjacentmore »to NLS1 may enhance cytosolic retention, which has clinical implications for inflammation-associated neoplastic processes.« less