PlantBind: an attention-based multi-label neural network for predicting plant transcription factor binding sites.

Identification of transcription factor binding sites (TFBSs) is essential to understanding of gene regulation. Designing computational models for accurate prediction of TFBSs is crucial because it is not feasible to experimentally assay all transcription factors (TFs) in all sequenced eukaryotic genomes. Although many methods have been proposed for the identification of TFBSs in humans, methods designed for plants are comparatively underdeveloped. Here, we present PlantBind, a method for integrated prediction and interpretation of TFBSs based on DNA sequences and DNA shape profiles. Built on an attention-based multi-label deep learning framework, PlantBind not only simultaneously predicts the potential binding sites of 315 TFs, but also identifies the motifs bound by transcription factors. During the training process, this model revealed a strong similarity among TF family members with respect to target binding sequences. Trans-species prediction performance using four Zea mays TFs demonstrated the suitability of this model for transfer learning. Overall, this study provides an effective solution for identifying plant TFBSs, which will promote greater understanding of transcriptional regulatory mechanisms in plants.

A generative model for constructing nucleic acid sequences binding to a protein.

BACKGROUND: Interactions between protein and nucleic acid molecules are essential to a variety of cellular processes. A large amount of interaction data generated by high-throughput technologies have triggered the development of several computational methods either to predict binding sites in a sequence or to determine whether a pair of sequences interacts or not. Most of these methods treat the problem of the interaction of nucleic acids with proteins as a classification problem rather than a generation problem. RESULTS: We developed a generative model for constructing single-stranded nucleic acids binding to a target protein using a long short-term memory (LSTM) neural network. Experimental results of the generative model are promising in the sense that DNA and RNA sequences generated by the model for several target proteins show high specificity and that motifs present in the generated sequences are similar to known protein-binding motifs. CONCLUSIONS: Although these are preliminary results of our ongoing research, our approach can be used to generate nucleic acid sequences binding to a target protein. In particular, it will help design efficient in vitro experiments by constructing an initial pool of potential aptamers that bind to a target protein with high affinity and specificity.

The cellular protein nucleolin preferentially binds long-looped G-quadruplex nucleic acids.

BACKGROUND: G-quadruplexes (G4s) are four-stranded nucleic acid structures that form in G-rich sequences. Nucleolin (NCL) is a cellular protein reported for its functions upon G4 recognition, such as induction of neurodegenerative diseases, tumor and virus mechanisms activation. We here aimed at defining NCL/G4 binding determinants. METHODS: Electrophoresis mobility shift assay was used to detect NCL/G4 binding; circular dichroism to assess G4 folding, topology and stability; dimethylsulfate footprinting to detect G bases involved in G4 folding. RESULTS: The purified full-length human NCL was initially tested on telomeric G4 target sequences to allow for modulation of loop, conformation, length, G-tract number, stability. G4s in promoter regions with more complex sequences were next employed. We found that NCL binding to G4s heavily relies on G4 loop length, independently of the conformation and oligonucleotide/loop sequence. Low stability G4s are preferred. When alternative G4 conformations are possible, those with longer loops are preferred upon binding to NCL, even if G-tracts need to be spared from G4 folding. CONCLUSIONS: Our data provide insight into how G4s and the associated proteins may control the ON/OFF molecular switch to several pathological processes, including neurodegeneration, tumor and virus activation. Understanding these regulatory determinants is the first step towards the development of targeted therapies. GENERAL SIGNIFICANCE: The indication that NCL binding preferentially stimulates and induces folding of G4s containing long loops suggests NCL ability to modify the overall structure and steric hindrance of the involved nucleic acid regions. This protein-induced modification of the G4 structure may represent a cellular mechanosensor mechanism to molecular signaling and disease pathogenesis. This article is part of a Special Issue entitled "G-quadruplex" Guest Editor: Dr. Concetta Giancola and Dr. Daniela Montesarchio.

Structural Explorations of NCp7-Nucleic Acid Complexes Give Keys to Decipher the Binding Process.

A comprehensive view of all the structural aspects related to NCp7 is essential to understand how this protein, crucial in many steps of the HIV-1 cycle, binds and anneals nucleic acids (NAs), mainly thanks to two zinc fingers, ZF1 and ZF2. Here, we inspected the structural properties of the available experimental models of NCp7 bound to either DNA or RNA molecules, or free of ligand. Our analyses included the characterization of the relative positioning of ZF1 and ZF2, accessibility measurements and the exhaustive, quantitative mapping of the contacts between amino acids and nucleotides by a recent tessellation method, VLDM. This approach unveiled the intimate connection between NA binding process and the conformations explored by the free protein. It also provided new insights into the functional specializations of ZF1 and ZF2. The larger accessibility of ZF2 in free NCp7 and the consistency of the ZF2/NA interface in different models and conditions give ZF2 the lead of the binding process. ZF1 contributes to stabilize the complexes through various organizations of the ZF1/NA interface. This work outcome is a global binding scheme of NCp7 to DNA and RNA, and an example of how protein-NA complexes are stabilized.