Distinguishing drug/non-drug-like small molecules in drug discovery using deep belief network

Hooshmand, Seyed Aghil; Jamalkandi, Sadegh Azimzadeh; Alavi, Seyed Mehdi; Masoudi‐Nejad, Ali

doi:10.1007/s11030-020-10065-7

Cited by 18 publications

(13 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DNNs have been established as a cutting‐edge strategy for various types of data, namely text, voice, image and even biological data 182 . Very recently, a new multimodality deep learning technique was used in COVID‐19 drug repurposing 183 and drug discovery 184 …”

Section: Computational Approaches For Gene Delivery: Room For Improve...mentioning

confidence: 99%

“…182 Very recently, a new multimodality deep learning technique was used in COVID-19 drug repurposing 183 and drug discovery. 184 Recently, a deep learning long short-term memory neural network model was reported to predict anticancer peptides, which was named ACP-DL. 185 The proposed ACP-DL is more appropriate than prevailing machine-learning models for an anticancer prediction mission with a critical comparison.…”

Section: Computational Approaches For Gene Delivery: Room For Improve...mentioning

confidence: 99%

See 1 more Smart Citation

Histidine‐enhanced gene delivery systems: The state of the art

Hooshmand

Sabet

Hasanzadeh

et al. 2022

The Journal of Gene Medicine

Self Cite

View full text Add to dashboard Cite

Gene therapy has emerged as a promising tool for treating different intractable diseases, particularly cancer or even viral diseases such as COVID-19 (coronavirus disease 2019). In this context, various non-viral gene carriers are being explored to transfer DNA or RNA sequences into target cells. Here, we review the applications of the naturally occurring amino acid histidine in the delivery of nucleic acids into cells.The biocompatibility of histidine-enhanced gene delivery systems has encouraged their wider use in gene therapy. Histidine-based gene carriers can involve the modification of peptides, dendrimers, lipids or nanocomposites. Several linear polymers, such as polyethylenimine, poly-L-lysine (synthetic) or dextran and chitosan (natural), have been conjugated with histidine residues to form complexes with nucleic acids for intracellular delivery. The challenges, opportunities and future research trends of histidine-based gene deliveries are investigated.

show abstract

Section: Computational Approaches For Gene Delivery: Room For Improve...mentioning

confidence: 99%

Section: Computational Approaches For Gene Delivery: Room For Improve...mentioning

confidence: 99%

Histidine‐enhanced gene delivery systems: The state of the art

Hooshmand

Sabet

Hasanzadeh

et al. 2022

The Journal of Gene Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…MACC fingerprint, which is a static binary of each molecule, was also determined using the PADEL package. MACC fingerprint may be more useful than the other static fingerprints such as PubChem, KRFP, and some dynamic fingerprints like ECFP [13]. The columns with zero variance were removed too.…”

Section: Preparation Of Datasetsmentioning

confidence: 99%

“…Considering the spread of SARS-CoV-2 at lightning speed, there is an urgent need to find promising drugs to inhibit the virus from spreading and control COVID-19. As part of our ongoing program associated with developing computational methods as well as drug repurposing [3,6,13], we aimed to introduce a multimodal RBM approach, named MM-RBM, to find the drugs that are very similar to the four above-mentioned drugs tested on COVID-19. To this end, we used the data on the chemical structures of medicines as well as DEGs identified after using drugs.…”

Section: Introductionmentioning

confidence: 99%

A multimodal deep learning-based drug repurposing approach for treatment of COVID-19

et al. 2020

Self Cite

View full text Add to dashboard Cite

Recently, various computational methods have been proposed to find new therapeutic applications of the existing drugs. The Multimodal Restricted Boltzmann Machine approach (MM-RBM), which has the capability to connect the information about the multiple modalities, can be applied to the problem of drug repurposing. The present study utilized MM-RBM to combine two types of data, including the chemical structures data of small molecules and differentially expressed genes as well as small molecules perturbations. In the proposed method, two separate RBMs were applied to find out the features and the specific probability distribution of each datum (modality). Besides, RBM was used to integrate the discovered features, resulting in the identification of the probability distribution of the combined data. The results demonstrated the significance of the clusters acquired by our model. These clusters were used to discover the medicines which were remarkably similar to the proposed medications to treat COVID-19. Moreover, the chemical structures of some small molecules as well as dysregulated genes' effect led us to suggest using these molecules to treat COVID-19. The results also showed that the proposed method might prove useful in detecting the highly promising remedies for COVID-19 with minimum side effects. All the source codes are accessible using https ://githu b.com/LBBSo ft/Multi modal-Drug-Repur posin g.git

show abstract

“…In this regard, most deep learning approaches for drug-likeness adopted a two-class classication (TCC) method, which aims to classify query molecules into drug or non-drug. 29,33,34 The TCC methods inevitably need both drug molecules for a positive set and non-drug molecules for a negative set. The positive set can readily be prepared with the known drug molecules.…”

Section: Introductionmentioning

confidence: 99%