Artificial intelligence (AI) researchers and cheminformatics specialists strive to identify effective drug precursors while optimizing costs and accelerating development processes. Digital molecular representation plays a crucial role in achieving this objective by making molecules machine-readable, thereby enhancing the accuracy of molecular prediction tasks and facilitating evidence-based decision making. This study presents a comprehensive review of small molecular representations and AI-driven drug discovery downstream tasks utilizing these representations. The research methodology begins with the compilation of small molecule databases, followed by an analysis of fundamental molecular representations and the models that learn these representations from initial forms, capturing patterns and salient features across extensive chemical spaces. The study then examines various drug discovery downstream tasks, including drug-target interaction (DTI) prediction, drug-target affinity (DTA) prediction, drug property (DP) prediction, and drug generation, all based on learned representations. The analysis concludes by highlighting challenges and opportunities associated with machine learning (ML) methods for molecular representation and improving downstream task performance. Additionally, the representation of small molecules and AI-based downstream tasks demonstrates significant potential in identifying traditional Chinese medicine (TCM) medicinal substances and facilitating TCM target discovery.
Artificial Intelligence ; Drug Discovery/methods* ; Humans ; Machine Learning ; Medicine, Chinese Traditional ; Small Molecule Libraries/chemistry*

The human pregnane X receptor (hPXR) plays a critical role in the metabolism, transport and clearance of xenobiotics in the liver and intestine. The hPXR can be activated by a structurally diverse of drugs to initiate clinically relevant drug-drug interactions. In this article, in silico investigation was performed on a structurally diverse set of drugs to identify critical structural features greatly related to their agonist activity towards hPXR. Heuristic method (HM)-Best Subset Modeling (BSM) and HM-Polynomial Neural Networks (PNN) were utilized to develop the linear and non-linear quantitative structure-activity relationship models. The applicability domain (AD) of the models was assessed by Williams plot. Statistically reliable models with good predictive power and explain were achieved (for HM-BSM, r (2)=0.881, q LOO (2) =0.797, q EXT (2) =0.674; for HM-PNN, r (2)=0.882, q LOO (2) =0.856, q EXT (2) =0.655). The developed models indicated that molecular aromatic and electric property, molecular weight and complexity may govern agonist activity of a structurally diverse set of drugs to hPXR.
Computer Simulation ; Humans ; Models, Statistical ; Molecular Weight ; Neural Networks (Computer) ; Quantitative Structure-Activity Relationship ; Receptors, Steroid ; agonists ; chemistry ; Small Molecule Libraries ; chemistry ; Static Electricity

Drug Evaluation, Preclinical ; methods ; Humans ; Intracellular Signaling Peptides and Proteins ; metabolism ; Protein Binding ; drug effects ; Small Molecule Libraries ; chemistry ; pharmacology ; Transcription Factors ; metabolism ; Tumor Suppressor Proteins ; metabolism

As an extension of the structure-based drug discovery, fragment-based drug discovery is matured increasingly, and plays an important role in drug development. Fragments in a small library, with lower molecular mass and high "ligand efficiency", are detected by SPR, MS, NMR, X-ray crystallography technologies and other biophysical methods. Then they are considered as starting points for chemical optimization with the guidance of structural biology methods to get good "drug-like" lead and candidate compounds. In this article, we reviewed the current progress of fragment-based drug discovery and detailed a number of examples to illustrate the novel strategies.
Computer-Aided Design ; Crystallography, X-Ray ; Drug Discovery ; methods ; Ligands ; Magnetic Resonance Spectroscopy ; Peptide Fragments ; chemical synthesis ; chemistry ; Protein Conformation ; Small Molecule Libraries ; Surface Plasmon Resonance

The pandemic of human immunodeficiency virus type one (HIV-1), the major etiologic agent of acquired immunodeficiency disease (AIDS), has led to over 33 million people living with the virus, among which 18 million are women and children. Until now, there is neither an effective vaccine nor a therapeutic cure despite over 30 years of efforts. Although the Thai RV144 vaccine trial has demonstrated an efficacy of 31.2%, an effective vaccine will likely rely on a breakthrough discovery of immunogens to elicit broadly reactive neutralizing antibodies, which may take years to achieve. Therefore, there is an urgency of exploring other prophylactic strategies. Recently, antiretroviral treatment as prevention is an exciting area of progress in HIV-1 research. Although effective, the implementation of such strategy faces great financial, political and social challenges in heavily affected regions such as developing countries where drug resistant viruses have already been found with growing incidence. Activating latently infected cells for therapeutic cure is another area of challenge. Since it is greatly difficult to eradicate HIV-1 after the establishment of viral latency, it is necessary to investigate strategies that may close the door to HIV-1. Here, we review studies on non-vaccine strategies in targeting viral entry, which may have critical implications for HIV-1 prevention.
AIDS Vaccines ; immunology ; therapeutic use ; Antibodies, Monoclonal ; immunology ; therapeutic use ; Antibodies, Neutralizing ; immunology ; therapeutic use ; Genetic Therapy ; HIV Infections ; drug therapy ; prevention & control ; HIV-1 ; drug effects ; immunology ; physiology ; Humans ; Peptides ; chemistry ; immunology ; Small Molecule Libraries ; chemistry ; pharmacology ; therapeutic use ; Virus Internalization ; drug effects

The growing demand for new therapeutic strategies in the medical and pharmaceutic fields has resulted in a pressing need for novel druggable targets. Paradoxically, however, the targets of certain drugs that are already widely used in clinical practice have largely not been annotated. Because the pharmacologic effects of a drug can only be appreciated when its interactions with cellular components are clearly delineated, an integrated deconvolution of drug-target interactions for each drug is necessary. The emerging field of chemical proteomics represents a powerful mass spectrometry (MS)-based affinity chromatography approach for identifying proteome-wide small molecule-protein interactions and mapping these interactions to signaling and metabolic pathways. This technique could comprehensively characterize drug targets, profile the toxicity of known drugs, and identify possible off-target activities. With the use of this technique, candidate drug molecules could be optimized, and predictable side effects might consequently be avoided. Herein, we provide a holistic overview of the major chemical proteomic approaches and highlight recent advances in this area as well as its potential applications in drug discovery.
Chromatography, Affinity ; Drug Delivery Systems ; methods ; Drug Design ; Drug Discovery ; methods ; Humans ; Mass Spectrometry ; Proteome ; chemistry ; Proteomics ; methods ; Small Molecule Libraries ; chemistry

Identification of the cellular targets of bioactive compounds is a major challenge and a key issue in chemical biology and drug discovery. As an important technology in functional proteomics, small molecule probes play a pivotal role in the identification of cellular targets of bioactive compounds. This review is intended to introduce the application principles and structural design philosophy of chemical probes for the purpose of mechanistic study. Recent cases of successful application were also discussed to further demonstrate the principles and significance ofbioactive small molecule-based probes.
Biotin ; metabolism ; Drug Delivery Systems ; Drug Design ; Drug Discovery ; methods ; Molecular Probe Techniques ; Molecular Probes ; chemistry ; Photoaffinity Labels ; Proteins ; metabolism ; Proteome ; chemistry ; Proteomics ; methods ; Small Molecule Libraries ; chemistry ; pharmacology

With the development of stem cells and regenerative medicine (treatment of various diseases using stem cells) research, the induction of differentiation of human stem cell technology has also made significant progress. The development of chemical biology offers a variety of small biological molecules for stem cell biology. This review focuses on how small molecule compounds (natural and synthetic) induce differentiation of stem cells.
Animals ; Cell Differentiation ; drug effects ; Drugs, Chinese Herbal ; isolation & purification ; pharmacology ; Embryonic Stem Cells ; cytology ; High-Throughput Screening Assays ; methods ; Humans ; Plants, Medicinal ; chemistry ; Regenerative Medicine ; trends ; Signal Transduction ; Small Molecule Libraries ; chemistry ; pharmacology ; Stem Cells ; cytology ; Wnt Proteins ; metabolism

Medical community and pharmaceutical companies are currently facing a dire need for discovery and identification of new druggable targets. However, the discovery of small-molecule target is an important and arduous task for the biological and medical scientists. To overcome the bottlenecks for target validation, many new approaches are being developed, such as chemical proteomics. As a part of proteomics approaches, chemical proteomics employs small-molecule compounds that can specifically interact with the target protein to interfere with and detect proteomics. Therefore, new target identification, drug discovery and research on multi-target-directed drugs will all be benefited from the further advances in chemical proteomics approaches. Chemical proteomics has the potential to greatly enhance the efficiency of the drug discovery process.
Animals ; Drug Delivery Systems ; methods ; Drug Design ; Drug Discovery ; Drugs, Chinese Herbal ; chemistry ; Humans ; Protein Array Analysis ; Proteomics ; methods ; Small Molecule Libraries ; chemistry

Circular dichroism (CD) is an useful technique for monitoring DNA conformation changes resulting from changes in environmental conditions, such as temperature, ionic strength, and pH, and also for the study of the interaction between DNA and ligands (including small molecules and proteins). CD spectroscopy of DNA arises from the asymmetric backbone sugars and by the helical structures often adopted by nucleic acids. By the interpretation of induced circular dichroism (ICD) of ligand signals resulting from the coupling of electric transition moments of the ligand, DNA bases within the asymmetric DNA environment, ligand-DNA interactions, as well as the DNA-binding mode can be assessed. A number of important conclusions have been reported that related to the observed ICD signals resulting from the interactions between intercalators and groove binders with DNA. If short oligonucleotide sequences are used in the study, sequences-specific of binding also can be deduced. CD determination requires smaller amounts of sample, and not limited by the molecular weight or size and can be performed rapidly; though CD is of low resolution, but it's a complement to NMR and X-ray diffraction methods. This review will introduce the characters of the CD spectra of DNA, and its application to the studies of DNA with small molecules; some progress of the studies in our laboratory will also be discussed. CD is expected to be used as a screening method in seeking more DNA-targeted drugs, such as, antineoplastic, antimicrobial and antiviral drugs.
Animals ; Antineoplastic Agents ; chemistry ; Base Sequence ; Circular Dichroism ; methods ; DNA ; chemistry ; metabolism ; Humans ; Intercalating Agents ; chemistry ; Ligands ; Protein Binding ; Small Molecule Libraries ; pharmacology