Artificial intelligence in small molecule drug discovery from 2018 to 2023: Does it really work?

Utilizing artificial intelligence (AI) in drug design represents an advanced approach for identifying targets and developing new drugs. Integrating AI techniques significantly reduces the workload involved in drug development and enhances the efficiency of early-stage drug discovery. This review aims to present a comprehensive overview of the utilization of AI methods in the field of small drug design, with a specific focus on four key areas: protein structure prediction, molecular virtual screening, molecular design, and absorption, distribution, metabolism, excretion, and toxicity (ADMET) prediction. Additionally, the role and limitations of AI in drug development are explored, and the impact of AI on decision-making processes is studied. It is important to note that while AI can bring numerous benefits to the early stage of drug development, the direction and quality of decision-making should still be emphasized, as AI should be considered as a tool rather than a decisive factor.

Application of Computational Biology and Artificial Intelligence in Drug Design.

Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computational approaches are being widely used to improve the efficacy and effectiveness of drug discovery and pipeline, leading to the approval of plenty of new drugs for marketing. The present review emphasizes on the applications of these indispensable computational approaches in aiding target identification, lead discovery, and lead optimization. Some challenges of using these approaches for drug design are also discussed. Moreover, we propose a methodology for integrating various computational techniques into new drug discovery and design.

Target-driven machine learning-enabled virtual screening (TAME-VS) platform for early-stage hit identification.

High-throughput screening (HTS) methods enable the empirical evaluation of a large scale of compounds and can be augmented by virtual screening (VS) techniques to save time and money by using potential active compounds for experimental testing. Structure-based and ligand-based virtual screening approaches have been extensively studied and applied in drug discovery practice with proven outcomes in advancing candidate molecules. However, the experimental data required for VS are expensive, and hit identification in an effective and efficient manner is particularly challenging during early-stage drug discovery for novel protein targets. Herein, we present our TArget-driven Machine learning-Enabled VS (TAME-VS) platform, which leverages existing chemical databases of bioactive molecules to modularly facilitate hit finding. Our methodology enables bespoke hit identification campaigns through a user-defined protein target. The input target ID is used to perform a homology-based target expansion, followed by compound retrieval from a large compilation of molecules with experimentally validated activity. Compounds are subsequently vectorized and adopted for machine learning (ML) model training. These machine learning models are deployed to perform model-based inferential virtual screening, and compounds are nominated based on predicted activity. Our platform was retrospectively validated across ten diverse protein targets and demonstrated clear predictive power. The implemented methodology provides a flexible and efficient approach that is accessible to a wide range of users. The TAME-VS platform is publicly available at https://github.com/bymgood/Target-driven-ML-enabled-VS to facilitate early-stage hit identification.

Simultaneously autotrophic denitrification and organics degradation in low-strength coal gasification wastewater (LSCGW) treatment via microelectrolysis-triggered Fe(II)/Fe(III) cycle.

The autotrophic iron-depended denitrification (AIDD), triggered by microelectrolysis, was established in the microelectrolysis-assistant up-flow anaerobic sludge blanket (MEA-UASB) with the purpose of low-strength coal gasification wastewater (LSCGW) treatment while control UASB operated in parallel. The results revealed that chemical oxygen demand (COD) removal efficiency and total nitrogen (TN) removal load at optimum current (2.5 A/m3) in MEA-UASB (83.2 ± 2.6% and 0.220 ± 0.010 kg N/m3·d) were 1.42-fold and 1.57-fold higher than those (58.5 ± 2.1% and 0.139 ± 0.011 kg N/m3·d) in UASB, verifying that AIDD and following dissimilatory iron reduction (DIR) process could offer the novel pathway to solve the electron donor-deficient and traditionally denitrification-infeasible problems. High-throughput 16S rRNA gene pyrosequencing shown that iron-oxidizing denitrifiers (Thiobacillus and Acidovorax species) and iron reducing bacteria (Geothrix and Ignavibacterium speices), acted as microbial iron cycle of contributors, were specially enriched at optimum operating condition. Additionally, the activities of microbial electron transfer chain, electron transporters (complex I, II, III and cytochrome c) and abundance of genes encoding important enzymes (narG, nirK/S, norB and nosZ) were remarkably promoted, suggesting that electron transport and consumption capacities were stimulated during denitrification process. This study could shed light on better understanding about microelectrolysis-triggered AIDD for treatment of refractory LSCGW and further widen its application potential in the future.

Exclusive microbially driven autotrophic iron-dependent denitrification in a reactor inoculated with activated sludge.

Autotrophic iron-dependent denitrification (AIDD) is arising as a promising process for nitrogen removal from wastewater with a low carbon to nitrogen ratio. However, there is still a debate about the existence of such a process in activated sludge systems. This work provides evidence and elucidated the feasibility of autotrophic Fe(II)-oxidizing nitrate-reducing culture for nitrogen removal by long-term reactor operation, batch experimental verification, unstructured kinetic modeling and microbial community analyses. A relatively stable nitrate removal rate was achieved coupled with the oxidation of ferrous ions in 3-month operation of reactor. The kinetic modeling suggests that the iron oxidation was a growth-associated process in AIDD. Utilization of extracellular polymeric substances (and/or soluble microbial products) as electron donor for denitrification by heterotrophic denitrifiers was not mainly responsible for nitrogen removal in the reactor. After long-term operation of the reactor with activated sludge as inoculum, the enrichment culture KS-like consortium, dominated by Fe(II) oxidizer, Gallionellaceae, was successfully acclimated for autotrophic Fe(II)-oxidizing nitrate reduction. This work extents our understanding about the existence of such an autotrophic Fe(II)-oxidizing nitrate-reducing culture in both natural and engineered systems, and opens a door for its potential application in wastewater treatment.