De novo molecular design with deep molecular generative models for PPI inhibitors.

We construct a protein-protein interaction (PPI) targeted drug-likeness dataset and propose a deep molecular generative framework to generate novel drug-likeness molecules from the features of the seed compounds. This framework gains inspiration from published molecular generative models, uses the key features associated with PPI inhibitors as input and develops deep molecular generative models for de novo molecular design of PPI inhibitors. For the first time, quantitative estimation index for compounds targeting PPI was applied to the evaluation of the molecular generation model for de novo design of PPI-targeted compounds. Our results estimated that the generated molecules had better PPI-targeted drug-likeness and drug-likeness. Additionally, our model also exhibits comparable performance to other several state-of-the-art molecule generation models. The generated molecules share chemical space with iPPI-DB inhibitors as demonstrated by chemical space analysis. The peptide characterization-oriented design of PPI inhibitors and the ligand-based design of PPI inhibitors are explored. Finally, we recommend that this framework will be an important step forward for the de novo design of PPI-targeted therapeutics.

Transformer-Based Molecular Generative Model for Antiviral Drug Design.

Since the Simplified Molecular Input Line Entry System (SMILES) is oriented to the atomic-level representation of molecules and is not friendly in terms of human readability and editable, however, IUPAC is the closest to natural language and is very friendly in terms of human-oriented readability and performing molecular editing, we can manipulate IUPAC to generate corresponding new molecules and produce programming-friendly molecular forms of SMILES. In addition, antiviral drug design, especially analogue-based drug design, is also more appropriate to edit and design directly from the functional group level of IUPAC than from the atomic level of SMILES, since designing analogues involves altering the R group only, which is closer to the knowledge-based molecular design of a chemist. Herein, we present a novel data-driven self-supervised pretraining generative model called "TransAntivirus" to make select-and-replace edits and convert organic molecules into the desired properties for design of antiviral candidate analogues. The results indicated that TransAntivirus is significantly superior to the control models in terms of novelty, validity, uniqueness, and diversity. TransAntivirus showed excellent performance in the design and optimization of nucleoside and non-nucleoside analogues by chemical space analysis and property prediction analysis. Furthermore, to validate the applicability of TransAntivirus in the design of antiviral drugs, we conducted two case studies on the design of nucleoside analogues and non-nucleoside analogues and screened four candidate lead compounds against anticoronavirus disease (COVID-19). Finally, we recommend this framework for accelerating antiviral drug discovery.

Bergamottin and PAP-1 Induced ACE2 Degradation to Alleviate Infection of SARS-CoV-2.

Angiotensin-converting enzyme 2 (ACE2), a functional receptor for SARS-CoV, now appears likely to mediate 2019-nCoV entry into human cells. However, inhibitors such as PAP-1 and bergamottin have been discovered; both of them can preferentially bind to ACE2, prevent RBD Spike S protein from binding to ACE2, and reduce the binding sites for RBD Spike S protein. In addition, we investigated the binding energy of PAP-1 and bergamottin with ACE2 through molecular docking with bio-layer interferometry (BLI) and found relatively high binding affinity (KD = 48.5 nM, 53.1 nM) between the PAP-1 and bergamottin groups. In addition, the nanomolar fraction had no effect on growth of the AT-II cell, but 150 µM PAP-1 and 75 µM bergamottin inhibited the proliferation of AT-II cells in vitro by 75% and 68%, respectively. Meanwhile, they significantly reduced ACE2 mRNA and proteins by 67%, 58% and 55%, 41%, respectively. These results indicate that psoralen compounds PAP-1 and bergamottin binding to ACE2 protein could be further developed in the fight against COVID-19 infection during the current pandemic. However, attention should be paid to the damage to human alveolar type II epithelial cells.

In Silico Study Identified Methotrexate Analog as Potential Inhibitor of Drug Resistant Human Dihydrofolate Reductase for Cancer Therapeutics.

Drug resistance is a core issue in cancer chemotherapy. A known folate antagonist, methotrexate (MTX) inhibits human dihydrofolate reductase (hDHFR), the enzyme responsible for the catalysis of 7,8-dihydrofolate reduction to 5,6,7,8-tetrahydrofolate, in biosynthesis and cell proliferation. Structural change in the DHFR enzyme is a significant cause of resistance and the subsequent loss of MTX. In the current study, wild type hDHFR and double mutant (engineered variant) F31R/Q35E (PDB ID: 3EIG) were subject to computational study. Structure-based pharmacophore modeling was carried out for wild type (WT) and mutant (MT) (variant F31R/Q35E) hDHFR structures by generating ten models for each. Two pharmacophore models, WT-pharma and MT-pharma, were selected for further computations, and showed excellent ROC curve quality. Additionally, the selected pharmacophore models were validated by the Guner-Henry decoy test method, which yielded high goodness of fit for WT-hDHFR and MT-hDHFR. Using a SMILES string of MTX in ZINC15 with the selections of 'clean', in vitro and in vivo options, 32 MTX-analogs were obtained. Eight analogs were filtered out due to their drug-like properties by applying absorption, distribution, metabolism, excretion, and toxicity (ADMET) assessment tests and Lipinski's Rule of five. WT-pharma and MT-pharma were further employed as a 3D query in virtual screening with drug-like MTX analogs. Subsequently, seven screening hits along with a reference compound (MTX) were subjected to molecular docking in the active site of WT- and MT-hDHFR. Through a clustering analysis and examination of protein-ligand interactions, one compound was found with a ChemPLP fitness score greater than that of MTX (reference compound). Finally, a simulation of molecular dynamics (MD) identified an MTX analog which exhibited strong affinity for WT- and MT-hDHFR, with stable RMSD, hydrogen bonds (H-bonds) in the binding site and the lowest MM/PBSA binding free energy. In conclusion, we report on an MTX analog which is capable of inhibiting hDHFR in wild type form, as well as in cases where the enzyme acquires resistance to drugs during chemotherapy treatment.

Effectiveness of occupational therapy in improving activities of daily living performance in complete cervical tetraplegic patients; A quasi experimental study.

OBJECTIVE: To determine the effectiveness of Occupational therapy (OT) in improving activities of daily living performance in complete cervical tetraplegic patients. METHODS: A quasi experimental study was conducted at Paraplegic Center Peshawar from May 2018 to March 2019. Seventy two spinal cord injury patients with complete cervical tetraplegia having age 18-60 years were included in the study using non probability convenience sampling technique. A trained Occupational therapist conducted two occupational therapy sessions per day, three times a week on alternative days for a period of six weeks. Self-care portion of Spinal cord injury independence measure (SCIM) was used to collect pre and post data. Data was analyzed using SPSS version 20. RESULTS: Mean age of the participants was 30.21±13.52.Majority of the participants were (n= 61, 84.7%) male while remaining 11 (15.3%) participants were female. Pre self-care total score was 0.39±0.987 and post self-care total score was 7.17±5.536. There was significant differences (P value <0.05) between pre and post scores of feeding, upper & lower body bathing, upper & lower body dressing, grooming and total self-care scores. CONCLUSION: Occupational therapy significantly improves activities of daily living performance in complete cervical tetraplegic spinal cord injury patients.

Correction to: Exploration for novel inhibitors showing back-to-front approach against VEGFR-2 kinase domain (4AG8) employing molecular docking mechanism and molecular dynamics simulations.

Following publication of the original article [1], the authors reported errors in Figure 3, Figure 14a, Figure 18, Figure 19b, Additional file 3 and Additional file 7.

Discovery of Novel Acetylcholinesterase Inhibitors as Potential Candidates for the Treatment of Alzheimer's Disease.

Acetylcholinesterase (AChE) catalyzes the hydrolysis of neurotransmitter acetylcholine to acetate and choline in a synaptic cleft. Deficits in cholinergic neurotransmitters are linked closely with the progression of Alzheimer's disease (AD), which is a neurodegenerative disorder characterized by memory impairment, and a disordered cognitive function. Since the previously approved AChE inhibitors, donepezil (Aricept), galantamine (Reminyl), and rivastigmine (Exelon), have side effects and several studies are being carried out out to develop novel AD drugs, we have applied a three-dimensional quantitative structure-activity relationship (3D QSAR) and structure-based pharmacophore modeling methodologies to identify potential candidate inhibitors against AChE. Herein, 3D QSAR and structure-based pharmacophore models were built from known inhibitors and crystal structures of human AChE in complex with donepezil, galantamine, huperzine A, and huprine W, respectively. The generated models were used as 3D queries to screen new scaffolds from various chemical databases. The hit compounds obtained from the virtual screening were subjected to an assessment of drug-like properties, followed by molecular docking. The final hit compounds were selected based on binding modes and molecular interactions in the active site of the enzyme. Furthermore, molecular dynamics simulations for AChE in complex with the final hits were performed to evaluate that they maintained stable interactions with the active site residues. The binding free energies of the final hits were also calculated using molecular mechanics/Poisson-Boltzmann surface area method. Taken together, we proposed that these hits can be promising candidates for anti-AD drugs.

Spinal cord injury due to fall from electricity poles after electrocution.

OBJECTIVE: The objective of this study was to report epidemiology, complications and rehabilitation outcomes of patients who sustained spinal cord injury (SCI) due to fall from electricity poles after electrocution. METHODS: A prospective observational study was conducted in which patients admitted to Paraplegic Centre Peshawar from July 2016 to July 2018 who sustained SCI due to fall from electricity poles after electrocution were included. Of total 852 patients, 39 (4.58%) sustained SCI due to fall from electricity poles after electrocution. Two patients were excluded and data of 37 patients was analyzed. RESULTS: The mean age of the participants was 35.03±13.47 years. Twenty-two (59.4%) patients had associated burns on different parts of body. Twenty-seven (72.9%) had pressure ulcers, 31 (83.8%) had spasticity, 18 (48.6%) had neuropathic pain and 2 (5.4%) had limb amputations due to injury. Mean Spinal cord injury independence measure score at the time of discharge was 53.4±5.7. CONCLUSION: SCI due to fall from electricity poles after electrocution is rare however combined effect of injury by electricity along with fall from electricity poles are associated with severe complications. Rehabilitation outcomes in these patients are also minimal.

Employment status of person with disability in Government Departments in Khyber Pakhtunkhwa Pakistan.

OBJECTIVE: The objective of the study was to determine whether anticipated number of person with disabilities was employed in different government departments of Khyber Pakhtunkhwa (KPK), Pakistan. METHODS: Using across sectional survey, data from 16 different departments of provincial government of KPK was collected by volunteers of 'Friends of Paraplegics. RESULTS: Out of total 1, 71,137 Govt. employees, only 1151 (0.67%) were person with disabilities. None of the included departments fulfilled 2% allocated job quota for person with disabilities. Majority of the employees included in study were from Elementary & Secondary Education Department (n=140345) and Agriculture, Livestock & Cooperation Department (n=14315). The number of person with disabilities in these departments were 960 (0.68%) and 68 (0.48%) respectively. The highest percentage of person with disabilities were working in Higher Education Archives & Libraries Department (1.65%)followed by Law, Parliamentary Affairs & Human Rights Department (1.42%), Planning & Development Department (1.39%) and Administration & Establishment Department (1.16%). CONCLUSION: It is concluded that a small number of person with disabilities are employed in different Govt. Departments. Moreover, these departments has not ensured providing 2% job quota for person with disabilities.

Biochemical and Structural Basis of Triclosan Resistance in a Novel Enoyl-Acyl Carrier Protein Reductase.

Enoyl-acyl carrier protein reductases (ENR), such as FabI, FabL, FabK, and FabV, catalyze the last reduction step in bacterial type II fatty acid biosynthesis. Previously, we reported metagenome-derived ENR homologs resistant to triclosan (TCL) and highly similar to 7-α hydroxysteroid dehydrogenase (7-AHSDH). These homologs are commonly found in Epsilonproteobacteria, a class that contains several human-pathogenic bacteria, including the genera Helicobacter and Campylobacter Here we report the biochemical and predicted structural basis of TCL resistance in a novel 7-AHSDH-like ENR. The purified protein exhibited NADPH-dependent ENR activity but no 7-AHSDH activity, despite its high homology with 7-AHSDH (69% to 96%). Because this ENR was similar to FabL (41%), we propose that this metagenome-derived ENR be referred to as FabL2. Homology modeling, molecular docking, and molecular dynamic simulation analyses revealed the presence of an extrapolated six-amino-acid loop specific to FabL2 ENR, which prevented the entry of TCL into the active site of FabL2 and was likely responsible for TCL resistance. Elimination of this extrapolated loop via site-directed mutagenesis resulted in the complete loss of TCL resistance but not enzyme activity. Phylogenetic analysis suggested that FabL, FabL2, and 7-AHSDH diverged from a common short-chain dehydrogenase reductase family. This study is the first to report the role of the extrapolated loop of FabL2-type ENRs in conferring TCL resistance. Thus, the FabL2 ENR represents a new drug target specific for pathogenic Epsilonproteobacteria.

Exploration for novel inhibitors showing back-to-front approach against VEGFR-2 kinase domain (4AG8) employing molecular docking mechanism and molecular dynamics simulations.

BACKGROUND: Angiogenesis is a process of formation of new blood vessels and is an important criteria demonstrated by cancer cells. Over a period of time, these cancer cells infect the other parts of the healthy body by a process called progression. The objective of the present article is to identify a drug molecule that inhibits angiogenesis and progression. METHODS: In this pursuit, ligand based pharmacophore virtual screening was employed, generating a pharmacophore model, Hypo1 consisting of four features. Furthermore, this Hypo1 was validated recruiting, Fischer's randomization, test set method and decoy set method. Later, Hypo1 was allowed to screen databases such as Maybridge, Chembridge, Asinex and NCI and were further filtered by ADMET filters and Lipinski's Rule of Five. A total of 699 molecules that passed the above criteria, were challenged against 4AG8, an angiogenic drug target employing GOLD v5.2.2. RESULTS: The results rendered by molecular docking, DFT and the MD simulations showed only one molecule (Hit) obeyed the back-to-front approach. This molecule displayed a dock score of 89.77, involving the amino acids, Glu885 and Cys919, Asp1046, respectively and additionally formed several important hydrophobic interactions. Furthermore, the identified lead molecule showed interactions with key residues when challenged with CDK2 protein, 1URW. CONCLUSION: The lead candidate showed several interactions with the crucial residues of both the targets. Furthermore, we speculate that the residues Cys919 and Leu83 are important in the development of dual inhibitor. Therefore, the identified lead molecule can act as a potential inhibitor for angiogenesis and progression.

Ginger (Zingiber officinale) phytochemicals-gingerenone-A and shogaol inhibit SaHPPK: molecular docking, molecular dynamics simulations and in vitro approaches.

BACKGROUND: Antibiotic resistance is a defense mechanism, harbored by pathogens to survive under unfavorable conditions. Among several antibiotic resistant microbial consortium, Staphylococcus aureus is one of the most havoc microorganisms. Staphylococcus aureus encodes a unique enzyme 6-hydroxymethyl-7,8-dihydropterin pyrophosphokinase (SaHPPK), against which, none of existing antibiotics have been reported. METHODS: Computational approaches have been instrumental in designing and discovering new drugs for several diseases. The present study highlights the impact of ginger phytochemicals on Staphylococcus aureus SaHPPK. Herein, we have retrieved eight ginger phytochemicals from published literature and investigated their inhibitory interactions with SaHPPK. To authenticate our work, the investigation proceeds considering the known antibiotics alongside the phytochemicals. Molecular docking was performed employing GOLD and CDOCKER. The compounds with the highest dock score from both the docking programmes were tested for their inhibitory capability in vitro. The binding conformations that were seated within the binding pocket showing strong interactions with the active sites residues rendered by highest dock score were forwarded towards the molecular dynamic (MD) simulation analysis. RESULTS: Based on molecular dock scores, molecular interaction with catalytic active residues and MD simulations studies, two ginger phytochemicals, gingerenone-A and shogaol have been proposed as candidate inhibitors against Staphylococcus aureus. They have demonstrated higher dock scores than the known antibiotics and have represented interactions with the key residues within the active site. Furthermore, these compounds have rendered considerable inhibitory activity when tested in vitro. Additionally, their superiority was corroborated by stable MD results conducted for 100 ns employing GROMACS package. CONCLUSIONS: Finally, we suggest that gingerenone-A and shogaol may either be potential SaHPPK inhibitors or can be used as fundamental platforms for novel SaHPPK inhibitor development.

Discovery of Non-Peptidic Compounds against Chagas Disease Applying Pharmacophore Guided Molecular Modelling Approaches.

Chagas disease is one of the primary causes of heart diseases accounting to 50,000 lives annually and is listed as the neglected tropical disease. Because the currently available therapies have greater toxic effects with higher resistance, there is a dire need to develop new drugs to combat the disease. In this pursuit, the 3D QSAR ligand-pharmacophore (pharm 1) and receptor-based pharmacophore (pharm 2) search was initiated to retrieve the candidate compounds from universal natural compounds database. The validated models were allowed to map the universal natural compounds database. The obtained lead candidates were subjected to molecular docking against cysteine protease (PDB code: 1ME3) employing -Cdocker available on the discovery studio. Subsequently, two Hits have satisfied the selection criteria and were escalated to molecular dynamics simulation and binding free energy calculations. These Hits have demonstrated higher dock scores, displayed interactions with the key residues portraying an ideal binding mode complemented by mapping to all the features of pharm 1 and pharm 2. Additionally, they have rendered stable root mean square deviation (RMSD) and potential energy profiles illuminating their potentiality as the prospective antichagastic agents. The study further demonstrates the mechanism of inhibition by tetrad residues compromising of Gly23 and Asn70 holding the ligand at each ends and the residues Gly65 and Gly160 clamping the Hits at the center. The notable feature is that the Hits lie in close proximity with the residues Glu66 and Leu67, accommodating within the S1, S2 and S3 subsites. Considering these findings, the study suggests that the Hits may be regarded as effective therapeutics against Chagas disease.

Effectiveness of transcutaneous electrical nerve stimulation in management of neuropathic pain in patients with post traumatic incomplete spinal cord injuries.

OBJECTIVE: To determine the effectiveness of Transcutaneous Electrical Nerve Stimulation (TENS) in management of neuropathic pain in post-traumatic incomplete spinal cord injury patients. METHODS: A quasi-experimental study was conducted at from January 2017 to June 2017 at Paraplegic Center Hayatabad, Peshawar. Total 60 incomplete spinal cord injured patients with diagnosis of neuropathic pain were subjected to high frequency TENS of 80 HZ. One session was of 45 minutes while there were two sessions per day. TENS was applied for four days in a week and all patients were followed for eight week duration. Pain intensity was measured by using VAS (Visual analogue scale). RESULTS: Mean pain intensity on VAS at baseline was 6.45 which was decreased to 4.77 post intervention at day-1 while it was decreased to 3.48 at day-4 of week one. After application of TENS for 8 weeks, mean pain intensity was decreased to 2.80 ± 1.74. During the consecutive sessions of the TENS application, the pain intensity decreases in a linear fashion and there were significant difference (p<0.05) between pre and post treatment sessions. CONCLUSION: TENS is useful and safe adjuvant in spinal cord injury patients for the management of neuropathic pain.

Corrigendum: Exploring the molecular mechanism of hepatitis virus inducing hepatocellular carcinoma by microarray data and immune infiltrates analysis.

[This corrects the article DOI: 10.3389/fimmu.2022.1032819.].

Application of a deep generative model produces novel and diverse functional peptides against microbial resistance.

Antimicrobial resistance could threaten millions of lives in the immediate future. Antimicrobial peptides (AMPs) are an alternative to conventional antibiotics practice against infectious diseases. Despite the potential contribution of AMPs to the antibiotic's world, their development and optimization have encountered serious challenges. Cutting-edge methods with novel and improved selectivity toward resistant targets must be established to create AMPs-driven treatments. Here, we present AMPTrans-lstm, a deep generative network-based approach for the rational design of AMPs. The AMPTrans-lstm pipeline involves pre-training, transfer learning, and module identification. The AMPTrans-lstm model has two sub-models, namely, (long short-term memory) LSTM sampler and Transformer converter, which can be connected in series to make full use of the stability of LSTM and the novelty of Transformer model. These elements could generate AMPs candidates, which can then be tailored for specific applications. By analyzing the generated sequence and trained AMPs, we prove that AMPTrans-lstm can expand the design space of the trained AMPs and produce reasonable and brand-new AMPs sequences. AMPTrans-lstm can generate functional peptides for antimicrobial resistance with good novelty and diversity, so it is an efficient AMPs design tool.

Structure based virtual screening and molecular simulation study of FDA-approved drugs to inhibit human HDAC6 and VISTA as dual cancer immunotherapy.

Cancer immunotherapy has significantly contributed to the treatment of various types of cancers mainly by targeting immune checkpoint inhibitors (ICI). Among them, V-domain immunoglobulin suppressor of T cell activation (VISTA) has been explored as a promising therapeutic target. Besides, histone deacetylase 6 (HDAC6) has been demonstrated to be efficacious target for several cancers. The current theoretical work was performed to explore the virtual repurposing of the FDA-approved drugs as inhibitors against these two (VISTA and HDAC6) cancers therapeutic targets. The crystal structure of the two proteins were downloaded from PDB and subjected to virtual screening by DrugRep webserver while using FDA-approved drugs library as ligands database. Our study revealed that Oxymorphone and Bexarotene are the top-ranked inhibitors of VISTA and HDAC6, respectively. The docking score of Bexarotene was predicted as - 10 kcal/mol while the docking score of Oxymorphone was predicted as - 6.2 kcal/mol. Furthermore, a total of 100 ns MD simulation revealed that the two drugs Oxymorphone and Bexarotene formed stable complexes with VISTA and HDAC6 drug targets. As compared to the standard drug the two drugs Oxymorphone and Bexarotene revealed great stability during the whole 100 ns MD simulation. The binding free energy calculation further supported the Root Mean Square Deviation (RMSD) result which stated that as compared to the ref/HDAC6 (- 18.0253 ± 2.6218) the binding free energy score of the Bexarotene/HDAC6 was good (- 51.9698 ± 3.1572 kcal/mol). The binding free energy score of Oxymorphone/VISTA and Ref/VISTA were calculated as - 36.8323 ± 3.4565, and - 21.5611 ± 4.8581 respectively. In conclusion, the two drugs deserve further consideration as cancer treatment option.

Exploring the molecular mechanism of hepatitis virus inducing hepatocellular carcinoma by microarray data and immune infiltrates analysis.

The number of new cases of hepatocellular carcinoma (HCC) worldwide reached 910,000, ranking the sixth, 80% HCC is associated with viruses, so exploring the molecular mechanism of viral carcinogenicity is imperative. The study showed that both HBV and HCV associated HCC and non-viral HCC have the same molecular phenotype (low gene expression and inhibition of immune pathways), but in the tumor immune micro-environment, there is excessive M2-type macrophage polarization in virus-associated hepatocellular carcinoma. To address this phenomenon, the data sets were analyzed and identified five hub genes (POLR2A, POLR2B, RPL5, RPS6, RPL23A) involved in viral gene expression and associated with PI3K-Akt-mTOR pathway activation by six algorithms. In addition, numerous studies have reported that M2-type macrophages participate in the hepatic fibro-pathological process of the development of HCC and are regulated by the PI3K-Akt-mTOR pathway. On this basis, the study showed that hepatitis virus causes abnormal expression of hub genes, leading to the activation of the pathway, which in turn promote the differentiation of M2-type macrophages and eventually promote the formation of liver fibrosis, leading to the occurrence of HCC. In addition, these hub genes are regulated by transcription factors and m6A enzyme, and have good prognosis and diagnostic value. With regard to drug reuse, the results suggest that patients with virus-related HCC for whom Cytidine triphosphate disodium salt and Guanosine-5'-Triphosphate are used as supplementary therapy, and may have a better prognosis. In conclusion, the study has identified novel molecules that are carcinogenic to hepatitis viruses and are expected to serve as molecular markers and targets for diagnosis and treatment.

3D-QSAR-Based Pharmacophore Modeling, Virtual Screening, and Molecular Dynamics Simulations for the Identification of Spleen Tyrosine Kinase Inhibitors.

Spleen tyrosine kinase (SYK) is an essential mediator of immune cell signaling and has been anticipated as a therapeutic target for autoimmune diseases, notably rheumatoid arthritis, allergic rhinitis, asthma, and cancers. Significant attempts have been undertaken in recent years to develop SYK inhibitors; however, limited success has been achieved due to poor pharmacokinetics and adverse effects of inhibitors. The primary goal of this research was to identify potential inhibitors having high affinity, selectivity based on key molecular interactions, and good drug-like properties than the available inhibitor, fostamatinib. In this study, a 3D-QSAR model was built for SYK based on known inhibitor IC50 values. The best pharmacophore model was then used as a 3D query to screen a drug-like database to retrieve hits with novel chemical scaffolds. The obtained compounds were subjected to binding affinity prediction using the molecular docking approach, and the results were subsequently validated using molecular dynamics (MD) simulations. The simulated compounds were ranked according to binding free energy (ΔG), and the binding affinity was compared with fostamatinib. The binding mode analysis of selected compounds revealed that the hit compounds form hydrogen bond interactions with hinge region residue Ala451, glycine-rich loop residue Lys375, Ser379, and DFG motif Asp512. Identified hits were also observed to form a desirable interaction with Pro455 and Asn457, the rare feature observed in SYK inhibitors. Therefore, we argue that identified hit compounds ZINC98363745, ZINC98365358, ZINC98364133, and ZINC08789982 may help in drug design against SYK.

Development of an innovative data-driven system to generate descriptive prediction equation of dielectric constant on small sample sets.

Dielectric constant (DC, ε) is a fundamental parameter in material sciences to measure polarizability of the system. In industrial processes, its value is an imperative indicator, which demonstrates the dielectric property of material and compiles information including separation information, chemical equilibrium, chemical reactivity analysis, and solubility modeling. Since, the available ε-prediction models are fairly primitive and frequently suffer from serious failures especially when deals with strong polar compounds. Therefore, we have developed a novel data-driven system to improve the efficiency and wide-range applicability of ε using in material sciences. This innovative scheme adopts the correlation distance and genetic algorithm to discriminate features' combination and avoid overfitting. Herein, the prediction output of the single ML model as a coding to estimate the target value by simulating the layer-by-layer extraction in deep learning, and enabling instant search for the optimal combination of features is recruited. Our model established an improved correlation value of 0.956 with target as compared to the previously available best traditional ML result of 0.877. Our framework established a profound improvement, especially for material systems possessing ε value >50. In terms of interpretability, we have derived a conceptual computational equation from a minimum generating tree. Our innovative data-driven system is preferentially superior over other methods due to its application for the prediction of dielectric constants as well as for the prediction of overall micro and macro-properties of any multi-components complex.