SAnDReS 2.0: Development of machine-learning models to explore the scoring function space.

Classical scoring functions may exhibit low accuracy in determining ligand binding affinity for proteins. The availability of both protein-ligand structures and affinity data make it possible to develop machine-learning models focused on specific protein systems with superior predictive performance. Here, we report a new methodology named SAnDReS that combines AutoDock Vina 1.2 with 54 regression methods available in Scikit-Learn to calculate binding affinity based on protein-ligand structures. This approach allows exploration of the scoring function space. SAnDReS generates machine-learning models based on crystal, docked, and AlphaFold-generated structures. As a proof of concept, we examine the performance of SAnDReS-generated models in three case studies. For all three cases, our models outperformed classical scoring functions. Also, SAnDReS-generated models showed predictive performance close to or better than other machine-learning models such as KDEEP, CSM-lig, and ΔVinaRF20. SAnDReS 2.0 is available to download at https://github.com/azevedolab/sandres.

Exploring Scoring Function Space: Developing Computational Models for Drug Discovery.

BACKGROUND: The idea of scoring function space established a systems-level approach to address the development of models to predict the affinity of drug molecules by those interested in drug discovery. OBJECTIVE: Our goal here is to review the concept of scoring function space and how to explore it to develop machine learning models to address protein-ligand binding affinity. METHOD: We searched the articles available in PubMed related to the scoring function space. We also utilized crystallographic structures found in the protein data bank (PDB) to represent the protein space. RESULTS: The application of systems-level approaches to address receptor-drug interactions allows us to have a holistic view of the process of drug discovery. The scoring function space adds flexibility to the process since it makes it possible to see drug discovery as a relationship involving mathematical spaces. CONCLUSION: The application of the concept of scoring function space has provided us with an integrated view of drug discovery methods. This concept is useful during drug discovery, where we see the process as a computational search of the scoring function space to find an adequate model to predict receptor-drug binding affinity.

Identification of Molecular Mechanisms Involved in Viral Infection Progression Based on Text Mining: Case Study for HIV Infection.

Viruses cause various infections that may affect human lifestyle for durations ranging from several days to for many years. Although preventative and therapeutic remedies are available for many viruses, they may still have a profound impact on human life. The human immunodeficiency virus type 1 is the most common cause of HIV infection, which represents one of the most dangerous and complex diseases since it affects the immune system and causes its disruption, leading to secondary complications and negatively influencing health-related quality of life. While highly active antiretroviral therapy may decrease the viral load and the velocity of HIV infection progression, some individual peculiarities may affect viral load control or the progression of T-cell malfunction induced by HIV. Our study is aimed at the text-based identification of molecular mechanisms that may be involved in viral infection progression, using HIV as a case study. Specifically, we identified human proteins and genes which commonly occurred, overexpressed or underexpressed, in the collections of publications relevant to (i) HIV infection progression and (ii) acute and chronic stages of HIV infection. Then, we considered biological processes that are controlled by the identified protein and genes. We verified the impact of the identified molecules in the associated clinical study.

CLC-Pred 2.0: A Freely Available Web Application for In Silico Prediction of Human Cell Line Cytotoxicity and Molecular Mechanisms of Action for Druglike Compounds.

In vitro cell-line cytotoxicity is widely used in the experimental studies of potential antineoplastic agents and evaluation of safety in drug discovery. In silico estimation of cytotoxicity against hundreds of tumor cell lines and dozens of normal cell lines considerably reduces the time and costs of drug development and the assessment of new pharmaceutical agent perspectives. In 2018, we developed the first freely available web application (CLC-Pred) for the qualitative prediction of cytotoxicity against 278 tumor and 27 normal cell lines based on structural formulas of 59,882 compounds. Here, we present a new version of this web application: CLC-Pred 2.0. It also employs the PASS (Prediction of Activity Spectra for Substance) approach based on substructural atom centric MNA descriptors and a Bayesian algorithm. CLC-Pred 2.0 provides three types of qualitative prediction: (1) cytotoxicity against 391 tumor and 47 normal human cell lines based on ChEMBL and PubChem data (128,545 structures) with a mean accuracy of prediction (AUC), calculated by the leave-one-out (LOO CV) and the 20-fold cross-validation (20F CV) procedures, of 0.925 and 0.923, respectively; (2) cytotoxicity against an NCI60 tumor cell-line panel based on the Developmental Therapeutics Program's NCI60 data (22,726 structures) with different thresholds of IG50 data (100, 10 and 1 nM) and a mean accuracy of prediction from 0.870 to 0.945 (LOO CV) and from 0.869 to 0.942 (20F CV), respectively; (3) 2170 molecular mechanisms of actions based on ChEMBL and PubChem data (656,011 structures) with a mean accuracy of prediction 0.979 (LOO CV) and 0.978 (20F CV). Therefore, CLC-Pred 2.0 is a significant extension of the capabilities of the initial web application.

Extraction of Data on Parent Compounds and Their Metabolites from Texts of Scientific Abstracts.

The growing amount of experimental data on chemical objects includes properties of small molecules, results of studies of their interaction with human and animal proteins, and methods of synthesis of organic compounds (OCs). The data obtained can be used to identify the names of OCs automatically, including all possible synonyms and relevant data on the molecular properties and biological activity. Utilization of different synonymic names of chemical compounds allows researchers to increase the completeness of data on their properties available from publications. Enrichment of the data on the names of chemical compounds by information about their possible metabolites can help estimate the biological effects of parent compounds and their metabolites more thoroughly. Therefore, an attempt at automated extraction of the names of parent compounds and their metabolites from the texts is a rather important task. In our study, we aimed at developing a method that provides the extraction of the named entities (NEs) of parent compounds and their metabolites from abstracts of scientific publications. Based on the application of the conditional random fields' algorithm, we extracted the NEs of chemical compounds. We developed a set of rules allowing identification of parent compound NEs and their metabolites in the texts. We evaluated the possibility of extracting the names of potential metabolites based on cosine similarity between strings representing names of parent compounds and all other chemical NEs found in the text. Additionally, we used conditional random fields to fetch the names of parent compounds and their metabolites from the texts based on the corpus of texts labeled manually. Our computational experiments showed that usage of rules in combination with cosine similarity could increase the accuracy of recognition of the names of metabolites compared to the rule-based algorithm and application of a machine-learning algorithm (conditional random fields).

A Computational Approach for the Prediction of Treatment History and the Effectiveness or Failure of Antiretroviral Therapy.

Human Immunodeficiency Virus Type 1 (HIV-1) infection is associated with high mortality if no therapy is provided. Currently, the treatment of an HIV-1 positive patient requires that several drugs should be taken simultaneously. The resistance of the virus to an antiretroviral drug may lead to treatment failure. Our approach focuses on predicting the exposure of a particular viral variant to an antiretroviral drug or drug combination. It also aims at the prediction of drug treatment success or failure. We utilized nucleotide sequences of HIV-1 encoding protease and reverse transcriptase to perform such types of prediction. The PASS (Prediction of Activity Spectra for Substances) algorithm based on the naive Bayesian classifier was used to make a prediction. We calculated the probability of whether a sequence belonged (P1) or did not belong (P0) to the class associated with exposure of the viral sequence to the set of drugs that can be associated with resistance to the set of drugs. The accuracy calculated as the average Area Under the ROC (Receiver Operating Characteristic) Curve (AUC/ROC) for classifying exposure of the sequence to the HIV-1 protease inhibitors was 0.81 (±0.07), and for HIV-1 reverse transcriptase, it was 0.83 (±0.07). To predict cases of treatment effectiveness or failure, we used P1 and P0 values, obtained in PASS, along with the binary vector constructed based on short nucleotide descriptors and the applied random forest classifier. Average AUC/ROC prediction accuracy for the prediction of treatment effectiveness or failure for the combinations of HIV-1 protease inhibitors was 0.82 (±0.06) and of HIV-1 reverse transcriptase was 0.76 (±0.09).

Automated Extraction of Information From Texts of Scientific Publications: Insights Into HIV Treatment Strategies.

Text analysis can help to identify named entities (NEs) of small molecules, proteins, and genes. Such data are very important for the analysis of molecular mechanisms of disease progression and development of new strategies for the treatment of various diseases and pathological conditions. The texts of publications represent a primary source of information, which is especially important to collect the data of the highest quality due to the immediate obtaining information, in comparison with databases. In our study, we aimed at the development and testing of an approach to the named entity recognition in the abstracts of publications. More specifically, we have developed and tested an algorithm based on the conditional random fields, which provides recognition of NEs of (i) genes and proteins and (ii) chemicals. Careful selection of abstracts strictly related to the subject of interest leads to the possibility of extracting the NEs strongly associated with the subject. To test the applicability of our approach, we have applied it for the extraction of (i) potential HIV inhibitors and (ii) a set of proteins and genes potentially responsible for viremic control in HIV-positive patients. The computational experiments performed provide the estimations of evaluating the accuracy of recognition of chemical NEs and proteins (genes). The precision of the chemical NEs recognition is over 0.91; recall is 0.86, and the F1-score (harmonic mean of precision and recall) is 0.89; the precision of recognition of proteins and genes names is over 0.86; recall is 0.83; while F1-score is above 0.85. Evaluation of the algorithm on two case studies related to HIV treatment confirms our suggestion about the possibility of extracting the NEs strongly relevant to (i) HIV inhibitors and (ii) a group of patients i.e., the group of HIV-positive individuals with an ability to maintain an undetectable HIV-1 viral load overtime in the absence of antiretroviral therapy. Analysis of the results obtained provides insights into the function of proteins that can be responsible for viremic control. Our study demonstrated the applicability of the developed approach for the extraction of useful data on HIV treatment.

Data Mining Approach for Extraction of Useful Information About Biologically Active Compounds from Publications.

A lot of high quality data on the biological activity of chemical compounds are required throughout the whole drug discovery process: from development of computational models of the structure-activity relationship to experimental testing of lead compounds and their validation in clinics. Currently, a large amount of such data is available from databases, scientific publications, and patents. Biological data are characterized by incompleteness, uncertainty, and low reproducibility. Despite the existence of free and commercially available databases of biological activities of compounds, they usually lack unambiguous information about peculiarities of biological assays. On the other hand, scientific papers are the primary source of new data disclosed to the scientific community for the first time. In this study, we have developed and validated a data-mining approach for extraction of text fragments containing description of bioassays. We have used this approach to evaluate compounds and their biological activity reported in scientific publications. We have found that categorization of papers into relevant and irrelevant may be performed based on the machine-learning analysis of the abstracts. Text fragments extracted from the full texts of publications allow their further partitioning into several classes according to the peculiarities of bioassays. We demonstrate the applicability of our approach to the comparison of the endpoint values of biological activity and cytotoxicity of reference compounds.

A Computational Approach for the Prediction of HIV Resistance Based on Amino Acid and Nucleotide Descriptors.

The high variability of the human immunodeficiency virus (HIV) is an important cause of HIV resistance to reverse transcriptase and protease inhibitors. There are many variants of HIV type 1 (HIV-1) that can be used to model sequence-resistance relationships. Machine learning methods are widely and successfully used in new drug discovery. An emerging body of data regarding the interactions of small drug-like molecules with their protein targets provides the possibility of building models on "structure-property" relationships and analyzing the performance of various machine-learning techniques. In our research, we analyze several different types of descriptors in order to predict the resistance of HIV reverse transcriptase and protease to the marketed antiretroviral drugs using the Random Forest approach. First, we represented amino acid sequences as a set of short peptide fragments, which included several amino acid residues. Second, we represented nucleotide sequences as a set of fragments, which included several nucleotides. We compared these two approaches using open data from the Stanford HIV Drug Resistance Database. We have determined the factors that modulate the performance of prediction: in particular, we observed that the prediction performance was more sensitive to certain drugs than a type of the descriptor used.