Template-based molecular generation offers a promising avenue for drug design by ensuring generated compounds are synthetically accessible through predefined reaction templates and building blocks. In this work, we tackle three core challenges in template-based GFlowNets: (1) minimizing synthesis cost, (2) scaling to large building block libraries, and (3) effectively utilizing small fragment sets. We propose **Recursive Cost Guidance**, a backward policy framework that employs auxiliary machine learning models to approximate synthesis cost and viability. This guidance steers generation toward low-cost synthesis pathways, significantly enhancing cost-efficiency, molecular diversity, and quality, especially when paired with an **Exploitation Penalty** that balances the trade-off between exploration and exploitation. To enhance performance in smaller building block libraries, we develop a **Dynamic Library** mechanism that reuses intermediate high-reward states to construct full synthesis trees. Our approach establishes state-of-the-art results in template-based molecular generation.

Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.

UNLABELLED: The MolClass toolkit and data portal generate computational models from user-defined small molecule datasets based on structural features identified in hit and non-hit molecules in different screens. Each new model is applied to all datasets in the database to classify compound specificity. MolClass thus defines a likelihood value for each compound entry and creates an activity fingerprint across diverse sets of screens. MolClass uses a variety of machine-learning methods to find molecular patterns and can therefore also assign a priori predictions of bioactivities for previously untested molecules. The power of the MolClass resource will grow as a function of the number of screens deposited in the database. AVAILABILITY AND IMPLEMENTATION: The MolClass webportal, software package and source code are freely available for non-commercial use at http://tyerslab.bio.ed.ac.uk/molclass. A MolClass tutorial and a guide on how to build models from datasets can also be found on the web site. MolClass uses the chemistry development kit (CDK), WEKA and MySQL for its core functionality. A REST service is available at http://tyerslab.bio.ed.ac.uk/molclass/api based on the OpenTox API 1.2.

UNLABELLED: The Biological General Repository for Interaction Datasets (BioGRID) representational state transfer (REST) service allows full URL-based access to curated protein and genetic interaction data at the BioGRID database. Appending URL parameters allows filtering of data by various attributes including gene names and identifiers, PubMed ID and evidence type. We also describe two visualization tools that interface with the REST service, the BiogridPlugin2 for Cytoscape and the BioGRID WebGraph. AVAILABILITY AND IMPLEMENTATION: BioGRID data and applications are completely free for commercial and non-commercial use. http://webservice.thebiogrid.org/resources/interactions (REST Service), http://wiki.thebiogrid.org/doku.php/biogridrest(REST Service parameter list and help), http://webservice.thebiogrid.org/resources/application.wadl(REST Service WADL), http://thebiogrid.org/download.php (BiogridPlugin2, v2.1 download), http://wiki.thebiogrid.org/doku.php/biogridplugin2 (BiogridPlugin2 help) and http://tyerslab.bio.ed.ac.uk/tools/BioGRID_webgraph.php(BioGRID WebGraph).

BACKGROUND: The vast amount of data published in the primary biomedical literature represents a challenge for the automated extraction and codification of individual data elements. Biological databases that rely solely on manual extraction by expert curators are unable to comprehensively annotate the information dispersed across the entire biomedical literature. The development of efficient tools based on natural language processing (NLP) systems is essential for the selection of relevant publications, identification of data attributes and partially automated annotation. One of the tasks of the Biocreative 2010 Challenge III was devoted to the evaluation of NLP systems developed to identify articles for curation and extraction of protein-protein interaction (PPI) data. RESULTS: The Biocreative 2010 competition addressed three tasks: gene normalization, article classification and interaction method identification. The BioGRID and MINT protein interaction databases both participated in the generation of the test publication set for gene normalization, annotated the development and test sets for article classification, and curated the test set for interaction method classification. These test datasets served as a gold standard for the evaluation of data extraction algorithms. CONCLUSION: The development of efficient tools for extraction of PPI data is a necessary step to achieve full curation of the biomedical literature. NLP systems can in the first instance facilitate expert curation by refining the list of candidate publications that contain PPI data; more ambitiously, NLP approaches may be able to directly extract relevant information from full-text articles for rapid inspection by expert curators. Close collaboration between biological databases and NLP systems developers will continue to facilitate the long-term objectives of both disciplines.

BACKGROUND: Determining usefulness of biomedical text mining systems requires realistic task definition and data selection criteria without artificial constraints, measuring performance aspects that go beyond traditional metrics. The BioCreative III Protein-Protein Interaction (PPI) tasks were motivated by such considerations, trying to address aspects including how the end user would oversee the generated output, for instance by providing ranked results, textual evidence for human interpretation or measuring time savings by using automated systems. Detecting articles describing complex biological events like PPIs was addressed in the Article Classification Task (ACT), where participants were asked to implement tools for detecting PPI-describing abstracts. Therefore the BCIII-ACT corpus was provided, which includes a training, development and test set of over 12,000 PPI relevant and non-relevant PubMed abstracts labeled manually by domain experts and recording also the human classification times. The Interaction Method Task (IMT) went beyond abstracts and required mining for associations between more than 3,500 full text articles and interaction detection method ontology concepts that had been applied to detect the PPIs reported in them. RESULTS: A total of 11 teams participated in at least one of the two PPI tasks (10 in ACT and 8 in the IMT) and a total of 62 persons were involved either as participants or in preparing data sets/evaluating these tasks. Per task, each team was allowed to submit five runs offline and another five online via the BioCreative Meta-Server. From the 52 runs submitted for the ACT, the highest Matthew's Correlation Coefficient (MCC) score measured was 0.55 at an accuracy of 89% and the best AUC iP/R was 68%. Most ACT teams explored machine learning methods, some of them also used lexical resources like MeSH terms, PSI-MI concepts or particular lists of verbs and nouns, some integrated NER approaches. For the IMT, a total of 42 runs were evaluated by comparing systems against manually generated annotations done by curators from the BioGRID and MINT databases. The highest AUC iP/R achieved by any run was 53%, the best MCC score 0.55. In case of competitive systems with an acceptable recall (above 35%) the macro-averaged precision ranged between 50% and 80%, with a maximum F-Score of 55%. CONCLUSIONS: The results of the ACT task of BioCreative III indicate that classification of large unbalanced article collections reflecting the real class imbalance is still challenging. Nevertheless, text-mining tools that report ranked lists of relevant articles for manual selection can potentially reduce the time needed to identify half of the relevant articles to less than 1/4 of the time when compared to unranked results. Detecting associations between full text articles and interaction detection method PSI-MI terms (IMT) is more difficult than might be anticipated. This is due to the variability of method term mentions, errors resulting from pre-processing of articles provided as PDF files, and the heterogeneity and different granularity of method term concepts encountered in the ontology. However, combining the sophisticated techniques developed by the participants with supporting evidence strings derived from the articles for human interpretation could result in practical modules for biological annotation workflows.

The multitude of functions performed in the cell are largely controlled by a set of carefully orchestrated protein interactions often facilitated by specific binding of conserved domains in the interacting proteins. Interacting domains commonly exhibit distinct binding specificity to short and conserved recognition peptides called binding profiles. Although many conserved domains are known in nature, only a few have well-characterized binding profiles. Here, we describe a novel predictive method known as domain-motif interactions from structural topology (D-MIST) for elucidating the binding profiles of interacting domains. A set of domains and their corresponding binding profiles were derived from extant protein structures and protein interaction data and then used to predict novel protein interactions in yeast. A number of the predicted interactions were verified experimentally, including new interactions of the mitotic exit network, RNA polymerases, nucleotide metabolism enzymes, and the chaperone complex. These results demonstrate that new protein interactions can be predicted exclusively from sequence information.

It has been claimed that proteins with more interaction partners (hubs) are both physiologically more important (i.e., less dispensable) and, owing to an assumed high density of binding sites, slow evolving. Not all analyses, however, support these results, probably because of biased and less-than reliable global protein interaction data. Here we provide the first examination of these issues using a comprehensive literature-curated dataset of well-substantiated protein interactions in Saccharomyces cerevisiae. Whereas use of less reliable yeast two-hybrid data alone can reject the possibility that local connectivity correlates with measures of dispensability, in higher quality datasets a relatively robust correlation is observed. In contrast, local connectivity does not correlate with the rate of protein evolution even in reliable datasets. This perhaps surprising lack of correlation with evolutionary rate appears in part to arise from the fact that hub proteins do not have a higher density of residues associated with binding. However, hub proteins do have at least one other set of unusual features, namely rapid turnover and regulation, as manifest in high mRNA decay rates and a large number of phosphorylation sites. This, we suggest, is an adaptation to minimize unwanted activation of pathways that might be mediated by adventitious binding to hubs, were they to actively persist longer than required at any given time point. We conclude that hub proteins are more important for cellular growth rate and under tight regulation but are not slow evolving.