Aug 2026· ACS Environmental Au· 0 citations· 73 references
TL;DR
This tutorial provides a comprehensive, end-to-end workflow from raw data to deployed models,icitly designed for environmental chemists with limited prior experience in ML modeling while also providing practical guidance for other users seeking to strengthen their modeling workflows.
Abstract
Machine learning (ML) holds immense promise for predictive modeling but is often misapplied without a systematic understanding of the full model development pipeline. This tutorial provides a comprehensive, end-to-end workflow─from raw data to deployed models─explicitly designed for environmental chemists with limited prior experience in ML modeling while also providing practical guidance for other users seeking to strengthen their modeling workflows. Using a public high-performance liquid chromatography small molecule retention time (SMRT) data set containing over 80,000 small molecules, this tutorial demonstrates critical stages: data cleaning via chemical similarity and scaffold analysis, application-oriented data splitting, feature engineering with molecular fingerprints and graphs, model development using commonly used LightGBM and Graph Convolutional Network (GCN), and model interpretation with different methods. This work highlights how domain knowledge guides each step to avoid common pitfalls, such as overestimating model performance through inappropriate data splits. The work concludes with a robust deployment framework that ensures models are both accurate and accessible. All code is openly available, providing an example implementation for users to reference when developing ML models across diverse applications.
Accurate prediction of melting points for pure molecules remains a significant challenge in predictive chemistry, with implications across various scientific fields, including materials science, drug discovery, and separations chemistry. Traditional methods, such as group contribution (GC) techniques, have shown limited success due to the complex relationship between molecular structure and melting point. In this study, we present a data-driven machine learning (ML) approach to predict the melting points of organic compounds, leveraging both 2D and 3D molecular descriptors. Our results indicate that ML models can significantly improve melting-point predictions, providing a robust tool for the scientific community. Scientific contributionOur detailed analysis on melting point prediction, along with SHAP explainability, reveals the top influencing features for the prediction. The P2MAT application we developed as part of this study can predict both melting and boiling points from a SMILES string. P2MAT is available as an easy-to-install, user-friendly GUI for maximum outreach to the scientific community. Our benchmark analysis demonstrates the excellence of our method for predicting melting points.
Md Kamruzzaman, Alexander Landera, N. Menon et al.· Journal of Cheminformatics· 1 citation
The VizFold plugin is described, a modular framework that can be extended toward end-to-end composable pipelines and demonstrated feasibility through standardized hook-based tracing for ESMFold and Boltz-2, archive validation, and reproducible deployment on an HPC cluster using managed caches, modules, quotas, and Slurm workflows.
Jayanth Vennamreddy, Arish Virani, Kevin Yin et al.· Practice and Experience in A...· 0 citations
Monroe is presented, a new MFM with several innovations over the existing state of the art: increased scale allowing pre-training on over 81 million molecules from the PM6 quantum chemistry dataset; improved graph representation of stereochemistry; improved training losses including conformer denoising and embedding decorrelation; improved multi-task learning; and the use of a prior-data-fitted model (TabPFN) for downstream in-context prediction.
Blazej Banaszewski, Andrew W. Fitzgibbon· 0 citations
The rapid expansion of in silico methodologies has reshaped modern drug discovery and toxicology research; however, robust prediction of ADMET endpoints remains limited by the scarcity and heterogeneity of experimental data. In particular, toxicological data sets are often fragmented across species, complicating the development of reliable and generalizable machine learning models. To address this challenge, we introduce a dedicated Python-based computational package, ADMET-XSpec, designed for the systematic development, training, and evaluation of ML models with an explicit consideration of interspecies data integration. The framework enables controlled incorporation of chemical space originating from different species and different assay types, allowing users to flexibly construct single-species models, as well as models augmented with cross-species information. This design facilitates systematic investigation of how additional data from other organisms influence model performance without imposing assumptions inherent to specific transfer learning paradigms. By supporting standardized preprocessing, scalable integration of heterogeneous data sets, and rigorous benchmarking, the proposed tool provides a unified environment for studying cross-species effects in ADMET modeling. Overall, this work delivers a practical resource for the ADMET modeling community and offers insights into how interspecies and interassay data integration can improve model robustness and generalizability while clarifying the conditions under which cross-species and cross-assay data information is beneficial for predictive toxicology. The package is freely available at https://github.com/hubertrybka/admet-xspec. ADMET-XSpec advances the state of the art by providing the first dedicated framework for controlled interspecies and interassay data integration in ADMET modeling, offering quantitative guidance on when and how cross-species and cross-assay data improve predictive performance.
Hubert Rybka, Konrad Masztalerz, Sabina Podlewska· Chemical Research in Toxicol...· 0 citations
High-quality molecular datasets are essential for reliable machine learning in cheminformatics and bioinformatics, yet dataset quality is rarely assessed systematically and its relationship with downstream model performance remains poorly understood. Here, we present MolJam, an open-source frame-work for quantitative assessment of molecular dataset quality across five dimensions—structural integrity, data quality, experimental information quality, chemical space coverage, and data distribution—using 12 standardized metrics. Application of MolJam to 11 MoleculeNet and 8 ChEMBL-derived datasets revealed widespread and heterogeneous quality issues, including undefined stereochemistry in up to 70.72% of molecules, inconsistent molecular representations, and contradictory labels. We next asked whether improving these quality metrics necessarily improves machine learning performance. Refinement of the ESOL and Lipophilicity datasets increased their MolJam quality scores but produced mixed effects on predictive performance, suggesting a competing influence of reduced dataset size. Controlled ablation experiments further demonstrated that both dataset quality and data quantity contribute to model performance and, notably, that retaining molecules with incomplete stereochemical information can outperform their removal when the resulting gain in data quantity offsets the quality penalty. Thus, molecular dataset curation cannot be reduced to maximizing data cleanliness alone but requires balancing multiple dimensions of data quality against information loss. MolJam provides a standardized framework for diagnosing molecular dataset limitations, comparing benchmark quality, and quantitatively evaluating how data curation decisions influence downstream machine learning.
Deep-Interact Studio is, to the authors' knowledge, the only such platform to combine fine-grained per-layer model customization with multi-model comparison and interpretability, offering a flexible and transparent alternative to fixed, single-purpose tools.
Dipayan Sarkar, K. Bardhan, Chiranjib Sarkar· bioRxiv· 0 citations