Retrieval tasks play central roles in real-world machine learning systems such as search engine, recommender sys-tem, and retrieval-augmented generation (RAG). Achieving decent performance in these tasks often requires fine-tuning various pretrained models on specific datasets and selecting the best candidate, a process that can be both time and resource consuming. To tackle the problem, we introduce a novel and efficient method, called RetMMD, that leverages Maximum Mean Discrepancy (MMD) and kernel methods to assess the transferability of pretrained models in retrieval tasks. RetMMD is calculated on pretrained model and tar-get dataset without any fine-tuning involved. Specifically, given some query, we quantify the distribution discrepancy between relevant and irrelevant document embeddings, by estimating the similarities within their mappings in the fine-tuned embedding space through kernel method. This discrep-ancy is averaged over multiple queries, taking into account the distribution characteristics of the target dataset. Ex-periments suggest that the proposed metric calculated on pretrained models closely aligns with retrieval performance post fine-tuning. The observation holds across a variety of datasets, including image, text, and multi-modal domains, indicating the potential of using MMD and kernel meth-ods for transfer learning evaluation in retrieval scenarios. In addition, we also design a way of evaluating dataset transferability for retrieval tasks, with experimental results demonstrating the effectiveness of the proposed approach.

MOTIVATION: Protein structure prediction remains as one of the most important problems in computational biology and biophysics. In the past few years, protein residue-residue contact prediction has undergone substantial improvement, which has made it a critical driving force for successful protein structure prediction. Boosting the accuracy of contact predictions has, therefore, become the forefront of protein structure prediction. RESULTS: We show a novel contact map refinement method, ContactGAN, which uses Generative Adversarial Networks (GAN). ContactGAN was able to make a significant improvement over predictions made by recent contact prediction methods when tested on three datasets including protein structure modeling targets in CASP13 and CASP14. We show improvement of precision in contact prediction, which translated into improvement in the accuracy of protein tertiary structure models. On the other hand, observed improvement over trRosetta was relatively small, reasons for which are discussed. ContactGAN will be a valuable addition in the structure prediction pipeline to achieve an extra gain in contact prediction accuracy. AVAILABILITY AND IMPLEMENTATION: https://github.com/kiharalab/ContactGAN. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Function annotation of proteins is fundamental in contemporary biology across fields including genomics, molecular biology, biochemistry, systems biology and bioinformatics. Function prediction is indispensable in providing clues for interpreting omics-scale data as well as in assisting biologists to build hypotheses for designing experiments. As sequencing genomes is now routine due to the rapid advancement of sequencing technologies, computational protein function prediction methods have become increasingly important. A conventional method of annotating a protein sequence is to transfer functions from top hits of a homology search; however, this approach has substantial short comings including a low coverage in genome annotation. RESULTS: Here we have developed Phylo-PFP, a new sequence-based protein function prediction method, which mines functional information from a broad range of similar sequences, including those with a low sequence similarity identified by a PSI-BLAST search. To evaluate functional similarity between identified sequences and the query protein more accurately, Phylo-PFP reranks retrieved sequences by considering their phylogenetic distance. Compared to the Phylo-PFP's predecessor, PFP, which was among the top ranked methods in the second round of the Critical Assessment of Functional Annotation (CAFA2), Phylo-PFP demonstrated substantial improvement in prediction accuracy. Phylo-PFP was further shown to outperform prediction programs to date that were ranked top in CAFA2. AVAILABILITY AND IMPLEMENTATION: Phylo-PFP web server is available for at http://kiharalab.org/phylo_pfp.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Biological experiments including proteomics and transcriptomics approaches often reveal sets of proteins that are most likely to be involved in a disease/disorder. To understand the functional nature of a set of proteins, it is important to capture the function of the proteins as a group, even in cases where function of individual proteins is not known. In this work, we propose a model that takes groups of proteins found to work together in a certain biological context, integrates them into functional relevance networks, and subsequently employs an iterative inference on graphical models to identify group functions of the proteins, which are then extended to predict function of individual proteins. RESULTS: The proposed algorithm, iterative group function prediction (iGFP), depicts proteins as a graph that represents functional relevance of proteins considering their known functional, proteomics and transcriptional features. Proteins in the graph will be clustered into groups by their mutual functional relevance, which is iteratively updated using a probabilistic graphical model, the conditional random field. iGFP showed robust accuracy even when substantial amount of GO annotations were missing. The perspective of 'group' function annotation opens up novel approaches for understanding functional nature of proteins in biological systems.Availability and implementation: http://kiharalab.org/iGFP/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.